Gómez Santiago, Mantilla Daniel, Rangel Edgar, Ortiz Andrés, D Vera Daniela, Martínez Fabio
Biomedical Imaging and Learning Laboratory (BIVL2ab), Universidad Industrial de Santander, Bucaramanga, 680002, Colombia.
Clínica FOSCAL, Floridablanca, 681004, Colombia.
Biomed Phys Eng Express. 2023 Apr 5;9(3). doi: 10.1088/2057-1976/acc853.
The key component of stroke diagnosis is the localization and delineation of brain lesions, especially from MRI studies. Nonetheless, this manual delineation is time-consuming and biased by expert opinion. The main purpose of this study is to introduce an autoencoder architecture that effectively integrates cross-attention mechanisms, together with hierarchical deep supervision to delineate lesions under scenarios of remarked unbalance tissue classes, challenging geometry of the shape, and a variable textural representation. This work introduces a cross-attention deep autoencoder that focuses on the lesion shape through a set of convolutional saliency maps, forcing skip connections to preserve the morphology of affected tissue. Moreover, a deep supervision training scheme was herein adapted to induce the learning of hierarchical lesion details. Besides, a special weighted loss function remarks lesion tissue, alleviating the negative impact of class imbalance. The proposed approach was validated on the public ISLES2017 dataset outperforming state-of-the-art results, achieving a dice score of 0.36 and a precision of 0.42. Deeply supervised cross-attention autoencoders, trained to pay more attention to lesion tissue, are better at estimating ischemic lesions in MRI studies. The best architectural configuration was achieved by integrating ADC, TTP and Tmax sequences. The contribution of deeply supervised cross-attention autoencoders allows better support the discrimination between healthy and lesion regions, which in consequence results in favorable prognosis and follow-up of patients.
中风诊断的关键要素是脑损伤的定位与描绘，尤其是通过磁共振成像（MRI）研究来实现。然而，这种人工描绘既耗时又受专家意见的影响。本研究的主要目的是引入一种自动编码器架构，该架构有效地整合了交叉注意力机制以及分层深度监督，以便在组织类别显著不平衡、形状几何结构具有挑战性以及纹理表示多变的情况下描绘损伤。这项工作引入了一种交叉注意力深度自动编码器，它通过一组卷积显著性图聚焦于损伤形状，强制使用跳跃连接来保留受影响组织的形态。此外，本文采用了一种深度监督训练方案来引导对分层损伤细节的学习。此外，一种特殊的加权损失函数突出了损伤组织，减轻了类别不平衡的负面影响。所提出的方法在公开的ISLES2017数据集上得到验证，其性能优于现有技术成果，骰子系数得分为0.36，精度为0.42。经过训练以更多关注损伤组织的深度监督交叉注意力自动编码器，在MRI研究中更擅长估计缺血性损伤。通过整合表观扩散系数（ADC）、灌注达峰时间（TTP）和最大峰值时间（Tmax）序列实现了最佳的架构配置。深度监督交叉注意力自动编码器的贡献有助于更好地支持区分健康区域和损伤区域，从而为患者带来良好的预后和随访效果。
