当前位置: X-MOL 学术IETE Tech. Rev. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Deep Learning-based System for Detecting Anemia from Eye Conjunctiva Images Taken from a Smartphone
IETE Technical Review ( IF 2.4 ) Pub Date : 2023-08-10 , DOI: 10.1080/02564602.2023.2242318
Pallavi 1 , Bijit Basumatary 1 , Rahul Shukla 1 , Rakesh Kumar 2 , Bodhisatwa Das 1 , Ashish Kumar Sahani 1
Affiliation  

Anemia is a severe health condition commonly prevalent among women of reproductive age and children below five years. Screening patients before the condition becomes critical and can save many lives. World Health Organization (WHO) has set the “Global nutrition target 2025-anemia,” aiming to reduce 50% of anemia cases among women of reproductive age. This target can be achieved through a time-efficient, cost-effective, and easy-to-use tool. Traditional testing methods require specific chemicals, machines, and equipment that are not available everywhere. It also requires the presence of nurses, laboratory workers, and doctors. These methods are costly, time-consuming, and produce biohazard waste, thus polluting the environment. We developed an Artificial Intelligence (AI)-based bot that can be used for screening people for anemia. The bot service is based on two models: a segmentation model to segment the Region of Interest (ROI) and a classification model to classify anemic cases from normal ones. To train the model, we have collected data from 160 anemic and 140 non-anemic persons. In this paper, we have explained the architecture of the models, all the training parameters, and their deployment on cloud services using the REAN chatbot service. We manage to reach an Intersection Over Union (IOU) score of 0.922 for the segmentation model; validation recall of 0.95 and validation accuracy of 0.9699 for the classification model. This system is easy to use and does not depend on the availability of comprehensive laboratory infrastructure or trained personnel and thus can enable screening of anemia in low-resource settings.



中文翻译:

基于深度学习的系统,用于通过智能手机拍摄的眼结膜图像检测贫血

贫血是一种严重的健康状况,常见于育龄妇女和五岁以下儿童。在病情变得危急之前对患者进行筛查可以挽救许多生命。世界卫生组织(WHO)制定了“2025年全球营养目标——贫血”,旨在将育龄妇女贫血病例减少50%。这一目标可以通过省时、经济且易于使用的工具来实现。传统的测试方法需要特定的化学品、机器和设备,但并非到处都有。它还需要护士、实验室工作人员和医生在场。这些方法成本高昂、耗时,并产生生物危害废物,从而污染环境。我们开发了一种基于人工智能 (AI) 的机器人,可用于筛查人们是否患有贫血。该机器人服务基于两个模型:用于分割感兴趣区域 (ROI) 的分割模型和用于对贫血病例与正常病例进行分类的分类模型。为了训练该模型,我们收集了 160 名贫血者和 140 名非贫血者的数据。在本文中,我们解释了模型的架构、所有训练参数以及使用 REAN 聊天机器人服务在云服务上的部署。我们的分割模型的 Intersection Over Union (IOU) 分数达到了 0.922;分类模型的验证召回率为 0.95,验证准确度为 0.9699。该系统易于使用,不依赖于综合实验室基础设施或训练有素的人员,因此可以在资源匮乏的环境中筛查贫血。用于分割感兴趣区域 (ROI) 的分割模型和用于将贫血病例与正常病例分类的分类模型。为了训练该模型,我们收集了 160 名贫血者和 140 名非贫血者的数据。在本文中,我们解释了模型的架构、所有训练参数以及使用 REAN 聊天机器人服务在云服务上的部署。我们的分割模型的 Intersection Over Union (IOU) 分数达到了 0.922;分类模型的验证召回率为 0.95,验证准确度为 0.9699。该系统易于使用,不依赖于综合实验室基础设施或训练有素的人员,因此可以在资源匮乏的环境中筛查贫血。用于分割感兴趣区域 (ROI) 的分割模型和用于将贫血病例与正常病例分类的分类模型。为了训练该模型,我们收集了 160 名贫血者和 140 名非贫血者的数据。在本文中,我们解释了模型的架构、所有训练参数以及使用 REAN 聊天机器人服务在云服务上的部署。我们的分割模型的 Intersection Over Union (IOU) 分数达到了 0.922;分类模型的验证召回率为 0.95,验证准确度为 0.9699。该系统易于使用,不依赖于综合实验室基础设施或训练有素的人员,因此可以在资源匮乏的环境中筛查贫血。

更新日期:2023-08-12
down
wechat
bug