PCA-U-Net based breast cancer nest segmentation from microarray hyperspectral images

The incidence of breast cancer is tending younger globally, and tumor development, clinical treatment, and prognosis are largely influenced by histopathological diagnosis. For diagnosed patients, the distinction between the cancer nests and normal tissue is the basis of breast cancer treatment. Microscopic hyperspectral imaging technology has shown its potential in auxiliary pathological examinations due to the superior imaging modality and data characteristics. This paper presents a method for cancer nest segmentation from hyperspectral images of breast cancer tissue microarray samples. The scheme combines the strengths of the U-Net neural network and unsupervised principal component analysis, which reduces the amount of calculation and improves the recognition accuracy. The experimental accuracy of cancer nest segmentation reaches 87.14%. Furthermore, a set of quantitative pathological characteristic parameters reflects the degree of breast cancer lesions from multiple angles, providing a relatively comprehensive reference for the pathologist's diagnosis. In-depth exploration of the combined development of deep learning and microscopic hyperspectral imaging technology is worthy to promote efficient diagnosis of breast tumors and concern for human health.