An automatic method for microscopic diagnosis of diseases based on URCNN. (February 2023)

• Record Type: Journal Article
• Authors: Hoorali, Fatemeh; Khosravi, Hossein; Moradi, Bagher
• Is Part Of: Biomedical signal processing and control. Volume 80(2023)Part 1
• Publication Date: 2023-02
• Subjects: Deep learning -- Instance segmentation -- Anthrax disease -- Mask-RCNN -- URCNN; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104240
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Providing a reliable system for automatic diagnosis of anthrax and other tissue diseases, metastasis, patient prognosis using the detection and segmentation of important components in microscopic images. Proposing an improved Mask-RCNN, called URCNN, in which the suggested enhanced FPN structure improves the detection accuracy of the RPN. Suggesting a U-shaped structure with dense skip connections as the mask branch in the head architecture of the Mask-RCNN. Improving the segmentation efficiency by proposing a hybrid weighted loss function. Producing better detection and segmentation results compared with the state-of-the-art architectures. Abstract: Anthrax is a rare but dangerous disease for humans. A common way to diagnose this disease is the microscopic examination of slides containing tissue samples of patients. This paper aims to develop a reliable system in histopathological image analysis for the diagnosis of tissue diseases, metastasis, patient prognosis, etc. Automatic diagnosis of anthrax is investigated via the detection and segmentation of Bacillus anthracis bacteria and major immune system cells. Most recent models for instance segmentation are based on Mask-RCNN. It has an acceptable performance in most cases, but due to the challenges in the field of microscopic images, it fails to accurately detect and segment some of the important objects. Here, we have improved the performance of Mask-RCNN by making some modifications as follows: (1) A U-shaped structure is used as the mask branch in the head of Mask-RCNN that takes the advantage of combining multi-scale feature maps, (2) An enhanced FPN structure is proposed, which takes advantage of the squeeze and excitation-residual blocks and squeeze and excitation-inception blocks, (3) A hybrid weighted loss function composed of L BCE, L Dice a n d L IoU is proposed to update the weights and (4) Finally, a dropout layer is added after each FC layer in the classifier structure of the head Mask-RCNN architecture to improve the generalization power of the model. Experimental results show that the proposed model outperforms the state-of-the-art architectures and is a reliable system for the automatic diagnosis of anthrax.