Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning
The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesi...
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-08-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/12/8/1968 |
_version_ | 1797410706522374144 |
---|---|
author | Balazs Feher Ulrike Kuchler Falk Schwendicke Lisa Schneider Jose Eduardo Cejudo Grano de Oro Tong Xi Shankeeth Vinayahalingam Tzu-Ming Harry Hsu Janet Brinz Akhilanand Chaurasia Kunaal Dhingra Robert Andre Gaudin Hossein Mohammad-Rahimi Nielsen Pereira Francesc Perez-Pastor Olga Tryfonos Sergio E. Uribe Marcel Hanisch Joachim Krois |
author_facet | Balazs Feher Ulrike Kuchler Falk Schwendicke Lisa Schneider Jose Eduardo Cejudo Grano de Oro Tong Xi Shankeeth Vinayahalingam Tzu-Ming Harry Hsu Janet Brinz Akhilanand Chaurasia Kunaal Dhingra Robert Andre Gaudin Hossein Mohammad-Rahimi Nielsen Pereira Francesc Perez-Pastor Olga Tryfonos Sergio E. Uribe Marcel Hanisch Joachim Krois |
author_sort | Balazs Feher |
collection | DOAJ |
description | The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50–0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw. |
first_indexed | 2024-03-09T04:34:16Z |
format | Article |
id | doaj.art-c384718046d147e3abd31d9b51afa1b0 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-09T04:34:16Z |
publishDate | 2022-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-c384718046d147e3abd31d9b51afa1b02023-12-03T13:32:11ZengMDPI AGDiagnostics2075-44182022-08-01128196810.3390/diagnostics12081968Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine LearningBalazs Feher0Ulrike Kuchler1Falk Schwendicke2Lisa Schneider3Jose Eduardo Cejudo Grano de Oro4Tong Xi5Shankeeth Vinayahalingam6Tzu-Ming Harry Hsu7Janet Brinz8Akhilanand Chaurasia9Kunaal Dhingra10Robert Andre Gaudin11Hossein Mohammad-Rahimi12Nielsen Pereira13Francesc Perez-Pastor14Olga Tryfonos15Sergio E. Uribe16Marcel Hanisch17Joachim Krois18Department of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, 1090 Vienna, AustriaDepartment of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, 1090 Vienna, AustriaDepartment of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, GermanyDepartment of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, GermanyDepartment of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, GermanyDepartment of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, 6525 GA Nijmegen, The NetherlandsDepartment of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, 6525 GA Nijmegen, The NetherlandsComputer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, USADepartment of Restorative Dentistry, Ludwig-Maximilians-University of Munich, 80336 Munich, GermanyDepartment of Oral Medicine and Radiology, Faculty of Dental Sciences, King George’s Medical University, Lucknow 226003, IndiaPeriodontics Division, Centre for Dental Education and Research, All India Institute of Medical Sciences, New Delhi 110029, IndiaDepartment of Oral and Maxillofacial Surgery, Charité—University Medicine Berlin, 14197 Berlin, GermanyDentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran 1416634793, IranPrivate Practice in Oral and Maxillofacial Radiology, Rio de Janeiro 22430-000, BrazilServei Salut Dental, Gerencia Atencio Primaria, Institut Balear de la Salut, 07003 Palma, SpainDepartment of Periodontology and Oral Biochemistry, Academic Centre for Dentistry Amsterdam, 1081 LA Amsterdam, The NetherlandsDepartment of Conservative Dentistry & Oral Health, Riga Stradins University, LV-1007 Riga, LatviaDepartment of Oral and Maxillofacial Surgery, University Clinic Münster, 48143 Münster, GermanyDepartment of Oral Diagnostics, Digital Health, and Health Services Research, Charité—University Medicine Berlin, 14197 Berlin, GermanyThe detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50–0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw.https://www.mdpi.com/2075-4418/12/8/1968artificial intelligencemachine learningsurgeryoralradiographycysts |
spellingShingle | Balazs Feher Ulrike Kuchler Falk Schwendicke Lisa Schneider Jose Eduardo Cejudo Grano de Oro Tong Xi Shankeeth Vinayahalingam Tzu-Ming Harry Hsu Janet Brinz Akhilanand Chaurasia Kunaal Dhingra Robert Andre Gaudin Hossein Mohammad-Rahimi Nielsen Pereira Francesc Perez-Pastor Olga Tryfonos Sergio E. Uribe Marcel Hanisch Joachim Krois Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning Diagnostics artificial intelligence machine learning surgery oral radiography cysts |
title | Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning |
title_full | Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning |
title_fullStr | Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning |
title_full_unstemmed | Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning |
title_short | Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning |
title_sort | emulating clinical diagnostic reasoning for jaw cysts with machine learning |
topic | artificial intelligence machine learning surgery oral radiography cysts |
url | https://www.mdpi.com/2075-4418/12/8/1968 |
work_keys_str_mv | AT balazsfeher emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT ulrikekuchler emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT falkschwendicke emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT lisaschneider emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT joseeduardocejudogranodeoro emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT tongxi emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT shankeethvinayahalingam emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT tzumingharryhsu emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT janetbrinz emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT akhilanandchaurasia emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT kunaaldhingra emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT robertandregaudin emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT hosseinmohammadrahimi emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT nielsenpereira emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT francescperezpastor emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT olgatryfonos emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT sergioeuribe emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT marcelhanisch emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning AT joachimkrois emulatingclinicaldiagnosticreasoningforjawcystswithmachinelearning |