Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT
© The Author(s) 2024. Published by Oxford University Press on behalf of the British Institute of Radiology and the International Association of Dentomaxillofacial Radiology. All rights reserved. For permissions, please email: journals.permissionsoup.com..
OBJECTIVES: Preoperative diagnosis of oral ameloblastoma (AME) and odontogenic keratocyst (OKC) has been a challenge in dentistry. This study uses radiomics approaches and machine learning (ML) algorithms to characterize cone beam computed tomography (CBCT) image features for the preoperative differential diagnosis of AME and OKC and compares ML algorithms to expert radiologists to validate performance.
METHODS: We retrospectively collected the data of 326 patients with AME and OKC, where all diagnoses were confirmed by histopathologic tests. A total of 348 features were selected to train six ML models for differential diagnosis by a five-fold cross-validation. We then compared the performance of ML-based diagnoses to those of radiologists.
RESULTS: Among the six ML models, XGBoost was effective in distinguishing AME and OKC in CBCT images, with its classification performance outperforming the other models. The mean precision, recall, accuracy, F1-score, and area under the curve (AUC) were 0.900, 0.807, 0.843, 0.841, and 0.872, respectively. Compared to the diagnostics by radiologists, ML-based radiomic diagnostics performed better.
CONCLUSIONS: Radiomic-based ML algorithms allow CBCT images of AME and OKC to be distinguished accurately, facilitating the preoperative differential diagnosis of AME and OKC.
ADVANCES IN KNOWLEDGE: ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
|---|---|
| Enthalten in: |
Dento maxillo facial radiology - (2024) vom: 16. Apr. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Song, Yang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Ameloblastoma |
|---|
| Anmerkungen: |
Date Revised 16.04.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1093/dmfr/twae016 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM371163587 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM371163587 | ||
| 003 | DE-627 | ||
| 005 | 20240417233318.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240417s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/dmfr/twae016 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1378.xml |
| 035 | |a (DE-627)NLM371163587 | ||
| 035 | |a (NLM)38627247 | ||
| 035 | |a (PII)twae016 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Song, Yang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT |
| 264 | 1 | |c 2024 | |
| 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 16.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a © The Author(s) 2024. Published by Oxford University Press on behalf of the British Institute of Radiology and the International Association of Dentomaxillofacial Radiology. All rights reserved. For permissions, please email: journals.permissionsoup.com. | ||
| 520 | |a OBJECTIVES: Preoperative diagnosis of oral ameloblastoma (AME) and odontogenic keratocyst (OKC) has been a challenge in dentistry. This study uses radiomics approaches and machine learning (ML) algorithms to characterize cone beam computed tomography (CBCT) image features for the preoperative differential diagnosis of AME and OKC and compares ML algorithms to expert radiologists to validate performance | ||
| 520 | |a METHODS: We retrospectively collected the data of 326 patients with AME and OKC, where all diagnoses were confirmed by histopathologic tests. A total of 348 features were selected to train six ML models for differential diagnosis by a five-fold cross-validation. We then compared the performance of ML-based diagnoses to those of radiologists | ||
| 520 | |a RESULTS: Among the six ML models, XGBoost was effective in distinguishing AME and OKC in CBCT images, with its classification performance outperforming the other models. The mean precision, recall, accuracy, F1-score, and area under the curve (AUC) were 0.900, 0.807, 0.843, 0.841, and 0.872, respectively. Compared to the diagnostics by radiologists, ML-based radiomic diagnostics performed better | ||
| 520 | |a CONCLUSIONS: Radiomic-based ML algorithms allow CBCT images of AME and OKC to be distinguished accurately, facilitating the preoperative differential diagnosis of AME and OKC | ||
| 520 | |a ADVANCES IN KNOWLEDGE: ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a ameloblastoma | |
| 650 | 4 | |a cone beam computed tomography | |
| 650 | 4 | |a differential diagnosis | |
| 650 | 4 | |a odontogenic keratocyst | |
| 650 | 4 | |a radiomics | |
| 700 | 1 | |a Ma, Sirui |e verfasserin |4 aut | |
| 700 | 1 | |a Mao, Bing |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Kun |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Yuan |e verfasserin |4 aut | |
| 700 | 1 | |a Ma, Jingdong |e verfasserin |4 aut | |
| 700 | 1 | |a Jia, Jun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Dento maxillo facial radiology |d 1975 |g (2024) vom: 16. Apr. |w (DE-627)NLM002901382 |x 1476-542X |7 nnns |
| 773 | 1 | 8 | |g year:2024 |g day:16 |g month:04 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1093/dmfr/twae016 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 16 |c 04 | ||