Zheng Yao, Huang Dong, Hao Xiaoshuo, Wei Jie, Lu Hongbing, Liu Yang
Air Force Medical University, No. 169 Changle West Road, Xi'an, 710032, ShaanXi, China.
Air Force Medical University, No. 169 Changle West Road, Xi'an, 710032, ShaanXi, China; Shaanxi Provincial Key Laboratory of Bioelectromagnetic Detection and Intelligent Perception, No. 169 Changle West Road, Xi'an, 710032, ShaanXi, China.
Comput Biol Med. 2023 Oct;165:107332. doi: 10.1016/j.compbiomed.2023.107332. Epub 2023 Aug 12.
Accurate grading of brain tumors plays a crucial role in the diagnosis and treatment of glioma. While convolutional neural networks (CNNs) have shown promising performance in this task, their clinical applicability is still constrained by the interpretability and robustness of the models. In the conventional framework, the classification model is trained first, and then visual explanations are generated. However, this approach often leads to models that prioritize classification performance or complexity, making it difficult to achieve a precise visual explanation. Motivated by these challenges, we propose the Unified Visualization and Classification Network (UniVisNet), a novel framework that aims to improve both the classification performance and the generation of high-resolution visual explanations. UniVisNet addresses attention misalignment by introducing a subregion-based attention mechanism, which replaces traditional down-sampling operations. Additionally, multiscale feature maps are fused to achieve higher resolution, enabling the generation of detailed visual explanations. To streamline the process, we introduce the Unified Visualization and Classification head (UniVisHead), which directly generates visual explanations without the need for additional separation steps. Through extensive experiments, our proposed UniVisNet consistently outperforms strong baseline classification models and prevalent visualization methods. Notably, UniVisNet achieves remarkable results on the glioma grading task, including an AUC of 94.7%, an accuracy of 89.3%, a sensitivity of 90.4%, and a specificity of 85.3%. Moreover, UniVisNet provides visually interpretable explanations that surpass existing approaches. In conclusion, UniVisNet innovatively generates visual explanations in brain tumor grading by simultaneously improving the classification performance and generating high-resolution visual explanations. This work contributes to the clinical application of deep learning, empowering clinicians with comprehensive insights into the spatial heterogeneity of glioma.
脑肿瘤的准确分级在胶质瘤的诊断和治疗中起着至关重要的作用。虽然卷积神经网络（CNN）在这项任务中表现出了良好的性能，但其临床适用性仍然受到模型的可解释性和鲁棒性的限制。在传统框架中，分类模型首先进行训练，然后生成可视化解释。然而，这种方法往往导致模型优先考虑分类性能或复杂性，难以实现精确的可视化解释。受这些挑战的启发，我们提出了统一可视化与分类网络（UniVisNet），这是一个旨在提高分类性能和生成高分辨率可视化解释的新颖框架。UniVisNet通过引入基于子区域的注意力机制来解决注意力错位问题，该机制取代了传统的下采样操作。此外，融合多尺度特征图以实现更高的分辨率，从而能够生成详细的可视化解释。为了简化流程，我们引入了统一可视化与分类头（UniVisHead），它无需额外的分离步骤即可直接生成可视化解释。通过广泛的实验，我们提出的UniVisNet始终优于强大的基线分类模型和流行的可视化方法。值得注意的是，UniVisNet在胶质瘤分级任务上取得了显著成果，包括曲线下面积（AUC）为94.7%、准确率为89.3%、灵敏度为90.4%和特异性为85.3%。此外，UniVisNet提供了超越现有方法的视觉可解释性解释。总之，UniVisNet通过同时提高分类性能和生成高分辨率可视化解释，创新性地在脑肿瘤分级中生成可视化解释。这项工作有助于深度学习的临床应用，使临床医生能够全面了解胶质瘤的空间异质性。
