基于超参数优化的三维U-Net脑肿瘤分割

A. Gamal, Khaled Bedda, Nada Ashraf, Salma Ayman, M. Abdallah, M. Rushdi
{"title":"基于超参数优化的三维U-Net脑肿瘤分割","authors":"A. Gamal, Khaled Bedda, Nada Ashraf, Salma Ayman, M. Abdallah, M. Rushdi","doi":"10.1109/NILES53778.2021.9600556","DOIUrl":null,"url":null,"abstract":"For the sake of proper diagnosis and treatment, accurate brain tumour segmentation is required. Because manual brain tumour segmentation is a time-consuming, costly, and subjective task, effective automated approaches for this purpose are generally desired. However, because brain tumours vary greatly in terms of location, shape, and size, establishing automatic segmentation algorithms has remained challenging throughout the years. Automatic segmentation of brain tumour is the process of separating abnormal tissues from normal tissues, such as white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Brian segmentation needs typically to be carried out for different image modalities in order to reveal important metabolic and physiological information. These modalities include positron emission tomography (PET), computer tomography (CT) image and magnetic resonance image (MRI). Multimodal imaging techniques (such as PET/CT and PET/MRI) that combine the information from multiple imaging modalities contribute more for accurate brain tumour segmentation. In this work, we introduce a deep learning framework for automated segmentation of 3D brain tumors that can save physicians time and provide an accurate reproducible solution for further tumor analysis and monitoring. In particular, a 3D U-Net was trained on brain MRI data obtained from the 2018 Brain tumor Image Segmentation (BraTS) challenge. Three optimizers (RMSProp, Adam and Nadam) and three loss functions (Dice loss, focal Tversky loss, Log-Cosh loss functions) were used. We demonstrated that some loss functions and optimizers combinations perform better than other ones. For example, using the Log-Cosh loss function along with RMSProp optimizer resulted in the highest Dice coefficient, 0.75. Indeed, we also optimized the network hyperparameters in order to enhance the segmentation outcomes. These results demonstrate the feasibility and effectiveness of the proposed deep learning scheme with optimized hyperparemeters and appropriate selection of the optimizer and loss function.","PeriodicalId":249153,"journal":{"name":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Brain Tumor Segmentation using 3D U-Net with Hyperparameter Optimization\",\"authors\":\"A. Gamal, Khaled Bedda, Nada Ashraf, Salma Ayman, M. Abdallah, M. Rushdi\",\"doi\":\"10.1109/NILES53778.2021.9600556\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"For the sake of proper diagnosis and treatment, accurate brain tumour segmentation is required. Because manual brain tumour segmentation is a time-consuming, costly, and subjective task, effective automated approaches for this purpose are generally desired. However, because brain tumours vary greatly in terms of location, shape, and size, establishing automatic segmentation algorithms has remained challenging throughout the years. Automatic segmentation of brain tumour is the process of separating abnormal tissues from normal tissues, such as white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Brian segmentation needs typically to be carried out for different image modalities in order to reveal important metabolic and physiological information. These modalities include positron emission tomography (PET), computer tomography (CT) image and magnetic resonance image (MRI). Multimodal imaging techniques (such as PET/CT and PET/MRI) that combine the information from multiple imaging modalities contribute more for accurate brain tumour segmentation. In this work, we introduce a deep learning framework for automated segmentation of 3D brain tumors that can save physicians time and provide an accurate reproducible solution for further tumor analysis and monitoring. In particular, a 3D U-Net was trained on brain MRI data obtained from the 2018 Brain tumor Image Segmentation (BraTS) challenge. Three optimizers (RMSProp, Adam and Nadam) and three loss functions (Dice loss, focal Tversky loss, Log-Cosh loss functions) were used. We demonstrated that some loss functions and optimizers combinations perform better than other ones. For example, using the Log-Cosh loss function along with RMSProp optimizer resulted in the highest Dice coefficient, 0.75. Indeed, we also optimized the network hyperparameters in order to enhance the segmentation outcomes. These results demonstrate the feasibility and effectiveness of the proposed deep learning scheme with optimized hyperparemeters and appropriate selection of the optimizer and loss function.\",\"PeriodicalId\":249153,\"journal\":{\"name\":\"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NILES53778.2021.9600556\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NILES53778.2021.9600556","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

为了正确的诊断和治疗,需要准确的脑肿瘤分割。由于手动脑肿瘤分割是一项耗时、昂贵且主观的任务,因此通常需要有效的自动化方法来实现这一目的。然而,由于脑肿瘤在位置、形状和大小方面差异很大,因此建立自动分割算法多年来一直具有挑战性。脑肿瘤自动分割是将异常组织从正常组织中分离出来的过程,如白质(WM)、灰质(GM)、脑脊液(CSF)等。为了揭示重要的代谢和生理信息,通常需要对不同的图像模式进行脑分割。这些模式包括正电子发射断层扫描(PET),计算机断层扫描(CT)图像和磁共振成像(MRI)。多模式成像技术(如PET/CT和PET/MRI)结合了多种成像模式的信息,有助于更准确地分割脑肿瘤。在这项工作中,我们引入了一个用于3D脑肿瘤自动分割的深度学习框架,可以节省医生的时间,并为进一步的肿瘤分析和监测提供准确的可复制解决方案。特别是,3D U-Net在2018年脑肿瘤图像分割(BraTS)挑战中获得的脑MRI数据上进行了训练。使用了3种优化器(RMSProp、Adam和Nadam)和3种损失函数(Dice损失、focal Tversky损失、Log-Cosh损失函数)。我们证明了一些损失函数和优化器组合比其他损失函数和优化器组合表现更好。例如,使用Log-Cosh损失函数和RMSProp优化器会产生最高的Dice系数0.75。实际上,我们还优化了网络超参数,以增强分割结果。这些结果证明了所提出的超参数优化深度学习方案的可行性和有效性,以及优化器和损失函数的适当选择。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Brain Tumor Segmentation using 3D U-Net with Hyperparameter Optimization
For the sake of proper diagnosis and treatment, accurate brain tumour segmentation is required. Because manual brain tumour segmentation is a time-consuming, costly, and subjective task, effective automated approaches for this purpose are generally desired. However, because brain tumours vary greatly in terms of location, shape, and size, establishing automatic segmentation algorithms has remained challenging throughout the years. Automatic segmentation of brain tumour is the process of separating abnormal tissues from normal tissues, such as white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Brian segmentation needs typically to be carried out for different image modalities in order to reveal important metabolic and physiological information. These modalities include positron emission tomography (PET), computer tomography (CT) image and magnetic resonance image (MRI). Multimodal imaging techniques (such as PET/CT and PET/MRI) that combine the information from multiple imaging modalities contribute more for accurate brain tumour segmentation. In this work, we introduce a deep learning framework for automated segmentation of 3D brain tumors that can save physicians time and provide an accurate reproducible solution for further tumor analysis and monitoring. In particular, a 3D U-Net was trained on brain MRI data obtained from the 2018 Brain tumor Image Segmentation (BraTS) challenge. Three optimizers (RMSProp, Adam and Nadam) and three loss functions (Dice loss, focal Tversky loss, Log-Cosh loss functions) were used. We demonstrated that some loss functions and optimizers combinations perform better than other ones. For example, using the Log-Cosh loss function along with RMSProp optimizer resulted in the highest Dice coefficient, 0.75. Indeed, we also optimized the network hyperparameters in order to enhance the segmentation outcomes. These results demonstrate the feasibility and effectiveness of the proposed deep learning scheme with optimized hyperparemeters and appropriate selection of the optimizer and loss function.
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
自引率
0.00%
发文量
0
期刊最新文献
Numerical Corrections to Estimate Depletion Region Width in Pseudo-two-dimensional Model of Double-Gate Tunneling FET GSK-RL: Adaptive Gaining-sharing Knowledge algorithm using Reinforcement Learning The Fluorescent Effect of Chitosan Magnetitic Nanoparticles for Near-Infrared Imaging Facility layout and supply chain management of food service industries: A case study Investigation of root causes of order unfulfillment: A Logistics case study
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1