应用MultiCNN_LSTM分类器对ROP的1、2、3期及Preplus、Plus病进行分类

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX Pub Date : 2025-01-25 DOI:10.1016/j.mex.2025.103182

Ranjana Agrawal , Sucheta Kulkarni , Madan Deshpande , Anita Gaikwad , Rahee Walambe , Ketan V. Kotecha

{"title":"应用MultiCNN_LSTM分类器对ROP的1、2、3期及Preplus、Plus病进行分类","authors":"Ranjana Agrawal , Sucheta Kulkarni , Madan Deshpande , Anita Gaikwad , Rahee Walambe , Ketan V. Kotecha","doi":"10.1016/j.mex.2025.103182","DOIUrl":null,"url":null,"abstract":"<div><div>Retinopathy of prematurity (ROP) is a retinal disorder that can cause blindness in premature infants with low birth weight. Early detection and timely treatment are crucial to prevent blindness associated with ROP. It's essential to identify the stage and presence of Plus disease accurately when examining retinal images of at-risk infants. We are developing an explainable automated ROP screening system for the HVDROPDB datasets. The fundus images were classified as without stage (Normal)/with Stage (ROP) by segmenting the ridge. Stages 1–3 were classified using machine Learning (ML) models.<ul><li><span>•</span><span><div>This study aims to improve accuracy of Stages 1–3 classification and identify Pre-plus/ Plus disease using MultiCNN_LSTM networks. This is accomplished by using multiple CNNs (Convolutional Neural Networks) to extract features and LSTM (Long Short-Term Memory) classifier to classify images.</div></span></li><li><span>•</span><span><div>Cropped STAGE dataset and HVDROPDB-PLUS dataset are constructed with RetCam and Neo images.</div></span></li><li><span>•</span><span><div>The proposed networks outperform individual CNNs and CNN_LSTM networks in terms of accuracy and F1 score.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"14 ","pages":"Article 103182"},"PeriodicalIF":1.6000,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Classification of Stages 1,2,3 and Preplus, Plus disease of ROP using MultiCNN_LSTM classifier\",\"authors\":\"Ranjana Agrawal , Sucheta Kulkarni , Madan Deshpande , Anita Gaikwad , Rahee Walambe , Ketan V. Kotecha\",\"doi\":\"10.1016/j.mex.2025.103182\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Retinopathy of prematurity (ROP) is a retinal disorder that can cause blindness in premature infants with low birth weight. Early detection and timely treatment are crucial to prevent blindness associated with ROP. It's essential to identify the stage and presence of Plus disease accurately when examining retinal images of at-risk infants. We are developing an explainable automated ROP screening system for the HVDROPDB datasets. The fundus images were classified as without stage (Normal)/with Stage (ROP) by segmenting the ridge. Stages 1–3 were classified using machine Learning (ML) models.<ul><li><span>•</span><span><div>This study aims to improve accuracy of Stages 1–3 classification and identify Pre-plus/ Plus disease using MultiCNN_LSTM networks. This is accomplished by using multiple CNNs (Convolutional Neural Networks) to extract features and LSTM (Long Short-Term Memory) classifier to classify images.</div></span></li><li><span>•</span><span><div>Cropped STAGE dataset and HVDROPDB-PLUS dataset are constructed with RetCam and Neo images.</div></span></li><li><span>•</span><span><div>The proposed networks outperform individual CNNs and CNN_LSTM networks in terms of accuracy and F1 score.</div></span></li></ul></div></div>\",\"PeriodicalId\":18446,\"journal\":{\"name\":\"MethodsX\",\"volume\":\"14 \",\"pages\":\"Article 103182\"},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2025-01-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"MethodsX\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2215016125000305\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"MethodsX","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215016125000305","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

早产儿视网膜病变（ROP）是一种视网膜疾病，可导致低出生体重早产儿失明。早期发现和及时治疗对于预防ROP相关失明至关重要。在检查高危婴儿的视网膜图像时，准确识别Plus疾病的阶段和存在是至关重要的。我们正在为HVDROPDB数据集开发一种可解释的自动化ROP筛选系统。通过对眼底脊的分割，将眼底图像分为无分期(Normal)/分期（ROP）。使用机器学习（ML）模型对1-3阶段进行分类。•本研究旨在使用MultiCNN_LSTM网络提高1-3阶段分类的准确性，并识别Pre-plus/ Plus疾病。这是通过使用多个cnn（卷积神经网络）提取特征和LSTM（长短期记忆）分类器对图像进行分类来实现的。•裁剪STAGE数据集和HVDROPDB-PLUS数据集使用RetCam和Neo图像构建。•提出的网络在准确性和F1分数方面优于单个cnn和CNN_LSTM网络。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Classification of Stages 1,2,3 and Preplus, Plus disease of ROP using MultiCNN_LSTM classifier

查看原文本刊更多论文

Classification of Stages 1,2,3 and Preplus, Plus disease of ROP using MultiCNN_LSTM classifier

Retinopathy of prematurity (ROP) is a retinal disorder that can cause blindness in premature infants with low birth weight. Early detection and timely treatment are crucial to prevent blindness associated with ROP. It's essential to identify the stage and presence of Plus disease accurately when examining retinal images of at-risk infants. We are developing an explainable automated ROP screening system for the HVDROPDB datasets. The fundus images were classified as without stage (Normal)/with Stage (ROP) by segmenting the ridge. Stages 1–3 were classified using machine Learning (ML) models.

•
This study aims to improve accuracy of Stages 1–3 classification and identify Pre-plus/ Plus disease using MultiCNN_LSTM networks. This is accomplished by using multiple CNNs (Convolutional Neural Networks) to extract features and LSTM (Long Short-Term Memory) classifier to classify images.
•
Cropped STAGE dataset and HVDROPDB-PLUS dataset are constructed with RetCam and Neo images.
•
The proposed networks outperform individual CNNs and CNN_LSTM networks in terms of accuracy and F1 score.

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