FPGA-Based Computer-Aided Diagnosis for Kidney CT Images Abnormality Classification Using NSCT and a Modified YOLOv11
DOI:
https://doi.org/10.59992/IJSR.2026.v5n2p12Keywords:
CT Images, Nonsubsampled Contourlet Transform, YOLOv-11Abstract
Kidney disease diagnosis often relies on expert radiologists and advanced imaging analysis, which may be limited or unavailable in remote healthcare settings. This paper presents an FPGA-oriented computer-aided diagnosis scheme for binary kidney abnormality classification (normal vs. abnormal) that combines kidney ROI extraction with nonsubsampled contourlet transform (NSCT) feature compaction and a modified YOLOv11 classifier. After normalization and kidney segmentation, NSCT is applied to the ROI and only the final low-frequency sub-band is retained as a compact, structure-preserving representation for classification. The key novelty is a lightweight YOLOv11 classification variant tailored for deployment constraints by reducing depth scaling and removing attention modules to support efficient fixed-point implementation while retaining discriminative power with NSCT low-frequency inputs. The proposed method has been achieved better results as shown in accuracy, sensitivity, and specificity (i.e.: 97.45%, 98.23%, and 97.45%) respectively. The higher performance of Zynq based hardware shows 68 ms latency in image, and 14.7 images/ throughput, performing better real-time for kidney CT disease classification.
References
[1] MackMJ. Minimally invasive and robotic surgery. JAMA 2001;285(5):568–72.
[2] Tang, C.; Guss, D.; Tanaka, M.J.; Lubberts, B. Portable ultrasound devices: A method to improve access to medical imaging, barriers to implementation, and the need for future advancements. Clin. Imaging 2022, 81, 147–149. [CrossRef]
[3] Altman, M. B., Wan, W., Hosseini, A. S., Nowdeh, S. A., & Alizadeh, M. (2024). Machine learning algorithms for FPGA Implementation in biomedical engineering applications: A review. Heliyon, 10(4).
[4] Murat, A. A., & Kiran, M. S. (2025). A comprehensive review on YOLO versions for object detection. Engineering Science and Technology, an International Journal, 70, 102161.
[5] Garzetti, F., Lusardi, N., Ronconi, E., Costa, A., & Geraci, A. (2024). Novel machine learning-driven optimizing decoding solutions for FPGA-based time-to-digital converters. Measurement, 238, 115313.
[6] Eppendorf, K.A.; Lafarge, M.W.; Veta, M.; Pluim, J.P. Progressively-trained convolutional neural networks for deformable image registration. IEEE Trans. Med. Imaging 2019, 39, 1594–1604.
[7] Anusha C, Rao KN, Rao TL. A systematic review on automatic segmentation of renal tumors and cysts using various convolutional neural network architectures in radiological images. Computers in Biology and Medicine. 2025;198(Pt A):111177. doi:10.1016/j.compbiomed.2025.111177.
[8] Kan HC, Fan GM, Wei MH, Lin PH, Shao IH, Yu KJ, et al. Automated kidney tumor segmentation in CT images using deep learning: A multi-stage approach. Academic Radiology. 2025;32(12):7193-7203. doi:10.1016/j.acra.2025.08.020.
[9] Obaid W, Hussain A, Rabie T, Abd DH, Mansoor W. Multi-model deep learning approach for the classification of kidney diseases using medical images. Informatics in Medicine Unlocked. 2025;57:101663. doi:10.1016/j.imu.2025.101663.
[10] Panchal N, Raikar MM, Baligar VP. Kidney stone detection using deep learning model. Procedia Computer Science. 2025;260:56-63. doi:10.1016/j.procs.2025.03.177.
[11] Han JH, Kim BW, Kim TM, Ko JY, Choi SJ, Kang M, et al. Fully automated segmentation and classification of renal tumors on CT scans via machine learning. BMC Cancer. 2025;25(1):173. doi:10.1186/s12885-025-13582-6.
[12] C.T. Chien, R.Y. Ju, K.Y. Chou, J.S. Chiang, YOLOv9 for fracture detection in pediatric wrist trauma X-ray images, Electron. Lett 60 (11) (2024) e13248.
[13] Bachanek S, Wuerzberg P, Biggemann L, Janssen TY, Nietert M, Lotz J, et al. Renal tumor segmentation, visualization, and segmentation confidence using ensembles of neural networks in patients undergoing surgical resection. European Radiology. 2025;35(4):2147-2156. doi:10.1007/s00330-024-11026-6.
[14] Aridhi E, Laabidi K, Mami A. FPGA technology in healthcare: A comprehensive review of hardware and software solutions for diagnostics, imaging, and patient care. Array. 2025;100622. doi:10.1016/j.array.2025.100622.
[15] Sayed R, Ahmed H, Elshennawy A, et al. HW–SW co-design of binary weight CNN for image classification on FPGA. Journal of Supercomputing. 2025. doi:10.1007/s11227-025-07430-7.
[16] Shawahna A, Sait SM, El-Maleh A. FPGA-based accelerators of deep learning networks for learning and classification: A review. IEEE Access. 2019;7:7823-7859. doi:10.1109/ACCESS.2018.2890150.
[17] da Cunha AL, Zhou J, Do MN. The nonsubsampled contourlet transform: theory, design, and applications. IEEE Transactions on Image Processing. 2006;15(10):3089-3101. minhdo.ece.illinois.edu
[18] Zhou J, Do MN. Nonsubsampled contourlet transform: construction and application in enhancement. Proceedings of IEEE International Conference on Image Processing (ICIP). 2005/2006 era foundational NSCT construction and enhancement usage.
[19] Raman AG, Fisher D, Rich JM, et al. Evaluation of nnU-Net for kidney tumor segmentation on a large external patient cohort. European Journal of Radiology Artificial Intelligence. 2025;3:100035. doi:10.1016/j.ejrai.2025.100035.
[20] Gan X, Zhu S, Zhang Y, et al. Dual-perspective decoupling network for kidney tumor segmentation on CT images. Neural Networks. 2025;193:108042. doi:10.1016/j.neunet.2025.108042.
[21] Hua, J.; Zeng, L.; Li, G.; Ju, Z. Learning for a Robot: Deep Reinforcement Learning, Imitation Learning, Transfer Learning. Sensors2021, 21, 1278.
[22] Fu, Q., Liu, X., Yan, Y., & Guo, Z. (2025). Mixed image detection method of belt coal blockage and leakage based on improved RetinaNet mode. Discover Applied Sciences, 7(6), 520.
[23] Choudhary, G., & Sethi, D. (2025). HVD-NSCTFusion: a new hybrid image fusion framework based on hilbert vibration decomposition and non-subsampled contourlet transform for multiple applications. Multimedia Tools and Applications, 1-39.
[24] Khanam, R., Asghar, T., & Hussain, M. (2025, February). Comparative performance evaluation of yolov5, yolov8, and yolov11 for solar panel defect detection. In Solar (Vol. 5, No. 1, p. 6). MDPI.
[26] H. Chen, et al., Choice of activation function in convolutional neural networks for
person re-identification in video surveillance systems, Program. Comput. Softw. 48 (5) (2022) 312–321.
[27] Y. Wang, et al., Multichannel time-to-digital converters with automatic calibration
in Xilinx Zynq-7000 FPGA devices, IEEE Trans. Ind. Electron. 69 (9) (2022) 9634–9643.
[28] Jocher, G.; Chaurasia, A.; Qiu, J. Ultralytics YOLOv8 2023. https://github.com/ ultralytics/ultralytics (accessed 02.06.2024).
[29] Wang, C.; Yeh, I.; Liao, H. YOLOv9: Learning what you want to learn using programmable gradient information. arXiv 2024. arXiv preprint arXiv:2402.13616.
[30] Wang, A.; Chen, H.; Liu, L.; Chen, K.; Lin, Z.; Han, J.; Ding, G. YOLOv10: Real- Time End-to-End Object Detection. arXiv preprint arXiv:2405.14458 2024.
[31] Sait, S. M., El-Maleh, A., Altakrouri, M., & Shawahna, A. (2022). Optimization of FPGA-based CNN accelerators using metaheuristics. arXiv preprint arXiv:2209.11272.
