Deepnet-based surgical tools detection in laparoscopic videos

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems Pub Date : 2025-04-11 DOI:10.1016/j.knosys.2025.113517

Praveen SR Konduri , G Siva Nageswara Rao

{"title":"Deepnet-based surgical tools detection in laparoscopic videos","authors":"Praveen SR Konduri , G Siva Nageswara Rao","doi":"10.1016/j.knosys.2025.113517","DOIUrl":null,"url":null,"abstract":"<div><div>Recently, deep learning has revolutionized significant advances in image classification, especially in Medical image (MI) processing. Surgical Data Science (SDS) has been developed as a scientific research field that aims to improve the health status of patients. Laparoscopic videos possess a highly significant information source that is integrally present in minimally invasive surgeries. Recognizing surgical tools based on the videos has promoted greater interest because of their significance. In most existing research, single-tool detection is carried out, but multiple-tool recognition is not concentrated well. However, multiple-tool recognition poses numerous challenges, including diverse lighting conditions, the appearance of multiple instruments in different representations, tissue blood, etc. Also, the detection speed of learning methodology is very low because of inherent complexities and improper handling of huge amounts of data. The proposed research introduces a novel DeepNet-Tool for automatic multi-tool classification in laparoscopy videos to address these existing challenges. This paper focuses on solving the spatial-temporal issues in detecting Surgical Tools (STs). The proposed model is implemented in Python, and the overall accuracy is 97.36 % with the Cholec80 dataset, 98.67 % with the EndoVis dataset, 99.73 % on EndoVis and 98.67 % on LapGyn4, respectively. Experimental outcomes of the proposed DeepNet-Tool showed higher effectiveness compared with other deep learning methods on the ST classification task. Thus, the proposed model has revealed the potential for clinical use in accurate ST classification.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"318 ","pages":"Article 113517"},"PeriodicalIF":7.2000,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705125005635","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Recently, deep learning has revolutionized significant advances in image classification, especially in Medical image (MI) processing. Surgical Data Science (SDS) has been developed as a scientific research field that aims to improve the health status of patients. Laparoscopic videos possess a highly significant information source that is integrally present in minimally invasive surgeries. Recognizing surgical tools based on the videos has promoted greater interest because of their significance. In most existing research, single-tool detection is carried out, but multiple-tool recognition is not concentrated well. However, multiple-tool recognition poses numerous challenges, including diverse lighting conditions, the appearance of multiple instruments in different representations, tissue blood, etc. Also, the detection speed of learning methodology is very low because of inherent complexities and improper handling of huge amounts of data. The proposed research introduces a novel DeepNet-Tool for automatic multi-tool classification in laparoscopy videos to address these existing challenges. This paper focuses on solving the spatial-temporal issues in detecting Surgical Tools (STs). The proposed model is implemented in Python, and the overall accuracy is 97.36 % with the Cholec80 dataset, 98.67 % with the EndoVis dataset, 99.73 % on EndoVis and 98.67 % on LapGyn4, respectively. Experimental outcomes of the proposed DeepNet-Tool showed higher effectiveness compared with other deep learning methods on the ST classification task. Thus, the proposed model has revealed the potential for clinical use in accurate ST classification.

查看原文本刊更多论文

基于深度网络的腹腔镜视频手术工具检测

近年来，深度学习在图像分类方面取得了革命性的进展，特别是在医学图像（MI）处理方面。外科数据科学（SDS）是一门旨在改善患者健康状况的科学研究领域。腹腔镜视频在微创手术中是一个非常重要的信息源。基于视频的手术工具识别由于其重要性而引起了更大的兴趣。现有的研究大多是单刀检测，多刀识别不够集中。然而，多工具识别带来了许多挑战，包括不同的照明条件，多种仪器以不同的形式出现，组织血液等。此外，由于固有的复杂性和对大量数据的不当处理，学习方法的检测速度非常低。该研究引入了一种新的DeepNet-Tool，用于腹腔镜视频的自动多工具分类，以解决这些现有的挑战。本文的重点是解决手术工具（STs）检测中的时空问题。该模型在Python中实现，在Cholec80数据集上的总体准确率为97.36%，在EndoVis数据集上的准确率为98.67%，在EndoVis数据集上的准确率为99.73%，在LapGyn4上的准确率为98.67%。实验结果表明，与其他深度学习方法相比，所提出的DeepNet-Tool在ST分类任务上具有更高的有效性。因此，所提出的模型揭示了在ST准确分类方面的临床应用潜力。

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

Knowledge-Based Systems 工程技术-计算机：人工智能

CiteScore

14.80

自引率

12.50%

发文量

1245

审稿时长

7.8 months

期刊介绍： Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.