Anatomical recognition of dissection layers, nerves, vas deferens, and microvessels using artificial intelligence during transabdominal preperitoneal inguinal hernia repair.

IF 2.6 2区医学 Q1 SURGERY

Hernia Pub Date : 2024-12-26 DOI:10.1007/s10029-024-03223-5

Kazuhito Mita, Nao Kobayashi, Kunihiko Takahashi, Takashi Sakai, Mayu Shimaguchi, Michitaka Kouno, Naoyuki Toyota, Minoru Hatano, Tsuyoshi Toyota, Junichi Sasaki

{"title":"Anatomical recognition of dissection layers, nerves, vas deferens, and microvessels using artificial intelligence during transabdominal preperitoneal inguinal hernia repair.","authors":"Kazuhito Mita, Nao Kobayashi, Kunihiko Takahashi, Takashi Sakai, Mayu Shimaguchi, Michitaka Kouno, Naoyuki Toyota, Minoru Hatano, Tsuyoshi Toyota, Junichi Sasaki","doi":"10.1007/s10029-024-03223-5","DOIUrl":null,"url":null,"abstract":"Purpose: In laparoscopic inguinal hernia surgery, proper recognition of loose connective tissue, nerves, vas deferens, and microvessels is important to prevent postoperative complications, such as recurrence, pain, sexual dysfunction, and bleeding. EUREKA (Anaut Inc., Tokyo, Japan) is a system that uses artificial intelligence (AI) for anatomical recognition. This system can intraoperatively confirm the aforementioned anatomical landmarks. In this study, we validated the accuracy of EUREKA in recognizing dissection layers, nerves, vas deferens, and microvessels during transabdominal preperitoneal inguinal hernia repair (TAPP).Methods: We used TAPP videos to compare EUREKA's recognition of loose connective tissue, nerves, vas deferens, and microvessels with the original surgical video and examined whether EUREKA accurately identified these structures. Intersection over Union (IoU) and F1/Dice scores were calculated to quantitively evaluate AI predictive images.Results: The mean IoU and F1/Dice scores were 0.33 and 0.50 for connective tissue, 0.24 and 0.38 for nerves, 0.50 and 0.66 for the vas deferens, and 0.30 and 0.45 for microvessels, respectively. Compared with the images without EUREKA visualization, dissection layers were very clearly recognized and displayed when appropriate tension was applied.","PeriodicalId":13168,"journal":{"name":"Hernia","volume":"29 1","pages":"52"},"PeriodicalIF":2.6000,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11671561/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hernia","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10029-024-03223-5","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SURGERY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: In laparoscopic inguinal hernia surgery, proper recognition of loose connective tissue, nerves, vas deferens, and microvessels is important to prevent postoperative complications, such as recurrence, pain, sexual dysfunction, and bleeding. EUREKA (Anaut Inc., Tokyo, Japan) is a system that uses artificial intelligence (AI) for anatomical recognition. This system can intraoperatively confirm the aforementioned anatomical landmarks. In this study, we validated the accuracy of EUREKA in recognizing dissection layers, nerves, vas deferens, and microvessels during transabdominal preperitoneal inguinal hernia repair (TAPP).

Methods: We used TAPP videos to compare EUREKA's recognition of loose connective tissue, nerves, vas deferens, and microvessels with the original surgical video and examined whether EUREKA accurately identified these structures. Intersection over Union (IoU) and F1/Dice scores were calculated to quantitively evaluate AI predictive images.

Results: The mean IoU and F1/Dice scores were 0.33 and 0.50 for connective tissue, 0.24 and 0.38 for nerves, 0.50 and 0.66 for the vas deferens, and 0.30 and 0.45 for microvessels, respectively. Compared with the images without EUREKA visualization, dissection layers were very clearly recognized and displayed when appropriate tension was applied.

查看原文本刊更多论文

应用人工智能识别经腹膜前腹股沟疝修补术中的夹层、神经、输精管和微血管。

目的：在腹腔镜腹股沟疝手术中，正确识别松散的结缔组织、神经、输精管和微血管对预防术后并发症如复发、疼痛、性功能障碍和出血是很重要的。EUREKA （Anaut Inc., Tokyo, Japan）是一个利用人工智能（AI）进行解剖识别的系统。该系统可以术中确认上述解剖标志。在本研究中，我们验证了EUREKA在经腹膜前腹股沟疝修补术（TAPP）中识别夹层、神经、输精管和微血管的准确性。方法：我们使用TAPP视频比较EUREKA对松散结缔组织、神经、输精管和微血管的识别与原始手术视频，并检查EUREKA是否准确识别这些结构。计算Union交集（IoU）和F1/Dice分数，定量评价AI预测图像。结果：结缔组织的平均IoU和F1/Dice评分分别为0.33和0.50，神经的平均IoU和F1/Dice评分分别为0.24和0.38，输精管的平均IoU和F1/Dice评分分别为0.50和0.66，微血管的平均IoU和F1/Dice评分分别为0.30和0.45。与未使用EUREKA可视化的图像相比，在适当的张力下，可以清晰地识别和显示解剖层。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Hernia SURGERY-

CiteScore

4.90

自引率

26.10%

发文量

171

审稿时长

4-8 weeks

期刊介绍： Hernia was founded in 1997 by Jean P. Chevrel with the purpose of promoting clinical studies and basic research as they apply to groin hernias and the abdominal wall . Since that time, a true revolution in the field of hernia studies has transformed the field from a ”simple” disease to one that is very specialized. While the majority of surgeries for primary inguinal and abdominal wall hernia are performed in hospitals worldwide, complex situations such as multi recurrences, complications, abdominal wall reconstructions and others are being studied and treated in specialist centers. As a result, major institutions and societies are creating specific parameters and criteria to better address the complexities of hernia surgery. Hernia is a journal written by surgeons who have made abdominal wall surgery their specific field of interest, but we will consider publishing content from any surgeon who wishes to improve the science of this field. The Journal aims to ensure that hernia surgery is safer and easier for surgeons as well as patients, and provides a forum to all surgeons in the exchange of new ideas, results, and important research that is the basis of professional activity.