Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, posing challenges for integration into real-world workflows. In this pre-registered prospective multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. Our results suggest that for a given model, segmentation accuracy can vary by up to 25% in Dice score as socio-technical factors such as voxel size, bone orientation, and patient conditions (e.g., osteosynthesis or pathology) shift from favorable to adverse. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as “plug-and-play” tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare.

Self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in various real-world scenarios. Unfortunately, challenges such as specular reflections and soft tissue deformations in endoscopic scenes greatly undermine the performance of these methods, inevitably compromising the accuracy of depth and ego-motion estimation. To address these two problems, we introduce a novel strategy based on image distance transform for robust self-supervised learning for monocular depth estimation, effectively handling specular reflections in endoscopic scenes. Furthermore, we propose a soft tissue deformation constraint based on biomechanical principles, which mitigates the adverse effects of deformed region pixels, ultimately enhancing the model's depth estimation precision. Additionally, our method employs a lightweight architecture ensuring a reduced number of model parameters and faster inference time. Extensive experiments are conducted on both public datasets (SCARED, SERV-CT) and our own datasets to validate the effectiveness of our method. Compared with other SOTA methods, our approach demonstrates comparable accuracy and robustness while ensuring faster inference time. On the SCARED dataset, our approach attains an RMSE of 4.96 mm with only 2.25M model parameters for depth estimation. Especially, experiment results on SERV-CT dataset and our own datasets further demonstrate the model's generalization ability and potential clinical value in computer-assisted surgical navigation.

Maxillary Sinus Lifting is a crucial surgical procedure for addressing insufficient alveolar bone mass andsevere resorption in dental implant therapy. To accurately analyze the geometry changesof the bone graft (BG) in the maxillary sinus (MS), it is essential to perform quantitative analysis. However, automated BG segmentation remains a major challenge due to the complex local appearance, including blurred boundaries, lesion interference, implant and artifact interference, and BG exceeding the MS. Currently, there are few tools available that can efficiently and accurately segment BG from cone beam computed tomography (CBCT) image. In this paper, we propose a distance-constrained attention network guided by prior anatomical knowledge for the automatic segmentation of BG. First, a guidance strategy of preoperative prior anatomical knowledge is added to a deep neural network (DNN), which improves its ability to identify the dividing line between the MS and BG. Next, a coordinate attention gate is proposed, which utilizes the synergy of channel and position attention to highlight salient features from the skip connections. Additionally, the geodesic distance constraint is introduced into the DNN to form multi-task predictions, which reduces the deviation of the segmentation result. In the test experiment, the proposed DNN achieved a Dice similarity coefficient of 85.48 6.38%, an average surface distance error is 0.57 0.34mm, and a 95% Hausdorff distance of 2.64 2.09mm, which is superior to the comparison networks. It markedly improves the segmentation accuracy and efficiency of BG and has potential applications in analyzing its volume change and absorption rate in the future.

Pelvic fracture is a severe trauma with a high rate of morbidity and mortality. Accurate and automatic diagnosis and surgical planning of pelvic fracture require effective identification and localization of the fracture zones. This is a challenging task due to the complexity of pelvic fractures, which often exhibit multiple fragments and sites, large fragment size differences, and irregular morphology. We have developed a novel two-stage method for the automatic identification and localization of complex pelvic fractures. Our method is unique in that it allows to combine the symmetry properties of the pelvic anatomy and capture the symmetric feature differences caused by the fracture on both the left and right sides, thereby overcoming the limitations of existing methods which consider only image or geometric features. It implements supervised contrastive learning with a novel Siamese deep neural network, which consists of two weight-shared branches with a structural attention mechanism, to minimize the confusion of local complex structures of the pelvic bones with the fracture zones. A structure-focused attention (SFA) module is designed to capture the spatial structural features and enhances the recognition ability of fracture zones. Comprehensive experiments on 103 clinical CT scans from the publicly available dataset CTPelvic1K show that our method achieves a mean accuracy and sensitivity of 0.92 and 0.93, which are superior to those reported with three SOTA contrastive learning methods and five advanced classification networks, demonstrating the effectiveness of identifying and localizing various types of complex pelvic fractures from clinical CT images.