[Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].
Y, L., H, Z., S, G., D, T., W, S., Y, M., & Z, J. (2026). [Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].. Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengx. https://doi.org/10.7507/1001-5515.202512001
Y L, H Z, S G, D T, W S, Y M, et al. [Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].. Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengx. 2026; doi: 10.7507/1001-5515.202512001
Y L, H Z, S G, et al. [Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].[J]. Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengx. 2026. DOI: 10.7507/1001-5515.202512001.
@article{y2026,
author = {Li Y and Zhang H and Geng S and Tan D and Shi W and Miao Y and Jiang Z},
title = {[Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina].},
journal = {Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengx},
year = {2026},
doi = {10.7507/1001-5515.202512001},
note = {PMID: 42366442},
}
TY - JOUR AU - Li Y AU - Zhang H AU - Geng S AU - Tan D AU - Shi W AU - Miao Y AU - Jiang Z TI - [Novel framework based on multi-stage random sampling and differentiable rendering for automated three-dimensional orientation estimation of skull base foramina]. T2 - Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengx PY - 2026 DO - 10.7507/1001-5515.202512001 AN - PMID:42366442 ER -
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. 颅底圆孔与卵圆孔是经皮穿刺三叉神经的关键解剖入路，其三维方向对于手术路径设计及规避邻近重要组织结构至关重要。然而，该三维方向存在明显的个体差异，且目前缺乏自动化定量评估手段。基于此，本研究将穿刺孔道方向估计转化为几何优化问题，提出一种由粗到精的求解框架，即首先通过自适应多阶段随机采样进行粗估计以快速覆盖可行区域，进而利用基于可微渲染的优化技术实现精细化估计。通过在16名受试者共计64个孔道结构上的研究表明，自动估计结果平均角度误差为2.21 °，小于医生间观察者变异度4.81 °，在精度上优于人工判断，为个性化穿刺路径规划提供了客观解剖基准，具有明确的临床转化潜力。.