MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1038/s41598-026-42654-1

Медицинская библиотека · Scientific reports · 2026

Explainable deep learning for early diagnosis of chronic kidney disease from CT images in Bangladeshi patients.

Jahan Fariha, Reza Ahmed Shakib, Morol Md Kishor, Nandi Dip, Hossen Md Jakir, Rahman Mashiour

СтатьяПеревод в очереди

Аннотация

Kidney failure, or end-stage renal disease (ESRD), represents the final stage of chronic kidney disease (CKD) and poses a life-threatening risk if not addressed promptly. Early detection of CKD is critical for preventing progression to ESRD, yet current diagnostic methods remain time-consuming and often reliant on manual interpretation. This study introduces an integrated framework for automated CKD diagnosis, specifically designed for the Bangladeshi population, which combines segmentation, classification, and explainable artificial intelligence (XAI). Using the CT Kidney Dataset, a modified U-Net model was developed for kidney region segmentation, achieving an accuracy of 98%, a Dice coefficient of 98%, and an Intersection over Union (IoU) of 97%. For the classification task, a novel lightweight Kid-Net model, based on EfficientNetB3, was proposed, achieving 99.30% accuracy in cross-validation for distinguishing between normal, cyst, stone, and tumor categories. To enhance model transparency, Grad-CAM was applied for visualizing the regions of interest, thus improving interpretability. Furthermore, the KidVision framework was introduced to outline the clinical deployment pipeline, offering a scalable and efficient solution for real-world nephrology applications. The results demonstrate that the proposed framework not only delivers high accuracy but also facilitates early and automated detection of kidney-related disorders, contributing to improved clinical decision-making and patient outcomes.

Для цитирования: Jahan Fariha, Reza Ahmed Shakib, Morol Md Kishor, Nandi Dip, Hossen Md Jakir, Rahman Mashiour. Explainable deep learning for early diagnosis of chronic kidney disease from CT images in Bangladeshi patients.. Scientific reports. 2026. DOI: 10.1038/s41598-026-42654-1.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.