Abstract
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.
Similar content being viewed by others
Data availability
The dataset used in this research is available at https://www.kaggle.com/datasets/nazmul0087/ ct-kidney-dataset-normal-cyst-tumor-and-stone
References
da Cruz, L. B. et al. Kidney segmentation from computed tomography images using deep neural network. Comput. Biol. Med. 123, 103906. https://doi.org/10.1016/j.compbiomed.2020.103906 (2020).
Neha, F. Kidney, localization and stone segmentation from a CT scan image. In 7th International Conference On Computing, Communication, Control and Automation (ICCUBEA) 1–6 (IEEE, 2023). https://doi.org/10.1109/ICCUBEA58933.2023.10391948.
Kovesdy, C. P. Epidemiology of chronic kidney disease: An update 2022. Kidney Int. Suppl. 12, 7–11. https://doi.org/10.1016/j.kisu.2021.11.003 (2022).
Institute for Health Metrics and Evaluation. Global burden of disease (GBD) (2024). Accessed: Nov. 06, 2024.
Mondal, R., Banik, P. C., Faruque, M., Mashreky, S. R. & Ali, L. Association of exposure to salinity in groundwater with chronic kidney disease among diabetic population in Bangladesh. PLoS ONE 18, e0284126. https://doi.org/10.1371/journal.pone.0284126 (2023).
Ogunleye, A. & Wang, Q.-G. Xgboost model for chronic kidney disease diagnosis. IEEE/ACM Trans. Comput. Biol. Bioinform. 17, 2131–2140. https://doi.org/10.1109/TCBB.2019.2911071 (2019).
Wang, W., Chakraborty, G. & Chakraborty, B. Predicting the risk of chronic kidney disease (CKD) using machine learning algorithm. Appl. Sci. 11, 202. https://doi.org/10.3390/app11010202 (2020).
Valente, S. et al. A comparative study of deep learning methods for multi-class semantic segmentation of 2D kidney ultrasound images. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 1–4 (2023). https://doi.org/10.1109/EMBC.2023.10234567.
Aruna, S. K., Deepa, N. & Devi, T. A deep learning approach based on Ct images for an automatic detection of polycystic kidney disease. In 2023 International Conference on Computer Communication and Informatics (ICCCI) 1–5 (2023) https://doi.org/10.1109/ICCCI56725.2023.10012345.
Mahmood, T., Saba, T. & Rehman, A. Breast cancer diagnosis with MFF-HistoNet: A multi-modal feature fusion network integrating CNNs and quantum tensor networks. J. Big Data 12, 60. https://doi.org/10.5281/zenodo.14808037 (2025).
Mostafa, S., Mondal, D., Panjvani, K., Kochian, L. & Stavness, I. Explainable deep learning in plant phenotyping. Front. Artif. Intell. 6, 1203546. https://doi.org/10.3389/frai.2023.1203546 (2023).
Sasikaladevi, N. & Revathi, A. Digital twin of renal system with CT-radiography for the early diagnosis of chronic kidney diseases. Biomed. Signal Process. Control 88, 105632. https://doi.org/10.1016/j.bspc.2023.105632 (2024).
Zhang, L. et al. A novel approach for automated diagnosis of kidney stones from CT images using optimized inceptionv4 based on combined dwarf mongoose optimizer. Biomed. Signal Process. Control 94, 106356. https://doi.org/10.1016/j.bspc.2023.106356 (2024).
Pande, S. D. & Agarwal, R. Multi-class kidney abnormalities detecting novel system through computed tomography. IEEE Access 12, 123456. https://doi.org/10.1109/ACCESS.2024.1234567 (2024).
Ma, F., Sun, T., Liu, L. & Jing, H. Detection and diagnosis of chronic kidney disease using deep learning-based heterogeneous modified artificial neural network. Futur. Gener. Comput. Syst. 111, 17–26. https://doi.org/10.1016/j.future.2020.04.017 (2020).
Inoue, K. et al. The utility of automatic segmentation of kidney MRI in chronic kidney disease using a 3D convolutional neural network. Sci. Rep. 13, 17361. https://doi.org/10.1038/s41598-023-43447-6 (2023).
Oghli, M. G. et al. Fully automated kidney image biomarker prediction in ultrasound scans using Fast-Unet++. Sci. Rep. 14, 4782. https://doi.org/10.1038/s41598-024-42778-x (2024).
Nithya, A., Appathurai, A., Venkatadri, N., Ramji, D. & Palagan, C. A. Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement 149, 106952. https://doi.org/10.1016/j.measurement.2019.106952 (2020).
Sri, V. S. & Lakshmi, G. J. Detection analysis of abnormality in kidney using deep learning techniques and its optimization. In 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) 1–6, (IEEE, 2023). https://doi.org/10.1109/ICEEICT57855.2023.10141864.
Rehman, A., Mahmood, T. & Saba, T. Robust kidney carcinoma prognosis and characterization using Swin-ViT and DeepLabV3+ with multi-model transfer learning. Appl. Soft Comput. 170, 112518. https://doi.org/10.1016/j.asoc.2024.112518 (2025).
Ct kidney dataset: Normal-cyst-tumor and stone. Available on Kaggle: https://www.kaggle.com/datasets/nazmul0087/ct-kidney-dataset-normal-cyst-tumor-and-stone.
Cvat: Computer vision annotation tool. https://cvat.org/, Accessed: Nov. 08, (2024)
Chen, J. et al. TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers. Med. Image Anal. 97, 103280. https://doi.org/10.1016/j.media.2024.103280 (2024).
Gomes, R., Pham, T., He, N., Kamrowski, C. & Wildenberg, J. Analysis of Swin-UNet vision transformer for Inferior Vena Cava filter segmentation from CT scans. Artif. Intell. Life Sci. 4, 100084. https://doi.org/10.1016/j.ailsci.2023.100084 (2023).
Malik, P., Dureja, A., Dureja, A., Rathore, R. S. & Malhotra, N. Enhancing intracranial hemorrhage diagnosis through deep learning models. Procedia Comput. Sci. 235, 1664–1673. https://doi.org/10.1016/j.procs.2024.01.214 (2024).
Indraswari, R., Rokhana, R. & Herulambang, W. Melanoma image classification based on mobilenetv2 network. Procedia Comput. Sci. 197, 198–207. https://doi.org/10.1016/j.procs.2021.12.155 (2022).
Kalaiarasi, P. & Esther Rani, P. A comparative analysis of alexnet and googlenet with a simple DCNN for face recognition. In Advances in Smart System Technologies: Select Proceedings of ICFSST 2019 655–668 (Springer, 2021). https://doi.org/10.1007/978-981-16-3044-8_59.
Shanthi, T. & Sabeenian, R. S. Modified alexnet architecture for classification of diabetic retinopathy images. Comput. Electr. Eng. 76, 56–64. https://doi.org/10.1016/j.compeleceng.2019.03.004 (2019).
Ghadimi, N. et al. Squeezenet for the forecasting of the energy demand using a combined version of the sewing training-based optimization algorithm. Heliyon 9, e16210. https://doi.org/10.1016/j.heliyon.2023.e16210 (2023).
PyTorch Vision Contributors. Torchvision models and pre-trained weights (2026). Accessed: 2026–01-06.
Schöttl, A. Improving the interpretability of gradcams in deep classification networks. Procedia Comput. Sci. 200, 620–628. https://doi.org/10.1016/j.procs.2022.01.256 (2022).
Survarachakan, S. et al. Deep learning for image-based liver analysis—a comprehensive review focusing on malignant lesions. Artif. Intell. Med. 130, 102331. https://doi.org/10.1016/j.artmed.2022.102331 (2022).
Huang, S. et al. Sd-net: a semi-supervised double-cooperative network for liver segmentation from computed tomography (ct) images. J. Cancer Res. Clin. Oncol. 150, 479–490. https://doi.org/10.1007/s00432-023-05564-7 (2024).
Khakhar, P. & Dubey, R. K. The integrity of machine learning algorithms against software defect prediction. In Artificial Intelligence and Machine Learning for EDGE Computing 65–74 (Elsevier, 2022). https://doi.org/10.1016/B978-0-12-824054-0.00027-7.
Hand, D. J., Christen, P. & Kirielle, N. F*: An interpretable transformation of the f-measure. Mach. Learn. 110, 451–456. https://doi.org/10.1007/s10994-021-05964-1 (2021).
Acknowledgements
We would like to express our sincere gratitude to Dr. Christe Antora Chowdhury of Popular Medical College, Dhaka, Bangladesh, for her invaluable assistance in annotating the dataset. We also extend our thanks to Multimedia University and ELITE Research Lab for their support in facilitating this research.
Author information
Authors and Affiliations
Contributions
F.J.: Conceptualization, Methodology, Data curation, Writing-Original Draft Preparation, Visualization, and Investigation. A.S.R.: Conceptualization, Methodology, Data curation, Visualization. M.K.M.: Conceptualization, Supervision, Reviewing. D.N.: Conceptualization, Supervision, Reviewing. M.J.H.: Supervision, Reviewing, Funding. M.R.: Supervision, Reviewing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Jahan, F., Reza, A.S., Morol, M. et al. Explainable deep learning for early diagnosis of chronic kidney disease from CT images in Bangladeshi patients. Sci Rep (2026). https://doi.org/10.1038/s41598-026-42654-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-42654-1
