Artificial intelligence vs. semi-automated segmentation for assessment of dental periapical lesion volume index score: A cone-beam CT study

• Published in: Computers in biology and medicine Vol. 175; p. 108527
• Main Authors: Boubaris, Matthew, Cameron, Andrew, Manakil, Jane, George, Roy
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2024; Elsevier Limited
• Subjects: Artificial intelligence; Automation; Computed tomography; Cone-beam computed tomography; Dental roots; Dentistry; Endodontics; Gum disease; Image segmentation; Lesions; Periapical disease; Recall; Segmentation; Teeth; Three dimensional analysis; Volume measurement; United States > US; San Francisco California; Endodontics; Dentistry; Cone-beam computed tomography; Artificial intelligence; Periapical disease
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108527

Cone beam computed tomography periapical volume index (CBCTPAVI) is a categorisation tool to assess periapical lesion size in three-dimensions and predict treatment outcomes. This index was determined using a time-consuming semi-automatic segmentation technique. This study compared artificial intelligence (AI) with semi-automated segmentation to determine AI's ability to accurately determine CBCTPAVI score. CBCTPAVI scores for 500 tooth roots were determined using both the semi-automatic segmentation technique in three-dimensional imaging analysis software (Mimics Research™) and AI (Diagnocat™). A confusion matrix was created to compare the CBCTPAVI score by the AI with the semi-automatic segmentation technique. Evaluation metrics, precision, recall, F1-score (2×precision×recallprecision+recall), and overall accuracy were determined. In 84.4 % (n = 422) of cases the AI classified CBCTPAVI score the same as the semi-automated technique. AI was unable to classify any lesion as index 1 or 2, due to its limitation in small volume measurement. When lesions classified as index 1 and 2 by the semi-automatic segmentation technique were excluded, the AI demonstrated levels of precision, recall and F1-score, all above 0.85, for indices 0, 3–6; and accuracy over 90 %. Diagnocat™ with its ability to determine CBCTPAVI score in approximately 2 min following upload of the CBCT could be an excellent and efficient tool to facilitate better monitoring and assessment of periapical lesions in everyday clinical practice and/or radiographic reporting. However, to assess three-dimensional healing of smaller lesions (with scores 1 and 2), further advancements in AI technologies are needed. [Display omitted]