基于深度学习的腹腔镜结直肠手术中输尿管实时识别。

IF 3.2 2区 医学 Q2 GASTROENTEROLOGY & HEPATOLOGY
Diseases of the Colon & Rectum Pub Date : 2024-10-01 Epub Date: 2024-07-03 DOI:10.1097/DCR.0000000000003335
Satoshi Narihiro, Daichi Kitaguchi, Hiro Hasegawa, Nobuyoshi Takeshita, Masaaki Ito
{"title":"基于深度学习的腹腔镜结直肠手术中输尿管实时识别。","authors":"Satoshi Narihiro, Daichi Kitaguchi, Hiro Hasegawa, Nobuyoshi Takeshita, Masaaki Ito","doi":"10.1097/DCR.0000000000003335","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Iatrogenic ureteral injury is a serious complication of abdominopelvic surgery. Identifying the ureters intraoperatively is essential to avoid iatrogenic ureteral injury. We developed a model that may minimize this complication.</p><p><strong>Impact of innovation: </strong>We applied a deep learning-based semantic segmentation algorithm to the ureter recognition task and developed a deep learning model called UreterNet. This study aimed to verify whether the ureters could be identified in videos of laparoscopic colorectal surgery.</p><p><strong>Technology, materials, and methods: </strong>Semantic segmentation of the ureter area was performed using a convolutional neural network-based approach. Feature Pyramid Networks were used as the convolutional neural network architecture for semantic segmentation. Precision, recall, and the Dice coefficient were used as the evaluation metrics in this study.</p><p><strong>Preliminary results: </strong>We created 14,069 annotated images from 304 videos, with 9537, 2266, and 2266 images in the training, validation, and test data sets, respectively. Concerning ureter recognition performance, the precision, recall, and Dice coefficient for the test data were 0.712, 0.722, and 0.716, respectively. Regarding the real-time performance on recorded videos, it took 71 milliseconds for UreterNet to infer all pixels corresponding to the ureter from a single still image and 143 milliseconds to output and display the inferred results as a segmentation mask on the laparoscopic monitor.</p><p><strong>Conclusions: </strong>UreterNet is a noninvasive method for identifying the ureter in videos of laparoscopic colorectal surgery and can potentially improve surgical safety.</p><p><strong>Future directions: </strong>Although this deep learning model could lead to the development of an image-navigated surgical system, it is necessary to verify whether UreterNet reduces the occurrence of iatrogenic ureteral injury.</p>","PeriodicalId":11299,"journal":{"name":"Diseases of the Colon & Rectum","volume":" ","pages":"e1596-e1599"},"PeriodicalIF":3.2000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep Learning-Based Real-Time Ureter Identification in Laparoscopic Colorectal Surgery.\",\"authors\":\"Satoshi Narihiro, Daichi Kitaguchi, Hiro Hasegawa, Nobuyoshi Takeshita, Masaaki Ito\",\"doi\":\"10.1097/DCR.0000000000003335\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Iatrogenic ureteral injury is a serious complication of abdominopelvic surgery. Identifying the ureters intraoperatively is essential to avoid iatrogenic ureteral injury. We developed a model that may minimize this complication.</p><p><strong>Impact of innovation: </strong>We applied a deep learning-based semantic segmentation algorithm to the ureter recognition task and developed a deep learning model called UreterNet. This study aimed to verify whether the ureters could be identified in videos of laparoscopic colorectal surgery.</p><p><strong>Technology, materials, and methods: </strong>Semantic segmentation of the ureter area was performed using a convolutional neural network-based approach. Feature Pyramid Networks were used as the convolutional neural network architecture for semantic segmentation. Precision, recall, and the Dice coefficient were used as the evaluation metrics in this study.</p><p><strong>Preliminary results: </strong>We created 14,069 annotated images from 304 videos, with 9537, 2266, and 2266 images in the training, validation, and test data sets, respectively. Concerning ureter recognition performance, the precision, recall, and Dice coefficient for the test data were 0.712, 0.722, and 0.716, respectively. Regarding the real-time performance on recorded videos, it took 71 milliseconds for UreterNet to infer all pixels corresponding to the ureter from a single still image and 143 milliseconds to output and display the inferred results as a segmentation mask on the laparoscopic monitor.</p><p><strong>Conclusions: </strong>UreterNet is a noninvasive method for identifying the ureter in videos of laparoscopic colorectal surgery and can potentially improve surgical safety.</p><p><strong>Future directions: </strong>Although this deep learning model could lead to the development of an image-navigated surgical system, it is necessary to verify whether UreterNet reduces the occurrence of iatrogenic ureteral injury.</p>\",\"PeriodicalId\":11299,\"journal\":{\"name\":\"Diseases of the Colon & Rectum\",\"volume\":\" \",\"pages\":\"e1596-e1599\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Diseases of the Colon & Rectum\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/DCR.0000000000003335\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/3 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"GASTROENTEROLOGY & HEPATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diseases of the Colon & Rectum","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/DCR.0000000000003335","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/3 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

背景:输尿管先天性损伤是腹盆腔手术的一种严重并发症。术中识别输尿管是避免输尿管先天性损伤的关键。在此,我们开发了一种模型,可将这种并发症降至最低:我们将基于深度学习的语义分割算法应用于输尿管识别任务,并开发了一个名为 UreterNet 的深度学习模型。本研究旨在验证能否在腹腔镜结直肠手术视频中识别出输尿管:使用基于卷积神经网络的方法对输尿管区域进行语义分割。特征金字塔网络被用作语义分割的卷积神经网络架构。本研究采用精确度、召回率和骰子系数作为评价指标:我们从 304 个视频中创建了 14,069 张注释图像,其中训练、验证和测试数据集分别有 9537 张、2266 张和 2266 张图像。在输尿管识别性能方面,测试数据的精确度、召回率和 Dice 系数分别为 0.712、0.722 和 0.716。在录制视频的实时性能方面,UreterNet 从一张静止图像中推断出输尿管对应的所有像素需要 71 毫秒,将推断结果作为分割掩码输出并显示在腹腔镜显示器上需要 143 毫秒:UreterNet 是一种在腹腔镜结直肠手术视频中识别输尿管的无创方法,有可能提高手术安全性。虽然这可能导致图像导航手术系统的开发,但有必要验证输尿管网是否能减少输尿管先天性损伤的发生。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep Learning-Based Real-Time Ureter Identification in Laparoscopic Colorectal Surgery.

Background: Iatrogenic ureteral injury is a serious complication of abdominopelvic surgery. Identifying the ureters intraoperatively is essential to avoid iatrogenic ureteral injury. We developed a model that may minimize this complication.

Impact of innovation: We applied a deep learning-based semantic segmentation algorithm to the ureter recognition task and developed a deep learning model called UreterNet. This study aimed to verify whether the ureters could be identified in videos of laparoscopic colorectal surgery.

Technology, materials, and methods: Semantic segmentation of the ureter area was performed using a convolutional neural network-based approach. Feature Pyramid Networks were used as the convolutional neural network architecture for semantic segmentation. Precision, recall, and the Dice coefficient were used as the evaluation metrics in this study.

Preliminary results: We created 14,069 annotated images from 304 videos, with 9537, 2266, and 2266 images in the training, validation, and test data sets, respectively. Concerning ureter recognition performance, the precision, recall, and Dice coefficient for the test data were 0.712, 0.722, and 0.716, respectively. Regarding the real-time performance on recorded videos, it took 71 milliseconds for UreterNet to infer all pixels corresponding to the ureter from a single still image and 143 milliseconds to output and display the inferred results as a segmentation mask on the laparoscopic monitor.

Conclusions: UreterNet is a noninvasive method for identifying the ureter in videos of laparoscopic colorectal surgery and can potentially improve surgical safety.

Future directions: Although this deep learning model could lead to the development of an image-navigated surgical system, it is necessary to verify whether UreterNet reduces the occurrence of iatrogenic ureteral injury.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.50
自引率
7.70%
发文量
572
审稿时长
3-8 weeks
期刊介绍: Diseases of the Colon & Rectum (DCR) is the official journal of the American Society of Colon and Rectal Surgeons (ASCRS) dedicated to advancing the knowledge of intestinal disorders by providing a forum for communication amongst their members. The journal features timely editorials, original contributions and technical notes.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信