SegEIR-Net: A Robust Histopathology Image Analysis Framework for Accurate Breast Cancer Classification.

BACKGROUND: Breast Cancer (BC) is a significant threat affecting women globally. An accurate and reliable disease classification method is required to get an early diagnosis. However, existing approaches lack accurate and robust classification. OBJECTIVE: This study aims to design a model to classify BC Histopathology images accurately by leveraging segmentation techniques. METHODS: This work proposes a combined segmentation and classification approach for classifying BC using histopathology images to address these issues. Chan-Vese algorithm is used for segmentation to accurately delineate regions of interest within the histopathology images, followed by the proposed SegEIR-Net (Segmentation using EfficientNet, InceptionNet, and ResNet) for classification. Bilateral Filtering is also employed for noise reduction. The proposed model uses three significant networks, ResNet, InceptionNet, and EfficientNet, concatenates the outputs from each block followed by Dense and Dropout layers. The model is trained on the breakHis dataset for four different magnifications and tested on BACH (BreAst Cancer Histology) and UCSB (University of California, Santa Barbara) datasets. RESULTS: SegEIR-Net performs better than the existing State-of-the-Art (SOTA) methods in terms of accuracy on all three datasets, proving the robustness of the proposed model. The accuracy achieved on breakHis dataset are 98.66%, 98.39%, 97.52%, 95.22% on different magnifications, and 93.33% and 96.55% on BACH and UCSB datasets. CONCLUSION: These performance results indicate the robustness of the proposed SegEIR-Net framework in accurately classifying BC from histopathology images.

Clinical correlation between incipient C-reactive protein and kidney injury of anti-neutrophil cytoplasmic antibody associated vasculitis / 中华肾脏病杂志

Objective To investigate the relationship between the incipient serum C-reactive protein (CRP) and clinicopathologic features in anti-neutrophil cytoplasmic antibody associated vasculitis (AAV).Methods Data of 138 consecutive AAV patients were collected.According to their serum CRP levels,patients were divided into group 1 with normal CRP,group 2 with slightly increased CRP and group 3 with severely increased CRP.Clinical features of AAV and histopathologic features of the kidney injury were compared among groups.Results CRP levels increased in 77.53％ AAV patients on admission.Patients in the group of severely increased CRP had the highest levels of BVAS,serum C3,serum ANCA titer,leukocyte counts and the lowest levels of hemoglobin and albumin among the 3 groups (all P ＜ 0.05).The mortality during the stage of therapy was highest in patients with severely increased CRP (P ＜ 0.05).The focal kidney damage was more obvious in patients with severely increased CRP.There was no significant difference in renal prognosis among patients with different CRP levels.Conclusion The levels of incipient serum C-reactive protein of AAV vary in different patients and are positively correlated with patients' inflammation status as well as the disease activity,but are not correlated with the severity of kidney injury.