Mubarak Hasan K, Zhou Ximing, Palsgrove Doreen, Sumer Baran D, Chen Amy Y, Fei Baowei
Center for Imaging and Surgical Innovation, The University of Texas at Dallas, Richardson, TX.
Department of Bioengineering, The University of Texas at Dallas, Richardson, TX.
Proc SPIE Int Soc Opt Eng. 2024 Feb;12933. doi: 10.1117/12.3007869. Epub 2024 Apr 3.
Head and neck squamous cell carcinoma (HNSCC) has a high mortality rate. In this study, we developed a Stokes-vector-derived polarized hyperspectral imaging (PHSI) system for H&E-stained pathological slides with HNSCC and built a dataset to develop a deep learning classification method based on convolutional neural networks (CNN). We use our polarized hyperspectral microscope to collect the four Stokes parameter hypercubes (S0, S1, S2, and S3) from 56 patients and synthesize pseudo-RGB images using a transformation function that approximates the human eye's spectral response to visual stimuli. Each image is divided into patches. Data augmentation is applied using rotations and flipping. We create a four-branch model architecture where each branch is trained on one Stokes parameter individually, then we freeze the branches and fine-tune the top layers of our model to generate final predictions. Our results show high accuracy, sensitivity, and specificity, indicating that our model performed well on our dataset. Future works can improve upon these results by training on more varied data, classifying tumors based on their grade, and introducing more recent architectural techniques.
头颈部鳞状细胞癌（HNSCC）死亡率很高。在本研究中，我们为患有HNSCC的苏木精和伊红（H&E）染色病理切片开发了一种基于斯托克斯矢量的偏振高光谱成像（PHSI）系统，并构建了一个数据集，以开发基于卷积神经网络（CNN）的深度学习分类方法。我们使用偏振高光谱显微镜从56名患者中收集四个斯托克斯参数超立方体（S0、S1、S2和S3），并使用近似人眼对视觉刺激的光谱响应的变换函数合成伪RGB图像。将每个图像划分为图像块。通过旋转和翻转进行数据增强。我们创建了一个四分支模型架构，其中每个分支分别在一个斯托克斯参数上进行训练，然后冻结这些分支并对模型的顶层进行微调以生成最终预测。我们的结果显示出高准确率、灵敏度和特异性，表明我们的模型在我们的数据集上表现良好。未来的工作可以通过对更多样化的数据进行训练、根据肿瘤分级对肿瘤进行分类以及引入更新的架构技术来改进这些结果。
