Search

Deploying deep learning (DL) models in medical applications relies on predictive performance and other critical factors, such as conveying trustworthy predictive uncertainty. Uncertainty estimation (UE) methods provide potential solutions for evaluating prediction reliability and improving the model confidence calibration. Despite increasing interest in UE, challenges persist, such as the need for explicit methods to capture aleatoric uncertainty and align uncertainty estimates with real-life disagreements among domain experts. This paper proposes an Expert Disagreement-Guided Uncertainty Estimation (EDUE) for medical image segmentation. By leveraging variability in ground-truth annotations from multiple raters, we guide the model during training and incorporate random sampling-based strategies to enhance calibration confidence. Our method achieves 55% and 23% improvement in correlation on average with expert disagreements at the image and pixel levels, respectively, better calibration, and competitive segmentation performance compared to the state-of-the-art deep ensembles, requiring only a single forward pass.

Variability in staining protocols, such as different slide preparation techniques, chemicals, and scanner configurations, can result in a diverse set of whole slide images (WSIs). This distribution shift can negatively impact the performance of deep learning models on unseen samples, presenting a significant challenge for developing new computational pathology applications. In this study, we propose a method for improving the generalizability of convolutional neural networks (CNNs) to stain changes in a single-source setting for semantic segmentation. Recent studies indicate that style features mainly exist as covariances in earlier network layers. We design a channel attention mechanism based on these findings that detects stain-specific features and modify the previously proposed stain-invariant training scheme. We reweigh the outputs of earlier layers and pass them to the stain-adversarial training branch. We evaluate our method on multi-center, multi-stain datasets and demonstrate its effectiveness through interpretability analysis. Our approach achieves substantial improvements over baselines and competitive performance compared to other methods, as measured by various evaluation metrics. We also show that combining our method with stain augmentation leads to mutually beneficial results and outperforms other techniques. Overall, our study makes significant contributions to the field of computational pathology.

Alanoud Aladel,1 Fahmida Khatoon,2 Mohammad Idreesh Khan,3 Azzah Alsheweir,1 Malak Ghazi Almutairi,4 Sami Owaidh Almutairi,4 Faisal Khalid Almutairi,5 Kudaibergen Osmonaliev,6 Mirza Masroor Ali Beg6,7 1Department of Community Health Sciences, College of Applied Medical Sciences, King Saud University, Riyadh, Saudi Arabia; 2Biochemistry Department, College of Medicine, University of Ha’il, Ha’il, Saudi Arabia; 3Department of Clinical Nutrition, College of Applied Health Sciences in Ar Rass, Qassim University, Ar Rass, 51921, Saudi Arabia; 4Department of Clinical Nutrition, Almethnab General Hospital, Qassim Health Cluster, Ministry of Health, Al Mithnab, Saudi Arabia; 5Laboratory Department, Armed Forces Hospital in Qassim, Medical Services, Ministry of Defense Qassim Buraydah Al-Rass, Buraydah, Saudi Arabia; 6Faculty of Medicine, Alatoo International University, Bishkek, Kyrgyzstan; 7Centre for Promotion of Medical Research, Bishkek, KyrgyzstanCorrespondence: Mirza Masroor Ali Beg, Email mirzamasroor1986@gmail.comObjective: Growing epidemics of type-2 diabetes mellitus (T2DM) and obesity have become a serious health concern. Since miRNAs and vitamin levels affect the development and progression of numerous pathogenic diseases, including diabetes, the present study aimed to evaluate miRNA-143 and miRNA-145 expression and vitamin-D status among obese and non-obese T2DM patients.Methods: The study included 100 clinically confirmed newly diagnosed obese and non-obese T2DM cases and 100 healthy subjects. Total RNA was extracted from collected blood samples and 100 ng of RNA was used for cDNA synthesis, then TaqMan assay was performed to evaluate the miRNA-143 and miRNA-145 relative expression.Results: T2DM cases with hypertension (4.08 fold, p=0.01; 5.36 fold, p=0.009), fatigue (5.07 fold, p=0.04; 5.32 fold, p=0.03) and blurred vision (5.15 fold, p=0.01) showed higher miRNA-143 and miRNA-145 relative expression compared with their counterparts, respectively. A positi

Glioblastoma is a common brain malignancy that tends to occur in older adults and is almost always lethal. The effectiveness of chemotherapy, being the standard treatment for most cancer types, can be improved if a particular genetic sequence in the tumor known as MGMT promoter is methylated. However, to identify the state of the MGMT promoter, the conventional approach is to perform a biopsy for genetic analysis, which is time and effort consuming. A couple of recent publications proposed a connection between the MGMT promoter state and the MRI scans of the tumor and hence suggested the use of deep learning models for this purpose. Therefore, in this work, we use one of the most extensive datasets, BraTS 2021, to study the potency of employing deep learning solutions, including 2D and 3D CNN models and vision transformers. After conducting a thorough analysis of the models' performance, we concluded that there seems to be no connection between the MRI scans and the state of the MGMT promoter.

In this work, we present an end-to-end deep learning framework for X-ray image diagnosis. As the first step, our system determines whether a submitted image is an X-ray or not. After it classifies the type of the X-ray, it runs the dedicated abnormality classification network. In this work, we only focus on the chest X-rays for abnormality classification. However, the system can be extended to other X-ray types easily. Our deep learning classifiers are based on DenseNet-121 architecture. The test set accuracy obtained for 'X-ray or Not', 'X-ray Type Classification', and 'Chest Abnormality Classification' tasks are 0.987, 0.976, and 0.947, respectively, resulting into an end-to-end accuracy of 0.91. For achieving better results than the state-of-the-art in the 'Chest Abnormality Classification', we utilize the new RAdam optimizer. We also use Gradient-weighted Class Activation Mapping for visual explanation of the results. Our results show the feasibility of a generalized online projectional radiography diagnosis system., Comment: 4 pages, 5 figures