恶性骨病变的深度学习图像分割方法:系统综述与荟萃分析。

Frontiers in radiology Pub Date : 2023-08-08 eCollection Date: 2023-01-01 DOI:10.3389/fradi.2023.1241651
Joseph M Rich, Lokesh N Bhardwaj, Aman Shah, Krish Gangal, Mohitha S Rapaka, Assad A Oberai, Brandon K K Fields, George R Matcuk, Vinay A Duddalwar
{"title":"恶性骨病变的深度学习图像分割方法:系统综述与荟萃分析。","authors":"Joseph M Rich, Lokesh N Bhardwaj, Aman Shah, Krish Gangal, Mohitha S Rapaka, Assad A Oberai, Brandon K K Fields, George R Matcuk, Vinay A Duddalwar","doi":"10.3389/fradi.2023.1241651","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT).</p><p><strong>Method: </strong>The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review.</p><p><strong>Results: </strong>The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9.</p><p><strong>Discussion: </strong>Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.</p>","PeriodicalId":73101,"journal":{"name":"Frontiers in radiology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10442705/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.\",\"authors\":\"Joseph M Rich, Lokesh N Bhardwaj, Aman Shah, Krish Gangal, Mohitha S Rapaka, Assad A Oberai, Brandon K K Fields, George R Matcuk, Vinay A Duddalwar\",\"doi\":\"10.3389/fradi.2023.1241651\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT).</p><p><strong>Method: </strong>The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review.</p><p><strong>Results: </strong>The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9.</p><p><strong>Discussion: </strong>Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.</p>\",\"PeriodicalId\":73101,\"journal\":{\"name\":\"Frontiers in radiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10442705/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in radiology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fradi.2023.1241651\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in radiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fradi.2023.1241651","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

简介图像分割是量化恶性骨病变特征的重要过程,但对于放射科医生来说,这项任务既具有挑战性又费力。深度学习在放射学图像自动分割方面大有可为,包括恶性骨病变。本综述旨在研究计算机断层扫描(CT)、磁共振成像(MRI)和正电子发射断层扫描/CT(PET/CT)上基于深度学习的恶性骨病变图像分割方法:根据系统综述和元分析首选报告项目(Preferred Reporting Items for Systematic Reviews and Meta-Analyses,PRISMA)指南,在PubMed、Embase、Web of Science和Scopus电子数据库中对基于深度学习的CT和MRI恶性骨病变图像分割进行了文献检索。共有41篇发表于2017年2月至2023年3月期间的原创文章被纳入综述:大多数论文研究的是 MRI,其次是 CT、PET/CT 和 PET/MRI。研究原发性与继发性恶性肿瘤以及利用三维与二维数据的论文分布相对均匀。许多论文利用定制模型作为 U-Net 的修改或变体。最常用的评估指标是骰子相似系数(DSC)。大多数模型的骰子相似系数都在 0.6 以上,所有成像模式的中位数都在 0.85-0.9 之间:深度学习方法在分割 CT、MRI 和 PET/CT 上的恶性骨质病变方面表现出良好的能力。为帮助提高性能,通常采用的一些策略包括数据增强、利用大型公共数据集、预处理(包括去噪和裁剪)以及 U-Net 架构修改。未来的研究方向包括克服数据集和注释的同质性,以及临床应用的通用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Introduction: Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT).

Method: The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review.

Results: The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9.

Discussion: Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.

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
CiteScore
1.20
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信