Accurate segmentation of the mandible from cone-beam computed tomography (CBCT) scans is an important step for building a personalized 3D digital mandible model for maxillofacial surgery and orthodontic treatment planning because of the low radiation dose and short scanning duration. CBCT images, however, exhibit lower contrast and higher levels of noise and artifacts due to extremely low radiation in comparison with the conventional computed tomography (CT), which makes automatic mandible segmentation from CBCT data challenging. In this work, we propose a novel coarse-to-fine segmentation framework based on 3D convolutional neural network and recurrent SegUnet for mandible segmentation in CBCT scans. Specifically, the mandible segmentation is decomposed into two stages: localization of the mandible-like region by rough segmentation and further accurate segmentation of the mandible details. The method was evaluated using a dental CBCT dataset. In addition, we evaluated the proposed method and compared it with state-of-the-art methods in two CT datasets. The experiments indicate that the proposed algorithm can provide more accurate and robust segmentation results for different imaging techniques in comparison with the state-of-the-art models with respect to these three datasets.

Recently, accurate mandible segmentation in CT scans based on deep learning methods has attracted much attention. However, there still exist two major challenges, namely, metal artifacts among mandibles and large variations in shape or size among individuals. To address these two challenges, we propose a

For patients who suffer from severe dysfunction of the temporomandibular joint (TMJ), a total joint replacement (TJR) in the form of a prosthesis may be indicated. The position of the centre of rotation in TJRs is crucial for good postoperative oral function; however, it is not determined patient-specifically (PS) in any current TMJ-TJR. The aim of this current study was to develop a 4D-workflow to ascertain the PS mean axis of rotation, or fixed hinge, that mimics the patient’s specific physiological mouth opening. Twenty healthy adult patients were asked to volunteer for a 4D-scanning procedure. From these 4D-scanning recordings of mouth opening exercises, patient-specific centres of rotation and axes of rotation were determined using our JawAnalyser tool. The mean CR location was positioned 28 [mm] inferiorly and 5.5 [mm] posteriorly to the centre of condyle (CoC). The 95% confidence interval ranged from 22.9 to 33.7 [mm] inferior and 3.1 to 7.8 [mm] posterior to the CoC. This study succeeded in developing an accurate 4D-workflow to determine a PS mean axis of rotation that mimics the patient’s specific physiological mouth opening. Furthermore, a change in concept is necessary for all commercially available TMJ-TJR prostheses in order to comply with the PS CRs calculated by our study. In the meantime, it seems wise to stick to placing the CR 15 [mm] inferiorly to the CoC, or even beyond, towards 28 [mm] if the patient’s anatomy allows this.