Center-Focused Affinity Loss for Class Imbalance Histology Image Classification.

Early-stage cancer diagnosis potentially improves the chances of survival for many cancer patients worldwide. Manual examination of Whole Slide Images (WSIs) is a time-consuming task for analyzing tumor-microenvironment. To overcome this limitation, the conjunction of deep learning with computational pathology has been proposed to assist pathologists in efficiently prognosing the cancerous spread. Nevertheless, the existing deep learning methods are ill-equipped to handle fine-grained histopathology datasets. This is because these models are constrained via conventional softmax loss function, which cannot expose them to learn distinct representational embeddings of the similarly textured WSIs containing an imbalanced data distribution. To address this problem, we propose a novel center-focused affinity loss (CFAL) function that exhibits 1) constructing uniformly distributed class prototypes in the feature space, 2) penalizing difficult samples, 3) minimizing intra-class variations, and 4) placing greater emphasis on learning minority class features. We evaluated the performance of the proposed CFAL loss function on two publicly available breast and colon cancer datasets having varying levels of imbalanced classes. The proposed CFAL function shows better discrimination abilities as compared to the popular loss functions such as ArcFace, CosFace, and Focal loss. Moreover, it outperforms several SOTA methods for histology image classification across both datasets.

Comparison of pre- and post-hemodialysis PHQ-9 depression scores in patients with end-stage renal disease: A cross-sectional study.

OBJECTIVES: An overlap between the somatic symptoms of depression and those of uremia seen in end-stage renal disease (ESRD) patients may affect the diagnosis of depression. This study aims to evaluate the effect of hemodialysis on the diagnosis of depression among patients on maintenance hemodialysis as dialysis diminishes the uremic symptoms, and to compare depression scores before and after dialysis. METHODS: This was a cross-sectional analytic study conducted from November 2018 through April 2019, in three tertiary hospitals. Consenting participants aged 18 years or older, who had received hemodialysis for at least three months were included. The Patient Health Questionnaire (PHQ-9) tool was used to collect patients' data and to identify symptoms of depression Pre- and post-hemodialysis. Depression scores were compared using the paired sample Wilcoxon rank test or the McNemar test, where appropriate. RESULTS: Overall, 163 participants were enrolled in the study. The average age of the participants was 56.5 years old, whereas 44.8% were females. The prevalence of depressive symptoms before hemodialysis was 48.5%, with prevalence of mild, moderate and moderately severe of 34.4%, 11.7% and 2.5%, respectively. On the other hand, the prevalence of depressive symptoms after hemodialysis was 46.6% with 36.8%, 9.2% and 0.6% of the participants reporting mild, moderate and moderately severe symptoms, respectively. We found no significant difference in depression scores before and after dialysis (p-values > 0.05). CONCLUSION: Our study supports the fact that the prevalence of depression is high among patients with ESRD on maintenance hemodialysis. We didn't find a significant difference in depression scores among hemodialysis patients before and after dialysis, with negligible effect of uremic symptoms on the diagnosis of depression. We suggest adopting routine screening of depression among this high-risk group of patients.

Prevalence and associated factors of undiagnosed atrial fibrillation among end-stage renal disease patients on maintenance haemodialysis: a cross-sectional study.

BACKGROUND: Atrial fibrillation (AF) is the most prevalent sustained arrhythmia worldwide and it aggravates cardiovascular morbidity and mortality; however, this is largely under-diagnosed. Moreover, among end-stage renal disease patients on haemodialysis, AF is substantially more common and serious. The researchers conducted this study to assess the prevalence of, and the factors correlated with AF in Jordanian haemodialysis patients. METHODS: In a cross-sectional analysis conducted from October 2018 to February 2019 in four tertiary hospitals, the researchers enrolled all consenting patients aged 18 years or older who were on haemodialysis for at least three months prior to the study. We screened for AF clinically by pulse palpation, precordial auscultation, by an automated blood pressure monitor and an electrocardiogram. The researchers reported qualitative variables as counts and frequencies, while continuous variables were summarised using the mean or median where necessary. We used multiple logistic regression with backward selection to identify independent risk factors of AF. RESULTS: A total of 231 patients were enrolled; mean age was 54.8 ± 15.6 years (from 20 to 86), and 44.3% of them were women. The prevalence of AF was found to be 7.8% (95% CI, 4.8-12.2), with no gender disparity. Age (adjusted odds ratio [AOR] = 1.05; 95% CI, 1.01-1.10; p = 0.031), history of ischaemic heart disease (AOR = 3.74; 95% CI, 1.09-12.34; p = 0.033), history of smoking (AOR = 0.15; 95% CI, 0.02-0.60; p = 0.019), and low interdialytic weight gain (AOR = 0.50: 95% CI, 0.25-0.91; p = 0.031) were independently correlated to AF. CONCLUSIONS: The prevalence of AF among patients on maintenance haemodialysis is high, but largely undiagnosed. AF is generally associated with advancing age, history of ischaemic heart disease, lower interdialytic weight gain, and history of smoking. We suggest routine check-up of AF in this high-risk group of patients as anticoagulant therapy if indicated may prevent serious complications. However, there is a need for large-scale cohort studies and for the creation of regional chronic kidney disease and dialysis registries in the Middle East region.