深度学习在机器人辅助微创食管切除术中识别关键解剖结构
算法分割中位Dice分别为0.79(奇静脉/腔静脉)、0.74(主动脉)、0.89(肺),推理时间0.026秒(39 Hz);与专家标注相比,中位Dice分别为0.70、0.88、0.90。研究表明深度学习用于RAMIE解剖识别具有潜力,可实现实时识别,临床适用性需前瞻性研究评估。
要点
- CNN可实时分割RAMIE术中奇静脉/腔静脉、主动脉和右肺,推理时间0.026秒。
- 分割精度中位Dice:奇静脉/腔静脉0.79,主动脉0.74,右肺0.89。
- 与专家标注相比,中位Dice:奇静脉/腔静脉0.70,主动脉0.88,右肺0.90。
核心结论
- 深度学习语义分割在RAMIE视频帧中具有解剖识别潜力,算法推理时间支持实时识别。
主要发现
- 算法分割中位Dice:奇静脉和/或腔静脉0.79(IQR=0.20),主动脉0.74(IQR=0.86),肺0.89(IQR=0.30)。
- 推理时间为0.026秒(39 Hz)。
- 与专家外科医生标注相比,算法预测中位Dice:腔静脉和/或奇静脉0.70(IQR=0.19),主动脉0.88(IQR=0.07),肺0.90(IQR=0.10)。
临床怎么用
- 该算法有望在RAMIE术中辅助解剖定位和结构识别,但临床适用性尚需前瞻性临床研究评估。
局限性
- 研究为回顾性设计,临床适用性尚未在前瞻性临床研究中验证。
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
OBJECTIVE: To develop a deep learning algorithm for anatomy recognition in thoracoscopic video frames from robot-assisted minimally invasive esophagectomy (RAMIE) procedures using deep learning. BACKGROUND: RAMIE is a complex operation with substantial perioperative morbidity and a considerable learning curve. Automatic anatomy recognition may improve surgical orientation and recognition of anatomical structures and might contribute to reducing morbidity or learning curves. Studies regarding anatomy recognition in complex surgical procedures are currently lacking. METHODS: Eighty-three videos of consecutive RAMIE procedures between 2018 and 2022 were retrospectively collected at University Medical Center Utrecht. A surgical PhD candidate and an expert surgeon annotated the azygos vein and vena cava, aorta, and right lung on 1050 thoracoscopic frames. 850 frames were used for training of a convolutional neural network (CNN) to segment the anatomical structures. The remaining 200 frames of the dataset were used for testing the CNN. The Dice and 95% Hausdorff distance (95HD) were calculated to assess algorithm accuracy. RESULTS: The median Dice of the algorithm was 0.79 (IQR = 0.20) for segmentation of the azygos vein and/or vena cava. A median Dice coefficient of 0.74 (IQR = 0.86) and 0.89 (IQR = 0.30) were obtained for segmentation of the aorta and lung, respectively. Inference time was 0.026 s (39 Hz). The prediction of the deep learning algorithm was compared with the expert surgeon annotations, showing an accuracy measured in median Dice of 0.70 (IQR = 0.19), 0.88 (IQR = 0.07), and 0.90 (0.10) for the vena cava and/or azygos vein, aorta, and lung, respectively. CONCLUSION: This study shows that deep learning-based semantic segmentation has potential for anatomy recognition in RAMIE video frames. The inference time of the algorithm facilitated real-time anatomy recognition. Clinical applicability should be assessed in prospective clinical studies.
引用
- den Boer RB, Jaspers TJM, de Jongh C, et al. Deep learning-based recognition of key anatomical structures during robot-assisted minimally invasive esophagectomy. Surg Endosc. 2023. PMID: 36947221. doi:10.1007/s00464-023-09990-z
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。