Department of Radiation Oncology (Maastro), Maastricht University Medical Center+, GROW School for Developmental Biology and Oncology, Maastricht, the Netherlands.
Department of Radiation Oncology (Maastro), Maastricht University Medical Center+, GROW School for Developmental Biology and Oncology, Maastricht, the Netherlands.
Phys Med. 2021 Mar;83:161-173. doi: 10.1016/j.ejmp.2021.03.003. Epub 2021 Mar 26.
Magnetic Resonance Imaging (MRI) provides an essential contribution in the screening, detection, diagnosis, staging, treatment and follow-up in patients with a neurological neoplasm. Deep learning (DL), a subdomain of artificial intelligence has the potential to enhance the characterization, processing and interpretation of MRI images. The aim of this review paper is to give an overview of the current state-of-art usage of DL in MRI for neuro-oncology.
We reviewed the Pubmed database by applying a specific search strategy including the combination of MRI, DL, neuro-oncology and its corresponding search terminologies, by focussing on Medical Subject Headings (Mesh) or title/abstract appearance. The original research papers were classified based on its application, into three categories: technological innovation, diagnosis and follow-up.
Forty-one publications were eligible for review, all were published after the year 2016. The majority (N = 22) was assigned to technological innovation, twelve had a focus on diagnosis and seven were related to patient follow-up. Applications ranged from improving the acquisition, synthetic CT generation, auto-segmentation, tumor classification, outcome prediction and response assessment. The majority of publications made use of standard (T1w, cT1w, T2w and FLAIR imaging), with only a few exceptions using more advanced MRI technologies. The majority of studies used a variation on convolution neural network (CNN) architectures.
Deep learning in MRI for neuro-oncology is a novel field of research; it has potential in a broad range of applications. Remaining challenges include the accessibility of large imaging datasets, the applicability across institutes/vendors and the validation and implementation of these technologies in clinical practise.
磁共振成像（MRI）在神经肿瘤患者的筛查、检测、诊断、分期、治疗和随访中具有重要作用。深度学习（DL）是人工智能的一个分支，具有增强 MRI 图像特征描述、处理和解释的潜力。本文旨在综述目前 DL 在神经肿瘤学 MRI 中的应用现状。
我们通过应用特定的搜索策略，包括 MRI、DL、神经肿瘤学及其相应的搜索术语，在 Pubmed 数据库中进行了检索，重点关注医学主题词（Mesh）或标题/摘要。将原始研究论文根据其应用分为三类：技术创新、诊断和随访。
共有 41 篇论文符合纳入标准，均发表于 2016 年以后。其中 22 篇论文为技术创新，12 篇为诊断，7 篇为随访。应用范围包括改善采集、合成 CT 生成、自动分割、肿瘤分类、预后预测和反应评估。大多数出版物使用了标准（T1w、cT1w、T2w 和 FLAIR 成像），只有少数例外使用了更先进的 MRI 技术。大多数研究使用卷积神经网络（CNN）架构的变体。
神经肿瘤学 MRI 的深度学习是一个新兴的研究领域，它在广泛的应用中具有潜力。尚待解决的挑战包括获取大型成像数据集的便利性、跨机构/供应商的适用性以及这些技术在临床实践中的验证和实施。
