Deep Learning-Based Multi-Scale Attention Fusion Framework for Automated Kidney Cancer Localization and Classification Kidney Cancer
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 January 2026
,
Page 1-9
https://doi.org/10.22037/ijmtfm.v16.52494
Abstract
Background: CT imaging is one of the most commonly used methods for diagnosing renal malignancy. Manual evaluation is cumbersome and highly subjective as it depends on the skill set of an expert nephrologist.
Methods: This paper proposes an automated deep learning approach based on a two-stage model in lesion localization and early-stage kidney cancer classification. First, the kidney regions are segmented using an improved U-Net architecture with multi-scale feature fusion, enabling accurate identification of affected kidney regions. Next, the segmented lesion maps are fed into a classifier network (ResNet/DenseNet) to classify early-stage kidney cancer.
Results: Segmentation-based lesion information fusion improves stage-wise discrimination and limits false predictions during the early stages of kidney cancer detection. The proposed method clearly demonstrates improved predictive accuracy and operational efficiency compared to conventional end-to-end classification models. The integration of segmentation and classification provides more reliable identification of cancerous regions and supports improved stage-wise prediction.
Conclusion: The approach provides clinical interpretability by marking the affected portion of the kidney and assigning a stage-wise cancer label. The proposed framework can assist clinicians in early-stage kidney cancer assessment by providing both lesion localization and stage-wise classification. It also offers a promising basis for developing efficient and interpretable computer-aided diagnostic systems for renal malignancy.
- Kidney cancer, U-Net, CT, Feature fusion, Deep learning, Localization
How to Cite
References
[1] Zhang Y. Retinal OCT image segmentation with deep learning. Comput Vis Image Underst. 2025. [DOI: 10.1016/j.cviu.2025.103123]
[2] Bhoopalan S, et al. Hybrid methods for retinal OCT segmentation. Sci Rep. 2025. [DOI: 10.1038/s41598-025-89262-z]
[3] Soni A. Multi-scale feature fusion attention UNet for retinal vessel segmentation. Sci Rep. 2025. [DOI: 10.1038/s41598-025-28707-x]
[4] Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172(5):1122–31.e9. [DOI: 10.1016/j.cell.2018.02.010]
[5] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc IEEE Conf Comput Vis Pattern Recognit. 2016:770–8. [DOI: 10.1109/CVPR.2016.90]
[6] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proc IEEE Conf Comput Vis Pattern Recognit. 2017:2261–9. [DOI: 10.1109/CVPR.2017.243]
[7] Wang S. Deep learning for retinal OCT classification. IEEE Access. 2020. [DOI: 10.1109/ACCESS.2020.3015176]
[8] Tsuji K. Practical OCT classification using deep learning. Sci Rep. 2020. [DOI: 10.1038/s41598-020-68279-6]
[9] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. MICCAI. 2015:234–41. [DOI: 10.1007/978-3-319-24574-4_28]
[10] Oktay O. Attention U-Net for pancreas segmentation. arXiv Preprint. 2018. [DOI: 10.48550/arXiv.1804.03999]
[11] Ma J. Supervised attention U-Net for retinal vessel segmentation. Image Vis Comput. 2023. [DOI: 10.1016/j.imavis.2023.104207]
[12] Gao F. Macular edema segmentation in OCT using U-Net++. Appl Sci. 2022. [DOI: 10.3390/app10165701]
[13] Soni A. Multi-scale feature fusion attention UNet for retinal vessel segmentation. Sci Rep. 2025. [DOI: 10.1038/s41598-025-28707-x]
[14] Liu X. IMFF-Net: Integrated multi-scale feature fusion for retinal vessel segmentation. Biomed Signal Process Control. 2024. [DOI: 10.1016/j.bspc.2024.103907]
[15] Mani P, Ramachandran N, Paul SJ, Ramesh PV. Laceration assessment: advanced segmentation and classification framework for retinal disease categorization in optical coherence tomography images. J Opt Soc Am A. 2024. [DOI: 10.1364/JOSAA.526142]
[16] Diao Y. Dual guidance networks for OCT classification and segmentation. Comput Methods Programs Biomed. 2023. [DOI: 10.1016/j.cmpb.2023.107780]
[17] Zhang Z, Jiang S, Pan X. Ctnet: rethinking convolutional neural networks and vision transformer for medical image segmentation. Signal Image Video Process. 2024;18(3):2265–75. [DOI: 10.1007/s11760-023-02899-z]
[18] Seebock P. Anomaly-guided retinal OCT lesion segmentation using weak supervision. Med Image Anal. 2024. [DOI: 10.1016/j.media.2024.102905]
[19] Ganjee R, Ebrahimi Moghaddam M, Nourinia R. A generalizable approach based on the U-Net model for automatic intraretinal cyst segmentation in SD-OCT images. Int J Imaging Syst Technol. 2023. [DOI: 10.1002/ima.22893]
- Abstract Viewed: 2 times
- PDF Downloaded: 2 times