Background: Three-dimensional (3D) reconstruction of ossicular chain and bony labyrinth based on temporal bone high-resolution CT (HRCT) is useful for diagnosis and treatment guidance of middle and inner ear diseases. However, these structures are small and irregular, making manual reconstruction time-consuming. Purpose: To develop and validate an artificial intelligence (AI) model based on semisupervised learning for automated 3D reconstruction of ossicular chain and bony labyrinth on HRCT images. Methods: HRCT images from 304 ears of 152 consecutive patients retrospectively collected from a single center were randomly divided into training (246 ears), validation (28 ears), and internal test (30 ears) cohorts for model development. A novel semisupervised ear bone segmentation framework was used to train the AI model, and its performance was evaluated by Dice similarity coefficients. The trained algorithm was applied to a temporally independent test dataset of 30 ears of 15 patients from the same center for comparison with manual 3D reconstruction for processing time, target volume, and visual assessment of segmentation. Results: The AI model demonstrated a Dice score of 0.948 (95% CI, 0.940-0.955) for the internal and 0.979 (95% CI, 0.973-0.986) for the temporally independent test sets. In the latter dataset, the AI model required 2% or less processing time of manual 3D reconstruction for each ear (17.7 seconds ± 10.1 vs 1080.5 seconds ± 149.8; P < .001) and had an accuracy comparable to human experts in the volume and visual assessment of segmentation targets (P = .237-1.000). In a subgroup analysis, the model achieved accurate segmentation (Dice scores of 0.98-0.99) across various diseases (eg, otitis media, mastoiditis, otosclerosis, middle and inner ear malformations, Ménière disease). Conclusion: The AI model enables robust, efficient and accurate 3D reconstruction for the small structures such as ossicular chain and bony labyrinth on HRCT images.

Background: Radiation-induced cystic brain necrosis (RCN) can progress rapidly to life-threatening cerebral herniation. This study aimed to develop a predictive model integrating radiomic features and clinical variables to assess the risk of cerebral herniation in RCN patients. Methods: A total of 130 patients diagnosed with RCN following radiotherapy for nasopharyngeal carcinoma were retrospectively enrolled and randomly assigned to training (n = 91) and testing (n = 39) cohorts in a 7:3 ratio. Radiomic features were extracted from baseline T2-weighted magnetic resonance imaging (MRI), and a radiomic signature was constructed using least absolute shrinkage and selection operator regression. A multivariate Cox regression model was then developed by incorporating the radiomic signature and clinical variables to predict cerebral herniation. The model’s discriminative ability, calibration, and clinical utility were evaluated. Results: The radiomic signature based on five selected radiomic features demonstrated good predictive performance. The radiomic model, which integrated the radiomic signature and ratios of perilesional enhancement, exhibited favorable performance in both the training cohort (C-index: 0.841) and testing cohort (C-index: 0.867). The model successfully stratified patients into high- and low-risk groups. The calibration curves showed good agreement and the decision curve confirmed the clinical utility of the model. Conclusions: The MRI-based radiomic model, which integrates radiomic features and clinical variables, demonstrates robust performance in predicting cerebral herniation in RCN patients, offering a practical and user-friendly tool to support clinical decision-making.