Improved Diagnostic Accuracy of Ameloblastoma and Odontogenic Keratocyst on Cone-Beam CT by Artificial Intelligence
Copyright © 2022 Chai, Mao, Chen, Sun, Shen, Liu and Sun..
OBJECTIVE: The purpose of this study was to utilize a convolutional neural network (CNN) to make preoperative differential diagnoses between ameloblastoma (AME) and odontogenic keratocyst (OKC) on cone-beam CT (CBCT).
METHODS: The CBCT images of 178 AMEs and 172 OKCs were retrospectively retrieved from the Hospital of Stomatology, Wuhan University. The datasets were randomly split into a training dataset of 272 cases and a testing dataset of 78 cases. Slices comprising lesions were retained and then cropped to suitable patches for training. The Inception v3 deep learning algorithm was utilized, and its diagnostic performance was compared with that of oral and maxillofacial surgeons.
RESULTS: The sensitivity, specificity, accuracy, and F1 score were 87.2%, 82.1%, 84.6%, and 85.0%, respectively. Furthermore, the average scores of the same indexes for 7 senior oral and maxillofacial surgeons were 60.0%, 71.4%, 65.7%, and 63.6%, respectively, and those of 30 junior oral and maxillofacial surgeons were 63.9%, 53.2%, 58.5%, and 60.7%, respectively.
CONCLUSION: The deep learning model was able to differentiate these two lesions with better diagnostic accuracy than clinical surgeons. The results indicate that the CNN may provide assistance for clinical diagnosis, especially for inexperienced surgeons.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:11 |
---|---|
Enthalten in: |
Frontiers in oncology - 11(2021) vom: 01., Seite 793417 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chai, Zi-Kang [VerfasserIn] |
---|
Links: |
---|
Themen: |
Ameloblastoma |
---|
Anmerkungen: |
Date Revised 01.05.2022 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3389/fonc.2021.793417 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM336873158 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM336873158 | ||
003 | DE-627 | ||
005 | 20231226204227.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3389/fonc.2021.793417 |2 doi | |
028 | 5 | 2 | |a pubmed24n1122.xml |
035 | |a (DE-627)NLM336873158 | ||
035 | |a (NLM)35155194 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Chai, Zi-Kang |e verfasserin |4 aut | |
245 | 1 | 0 | |a Improved Diagnostic Accuracy of Ameloblastoma and Odontogenic Keratocyst on Cone-Beam CT by Artificial Intelligence |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 01.05.2022 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Copyright © 2022 Chai, Mao, Chen, Sun, Shen, Liu and Sun. | ||
520 | |a OBJECTIVE: The purpose of this study was to utilize a convolutional neural network (CNN) to make preoperative differential diagnoses between ameloblastoma (AME) and odontogenic keratocyst (OKC) on cone-beam CT (CBCT) | ||
520 | |a METHODS: The CBCT images of 178 AMEs and 172 OKCs were retrospectively retrieved from the Hospital of Stomatology, Wuhan University. The datasets were randomly split into a training dataset of 272 cases and a testing dataset of 78 cases. Slices comprising lesions were retained and then cropped to suitable patches for training. The Inception v3 deep learning algorithm was utilized, and its diagnostic performance was compared with that of oral and maxillofacial surgeons | ||
520 | |a RESULTS: The sensitivity, specificity, accuracy, and F1 score were 87.2%, 82.1%, 84.6%, and 85.0%, respectively. Furthermore, the average scores of the same indexes for 7 senior oral and maxillofacial surgeons were 60.0%, 71.4%, 65.7%, and 63.6%, respectively, and those of 30 junior oral and maxillofacial surgeons were 63.9%, 53.2%, 58.5%, and 60.7%, respectively | ||
520 | |a CONCLUSION: The deep learning model was able to differentiate these two lesions with better diagnostic accuracy than clinical surgeons. The results indicate that the CNN may provide assistance for clinical diagnosis, especially for inexperienced surgeons | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Inception v3 | |
650 | 4 | |a ameloblastoma | |
650 | 4 | |a cone-beam CT | |
650 | 4 | |a convolutional neural network | |
650 | 4 | |a deep learning | |
650 | 4 | |a odontogenic keratocyst | |
700 | 1 | |a Mao, Liang |e verfasserin |4 aut | |
700 | 1 | |a Chen, Hua |e verfasserin |4 aut | |
700 | 1 | |a Sun, Ting-Guan |e verfasserin |4 aut | |
700 | 1 | |a Shen, Xue-Meng |e verfasserin |4 aut | |
700 | 1 | |a Liu, Juan |e verfasserin |4 aut | |
700 | 1 | |a Sun, Zhi-Jun |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Frontiers in oncology |d 2011 |g 11(2021) vom: 01., Seite 793417 |w (DE-627)NLM218189583 |x 2234-943X |7 nnns |
773 | 1 | 8 | |g volume:11 |g year:2021 |g day:01 |g pages:793417 |
856 | 4 | 0 | |u http://dx.doi.org/10.3389/fonc.2021.793417 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 11 |j 2021 |b 01 |h 793417 |