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

作　　者：Jiansheng Wang Yan Wang Xiang Tao Qingli Li Li Sun Jiangang Chen Mei Zhou Menghan Hu Xiufeng Zhou 

机构地区：[1]Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University,Shanghai 200241,China [2]Engineering Center of SHMEC for Space Information and GNSS,Shanghai 200241,China [3]Obstetrics&Gynecology Hospital of Fudan University,Shanghai 200011,China [4]Engineering Research Center of Nanophotonics&Advanced Instrument,Ministry of Education,East China Normal University,Shanghai 200241,China [5]Dmetrix Ltd.Co.,Suzhou,Jiangsu 210000,China

出　　处：《Fundamental Research》2021年第5期631-640,共10页自然科学基础研究（英文版）

基　　金：funded by National Natural Science Foundation of China(Grant No.61975056;)the Shanghai Natural Science Foundation(Grant No.19ZR1416000);the Science and Technology Commission of Shanghai Municipality(Grants No.20440713100,19511120100,18DZ2270800).

摘　　要：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.

关 键 词：Microscopic hyperspectral imaging Breast cancer Tissue microarrays Deep learning 

分 类 号：R737.9[医药卫生—肿瘤] TP391.41[医药卫生—临床医学]