DSR-VGG：一种用于鼻咽组织病理图像分类的轻量级深度可分离残差VGG架构

文献信息

中文摘要

背景/目的： 深度卷积神经网络在组织病理图像分类中表现优异，但通常需要大量计算资源。本研究提出DSR-VGG，一种用于鼻咽组织病理图像分类的轻量级深度可分离残差VGG架构。方法：DSR-VGG由六个带残差投影捷径的深度可分离模块、全局平均池化、dropout正则化和一个分类层组成。采用逆频率加权随机采样策略以应对严重的类别不平衡。主要评估使用来自四个类别的88,002个鼻咽组织病理图像块：正常、淋巴组织增生、鼻咽炎症和鼻咽癌。训练使用三个随机种子重复进行，并使用补充公共数据集评估跨数据集架构稳健性。结果：在三次运行中，DSR-VGG达到99.764 ± 0.049%的准确率、99.070 ± 0.365%的平衡准确率和99.219 ± 0.215%的宏F1。该模型仅包含52.8万个参数，所需计算量约为0.31 GFLOPs，在所述GPU基准测试条件下实现2.38 ms的单图像推理延迟。尽管若干基线架构取得了略高的准确率，DSR-VGG在计算复杂度显著更低的情况下保持了有竞争力的预测性能。结论：DSR-VGG在组织病理图像块分类中提供了有利的准确率-复杂度权衡。然而，在临床部署之前，仍需进行患者/全切片图像不相交评估、独立多中心验证和全切片评估。

英文摘要

Background/Objectives: Deep convolutional neural networks achieve strong histopathological image-classification performance but often require substantial computational resources. This study proposes DSR-VGG, a lightweight Depthwise Separable Residual VGG architecture for nasopharyngeal histopathological image classification. Methods: DSR-VGG comprises six Depthwise Separable Blocks with residual projection shortcuts, global average pooling, dropout regularization, and a classification layer. An inverse-frequency weighted random sampling strategy was used to address severe class imbalance. The primary evaluation used 88,002 nasopharyngeal histopathology patches from four classes: Normal, lymphoid hyperplasia, nasopharyngeal inflammation, and nasopharyngeal carcinoma. Training was repeated using three random seeds, with supplementary public datasets used to assess cross-dataset architectural robustness. Results: Across three runs, DSR-VGG achieved 99.764 ± 0.049% accuracy, 99.070 ± 0.365% balanced accuracy, and 99.219 ± 0.215% macro-F1. The model contained only 0.528 million parameters, required approximately 0.31 GFLOPs, and achieved 2.38 ms single-image inference latency under the stated GPU benchmarking conditions. Although several baseline architectures achieved marginally higher accuracy, DSR-VGG maintained competitive predictive performance with substantially lower computational complexity. Conclusions: DSR-VGG provides a favorable accuracy-complexity trade-off for histopathological patch classification. However, patient-/WSI-disjoint evaluation, independent multi-center validation, and whole-slide assessment remain necessary before clinical deployment.