A deep learning network for Gleason grading of prostate biopsies using EfficientNet.

IF 1.3 4区医学 Q4 ENGINEERING, BIOMEDICAL Biomedical Engineering / Biomedizinische Technik Pub Date : 2023-04-25 DOI:10.1515/bmt-2022-0201

Karthik Ramamurthy, Abinash Reddy Varikuti, Bhavya Gupta, Nehal Aswani

{"title":"A deep learning network for Gleason grading of prostate biopsies using EfficientNet.","authors":"Karthik Ramamurthy, Abinash Reddy Varikuti, Bhavya Gupta, Nehal Aswani","doi":"10.1515/bmt-2022-0201","DOIUrl":null,"url":null,"abstract":"Objectives: The most crucial part in the diagnosis of cancer is severity grading. Gleason's score is a widely used grading system for prostate cancer. Manual examination of the microscopic images and grading them is tiresome and consumes a lot of time. Hence to automate the Gleason grading process, a novel deep learning network is proposed in this work.Methods: In this work, a deep learning network for Gleason grading of prostate cancer is proposed based on EfficientNet architecture. It applies a compound scaling method to balance the dimensions of the underlying network. Also, an additional attention branch is added to EfficientNet-B7 for precise feature weighting.Result: To the best of our knowledge, this is the first work that integrates an additional attention branch with EfficientNet architecture for Gleason grading. The proposed models were trained using H&E-stained samples from prostate cancer Tissue Microarrays (TMAs) in the Harvard Dataverse dataset.Conclusions: The proposed network was able to outperform the existing methods and it achieved an Kappa score of 0.5775.","PeriodicalId":8900,"journal":{"name":"Biomedical Engineering / Biomedizinische Technik","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2023-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Engineering / Biomedizinische Technik","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1515/bmt-2022-0201","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 2

Abstract

Objectives: The most crucial part in the diagnosis of cancer is severity grading. Gleason's score is a widely used grading system for prostate cancer. Manual examination of the microscopic images and grading them is tiresome and consumes a lot of time. Hence to automate the Gleason grading process, a novel deep learning network is proposed in this work.

Methods: In this work, a deep learning network for Gleason grading of prostate cancer is proposed based on EfficientNet architecture. It applies a compound scaling method to balance the dimensions of the underlying network. Also, an additional attention branch is added to EfficientNet-B7 for precise feature weighting.

Result: To the best of our knowledge, this is the first work that integrates an additional attention branch with EfficientNet architecture for Gleason grading. The proposed models were trained using H&E-stained samples from prostate cancer Tissue Microarrays (TMAs) in the Harvard Dataverse dataset.

Conclusions: The proposed network was able to outperform the existing methods and it achieved an Kappa score of 0.5775.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

使用EfficientNet进行前列腺活检格里森分级的深度学习网络。

目的:肿瘤的严重程度分级是诊断的关键。格里森评分是一种广泛使用的前列腺癌分级系统。人工检查显微图像并给它们分级是令人厌烦的，而且耗费大量时间。因此，为了实现格里森分级过程的自动化，本文提出了一种新的深度学习网络。方法:在本工作中，提出了一个基于effentnet架构的前列腺癌Gleason分级深度学习网络。它采用复合缩放方法来平衡底层网络的维度。此外，在EfficientNet-B7中增加了一个额外的注意分支，用于精确的特征加权。结果:据我们所知，这是第一个将额外的注意力分支与用于Gleason分级的EfficientNet体系结构集成在一起的工作。所提出的模型使用哈佛Dataverse数据集中来自前列腺癌组织微阵列(tma)的h&e染色样本进行训练。结论:所提出的网络优于现有的方法，Kappa得分为0.5775。

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分钟内获得全文去求助

来源期刊

Biomedical Engineering / Biomedizinische Technik 医学-工程：生物医学

CiteScore

3.50

自引率

5.90%

发文量

审稿时长

2-3 weeks

期刊介绍： Biomedical Engineering / Biomedizinische Technik (BMT) is a high-quality forum for the exchange of knowledge in the fields of biomedical engineering, medical information technology and biotechnology/bioengineering. As an established journal with a tradition of more than 60 years, BMT addresses engineers, natural scientists, and clinicians working in research, industry, or clinical practice.