深度学习在弥散加权MRI上检测卒中及血管区域分类
本研究回顾421例(271例急性缺血性卒中患者和150例DWI无缺血表现者)的DWI,构建卒中检测数据集和血管区域分类数据集,采用基于MobileNetV2和EfficientNet-B0的迁移学习CNN模型。改良MobileNetV2和EfficientNet-B0模型卒中检测准确率分别为96%(κ=0.92)和93%(κ=0.86),血管区域分类准确率分别为93%(κ=0.895)和87%(κ=0.805)。
要点
- 改良MobileNetV2在DWI卒中检测中准确率96%(κ=0.92),血管区域分类准确率93%(κ=0.895)。
- 改良EfficientNet-B0卒中检测准确率93%(κ=0.86),血管区域分类准确率87%(κ=0.805)。
- 模型可区分大脑中动脉、后循环及分水岭梗死,辅助快速判断血管区域。
核心结论
- 基于自定义顶层CNN模型的迁移学习方法在DWI上检测缺血性卒中及分类其血管区域类型均达到足够高的性能。
研究设计与样本
- 回顾性研究,纳入2017年1月至2020年4月间421例(271例急性缺血性卒中患者和150例DWI无缺血表现者)的DWI,构建卒中检测数据集(1800层,训练1400层、验证200层、测试200层)和血管区域分类数据集(1717层:大脑中动脉卒中883层、后循环卒中416层、分水岭卒中418层;训练1117层、验证300层、测试300层),采用基于MobileNetV2和EfficientNet-B0的迁移学习方法。
关键影像表现/征象
- 卒中检测:改良MobileNetV2模型准确率96%(κ=0.92)。
- 卒中检测:改良EfficientNet-B0模型准确率93%(κ=0.86)。
- 血管区域分类:改良MobileNetV2模型准确率93%(κ=0.895)。
- 血管区域分类:改良EfficientNet-B0模型准确率87%(κ=0.805)。
诊断标准与关键数值
- 卒中检测任务:以DWI有无缺血病灶为参考,改良MobileNetV2模型准确率96%(κ=0.92),改良EfficientNet-B0模型准确率93%(κ=0.86)。
- 血管区域分类任务:将卒中分为大脑中动脉、后循环或分水岭梗死,改良MobileNetV2模型准确率93%(κ=0.895),改良EfficientNet-B0模型准确率87%(κ=0.805)。
临床应用与阅片要点
- 基于DWI的CNN模型可能辅助缺血性卒中的快速检测及血管区域分类。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: Rapid detection and vascular territorial classification of stroke enable the determination of the most appropriate treatment. In this study, we aimed to investigate the performance of convolutional neural network (CNN) models in the detection and vascular territorial classification of stroke on diffusion-weighted images (DWI).
METHODS: DWI of 421 cases (271 acute ischemic stroke patients and 150 cases without any ischemia findings on DWI) obtained between January 2017 to April 2020 were reviewed. We created two custom datasets. A stroke detection dataset was created with 1800 slices (900 S and 900 normal) consisting of 1400 for training, 200 for validation, 200 for test. A vascular territorial type dataset was created with 1717 slices (883 middle cerebral artery stroke, 416 posterior circulatory stroke, and 418 watershed stroke) consisting of 1117 slices for training, 300 for validation, 300 for test. A transfer learning approach based on MobileNetV2 and EfficientNet-B0 CNN architecture was used. The performance of the models was evaluated.
RESULTS: Modified MobileNetV2 and EfficientNet-B0 models achieved 96% (κ: 0.92) and 93% (κ: 0.86) accuracy in stroke detection, respectively. In vascular territorial classification of stroke as middle cerebral artery, posterior circulation, or watershed infarction, an accuracy of 93% (κ: 0.895) was achieved with modified MobileNetV2 model and 87% (κ: 0.805) with modified EfficientNet-B0 CNN model.
CONCLUSION: Transfer learning approach with custom top CNN models achieve sufficiently high performance for both the detection of ischemic stroke and the classification of its vascular territorial type on DWI.
引用
- Cetinoglu, Koska, Uluc, et al. Detection and vascular territorial classification of stroke on diffusion-weighted MRI by deep learning. Eur J Radiol. 2021. PMID: 34839210. doi:10.1016/j.ejrad.2021.110050
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。