MC-GAT: multi-layer collaborative generative adversarial transformer for cholangiocarcinoma classification from hyperspectral pathological images

作者全名："Li, Yuan; Shi, Xu; Yang, Liping; Pu, Chunyu; Tan, Qijuan; Yang, Zhengchun; Huang, Hong"

作者地址："[Li, Yuan; Shi, Xu; Yang, Liping; Pu, Chunyu; Huang, Hong] Chongqing Univ, Key Lab Optoelect Technol & Syst Educ, Minist China, Chongqing 400044, Peoples R China; [Tan, Qijuan] Chongqing Univ, Dept Radiol, Canc Hosp, Chongqing 400030, Peoples R China; [Tan, Qijuan] Chongqing Canc Inst, Chongqing 400030, Peoples R China; [Tan, Qijuan] Chongqing Canc Hosp, Chongqing 400030, Peoples R China; [Yang, Zhengchun] Chongqing Hlth Ctr Women & Children, Dept Ultrasound, Chongqing 401147, Peoples R China; [Yang, Zhengchun] Chongqing Med Univ, Dept Ultrasound, Women & Childrens Hosp, Chongqing 401147, Peoples R China"

通信作者："Huang, H (通讯作者)，Chongqing Univ, Key Lab Optoelect Technol & Syst Educ, Minist China, Chongqing 400044, Peoples R China."

来源：BIOMEDICAL OPTICS EXPRESS

ESI学科分类：BIOLOGY & BIOCHEMISTRY

WOS号：WOS:000994399200020

JCR分区：Q1

影响因子：3.4

年份：2022

卷号：13

期号：11

开始页：5794

结束页：5812

文献类型：Article

关键词：　

摘要："Accurate histopathological analysis is the core step of early diagnosis of cholangio-carcinoma (CCA). Compared with color pathological images, hyperspectral pathological images have advantages for providing rich band information. Existing algorithms of HSI classification are dominated by convolutional neural network (CNN), which has the deficiency of distorting spectral sequence information of HSI data. Although vision transformer (ViT) alleviates this problem to a certain extent, the expressive power of transformer encoder will gradually decrease with increasing number of layers, which still degrades the classification performance. In addition, labeled HSI samples are limited in practical applications, which restricts the performance of methods. To address these issues, this paper proposed a multi-layer collaborative generative adversarial transformer termed MC-GAT for CCA classification from hyperspectral pathological images. MC-GAT consists of two pure transformer-based neural networks including a generator and a discriminator. The generator learns the implicit probability of real samples and transforms noise sequences into band sequences, which produces fake samples. These fake samples and corresponding real samples are mixed together as input to confuse the discriminator, which increases model generalization. In discriminator, a multi-layer collaborative transformer encoder is designed to integrate output features from different layers into collaborative features, which adaptively mines progressive relations from shallow to deep encoders and enhances the discrim-inating power of the discriminator. Experimental results on the Multidimensional Choledoch Datasets demonstrate that the proposed MC-GAT can achieve better classification results than many state-of-the-art methods. This confirms the potentiality of the proposed method in aiding pathologists in CCA histopathological analysis from hyperspectral imagery.(c) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement"

基金机构：National Natural Science Foundation of China [42071302]; Innovation Program for Chongqing Overseas Returnees [cx2019144]; Graduate Research and Innovation Foundation of Chongqing [CYB21060]; Higher Education and Research (NVIDIA); National Natural Science Foundation of China [42071302]; Innovation Program for Chongqing Overseas Returnees [cx2019144]; Graduate Research and Innovation Foundation of Chongqing [CYB21060]; Higher Education and Research (NVIDIA)

基金资助正文：National Natural Science Foundation of China (42071302); Innovation Program for Chongqing Overseas Returnees (cx2019144); Graduate Research and Innovation Foundation of Chongqing (CYB21060); Higher Education and Research (NVIDIA).