To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
The foramen ovale and foramen rotundum of the skull base serve as critical anatomical approaches for percutaneous puncture of the trigeminal ganglion. Their three-dimensional orientation is crucial for designing surgical pathways and avoiding adjacent vital structures. However, this orientation exhibits significant individual variability, and its assessment currently lacks automated quantitative methods. To address this issue, the present study formulates the puncture foramina orientation estimation as a geometric optimization problem and proposes a coarse-to-fine solution framework: first, a coarse estimate is obtained through adaptive multi-stage random sampling to rapidly cover the feasible region, followed by a refined estimate using optimization techniques based on differentiable rendering. Experiments on 64 foraminal structures from 16 subjects demonstrated that the average angular error of the automatically estimated results was 2.21 °, which is smaller than the inter-observer variability among physicians 4.81 °. The method outperforms manual judgment in terms of accuracy, providing an objective anatomical reference for personalized puncture path planning and demonstrating clear potential for clinical translation.