{"title":"疝:人工智能在视频腹腔镜腹股沟疝成形术中的实时解剖结构分割。","authors":"Franco J Marcelo, Pablo Zalazar, Florisel Papasidero, Ciro Hernandez, Jorge Ruiz Todone","doi":"10.1177/15533506251352101","DOIUrl":null,"url":null,"abstract":"<p><p>BackgroundLaparoscopic transabdominal preperitoneal (TAPP) hernioplasty, a minimally invasive procedure, reduces postoperative pain and recovery time but faces challenges like the \"ping-pong effect\" (alternating focus between operative field and monitors) and a 1%-2% error rate due to anatomical misidentification, risking complications like vascular injuries.ObjectiveTo develop and validate HernIA, an AI-based system for real-time segmentation of anatomical structures in TAPP, targeting an Intersection over Union (IoU) ≥85% and error reduction ≥50% compared to manual identification.MethodsHernIA employs YOLOv11m-seg, trained on 21 443 annotated laparoscopic images from 45 TAPP procedures at Clinica Colón and Hospital de Campaña Escuela Hogar. Annotation by expert laparoscopists achieved high inter-rater reliability (Cohen's kappa = 0.87). Validation used 5-fold cross-validation and a 10 800-frame dataset.ResultsHernIA achieved an IoU of 89.4% (±2.1%), Jaccard Index of 81.2%, mAP@50 of 92.3%, and F1 score of 0.94 (confidence threshold ∼0.45). It reduced identification errors by 62% in a simulated TAPP environment (10 800 frames, 24 FPS, 42 ms latency). Clinical validation was limited to one case of bilateral hernia repair.ConclusionHernIA enhances surgical precision and training in TAPP, with potential to reduce complications. Multi-center trials are needed to confirm generalizability.</p>","PeriodicalId":22095,"journal":{"name":"Surgical Innovation","volume":" ","pages":"15533506251352101"},"PeriodicalIF":1.2000,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HernIA: Real-Time Anatomical Structure Segmentation in Video Laparoscopic Inguinal Hernioplasties With AI.\",\"authors\":\"Franco J Marcelo, Pablo Zalazar, Florisel Papasidero, Ciro Hernandez, Jorge Ruiz Todone\",\"doi\":\"10.1177/15533506251352101\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>BackgroundLaparoscopic transabdominal preperitoneal (TAPP) hernioplasty, a minimally invasive procedure, reduces postoperative pain and recovery time but faces challenges like the \\\"ping-pong effect\\\" (alternating focus between operative field and monitors) and a 1%-2% error rate due to anatomical misidentification, risking complications like vascular injuries.ObjectiveTo develop and validate HernIA, an AI-based system for real-time segmentation of anatomical structures in TAPP, targeting an Intersection over Union (IoU) ≥85% and error reduction ≥50% compared to manual identification.MethodsHernIA employs YOLOv11m-seg, trained on 21 443 annotated laparoscopic images from 45 TAPP procedures at Clinica Colón and Hospital de Campaña Escuela Hogar. Annotation by expert laparoscopists achieved high inter-rater reliability (Cohen's kappa = 0.87). Validation used 5-fold cross-validation and a 10 800-frame dataset.ResultsHernIA achieved an IoU of 89.4% (±2.1%), Jaccard Index of 81.2%, mAP@50 of 92.3%, and F1 score of 0.94 (confidence threshold ∼0.45). It reduced identification errors by 62% in a simulated TAPP environment (10 800 frames, 24 FPS, 42 ms latency). Clinical validation was limited to one case of bilateral hernia repair.ConclusionHernIA enhances surgical precision and training in TAPP, with potential to reduce complications. Multi-center trials are needed to confirm generalizability.</p>\",\"PeriodicalId\":22095,\"journal\":{\"name\":\"Surgical Innovation\",\"volume\":\" \",\"pages\":\"15533506251352101\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2025-06-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Surgical Innovation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/15533506251352101\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"SURGERY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Surgical Innovation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/15533506251352101","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"SURGERY","Score":null,"Total":0}
引用次数: 0
摘要
腹腔镜经腹腹膜前疝成形术(TAPP)是一种微创手术,减少了术后疼痛和恢复时间,但面临着“乒乓效应”(手术视野和监护仪交替聚焦)和1%-2%的解剖学错误识别错误率等挑战,有血管损伤等并发症的风险。目的开发并验证HernIA,一种基于人工智能的TAPP解剖结构实时分割系统,与人工识别相比,IoU≥85%,错误率≥50%。方法shernia使用YOLOv11m-seg,对临床Colón和Campaña Escuela Hogar医院45例TAPP手术的21443张带注释的腹腔镜图像进行训练。腹腔镜专家的注释具有较高的评分间可靠性(Cohen’s kappa = 0.87)。验证使用5次交叉验证和10个800帧的数据集。结果shernia的IoU为89.4%(±2.1%),Jaccard指数为81.2%,mAP@50为92.3%,F1评分为0.94(置信阈值~ 0.45)。它在模拟TAPP环境(10800帧,24 FPS, 42毫秒延迟)中减少了62%的识别错误。临床验证仅限于一例双侧疝修补术。结论疝术提高了TAPP的手术精度和训练水平,具有减少并发症的潜力。需要多中心试验来证实其普遍性。
HernIA: Real-Time Anatomical Structure Segmentation in Video Laparoscopic Inguinal Hernioplasties With AI.
BackgroundLaparoscopic transabdominal preperitoneal (TAPP) hernioplasty, a minimally invasive procedure, reduces postoperative pain and recovery time but faces challenges like the "ping-pong effect" (alternating focus between operative field and monitors) and a 1%-2% error rate due to anatomical misidentification, risking complications like vascular injuries.ObjectiveTo develop and validate HernIA, an AI-based system for real-time segmentation of anatomical structures in TAPP, targeting an Intersection over Union (IoU) ≥85% and error reduction ≥50% compared to manual identification.MethodsHernIA employs YOLOv11m-seg, trained on 21 443 annotated laparoscopic images from 45 TAPP procedures at Clinica Colón and Hospital de Campaña Escuela Hogar. Annotation by expert laparoscopists achieved high inter-rater reliability (Cohen's kappa = 0.87). Validation used 5-fold cross-validation and a 10 800-frame dataset.ResultsHernIA achieved an IoU of 89.4% (±2.1%), Jaccard Index of 81.2%, mAP@50 of 92.3%, and F1 score of 0.94 (confidence threshold ∼0.45). It reduced identification errors by 62% in a simulated TAPP environment (10 800 frames, 24 FPS, 42 ms latency). Clinical validation was limited to one case of bilateral hernia repair.ConclusionHernIA enhances surgical precision and training in TAPP, with potential to reduce complications. Multi-center trials are needed to confirm generalizability.
期刊介绍:
Surgical Innovation (SRI) is a peer-reviewed bi-monthly journal focusing on minimally invasive surgical techniques, new instruments such as laparoscopes and endoscopes, and new technologies. SRI prepares surgeons to think and work in "the operating room of the future" through learning new techniques, understanding and adapting to new technologies, maintaining surgical competencies, and applying surgical outcomes data to their practices. This journal is a member of the Committee on Publication Ethics (COPE).