Self-Evolving Neural Imaging Models For Automated Disease Localization In Multimodal Scans

Dr. C. Moorthy; T. Kannan; S. Abiramasundari; Dr. J. Dhanasekar

doi:10.29284/ijasis.12.1.2026.15-27

Authors

Dr. C. Moorthy Assistant Professor, Department of Electronics and Communication Engineering, Dr. Mahalingam College of Engineering and Technology, Pollachi – 642003, Tamil Nadu, India.
T. Kannan Assistant Professor (Senior Scale), Dr. N.G.P Institute of Technology, Coimbatore, Tamil Nadu, India.
S. Abiramasundari Assistant Professor, Department of Electronics and Communication Engineering, Dr. Mahalingam College of Engineering and Technology, Pollachi, Tamil Nadu, India.
Dr. J. Dhanasekar Assistant Professor, Department of Electronics and Communication Engineering, Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India.

DOI:

https://doi.org/10.29284/ijasis.12.1.2026.15-27

Keywords:

Self-Evolving Neural Networks; Automated Disease Localization; Multimodal Medical Imaging; Rare Cardiovascular Diseases; MRI/CT/PET Fusion; Evolutionary Deep Learning; Adaptive Feature Extraction; Precision Cardiology; Clinical Decision Support; Cardiovascular Tissue Analysis.

Abstract

Early and precise localization of abnormal regions in multimodal medical imaging—such as MRI, CT, PET, and ultrasound—is essential for diagnosing complex and rare cardiovascular diseases. Traditional deep learning models often require large annotated datasets and frequent manual tuning, which limits scalability in clinical environments where annotated samples for rare cardiac abnormalities are scarce. To address this challenge, this study proposes a Self-Evolving Neural Imaging Model capable of autonomously adapting its architecture, parameters, and feature-extraction strategies for automated disease localization across heterogeneous imaging modalities. The proposed model integrates evolutionary neural optimization, multimodal attention fusion, and adaptive self-reconfiguration to enhance sensitivity to subtle tissue variations associated with rare cardiomyopathies, congenital defects, microvascular alterations, and inflammatory cardiovascular disorders. A hierarchical cross-modal encoder extracts spectral, structural, and intensity-based biomarkers, while an evolutionary controller iteratively improves model accuracy by exploring optimized architectural pathways without human intervention. Experimental evaluation on multimodal cardiovascular imaging datasets demonstrates that the proposed self-evolving system achieves 15–22% improvement in localization accuracy, significant reduction in false positives, and enhanced robustness under noise, motion artifacts, and modality variability. The model requires minimal annotation and displays strong generalization to unseen disease patterns, making it suitable for clinical deployment in early detection and precision diagnostics for rare cardiovascular diseases. This framework contributes to the advancement of intelligent, autonomous imaging systems aligned with JRCD’s mission to improve outcomes through early cardiovascular disease understanding and detection.

References

1. Jayaraman, S., Anithamary, M., Murugesh, K. and Dinesh, K., 2025. Challenges and Future Perspectives of Low-Power VLSI Circuits for Biomedical Applications: A Review. Exploring the Intricacies of Digital and Analog VLSI, pp.293-322.

2. Liu, J., Fan, J., Zhong, Z., Qiu, H., Xiao, J., Zhou, Y., Zhu, Z., Dai, G., Wang, N., Liu, Q. and Xie, Y., 2023. An ultra-low power reconfigurable biomedical AI processor with adaptive learning for versatile wearable intelligent health monitoring. IEEE transactions on biomedical circuits and systems, 17(5), pp.952-967.

3. Aijaz, M., Anusharani, V., Krishnan, M.M. and Muthamizhan, T., 2024, November. Innovative Circuit Designs for Achieving Ultra-Low Power Consumption in Wearable Electronics. In 2024 International Conference on Cybernation and Computation (CYBERCOM) (pp. 649-653). IEEE.

4. Ghasemzadeh, H. and Jafari, R., 2013. Ultra low-power signal processing in wearable monitoring systems: A tiered screening architecture with optimal bit resolution. ACM Transactions on Embedded Computing Systems (TECS), 13(1), pp.1-23.

5. Maheepala, M., Joordens, M.A. and Kouzani, A.Z., 2020. Low power processors and image sensors for vision-based IoT devices: A review. IEEE Sensors Journal, 21(2), pp.1172-1186.

6. Moustakas, V., Alimisis, V., Foufas, Z., Cheliotis, K., Mylona, A. and Sotiriadis, P.P., 2025, June. A Low-Power Analog Integrated Decision Tree for Diabetic Retinopathy Detection. In 2025 14th International Conference on Modern Circuits and Systems Technologies (MOCAST) (pp. 1-6). IEEE.

7. Rusci, M., Rossi, D., Lecca, M., Gottardi, M., Farella, E. and Benini, L., 2016. An event-driven ultra-low-power smart visual sensor. IEEE Sensors Journal, 16(13), pp.5344-5353.

8. Mohamed, A.R. and Al-Absi, M.A., 2025. Co-Design of Silicon-Based CMOS Rectifiers and Impedance Matching Networks for Low-Power IoT Systems: Trends and Insights. IEEE Access.

9. Kalpana K, Paulchamy B ,Stephen Jeswinde Nuagah, Piyush Kumar Shukla.,2023, “Design of a high‐performance advanced phase locked loop with high stability external loop filter”, IET Circuits Devices Systems,17(1), 1– 12.

10. Chandrakasan, A.P., Verma, N. and Daly, D.C., 2008. Ultralow-power electronics for biomedical applications. Annu. Rev. Biomed. Eng., 10(1), pp.247-274.

11. D. Paulraj, L. R, T. Jayasudha, M. Ishwarya Niranjana, T. Daniya and F. Daniel Shadrach, "Blockchain-based Wireless Sensor Network Security Through Authentication and Cluster Head Selection," 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India, 2023, pp. 1-5, doi: 10.1109/ICICACS57338.2023.10099593.

12. K. Karthikeyan, V. Parthipan, M. I. Niranjana, D. Prithvi, N. R. Franklin and N. Kaviarasu, "Enhancing Vehicular Communication Efficiency Through DSRC and LTE-V2x Integration," 2024 International Conference on Science Technology Engineering and Management (ICSTEM), Coimbatore, India, 2024, pp. 1-6, doi: 10.1109/ICSTEM61137.2024.10560623.

13. Kandpal, J., Sharma, D. and Goel, E., 2025. Biomedical Applications in VLSI Field. Handbook of Advanced Semiconductor Field Effect Transistorss, pp.365-382.

14. Muir, D.R. and Sheik, S., 2025. The road to commercial success for neuromorphic technologies. Nature communications, 16(1), p.3586.

15. Wei, Y., Zhou, J., Wang, Y., Liu, Y., Liu, Q., Luo, J., Wang, C., Ren, F. and Huang, L., 2020. A review of algorithm & hardware design for AI-based biomedical applications. IEEE transactions on biomedical circuits and systems, 14(2), pp.145-163.

16. V. V. Teresa and B. Anand, “Low Power Optimization of Finite Impulse Response Filter Feature Extraction by Using Thyroid Cancer Region Identification in Medical Images,” Journal of Medical Imaging and Health Informatics, vol. 10, no. 1, pp. 99–107, Jan. 2020, doi: 10.1166/jmihi.2020.2856.

17. B. Anand and V. V. Teresa, “Improved Modified Area Efficient Carry Select Adder (MAE-CSLA) Without Multiplexer,” Journal of Computational and Theoretical Nanoscience, vol. 14, no. 1, pp. 269–276, Jan. 2017, doi: 10.1166/jctn.2017.6316.

18. Yoo, J. and Shoaran, M., 2021. Neural interface systems with on-device computing: machine learning and neuromorphic architectures. Current opinion in biotechnology, 72, pp.95-101.

19. Laskar, M.J., Banerjee, A., Prasad, V. and Das, D., 2026. CMOS Circuits in the Design and Development of Implantable Medical Devices. Biomedical Materials & Devices, 4(1), pp.132-142.

20. Kodge, S., Chaudhary, H. and Sharad, M., 2017, July. Low power image acquisition scheme using on-pixel event driven halftoning. In 2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) (pp. 260-265). IEEE.