Zhang K C, Qiao Z, Yang L, Zhang T, Liu F L, Sun D C, Xie T Y, Guo L, Lu C R
Department of Gastric Surgery, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China.
Department of General Surgery, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China.
Zhonghua Wei Chang Wai Ke Za Zhi. 2024 May 25;27(5):464-470. doi: 10.3760/cma.j.cn441530-20240125-00041.
To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer. Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5-10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy. The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing. The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.
为研究基于计算机视觉的人工智能技术在胃癌根治性腹腔镜胃切除术场景中检测和识别器械及器官的可行性和准确性。从中国四家大型三级医院收集了8份完整的腹腔镜远端根治性胃切除术手术视频（中国人民解放军总医院第一医学中心[3例]、辽宁省肿瘤医院[2例]、江苏省人民医院溧阳分院[2例]、复旦大学附属上海肿瘤医院[1例]）。使用PR软件每隔5 - 10秒提取帧并转换为图像帧。为确保质量，人工进行去重以去除明显重复和模糊的图像帧。转换和去重后，得到3369张分辨率为1920×1080 PPI的帧图像。使用LabelMe对图像进行实例分割，分为以下23类：静脉、动脉、缝线、持针器、超声刀、吸引装置、出血、结肠、钳子、胆囊、小纱布、Hem - o - lok、Hem - o - lok施夹器、电灼钩、小肠、肝胃韧带、肝脏、网膜、胰腺、脾脏、手术吻合器、胃和套管针。帧图像以9:1的比例随机分配到训练集和验证集。使用YOLOv8深度学习框架进行模型训练和验证。使用精度、召回率、平均精度（AP）和平均平均精度（mAP）来评估检测和识别准确性。训练集包含3032张帧图像，涵盖23类共30895个实例分割计数。验证集包含337张帧图像，共3407个实例分割计数。使用YOLOv8m模型进行训练。训练集的损失曲线显示，随着迭代计算次数增加，损失值平稳逐渐下降。在训练集中，所有23类的AP值均高于0.90，mAP为0.99，而在验证集中，23类的mAP为0.82。对于个别类别，超声刀、持针器、钳子、胆囊、小纱布块和手术吻合器的AP值分别为0.96、0.94、0.91、0.91、0.91和0.91。该模型成功推断并应用于一段5分钟的腹腔镜胃肠吻合术缝合视频片段。这项多中心研究的主要发现是，计算机视觉能够在胃癌根治性腹腔镜胃切除术的各种场景中高效、准确且实时地检测器官和器械。
