Rich Joseph M, Bhardwaj Lokesh N, Shah Aman, Gangal Krish, Rapaka Mohitha S, Oberai Assad A, Fields Brandon K K, Matcuk George R, Duddalwar Vinay A
Keck School of Medicine, University of Southern California, Los Angeles, CA, United States.
Department of Applied Biostatistics and Epidemiology, University of Southern California, Los Angeles, CA, United States.
Front Radiol. 2023 Aug 8;3:1241651. doi: 10.3389/fradi.2023.1241651. eCollection 2023.
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).
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.
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.
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.
图像分割是量化恶性骨病变特征的重要过程，但对放射科医生来说，这项任务具有挑战性且费力。深度学习在放射学图像分割自动化方面已显示出前景，包括对恶性骨病变的分割。本综述的目的是研究基于深度学习的计算机断层扫描（CT）、磁共振成像（MRI）和正电子发射断层扫描/CT（PET/CT）上恶性骨病变的图像分割方法。
按照系统评价和Meta分析的首选报告项目（PRISMA）指南，在PubMed、Embase、科学网和Scopus电子数据库中对基于深度学习的CT和MRI上恶性骨病变图像分割进行文献检索。本综述共纳入了2017年2月至2023年3月期间发表的41篇原创文章。
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使用三维与二维数据的论文分布相对均匀。许多论文使用定制模型作为U-Net的修改或变体。最常见的评估指标是骰子相似系数（DSC）。大多数模型的DSC高于0.6，所有成像模态的中位数在0.85 - 0.9之间。
深度学习方法在CT、MRI和PET/CT上分割恶性骨病变显示出有前景的能力。一些通常用于帮助提高性能的策略包括数据增强、使用大型公共数据集、包括去噪和裁剪的预处理以及U-Net架构修改。未来的方向包括克服数据集和注释的同质性以及推广到临床应用。
