Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks
Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and...
Ausführliche Beschreibung
Autor*in: |
Blum, Friederike Maria Sophie [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2023 |
---|
Schlagwörter: |
---|
Anmerkung: |
© The Author(s) 2023 |
---|
Übergeordnetes Werk: |
Enthalten in: Clinical Oral Investigations - Springer-Verlag, 2001, 27(2023), 5 vom: 04. Apr., Seite 2255-2265 |
---|---|
Übergeordnetes Werk: |
volume:27 ; year:2023 ; number:5 ; day:04 ; month:04 ; pages:2255-2265 |
Links: |
---|
DOI / URN: |
10.1007/s00784-023-04978-4 |
---|
Katalog-ID: |
SPR050290568 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | SPR050290568 | ||
003 | DE-627 | ||
005 | 20230505064728.0 | ||
007 | cr uuu---uuuuu | ||
008 | 230505s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s00784-023-04978-4 |2 doi | |
035 | |a (DE-627)SPR050290568 | ||
035 | |a (SPR)s00784-023-04978-4-e | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Blum, Friederike Maria Sophie |e verfasserin |4 aut | |
245 | 1 | 0 | |a Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a © The Author(s) 2023 | ||
520 | |a Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. | ||
650 | 4 | |a Algorithm |7 (dpeaa)DE-He213 | |
650 | 4 | |a Artificial intelligence |7 (dpeaa)DE-He213 | |
650 | 4 | |a Craniofacial landmarks |7 (dpeaa)DE-He213 | |
650 | 4 | |a Cone-beam computed tomography |7 (dpeaa)DE-He213 | |
700 | 1 | |a Möhlhenrich, Stephan Christian |4 aut | |
700 | 1 | |a Raith, Stefan |4 aut | |
700 | 1 | |a Pankert, Tobias |4 aut | |
700 | 1 | |a Peters, Florian |4 aut | |
700 | 1 | |a Wolf, Michael |4 aut | |
700 | 1 | |a Hölzle, Frank |4 aut | |
700 | 1 | |a Modabber, Ali |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Clinical Oral Investigations |d Springer-Verlag, 2001 |g 27(2023), 5 vom: 04. Apr., Seite 2255-2265 |w (DE-627)SPR007794231 |7 nnns |
773 | 1 | 8 | |g volume:27 |g year:2023 |g number:5 |g day:04 |g month:04 |g pages:2255-2265 |
856 | 4 | 0 | |u https://dx.doi.org/10.1007/s00784-023-04978-4 |z kostenfrei |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_SPRINGER | ||
951 | |a AR | ||
952 | |d 27 |j 2023 |e 5 |b 04 |c 04 |h 2255-2265 |
author_variant |
f m s b fms fmsb s c m sc scm s r sr t p tp f p fp m w mw f h fh a m am |
---|---|
matchkey_str |
blumfriederikemariasophiemhlhenrichsteph:2023----:vlainfnriiilnelgneaeagrtmoatmtdoaiai |
hierarchy_sort_str |
2023 |
publishDate |
2023 |
allfields |
10.1007/s00784-023-04978-4 doi (DE-627)SPR050290568 (SPR)s00784-023-04978-4-e DE-627 ger DE-627 rakwb eng Blum, Friederike Maria Sophie verfasserin aut Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2023 Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 Möhlhenrich, Stephan Christian aut Raith, Stefan aut Pankert, Tobias aut Peters, Florian aut Wolf, Michael aut Hölzle, Frank aut Modabber, Ali aut Enthalten in Clinical Oral Investigations Springer-Verlag, 2001 27(2023), 5 vom: 04. Apr., Seite 2255-2265 (DE-627)SPR007794231 nnns volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 https://dx.doi.org/10.1007/s00784-023-04978-4 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2023 5 04 04 2255-2265 |
spelling |
10.1007/s00784-023-04978-4 doi (DE-627)SPR050290568 (SPR)s00784-023-04978-4-e DE-627 ger DE-627 rakwb eng Blum, Friederike Maria Sophie verfasserin aut Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2023 Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 Möhlhenrich, Stephan Christian aut Raith, Stefan aut Pankert, Tobias aut Peters, Florian aut Wolf, Michael aut Hölzle, Frank aut Modabber, Ali aut Enthalten in Clinical Oral Investigations Springer-Verlag, 2001 27(2023), 5 vom: 04. Apr., Seite 2255-2265 (DE-627)SPR007794231 nnns volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 https://dx.doi.org/10.1007/s00784-023-04978-4 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2023 5 04 04 2255-2265 |
allfields_unstemmed |
10.1007/s00784-023-04978-4 doi (DE-627)SPR050290568 (SPR)s00784-023-04978-4-e DE-627 ger DE-627 rakwb eng Blum, Friederike Maria Sophie verfasserin aut Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2023 Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 Möhlhenrich, Stephan Christian aut Raith, Stefan aut Pankert, Tobias aut Peters, Florian aut Wolf, Michael aut Hölzle, Frank aut Modabber, Ali aut Enthalten in Clinical Oral Investigations Springer-Verlag, 2001 27(2023), 5 vom: 04. Apr., Seite 2255-2265 (DE-627)SPR007794231 nnns volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 https://dx.doi.org/10.1007/s00784-023-04978-4 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2023 5 04 04 2255-2265 |
allfieldsGer |
10.1007/s00784-023-04978-4 doi (DE-627)SPR050290568 (SPR)s00784-023-04978-4-e DE-627 ger DE-627 rakwb eng Blum, Friederike Maria Sophie verfasserin aut Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2023 Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 Möhlhenrich, Stephan Christian aut Raith, Stefan aut Pankert, Tobias aut Peters, Florian aut Wolf, Michael aut Hölzle, Frank aut Modabber, Ali aut Enthalten in Clinical Oral Investigations Springer-Verlag, 2001 27(2023), 5 vom: 04. Apr., Seite 2255-2265 (DE-627)SPR007794231 nnns volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 https://dx.doi.org/10.1007/s00784-023-04978-4 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2023 5 04 04 2255-2265 |
allfieldsSound |
10.1007/s00784-023-04978-4 doi (DE-627)SPR050290568 (SPR)s00784-023-04978-4-e DE-627 ger DE-627 rakwb eng Blum, Friederike Maria Sophie verfasserin aut Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2023 Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 Möhlhenrich, Stephan Christian aut Raith, Stefan aut Pankert, Tobias aut Peters, Florian aut Wolf, Michael aut Hölzle, Frank aut Modabber, Ali aut Enthalten in Clinical Oral Investigations Springer-Verlag, 2001 27(2023), 5 vom: 04. Apr., Seite 2255-2265 (DE-627)SPR007794231 nnns volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 https://dx.doi.org/10.1007/s00784-023-04978-4 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2023 5 04 04 2255-2265 |
language |
English |
source |
Enthalten in Clinical Oral Investigations 27(2023), 5 vom: 04. Apr., Seite 2255-2265 volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 |
sourceStr |
Enthalten in Clinical Oral Investigations 27(2023), 5 vom: 04. Apr., Seite 2255-2265 volume:27 year:2023 number:5 day:04 month:04 pages:2255-2265 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Algorithm Artificial intelligence Craniofacial landmarks Cone-beam computed tomography |
isfreeaccess_bool |
true |
container_title |
Clinical Oral Investigations |
authorswithroles_txt_mv |
Blum, Friederike Maria Sophie @@aut@@ Möhlhenrich, Stephan Christian @@aut@@ Raith, Stefan @@aut@@ Pankert, Tobias @@aut@@ Peters, Florian @@aut@@ Wolf, Michael @@aut@@ Hölzle, Frank @@aut@@ Modabber, Ali @@aut@@ |
publishDateDaySort_date |
2023-04-04T00:00:00Z |
hierarchy_top_id |
SPR007794231 |
id |
SPR050290568 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR050290568</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505064728.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230505s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00784-023-04978-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR050290568</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00784-023-04978-4-e</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Blum, Friederike Maria Sophie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</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="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2023</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Algorithm</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Craniofacial landmarks</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cone-beam computed tomography</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Möhlhenrich, Stephan Christian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Raith, Stefan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pankert, Tobias</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Peters, Florian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wolf, Michael</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hölzle, Frank</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Modabber, Ali</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Clinical Oral Investigations</subfield><subfield code="d">Springer-Verlag, 2001</subfield><subfield code="g">27(2023), 5 vom: 04. Apr., Seite 2255-2265</subfield><subfield code="w">(DE-627)SPR007794231</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:5</subfield><subfield code="g">day:04</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:2255-2265</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00784-023-04978-4</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">27</subfield><subfield code="j">2023</subfield><subfield code="e">5</subfield><subfield code="b">04</subfield><subfield code="c">04</subfield><subfield code="h">2255-2265</subfield></datafield></record></collection>
|
author |
Blum, Friederike Maria Sophie |
spellingShingle |
Blum, Friederike Maria Sophie misc Algorithm misc Artificial intelligence misc Craniofacial landmarks misc Cone-beam computed tomography Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
authorStr |
Blum, Friederike Maria Sophie |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)SPR007794231 |
format |
electronic Article |
delete_txt_mv |
keep |
author_role |
aut aut aut aut aut aut aut aut |
collection |
springer |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks Algorithm (dpeaa)DE-He213 Artificial intelligence (dpeaa)DE-He213 Craniofacial landmarks (dpeaa)DE-He213 Cone-beam computed tomography (dpeaa)DE-He213 |
topic |
misc Algorithm misc Artificial intelligence misc Craniofacial landmarks misc Cone-beam computed tomography |
topic_unstemmed |
misc Algorithm misc Artificial intelligence misc Craniofacial landmarks misc Cone-beam computed tomography |
topic_browse |
misc Algorithm misc Artificial intelligence misc Craniofacial landmarks misc Cone-beam computed tomography |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
Clinical Oral Investigations |
hierarchy_parent_id |
SPR007794231 |
hierarchy_top_title |
Clinical Oral Investigations |
isfreeaccess_txt |
true |
familylinks_str_mv |
(DE-627)SPR007794231 |
title |
Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
ctrlnum |
(DE-627)SPR050290568 (SPR)s00784-023-04978-4-e |
title_full |
Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
author_sort |
Blum, Friederike Maria Sophie |
journal |
Clinical Oral Investigations |
journalStr |
Clinical Oral Investigations |
lang_code |
eng |
isOA_bool |
true |
recordtype |
marc |
publishDateSort |
2023 |
contenttype_str_mv |
txt |
container_start_page |
2255 |
author_browse |
Blum, Friederike Maria Sophie Möhlhenrich, Stephan Christian Raith, Stefan Pankert, Tobias Peters, Florian Wolf, Michael Hölzle, Frank Modabber, Ali |
container_volume |
27 |
format_se |
Elektronische Aufsätze |
author-letter |
Blum, Friederike Maria Sophie |
doi_str_mv |
10.1007/s00784-023-04978-4 |
title_sort |
evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
title_auth |
Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
abstract |
Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. © The Author(s) 2023 |
abstractGer |
Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. © The Author(s) 2023 |
abstract_unstemmed |
Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice. © The Author(s) 2023 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
container_issue |
5 |
title_short |
Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks |
url |
https://dx.doi.org/10.1007/s00784-023-04978-4 |
remote_bool |
true |
author2 |
Möhlhenrich, Stephan Christian Raith, Stefan Pankert, Tobias Peters, Florian Wolf, Michael Hölzle, Frank Modabber, Ali |
author2Str |
Möhlhenrich, Stephan Christian Raith, Stefan Pankert, Tobias Peters, Florian Wolf, Michael Hölzle, Frank Modabber, Ali |
ppnlink |
SPR007794231 |
mediatype_str_mv |
c |
isOA_txt |
true |
hochschulschrift_bool |
false |
doi_str |
10.1007/s00784-023-04978-4 |
up_date |
2024-07-03T14:36:04.703Z |
_version_ |
1803568928213958656 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR050290568</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505064728.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230505s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00784-023-04978-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR050290568</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00784-023-04978-4-e</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Blum, Friederike Maria Sophie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Evaluation of an artificial intelligence–based algorithm for automated localization of craniofacial landmarks</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</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="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2023</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Objectives Due to advancing digitalisation, it is of interest to develop standardised and reproducible fully automated analysis methods of cranial structures in order to reduce the workload in diagnosis and treatment planning and to generate objectifiable data. The aim of this study was to train and evaluate an algorithm based on deep learning methods for fully automated detection of craniofacial landmarks in cone-beam computed tomography (CBCT) in terms of accuracy, speed, and reproducibility. Materials and methods A total of 931 CBCTs were used to train the algorithm. To test the algorithm, 35 landmarks were located manually by three experts and automatically by the algorithm in 114 CBCTs. The time and distance between the measured values and the ground truth previously determined by an orthodontist were analyzed. Intraindividual variations in manual localization of landmarks were determined using 50 CBCTs analyzed twice. Results The results showed no statistically significant difference between the two measurement methods. Overall, with a mean error of 2.73 mm, the AI was 2.12% better and 95% faster than the experts. In the area of bilateral cranial structures, the AI was able to achieve better results than the experts on average. Conclusion The achieved accuracy of automatic landmark detection was in a clinically acceptable range, is comparable in precision to manual landmark determination, and requires less time. Clinical relevance Further enlargement of the database and continued development and optimization of the algorithm may lead to ubiquitous fully automated localization and analysis of CBCT datasets in future routine clinical practice.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Algorithm</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Craniofacial landmarks</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cone-beam computed tomography</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Möhlhenrich, Stephan Christian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Raith, Stefan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Pankert, Tobias</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Peters, Florian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wolf, Michael</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hölzle, Frank</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Modabber, Ali</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Clinical Oral Investigations</subfield><subfield code="d">Springer-Verlag, 2001</subfield><subfield code="g">27(2023), 5 vom: 04. Apr., Seite 2255-2265</subfield><subfield code="w">(DE-627)SPR007794231</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:5</subfield><subfield code="g">day:04</subfield><subfield code="g">month:04</subfield><subfield code="g">pages:2255-2265</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00784-023-04978-4</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">27</subfield><subfield code="j">2023</subfield><subfield code="e">5</subfield><subfield code="b">04</subfield><subfield code="c">04</subfield><subfield code="h">2255-2265</subfield></datafield></record></collection>
|
score |
7.399618 |