机器人辅助根治性前列腺切除术手术阶段识别的人工智能模型开发
本研究开发并评估基于卷积神经网络(CNN)的模型,用于识别机器人辅助腹腔镜根治性前列腺切除术(RARP)中的手术阶段,重点关注模型可解释性与跨平台验证。模型在 hinotori 系统测试集上准确率为 0.90,但在 da Vinci 数据集上降至 0.64,显示跨平台局限性。
要点
- CNN 模型在单一机器人平台测试集准确率达 0.90。
- 跨平台验证准确率降至 0.64,泛化能力有限。
- 梯度加权类激活映射提升可解释性,聚焦中央盆腔结构。
核心结论
- 模型在单一机器人平台表现高准确率,但跨平台性能需进一步优化。
- 可解释性技术有助于临床信任和工作流整合。
研究设计与样本
- 使用 EfficientNet B7 的 CNN,基于 75 例 hinotori 机器人系统 RARP 视频数据训练。
- 在 25 例 da Vinci 机器人系统 RARP 病例上验证跨平台泛化性。
主要发现
- hinotori 测试集准确率为 0.90,da Vinci 数据集准确率为 0.64。
- 阶段特异性 F1 分数范围为 0.77 至 0.97,精囊解剖和尖部解剖阶段性能较低。
- 梯度加权类激活映射显示模型关注中央盆腔结构而非瞬态器械。
临床怎么用
- 当前模型适用于单一机器人平台的手术阶段识别,跨平台应用需进一步验证和优化。
- 可解释性可视化可辅助临床医生理解模型决策,促进工作流整合。
局限性
- 跨平台泛化性有限,da Vinci 数据集准确率显著下降。
- 精囊解剖和尖部解剖阶段识别性能较低。
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
OBJECTIVES: To develop and evaluate a convolutional neural network (CNN)-based model for recognising surgical phases in robot-assisted laparoscopic radical prostatectomy (RARP), with an emphasis on model interpretability and cross-platform validation. METHODS: A CNN using EfficientNet B7 was trained on video data from 75 RARP cases with the hinotori robotic system. Seven phases were annotated: bladder drop, prostate preparation, bladder neck dissection, seminal vesicle dissection, posterior dissection, apical dissection, and vesicourethral anastomosis. A total of 808 774 video frames were extracted at 1 frame/s for training and testing. Validation was performed on 25 RARP cases using the da Vinci robotic system to assess cross-platform generalisability. Gradient-weighted class activation mapping was used to enhance interpretability by identifying key regions of interest for phase classification. RESULTS: The CNN achieved 0.90 accuracy on the hinotori test set but dropped to 0.64 on the da Vinci dataset, thus indicating cross-platform limitations. Phase-specific F1 scores ranged from 0.77 to 0.97, with lower performance in the phase of seminal vesicle dissection, and apical dissection. Gradient-weighted class activation mapping visualisations revealed the model's focus on central pelvic structures rather than transient instruments, enhancing interpretability and insights into phase classification. CONCLUSIONS: The model demonstrated high accuracy on a single robotic platform but requires further refinement for consistent cross-platform performance. Interpretability techniques will foster clinical trust and integration into workflows, advancing robotic surgery applications.
引用
- Ueki H, Uemura M, Chinzei K, et al. Developing an artificial intelligence model for phase recognition in robot-assisted radical prostatectomy. BJU Int. 2025. PMID: 40693331. doi:10.1111/bju.16862
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。