Pub Date : 2023-03-05DOI: 10.58769/joinssr.1175622
Mohammed Mansour, M. Demi̇rsoy, Mustafa Kutlu
For medical diagnostic tests, kidney segmentation from high-volume imagery is an important major. Since 3D medical images need a lot of GPU memory, slices and patches are used for training and inference in traditional neural network variant architectures, which necessarily slows down contextual learning. In this research, Mobile Net and Efficient Net CNN models were trained for segmenting human kidney images generated from The Human Biomolecular Atlas Program (HuBMAP). The purpose of this work is to evaluate the effectiveness of different strategies for Glomeruli identification in order to solve the issue. The high size images were decoded to be fitted and trained in the models first, then the CNN models were trained. The CNN models result show that the Efficient Net has the highest accuracy rate with 99.49 %, and Mobile Net with 99.33 %.
对于医学诊断测试，从大容量图像中分割肾脏是一个重要的专业。由于3D医学图像需要大量的GPU内存，传统的神经网络变体架构使用切片和补丁进行训练和推理，这必然会减慢上下文学习的速度。在本研究中，对Mobile Net和Efficient Net CNN模型进行训练，用于分割由人类生物分子图谱计划(HuBMAP)生成的人体肾脏图像。本工作的目的是评估肾小球识别不同策略的有效性，以解决这一问题。首先对大尺寸图像进行解码，在模型中进行拟合和训练，然后训练CNN模型。CNN模型结果表明，Efficient Net准确率最高，达到99.49%，Mobile Net准确率最高，达到99.33%。
{"title":"Kidney Segmentations Using CNN models","authors":"Mohammed Mansour, M. Demi̇rsoy, Mustafa Kutlu","doi":"10.58769/joinssr.1175622","DOIUrl":"https://doi.org/10.58769/joinssr.1175622","url":null,"abstract":"For medical diagnostic tests, kidney segmentation from high-volume imagery is an important major. Since 3D medical images need a lot of GPU memory, slices and patches are used for training and inference in traditional neural network variant architectures, which necessarily slows down contextual learning. In this research, Mobile Net and Efficient Net CNN models were trained for segmenting human kidney images generated from The Human Biomolecular Atlas Program (HuBMAP). The purpose of this work is to evaluate the effectiveness of different strategies for Glomeruli identification in order to solve the issue. The high size images were decoded to be fitted and trained in the models first, then the CNN models were trained. The CNN models result show that the Efficient Net has the highest accuracy rate with 99.49 %, and Mobile Net with 99.33 %.","PeriodicalId":397495,"journal":{"name":"Journal of Smart Systems Research","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132930064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：