深度学习用于直视光学戳卡置入时腹壁层次语义分割
该单中心初步研究从10例直视光学戳卡置入(DOTI)手术中提取951帧图像并逐像素标注,训练DeepLabV3+(ResNet-50骨干)模型分割腹直肌、腹直肌鞘与腹膜。五折交叉验证下平均IoU为0.794(95%CI 0.785-0.802),平均Dice为0.883(95%CI 0.878-0.889),提示该技术路线可行。
要点
- 模型对腹直肌、腹直肌鞘、腹膜的Dice分别为0.923、0.903、0.824。
- 组织类别间直接混淆仅0.0-0.3%,误差多位于组织-背景边界。
- 样本量小且为单中心,临床转化前需多中心前瞻性研究验证。
核心结论
- 该初步单中心研究显示,深度学习语义分割在光学戳卡置入过程中识别腹壁外组织层次具有技术可行性。
- 该框架为后续AI辅助手术引导研究提供了初步基础。
研究设计与样本
- 单中心初步研究,纳入10例直视光学戳卡置入(DOTI)手术,提取951帧图像进行逐像素标注。
- 标注分为腹直肌、腹直肌鞘、腹膜及背景四类,采用DeepLabV3+架构与ResNet-50骨干,五折交叉验证。
- 性能评估指标包括平均IoU、平均Dice系数、精确率、召回率与F1分数。
主要发现
- 模型平均IoU为0.794(95%CI 0.785-0.802),平均Dice为0.883(95%CI 0.878-0.889)。
- 分类别Dice为腹直肌0.923、腹直肌鞘0.903、腹膜0.824。
- 混淆矩阵显示组织类别间直接混淆为0.0-0.3%,多数错误局限于组织-背景边界。
临床怎么用
- 该模型目前仅作为技术可行性验证,尚不能直接用于临床手术引导。
- 未来或可辅助DOTI过程中识别腹壁层次、减少空间定向错误,但需进一步前瞻性验证。
局限性
- 患者队列小(10例DOTI手术),结果外推性受限。
- 为单中心初步研究,临床转化前需更大规模的多中心前瞻性研究。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: The initial entry phase of minimally invasive surgery-direct optical trocar insertion (DOTI)-remains high risk due to potential spatial disorientation. To our knowledge, this pilot study investigates a deep learning-based semantic segmentation framework for identifying critical abdominal wall layers during DOTI. METHODS: From 10 DOTI procedures, 951 frames were extracted and pixel-wise annotated into three anatomical classes-rectus muscle, rectus sheath, and peritoneum-plus background. A DeepLabV3+ architecture with ResNet-50 backbone was trained using five-fold cross-validation. Performance was assessed by mean Intersection over Union (mIoU), mean Dice coefficient (mDice), precision, recall, and F1-score. RESULTS: The model achieved a mean IoU of 0.794 (95% CI 0.785-0.802) and a mean Dice of 0.883 (95% CI 0.878-0.889). Class-specific Dice scores were 0.923 for rectus muscle, 0.903 for rectus sheath, and 0.824 for peritoneum. Confusion matrix analysis showed minimal direct confusion between anatomical tissue classes (0.0-0.3%), with most errors confined to tissue-background boundaries. CONCLUSION: This pilot single-center study demonstrates the technical feasibility of deep learning-based semantic segmentation for extra-abdominal tissue-layer identification during optical trocar insertion. Although the model showed consistent performance across five-fold cross-validation, the small patient cohort limits generalizability, and larger multi-center and prospective studies are required before clinical translation. The proposed framework provides a preliminary basis for future investigation of AI-assisted surgical guidance.
引用
- Farzadmanesh MJ, Jaliliyan A, Tavana P, et al. Deep learning-based semantic segmentation of abdominal wall layers during direct optical trocar insertion: toward AI-assisted surgical access. Surg Endosc. 2026. PMID: 42855513. doi:10.1007/s00464-026-13404-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。