Classification of renal biopsy direct immunofluorescence image using multiple attention convolutional neural network. (February 2022)

• Record Type: Journal Article
• Authors: Zhang, Liang; Li, Ming; Wu, Yongfei; Hao, Fang; Wang, Chen; Han, Weixia; Niu, Dan; Zheng, Wen
• Is Part Of: Computer methods and programs in biomedicine. Volume 214(2022)
• Publication Date: 2022-02
• Subjects: Image classification -- Direct immunofluorescence images -- Kidney pathology -- Multiple attention CNN; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106532
• Languages: English
• ISSNs: 0169-2607

Abstract

Research highlights: Propose a two-stage CNN framework including pre-segmentation module and multiple attention classification module. A multiple attention mechanism for immunofluorescence image recognition is proposed. We rigorously studied the automatic recognition and fusion of immunoglobulin deposition appearance and deposition location Abstract: Background and objectives: Direct immunofluorescence (DIF) is an important medical evaluation tool for renal pathology. In the DIF images, the deposition appearances and locations of immunoglobulin on glomeruli involve immunological characteristics of glomerulonephritis and thus can be used to aid in the identification of glomerulonephritis disease. Manual classification to such deposition patterns is time consuming and may lead to significant inter and intra operator variances. We wanted to automate the identification and fusion of deposition location and deposition appearance to assist physicians in achieving immunofluorescence reporting. Methods: In this paper, we propose a framework that consists of a pre-segmentation module and a classification module for automatically segmenting glomerulus object and classifying the deposition pattern of immunoglobulin on glomerulus object. For the pre-segmentation module, the glomerulus object is segmented out from the acquired DIF images using a segmentation network, which excludes other tissues and makes the classification module focus on the glomerulus. For the classification module, two branches of classifying deposition region and appearance, respectively, are formed by using multiple attentions convolutional neural network (MANet) based on the segmented images, and the classification results of the two pre-trained classification networks are fused with labels. Results: Experimental results show that the proposed framework achieves a high classification performance with an accuracy of 98% and 95% in terms of deposition region and appearance, respectively. The label fusion of deposition appearance and deposition classification is achieved with high accuracy based on well-trained classification. Conclusions: The data show that automated and accurate patterned immunofluorescence report generation is achieved, which can effectively help improve the diagnosis of autoimmune kidney disease.