MSKD: Structured knowledge distillation for efficient medical image segmentation
In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To addr...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Zhao, Libo [verfasserIn] Qian, Xiaolong [verfasserIn] Guo, Yinghui [verfasserIn] Song, Jiaqi [verfasserIn] Hou, Jinbao [verfasserIn] Gong, Jun [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023 |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Computers in biology and medicine - Amsterdam [u.a.] : Elsevier Science, 1970, 164 |
|---|---|
| Übergeordnetes Werk: |
volume:164 |
| DOI / URN: |
10.1016/j.compbiomed.2023.107284 |
|---|
| Katalog-ID: |
ELV062705571 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV062705571 | ||
| 003 | DE-627 | ||
| 005 | 20231205153658.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230906s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2023.107284 |2 doi | |
| 035 | |a (DE-627)ELV062705571 | ||
| 035 | |a (ELSEVIER)S0010-4825(23)00749-7 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |a 570 |q VZ |
| 084 | |a 42.00 |2 bkl | ||
| 084 | |a 44.09 |2 bkl | ||
| 100 | 1 | |a Zhao, Libo |e verfasserin |0 (orcid)0009-0009-5691-2301 |4 aut | |
| 245 | 1 | 0 | |a MSKD: Structured knowledge distillation for efficient medical image segmentation |
| 264 | 1 | |c 2023 | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. | ||
| 650 | 4 | |a Knowledge distillation | |
| 650 | 4 | |a Medical image segmentation | |
| 650 | 4 | |a Lightweight neural networks | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Teacher-student model | |
| 650 | 4 | |a Feature filtering distillation | |
| 650 | 4 | |a Region graph distillation | |
| 700 | 1 | |a Qian, Xiaolong |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Yinghui |e verfasserin |4 aut | |
| 700 | 1 | |a Song, Jiaqi |e verfasserin |4 aut | |
| 700 | 1 | |a Hou, Jinbao |e verfasserin |4 aut | |
| 700 | 1 | |a Gong, Jun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d Amsterdam [u.a.] : Elsevier Science, 1970 |g 164 |h Online-Ressource |w (DE-627)306356783 |w (DE-600)1496984-1 |w (DE-576)081952988 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:164 |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_32 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_100 | ||
| 912 | |a GBV_ILN_101 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_150 | ||
| 912 | |a GBV_ILN_151 | ||
| 912 | |a GBV_ILN_187 | ||
| 912 | |a GBV_ILN_213 | ||
| 912 | |a GBV_ILN_224 | ||
| 912 | |a GBV_ILN_230 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_702 | ||
| 912 | |a GBV_ILN_2001 | ||
| 912 | |a GBV_ILN_2003 | ||
| 912 | |a GBV_ILN_2004 | ||
| 912 | |a GBV_ILN_2005 | ||
| 912 | |a GBV_ILN_2007 | ||
| 912 | |a GBV_ILN_2009 | ||
| 912 | |a GBV_ILN_2010 | ||
| 912 | |a GBV_ILN_2011 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_2015 | ||
| 912 | |a GBV_ILN_2020 | ||
| 912 | |a GBV_ILN_2021 | ||
| 912 | |a GBV_ILN_2025 | ||
| 912 | |a GBV_ILN_2026 | ||
| 912 | |a GBV_ILN_2027 | ||
| 912 | |a GBV_ILN_2034 | ||
| 912 | |a GBV_ILN_2044 | ||
| 912 | |a GBV_ILN_2048 | ||
| 912 | |a GBV_ILN_2049 | ||
| 912 | |a GBV_ILN_2050 | ||
| 912 | |a GBV_ILN_2055 | ||
| 912 | |a GBV_ILN_2056 | ||
| 912 | |a GBV_ILN_2059 | ||
| 912 | |a GBV_ILN_2061 | ||
| 912 | |a GBV_ILN_2064 | ||
| 912 | |a GBV_ILN_2106 | ||
| 912 | |a GBV_ILN_2110 | ||
| 912 | |a GBV_ILN_2111 | ||
| 912 | |a GBV_ILN_2112 | ||
| 912 | |a GBV_ILN_2122 | ||
| 912 | |a GBV_ILN_2129 | ||
| 912 | |a GBV_ILN_2143 | ||
| 912 | |a GBV_ILN_2152 | ||
| 912 | |a GBV_ILN_2153 | ||
| 912 | |a GBV_ILN_2190 | ||
| 912 | |a GBV_ILN_2232 | ||
| 912 | |a GBV_ILN_2336 | ||
| 912 | |a GBV_ILN_2470 | ||
| 912 | |a GBV_ILN_2507 | ||
| 912 | |a GBV_ILN_4035 | ||
| 912 | |a GBV_ILN_4037 | ||
| 912 | |a GBV_ILN_4112 | ||
| 912 | |a GBV_ILN_4125 | ||
| 912 | |a GBV_ILN_4242 | ||
| 912 | |a GBV_ILN_4249 | ||
| 912 | |a GBV_ILN_4251 | ||
| 912 | |a GBV_ILN_4305 | ||
| 912 | |a GBV_ILN_4306 | ||
| 912 | |a GBV_ILN_4307 | ||
| 912 | |a GBV_ILN_4313 | ||
| 912 | |a GBV_ILN_4322 | ||
| 912 | |a GBV_ILN_4323 | ||
| 912 | |a GBV_ILN_4324 | ||
| 912 | |a GBV_ILN_4326 | ||
| 912 | |a GBV_ILN_4333 | ||
| 912 | |a GBV_ILN_4334 | ||
| 912 | |a GBV_ILN_4338 | ||
| 912 | |a GBV_ILN_4393 | ||
| 912 | |a GBV_ILN_4700 | ||
| 936 | b | k | |a 42.00 |q VZ |
| 936 | b | k | |a 44.09 |j Medizintechnik |q VZ |
| 951 | |a AR | ||
| 952 | |d 164 | ||
| author_variant |
l z lz x q xq y g yg j s js j h jh j g jg |
|---|---|
| matchkey_str |
article:18790534:2023----::sdtutrdnwegdsiltofrfiinmd |
| hierarchy_sort_str |
2023 |
| bklnumber |
42.00 44.09 |
| publishDate |
2023 |
| allfields |
10.1016/j.compbiomed.2023.107284 doi (DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 DE-627 ger DE-627 rda eng 610 570 VZ 42.00 bkl 44.09 bkl Zhao, Libo verfasserin (orcid)0009-0009-5691-2301 aut MSKD: Structured knowledge distillation for efficient medical image segmentation 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation Qian, Xiaolong verfasserin aut Guo, Yinghui verfasserin aut Song, Jiaqi verfasserin aut Hou, Jinbao verfasserin aut Gong, Jun verfasserin aut Enthalten in Computers in biology and medicine Amsterdam [u.a.] : Elsevier Science, 1970 164 Online-Ressource (DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 1879-0534 nnns volume:164 GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 42.00 VZ 44.09 Medizintechnik VZ AR 164 |
| spelling |
10.1016/j.compbiomed.2023.107284 doi (DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 DE-627 ger DE-627 rda eng 610 570 VZ 42.00 bkl 44.09 bkl Zhao, Libo verfasserin (orcid)0009-0009-5691-2301 aut MSKD: Structured knowledge distillation for efficient medical image segmentation 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation Qian, Xiaolong verfasserin aut Guo, Yinghui verfasserin aut Song, Jiaqi verfasserin aut Hou, Jinbao verfasserin aut Gong, Jun verfasserin aut Enthalten in Computers in biology and medicine Amsterdam [u.a.] : Elsevier Science, 1970 164 Online-Ressource (DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 1879-0534 nnns volume:164 GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 42.00 VZ 44.09 Medizintechnik VZ AR 164 |
| allfields_unstemmed |
10.1016/j.compbiomed.2023.107284 doi (DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 DE-627 ger DE-627 rda eng 610 570 VZ 42.00 bkl 44.09 bkl Zhao, Libo verfasserin (orcid)0009-0009-5691-2301 aut MSKD: Structured knowledge distillation for efficient medical image segmentation 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation Qian, Xiaolong verfasserin aut Guo, Yinghui verfasserin aut Song, Jiaqi verfasserin aut Hou, Jinbao verfasserin aut Gong, Jun verfasserin aut Enthalten in Computers in biology and medicine Amsterdam [u.a.] : Elsevier Science, 1970 164 Online-Ressource (DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 1879-0534 nnns volume:164 GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 42.00 VZ 44.09 Medizintechnik VZ AR 164 |
| allfieldsGer |
10.1016/j.compbiomed.2023.107284 doi (DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 DE-627 ger DE-627 rda eng 610 570 VZ 42.00 bkl 44.09 bkl Zhao, Libo verfasserin (orcid)0009-0009-5691-2301 aut MSKD: Structured knowledge distillation for efficient medical image segmentation 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation Qian, Xiaolong verfasserin aut Guo, Yinghui verfasserin aut Song, Jiaqi verfasserin aut Hou, Jinbao verfasserin aut Gong, Jun verfasserin aut Enthalten in Computers in biology and medicine Amsterdam [u.a.] : Elsevier Science, 1970 164 Online-Ressource (DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 1879-0534 nnns volume:164 GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 42.00 VZ 44.09 Medizintechnik VZ AR 164 |
| allfieldsSound |
10.1016/j.compbiomed.2023.107284 doi (DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 DE-627 ger DE-627 rda eng 610 570 VZ 42.00 bkl 44.09 bkl Zhao, Libo verfasserin (orcid)0009-0009-5691-2301 aut MSKD: Structured knowledge distillation for efficient medical image segmentation 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation Qian, Xiaolong verfasserin aut Guo, Yinghui verfasserin aut Song, Jiaqi verfasserin aut Hou, Jinbao verfasserin aut Gong, Jun verfasserin aut Enthalten in Computers in biology and medicine Amsterdam [u.a.] : Elsevier Science, 1970 164 Online-Ressource (DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 1879-0534 nnns volume:164 GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 42.00 VZ 44.09 Medizintechnik VZ AR 164 |
| language |
English |
| source |
Enthalten in Computers in biology and medicine 164 volume:164 |
| sourceStr |
Enthalten in Computers in biology and medicine 164 volume:164 |
| format_phy_str_mv |
Article |
| bklname |
Medizintechnik |
| institution |
findex.gbv.de |
| topic_facet |
Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Computers in biology and medicine |
| authorswithroles_txt_mv |
Zhao, Libo @@aut@@ Qian, Xiaolong @@aut@@ Guo, Yinghui @@aut@@ Song, Jiaqi @@aut@@ Hou, Jinbao @@aut@@ Gong, Jun @@aut@@ |
| publishDateDaySort_date |
2023-01-01T00:00:00Z |
| hierarchy_top_id |
306356783 |
| dewey-sort |
3610 |
| id |
ELV062705571 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV062705571</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231205153658.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230906s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compbiomed.2023.107284</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV062705571</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0010-4825(23)00749-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.09</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhao, Libo</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0009-0009-5691-2301</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">MSKD: Structured knowledge distillation for efficient medical image segmentation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Medical image segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Lightweight neural networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teacher-student model</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature filtering distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Region graph distillation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Qian, Xiaolong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Yinghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Song, Jiaqi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hou, Jinbao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gong, Jun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Computers in biology and medicine</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1970</subfield><subfield code="g">164</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)306356783</subfield><subfield code="w">(DE-600)1496984-1</subfield><subfield code="w">(DE-576)081952988</subfield><subfield code="x">1879-0534</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:164</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.00</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.09</subfield><subfield code="j">Medizintechnik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">164</subfield></datafield></record></collection>
|
| author |
Zhao, Libo |
| spellingShingle |
Zhao, Libo ddc 610 bkl 42.00 bkl 44.09 misc Knowledge distillation misc Medical image segmentation misc Lightweight neural networks misc Deep learning misc Teacher-student model misc Feature filtering distillation misc Region graph distillation MSKD: Structured knowledge distillation for efficient medical image segmentation |
| authorStr |
Zhao, Libo |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)306356783 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health 570 - Life sciences; biology |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
1879-0534 |
| topic_title |
610 570 VZ 42.00 bkl 44.09 bkl MSKD: Structured knowledge distillation for efficient medical image segmentation Knowledge distillation Medical image segmentation Lightweight neural networks Deep learning Teacher-student model Feature filtering distillation Region graph distillation |
| topic |
ddc 610 bkl 42.00 bkl 44.09 misc Knowledge distillation misc Medical image segmentation misc Lightweight neural networks misc Deep learning misc Teacher-student model misc Feature filtering distillation misc Region graph distillation |
| topic_unstemmed |
ddc 610 bkl 42.00 bkl 44.09 misc Knowledge distillation misc Medical image segmentation misc Lightweight neural networks misc Deep learning misc Teacher-student model misc Feature filtering distillation misc Region graph distillation |
| topic_browse |
ddc 610 bkl 42.00 bkl 44.09 misc Knowledge distillation misc Medical image segmentation misc Lightweight neural networks misc Deep learning misc Teacher-student model misc Feature filtering distillation misc Region graph distillation |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Computers in biology and medicine |
| hierarchy_parent_id |
306356783 |
| dewey-tens |
610 - Medicine & health 570 - Life sciences; biology |
| hierarchy_top_title |
Computers in biology and medicine |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)306356783 (DE-600)1496984-1 (DE-576)081952988 |
| title |
MSKD: Structured knowledge distillation for efficient medical image segmentation |
| ctrlnum |
(DE-627)ELV062705571 (ELSEVIER)S0010-4825(23)00749-7 |
| title_full |
MSKD: Structured knowledge distillation for efficient medical image segmentation |
| author_sort |
Zhao, Libo |
| journal |
Computers in biology and medicine |
| journalStr |
Computers in biology and medicine |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 500 - Science |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
zzz |
| author_browse |
Zhao, Libo Qian, Xiaolong Guo, Yinghui Song, Jiaqi Hou, Jinbao Gong, Jun |
| container_volume |
164 |
| class |
610 570 VZ 42.00 bkl 44.09 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Zhao, Libo |
| doi_str_mv |
10.1016/j.compbiomed.2023.107284 |
| normlink |
(ORCID)0009-0009-5691-2301 |
| normlink_prefix_str_mv |
(orcid)0009-0009-5691-2301 |
| dewey-full |
610 570 |
| author2-role |
verfasserin |
| title_sort |
mskd: structured knowledge distillation for efficient medical image segmentation |
| title_auth |
MSKD: Structured knowledge distillation for efficient medical image segmentation |
| abstract |
In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. |
| abstractGer |
In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. |
| abstract_unstemmed |
In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 |
| title_short |
MSKD: Structured knowledge distillation for efficient medical image segmentation |
| remote_bool |
true |
| author2 |
Qian, Xiaolong Guo, Yinghui Song, Jiaqi Hou, Jinbao Gong, Jun |
| author2Str |
Qian, Xiaolong Guo, Yinghui Song, Jiaqi Hou, Jinbao Gong, Jun |
| ppnlink |
306356783 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1016/j.compbiomed.2023.107284 |
| up_date |
2024-07-06T19:06:08.359Z |
| _version_ |
1803857709875855360 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV062705571</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231205153658.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230906s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.compbiomed.2023.107284</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV062705571</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0010-4825(23)00749-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.09</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhao, Libo</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0009-0009-5691-2301</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">MSKD: Structured knowledge distillation for efficient medical image segmentation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Medical image segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Lightweight neural networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teacher-student model</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature filtering distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Region graph distillation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Qian, Xiaolong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Yinghui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Song, Jiaqi</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hou, Jinbao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gong, Jun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Computers in biology and medicine</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1970</subfield><subfield code="g">164</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)306356783</subfield><subfield code="w">(DE-600)1496984-1</subfield><subfield code="w">(DE-576)081952988</subfield><subfield code="x">1879-0534</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:164</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.00</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.09</subfield><subfield code="j">Medizintechnik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">164</subfield></datafield></record></collection>
|
| score |
7.3998365 |