发表机构
Università Cattolica del Sacro Cuore; IHU Strasbourg; Fondazione Policlinico Universitario Agostino Gemelli IRCCS; University of Strasbourg; Sapienza University of Rome; University Hospital Virgen Macarena; University of Sevilla; Fondazione IRCCS - Ca’ Granda - Ospedale Maggiore Policlinico di Milano（圣心天主教大学; 斯特拉斯堡大学医院研究所; 阿戈斯蒂诺·杰梅里大学医院基金会IRCCS; 斯特拉斯堡大学; 罗马第一大学; 维尔gen马卡雷纳大学医院; 塞维利亚大学; IRCCS基金会-米兰马焦雷医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究开发AI-ColoWorkflow深度学习模型，基于多中心MIS-CRS数据训练，可可靠识别手术阶段，其泛化性能优于多数中心/手术类型特定模型，为外科AI混合训练策略提供依据。
AI 中文摘要
微创结直肠手术（MIS-CRS）的特点是存在显著变异性且结局不一致。ColoWorkflow是一种用于MIS-CRS手术工作流程视频评估（VBA）的工具，近期已得到验证，但手动VBA耗时，限制了其应用。本研究提出AI-ColoWorkflow，这是一种用于MIS-CRS自动化手术工作流程分析的深度学习模型。从4个中心及一个公开数据集收集了MIS-CRS的手术视频，按照ColoWorkflow对手术阶段和步骤进行手动标注。该深度学习模型结合了微调后的DINOv3视觉Transformer（用于逐帧视觉特征提取）与分层多阶段时间卷积网络，针对阶段和步骤识别进行联合优化。在保留的测试集上，将基于合并多中心数据训练的AI-ColoWorkflow与中心特定模型、手术类型特定模型进行对比，采用的评估指标包括宏F1分数、平衡准确率、精确率和召回率。AI-ColoWorkflow在阶段识别任务中达到宏F1为73.01%±10.27（平衡准确率73.43%），在步骤识别任务中达到39.82%±7.06（平衡准确率38.65%）。在多数实验中，全局模型（AI-ColoWorkflow）的性能优于中心特定模型和手术类型特定模型，仅在手术类型特定步骤识别任务中例外。在泛化分析中，阶段识别的平均F1为48.42%。AI-ColoWorkflow可可靠识别MIS-CRS的手术阶段，基于合并的多中心、多手术类型数据训练的单一模型，在MIS-CRS阶段识别任务中的泛化性能至少与中心特定模型或手术类型特定模型相当，且通常更优；而手术类型特定的步骤模型在某些手术类型中仍具优势，这为未来外科AI开发的混合训练策略提供了依据。
英文摘要
Minimally invasive colorectal surgeries (MIS-CRS) are characterised by significant variability and inconsistent outcomes. ColoWorkflow, a tool for the video-based assessment (VBA) of MIS-CRS workflow, was recently validated. However, manual VBA is time-consuming, limiting implementation. This study presents AI-ColoWorkflow, a deep learning model for automated surgical workflow analysis across MIS-CRS. Operative videos of MIS-CRS were collected from 4 centres and a publicly available dataset. Phases and steps were manually annotated according to ColoWorkflow. A deep learning model combining a fine-tuned DINOv3 vision transformer for per-frame visual feature extraction with a hierarchical multi-stage temporal convolutional network was jointly optimized for phase and step recognition. The model trained on pooled multicentric data, namely AI-ColoWorkflow was compared against centre-specific and procedure-specific models on a held-out test set. The following metrics were used for evaluation: macro F1 score, balanced accuracy, precision, and recall. AI-ColoWorkflow achieved a macro F1 of 73.01% $\pm$ 10.27 (balanced accuracy 73.43%) for phase recognition and 39.82% $\pm$ 7.06 (balanced accuracy 38.65%) for step recognition. The global model outperformed centre- and procedure-specific models in most experiments except procedure-specific step recognition. In the generalization analysis, mean F1 was 48.42% for phase recognition. AI-ColoWorkflow can reliably recognize MIS-CRS phases. A single model trained on pooled, multicentric, multi-procedural data generalises at least as well as and often better than centre- or procedure-specific models for phase recognition in MIS-CRS, while procedure-specific step models retain advantages for certain procedure types, motivating hybrid training strategies for future surgical AI development.
