Department of Medical Imaging, Henan Provincial People's Hospital & the People's Hospital of Zhengzhou University, Zhengzhou, People's Republic of China.
Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, United States of America.
Phys Med Biol. 2022 Jul 19;67(15). doi: 10.1088/1361-6560/ac7d33.
. Glioma is one of the most fatal cancers in the world which has been divided into low grade glioma (LGG) and high grade glioma (HGG), and its image grading has become a hot topic of contemporary research. Magnetic resonance imaging (MRI) is a vital diagnostic tool for brain tumor detection, analysis, and surgical planning. Accurate and automatic glioma grading is crucial for speeding up diagnosis and treatment planning. Aiming at the problems of (1) large number of parameters, (2) complex calculation, and (3) poor speed of the current glioma grading algorithms based on deep learning, this paper proposes a lightweight 3D UNet deep learning framework, which can improve classification accuracy in comparison with the existing methods.. To improve efficiency while maintaining accuracy, existing 3D UNet has been excluded, and depthwise separable convolution has been applied to 3D convolution to reduce the number of network parameters. The weight of parameters on the basis of space and channel compression & excitation module has been strengthened to improve the model in the feature map, reduce the weight of redundant parameters, and strengthen the performance of the model.. A total of 560 patients with glioma were retrospectively reviewed. All patients underwent MRI before surgery. The experiments were carried out on T1w, T2w, fluid attenuated inversion recovery, and CET1w images. Additionally, a way of marking tumor area by cube bounding box is presented which has no significant difference in model performance with the manually drawn ground truth. Evaluated on test datasets using the proposed model has shown good results (with accuracy of 89.29%).. This work serves to achieve LGG/HGG grading by simple, effective, and non-invasive diagnostic approaches to provide diagnostic suggestions for clinical usage, thereby facilitating hasten treatment decisions.
脑胶质瘤是世界上最致命的癌症之一，分为低级别胶质瘤（LGG）和高级别胶质瘤（HGG），其影像分级已成为当代研究的热点。磁共振成像（MRI）是脑肿瘤检测、分析和手术计划的重要诊断工具。准确和自动的脑胶质瘤分级对于加快诊断和治疗计划至关重要。针对当前基于深度学习的脑胶质瘤分级算法存在参数多、计算复杂、速度慢的问题，本文提出了一种轻量级的 3D UNet 深度学习框架，与现有方法相比，该框架可以提高分类精度。为了在保持准确性的同时提高效率，排除了现有的 3D UNet，并将深度可分离卷积应用于 3D 卷积，以减少网络参数的数量。在空间和通道压缩激励模块的基础上，加强了参数的权重，以提高模型在特征图中的性能，减少冗余参数的权重，增强模型的性能。回顾了 560 例脑胶质瘤患者。所有患者均在术前接受 MRI 检查。实验在 T1w、T2w、液体衰减反转恢复和 CET1w 图像上进行。此外，还提出了一种通过立方体边界框标记肿瘤区域的方法，该方法与手动绘制的真实边界框在模型性能上没有显著差异。在测试数据集上使用所提出的模型进行评估，结果显示出良好的效果（准确率为 89.29%）。这项工作旨在通过简单、有效和非侵入性的诊断方法实现 LGG/HGG 分级，为临床应用提供诊断建议，从而促进治疗决策的加快。
