Oral and Maxillofacial Radiology, Adams School of Dentistry, University of North Carolina, Chapel Hill, NC, USA.
Denti.AI Technology Inc., Toronto, Ontario, Canada.
Oral Surg Oral Med Oral Pathol Oral Radiol. 2024 Jul;138(1):173-183. doi: 10.1016/j.oooo.2023.09.011. Epub 2023 Oct 16.
The study aim was to develop and assess the performance of a deep learning (DL) algorithm in the detection of radiolucent intraosseous jaw lesions in cone beam computed tomography (CBCT) volumes.
A total of 290 CBCT volumes from more than 12 different scanners were acquired. Fields of view ranged from 6 × 6 × 6 cm to 18 × 18 × 16 cm. CBCT volumes contained either zero or at least one biopsy-confirmed intraosseous lesion. 80 volumes with no intraosseous lesions were included as controls and were not annotated. 210 volumes with intraosseous lesions were manually annotated using ITK-Snap 3.8.0. 150 volumes (10 control, 140 positive) were presented to the DL software for training. Validation was performed using 60 volumes (30 control, 30 positive). Testing was performed using the remaining 80 volumes (40 control, 40 positive).
The DL algorithm obtained an adjusted sensitivity by case, specificity by case, positive predictive value by case, and negative predictive value by case of 0.975, 0.825, 0.848, and 0.971, respectively.
A DL algorithm showed moderate success at lesion detection in their correct locations, as well as recognition of lesion shape and extent. This study demonstrated the potential of DL methods for intraosseous lesion detection in CBCT volumes.
本研究旨在开发并评估一种深度学习（DL）算法在检测锥形束 CT（CBCT）容积中骨内透光性病变中的性能。
共获取了来自 12 个以上不同扫描仪的 290 个 CBCT 容积。视野范围从 6×6×6cm 到 18×18×16cm 不等。CBCT 容积中要么没有骨内病变，要么至少有一个经活检证实的骨内病变。80 个无骨内病变的容积作为对照，未进行注释。使用 ITK-Snap 3.8.0 对 210 个具有骨内病变的容积进行手动注释。将 150 个容积（10 个对照，140 个阳性）提供给 DL 软件进行训练。使用 60 个容积（30 个对照，30 个阳性）进行验证。使用其余 80 个容积（40 个对照，40 个阳性）进行测试。
该 DL 算法在病例调整的敏感度、病例特异性、病例阳性预测值和病例阴性预测值方面的表现分别为 0.975、0.825、0.848 和 0.971。
DL 算法在正确位置的病变检测、病变形状和范围的识别方面取得了中等程度的成功。本研究表明，DL 方法在 CBCT 容积中的骨内病变检测中具有潜力。
