实时人工智能解剖识别在单孔经膀胱前列腺剜除术中的可行性研究
本研究回顾性分析37例单孔机器人辅助经膀胱前列腺剜除术(STEP)的手术视频,提取611帧标注图像训练基于YOLOv11的卷积神经网络,用于实时检测和分割膀胱颈、前列腺腺瘤及外周带。模型检测F1分数腺瘤0.88、膀胱颈0.69、外周带0.70,分割Dice系数分别为0.86、0.83、0.82,平均AP为0.43,推理速度>60帧/秒,证实实时解剖引导可行。
要点
- AI模型可实时识别STEP中膀胱颈、腺瘤和外周带,推理速度>60帧/秒。
- 腺瘤检测F1分数0.88,分割Dice系数0.86,表现最佳。
- 膀胱颈和外周带识别性能中等(F1 0.69/0.70,Dice 0.83/0.82)。
核心结论
- AI模型在STEP中提供实时解剖引导具有潜在可行性,为未来临床整合与性能优化奠定基础。
研究设计与样本
- 回顾性单中心研究,使用单一位专家 surgeon 完成的37例单孔机器人辅助经膀胱前列腺剜除术的手术视频。
- 从视频中提取611帧标注图像,标注膀胱颈、前列腺腺瘤和外周带,训练基于YOLOv11架构的卷积神经网络。
主要发现
- 检测F1分数:腺瘤0.88,膀胱颈0.69,外周带0.70。
- 分割Dice相似系数:腺瘤0.86,膀胱颈0.83,外周带0.82。
- 所有解剖类别的平均AP为0.43。
- 模型推理速度持续>60帧/秒,无感知延迟。
临床怎么用
- 该AI模型可在STEP术中实时识别关键解剖结构,辅助术者定位膀胱颈、腺瘤和外周带。
- 当前性能以腺瘤识别最佳,膀胱颈和外周带识别有待优化。
局限性
- 回顾性单中心小样本试点研究,仅纳入单一位专家 surgeon 的手术视频。
- 模型性能尚需外部验证和进一步优化。
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 evaluate the feasibility and accuracy of an artificial intelligence (AI) model to assist surgeons through automated real-time detection and segmentation of key anatomical structures during robot-assisted single-port transvesical enucleation of the prostate (STEP). PATIENTS AND METHODS: This retrospective single-centre study utilised surgical videos from patients undergoing single-port robot-assisted transvesical prostate enucleation performed by a single expert surgeon. Selected frames extracted from these surgical videos were manually annotated to identify anatomical landmarks during the key step of the procedure. The structures annotated were the bladder neck, prostatic adenoma, and the peripheral zone. A convolutional neural network based on the You Only Look Once version 11 architecture was trained using these annotated frames. Model performance was quantitatively assessed through recall, precision, F1-score, Intersection over Union, Dice Similarity Coefficient, and mean average precision (AP). Real-time performance was assessed qualitatively through visual inspection and confirmed quantitatively by measuring frame inference speeds. RESULTS: The study included 611 annotated frames derived from 37 surgical videos. The model demonstrated strong detection performance, with class-specific F1-scores of 0.88 (adenoma), 0.69 (bladder neck), and 0.70 (peripheral zone). Segmentation accuracy, measured by Dice Similarity Coefficient, resulted in adenoma: 0.86; bladder neck: 0.83; peripheral zone: 0.82. Mean AP across all anatomical classes was 0.43. The model consistently operated at >60 frames/s, confirming real-time applicability without perceptible lag. CONCLUSIONS: This pilot study demonstrates the potential utility of AI to provide intraoperative anatomical guidance during STEP, establishing a foundation for future clinical integration and performance optimization.
引用
- Morgantini LA, Cruciani L, Lettieri AC, et al. Real-time artificial intelligence-based anatomy recognition in single-port transvesical enucleation of the prostate. BJU Int. 2026. PMID: 42595333. doi:10.1111/bju.70424
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。