Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning

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

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

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.

Original languageEnglish
Article number1968
Pages (from-to)1-14
Number of pages14
JournalDiagnostics
Volume12
Issue number8
Early online date14 Aug 2022
DOIs
Publication statusPublished - Aug 2022

Bibliographical note

Special Issue: Artificial Intelligence in Oral Diagnostics.

Funding Information:
SU acknowledges financial support from the European Union’s Horizon 2020 research and innovation programme under the grant agreement No 857287.

Publisher Copyright:
© 2022 by the authors.

Funding

SU acknowledges financial support from the European Union’s Horizon 2020 research and innovation programme under the grant agreement No 857287.

FundersFunder number
Horizon 2020 Framework Programme857287
Horizon 2020 Framework Programme

    Keywords

    • artificial intelligence
    • cysts
    • diagnosis
    • machine learning
    • oral
    • radiography
    • surgery

    Fingerprint

    Dive into the research topics of 'Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning'. Together they form a unique fingerprint.

    Cite this