Abstract
The segmentation of medical and dental images is a fundamental step in automated clinical decision support systems. It supports the entire clinical workflow from diagnosis, therapy planning, intervention, and follow-up. In this paper, we propose a novel tool to accurately process a full-face segmentation in about 5 minutes that would otherwise require an average of 7h of manual work by experienced clinicians. This work focuses on the integration of the state-of-the-art UNEt TRansformers (UNETR) of the Medical Open Network for Artificial Intelligence (MONAI) framework. We trained and tested our models using 618 de-identified Cone-Beam Computed Tomography (CBCT) volumetric images of the head acquired with several parameters from different centers for a generalized clinical application. Our results on a 5-fold cross-validation showed high accuracy and robustness with a Dice score up to 0.962±0.02. Our code is available on our public GitHub repository.
Funder
American Association of Orthodontists Foundation
National Institute of Dental and Craniofacial Research
University of the Pacific
Publisher
Public Library of Science (PLoS)
Reference31 articles.
1. Computer-aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours;TW Way;Medical physics,2006
2. D D’Haese PF, Duay V, Li R, du Bois d’Aische A, Merchant TE, Cmelak AJ, et al. Automatic segmentation of brain structures for radiation therapy planning. In: Medical Imaging 2003: Image Processing. vol. 5032. International Society for Optics and Photonics; 2003. p. 517–526.
3. Deep learning-based liver segmentation for fusion-guided intervention;X Fang;International journal of computer assisted radiology and surgery,2020
4. Successful pulp revascularization of an autotransplantated mature premolar with fragile fracture apicoectomy and plasma rich in growth factors: a 3-year follow-up;J Gaviño Orduña;International Endodontic Journal,2020
5. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability;PA Yushkevich;Neuroimage,2006
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献