[论文解读] A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images
本文提出一种多路径2.5D卷积神经网络,通过三种解剖平面(轴向、冠状位、矢状位)处理T1和T1+FLAIR MRI切片,并采用多种归一化方法,利用3D CNN融合特征以提升脑卒中病灶分割性能。该方法在跨研究验证中实现了0.54的平均Dice系数,显著优于先前模型(包括标准UNet),并接近放射科专家水平的准确度。
Automatic identification of brain lesions from magnetic resonance imaging (MRI) scans of stroke survivors would be a useful aid in patient diagnosis and treatment planning. We propose a multi-modal multi-path convolutional neural network system for automating stroke lesion segmentation. Our system has nine end-to-end UNets that take as input 2-dimensional (2D) slices and examines all three planes with three different normalizations. Outputs from these nine total paths are concatenated into a 3D volume that is then passed to a 3D convolutional neural network to output a final lesion mask. We trained and tested our method on datasets from three sources: Medical College of Wisconsin (MCW), Kessler Foundation (KF), and the publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset. Cross-study validation results (with independent training and validation datasets) were obtained to compare with previous methods based on naive Bayes, random forests, and three recently published convolutional neural networks. Model performance was quantified in terms of the Dice coefficient. Training on the KF and MCW images and testing on the ATLAS images yielded a mean Dice coefficient of 0.54. This was reliably better than the next best previous model, UNet, at 0.47. Reversing the train and test datasets yields a mean Dice of 0.47 on KF and MCW images, whereas the next best UNet reaches 0.45. With all three datasets combined, the current system compared to previous methods also attained a reliably higher cross-validation accuracy. It also achieved high Dice values for many smaller lesions that existing methods have difficulty identifying. Overall, our system is a clear improvement over previous methods for automating stroke lesion segmentation, bringing us an important step closer to the inter-rater accuracy level of human experts.
研究动机与目标
- 旨在自动化脑MRI中的脑卒中病灶分割,以消除专家手动分割所耗费的大量时间。
- 旨在解决2D CNN仅分析单一平面的局限性,通过整合多平面和多序列MRI视图来提升性能。
- 旨在提升对小病灶或细微病灶的检测能力,这些病灶常被现有方法遗漏。
- 旨在开发一种鲁棒且可泛化的系统,并在来自多个机构的多样化数据集上进行验证。
- 旨在使自动化病灶分割的准确度更接近人类专家之间的评分者一致性水平。
提出的方法
- 该系统使用九个端到端的U-Net架构,每个架构处理来自三个解剖平面(轴向、冠状位、矢状位)之一的2D MRI切片,并采用三种不同的归一化技术。
- 每条2D路径从T1加权和T1+FLAIR MRI序列中提取特征,以增强对病灶对比度的敏感性。
- 九条2D路径的输出被拼接为一个3D特征体,以保留跨平面的空间上下文信息。
- 3D卷积神经网络处理融合后的3D特征体,生成最终的病灶掩膜。
- 该模型在MCW、凯斯勒基金会和ATLAS的数据集上进行端到端训练,并采用交叉研究验证以确保泛化能力。
- 应用数据增强和归一化策略,以提升在不同扫描协议和病灶类型下的鲁棒性。
实验结果
研究问题
- RQ1与标准2D U-Net模型相比,多路径2.5D CNN架构是否能提升脑卒中病灶分割的准确度?
- RQ2结合多种MRI对比(T1、T1+FLAIR)和解剖平面是否能提升对小病灶或细微病灶的检测能力?
- RQ3该模型能否在具有不同扫描参数和病灶特征的多个机构数据集之间实现良好泛化?
- RQ4在Dice系数方面,该模型的性能与人类专家之间的评分者一致性相比如何?
- RQ5该系统能否对急性/亚急性及慢性脑卒中病灶均实现高分割准确度?
主要发现
- 当在凯斯勒基金会和MCW数据集上训练并在ATLAS上测试时,该模型实现了0.54的平均Dice系数,显著优于次佳模型(UNet)的0.47。
- 当在ATLAS上训练并在凯斯勒和MCW上测试时,该模型实现了0.47的平均Dice系数,再次优于次佳的UNet模型(0.45)。
- 在合并数据集上,该模型在五折交叉验证中实现了0.62的平均Dice系数,接近人类专家评分者一致性范围(0.67–0.73)。
- 该模型在小病灶上的表现优于以往的自动化方法,显示出显著优势。
- 统计分析显示,与基线方法相比有显著改进,关键比较的p值均小于0.05,尤其在T1+FLAIR序列中检测病灶方面表现突出。
- 该系统在不同病灶阶段(亚急性与慢性)及病因类型(缺血性和出血性)中均表现出鲁棒性,表明其具有广泛的临床适用性。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。