Low-Power VLSI Implementation of Logistic Regression Model for Real-Time Breast Cancer Classification
Keywords:
Breast cancer classification, Hardware optimization, Logistic regression, Precision scaling, Power efficiency, VLSI architectureAbstract
Breast cancer is a leading cause of death among women worldwide, making early and accurate diagnosis essential. This study presents a low-power analog artificial neural network (AANN) architecture for classifying breast tumors as benign or malignant using the Wisconsin Breast Cancer Dataset. The proposed model is optimized for very large scale integration (VLSI) implementation, targeting portable and energy-constrained diagnostic systems. The AANN achieves high classification performance with an accuracy of 96.90%, sensitivity of 95.42%, specificity of 99.12%, and a Matthew’s correlation coefficient (MCC) of 0.9432. Only 22 misclassifications occurred among 699 cases, with a relatively low false negative rate, ensuring reliable cancer detection. Robustness was evaluated using Monte Carlo simulations over 1000 iterations, accounting for 12% process variations. The model maintained stability with only 28 misclassifications, indicating high tolerance to transistor-level variability. Additional testing under process corners, temperature extremes (–40°C to 125°C), and ±10% voltage fluctuations confirmed the circuit’s resilience under real-world conditions. Performance was consistent even with imaging challenges such as motion artifacts and dense tissue. Compared to existing GPU-based and CMOS implementations, the proposed AANN demonstrated superior energy efficiency. Using a 9-10-2 topology and ±900 mV supply, it consumed only 31.98 µW power and 0.96 mJ energy per classification significantly lower than prior designs. Overall, the proposed AANN offers a reliable, accurate, and ultra-low-power solution for breast cancer classification, making it highly suitable for integration into portable or implantable diagnostic devices, especially in resource-limited settings.
References
M. M. Sunilkumar, C. G. Finni, A. S. Lijimol, and M. R. Rajagopal, “Health-related suffering and palliative care in breast cancer,” Curr. Breast Cancer Rep., vol. 13, pp. 241–246, 2021, doi: https://doi.org/10.1007/s12609-021-00431-1
P. Singh, S. Tripathi, and S. Gupta, “A unified approach for optimal dose delivery and trajectory optimization for the treatment of prostate cancer,” Biomed. Signal Process. Control, vol. 69, p. 102884, 2021, doi: https://doi.org/10.1016/j.bspc.2021.102884
P. Singh, S. Singh, A. Mishra, and S. K. Mishra, “Multimodality treatment planning using the Markov decision process: A comprehensive study of applications and challenges,” Res. Biomed. Eng., pp. 1–16, 2024, doi: https://doi.org/10.1007/s42600-024-00349-4
H. Sayadi et al., “Towards accurate run-time hardware-assisted stealthy malware detection: A lightweight, yet effective time series CNN-based approach,” Cryptography, vol. 5, no. 4, p. 28, 2021, doi: https://doi.org/10.3390/cryptography5040028
P. Singh, S. Tripathi, and R. K. Tamrakar, “Fluence map optimisation for prostate cancer intensity-modulated radiotherapy planning using iterative solution method,” Polish J. Med. Phys. Eng., vol. 26, no. 4, pp. 201–209, 2020, doi: https://doi.org/10.2478/pjmpe-2020-0024
C. Guo, A. Hannun, B. Knott, L. van der Maaten, M. Tygert, and R. Zhu, “Secure multiparty computations in floating-point arithmetic,” Inf. Inference A J. IMA, vol. 11, no. 1, pp. 103–135, 2022, doi: https://doi.org/10.1093/imaiai/iaaa038
Y. Xu, T. M. Khan, Y. Song, and E. Meijering, “Edge deep learning in computer vision and medical diagnostics: A comprehensive survey,” Artif. Intell. Rev., vol. 58, no. 3, pp. 1–78, 2025, doi: https://doi.org/10.1007/s10462-024-11033-5
P. Singh, N. K. Dewangan, R. M. Potdar, S. Singh, A. Mishra, and S. K. Mishra, “An optimal framework for the effective delivery of the radiation to the target by considering the case of head and neck cancer,” Polish J. Med. Phys. Eng., vol. 30, no. 3, pp. 132–144, 2024, doi: https://doi.org/10.2478/pjmpe-2024-0016
P. Singh and S. Tripathi, “Optimal delivery of fluence profile using dynamic multi-leaf collimator leaf trajectory optimization,” ECS Trans., vol. 107, no. 1, p. 19225, 2022, doi: https://doi.org/10.1149/10701.19225ecst
S. Mahmud, “Enhancing the safety and reliability of closed-loop medical control systems.” University of South Florida, 2023, Available: https://www.proquest.com/openview/55dfee80af8a40c2ee13c63efb40df9b/1?pq-origsite=gscholar&cbl=18750&diss=y
J. R. P. K. R. Ande and M. A. Khair, “High-performance VLSI architectures for artificial intelligence and machine learning applications,” Int. J. Reciprocal Symmetry Theor. Phys., vol. 6, no. 1, pp. 20–30, 2019, Available: https://upright.pub/index.php/ijrstp/article/view/121
R. Muralidhar, R. Borovica-Gajic, and R. Buyya, “Energy efficient computing systems: Architectures, abstractions, and modeling to techniques and standards,” ACM Comput. Surv., vol. 54, no. 11s, pp. 1–37, 2022, doi: https://doi.org/10.1145/3511094
A. M. Dalloo, A. Jaleel Humaidi, A. K. Al Mhdawi and H. Al-Raweshidy, “Approximate computing: Concepts, architectures, challenges, applications, and future directions,” in IEEE Access, vol. 12, pp. 146022-146088, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3467375
B. Moons, B. De Brabandere, L. Van Gool and M. Verhelst, “Energy-efficient ConvNets through approximate computing,” 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, 2016, pp. 1-8, doi: https://doi.org/10.1109/WACV.2016.7477614
P. Singh, S. Tripathi, and R. K. Tamrakar, “Dose-volume constraints based inverse treatment planning for optimizing the delivery of radiation therapy,” Gedrag Organ. Rev, vol. 33, no. 3, pp. 1049–1058, Sep. 2020, Available: https://www.researchgate.net/publication/344574136
G. Marques, R. Pitarma, N. M. Garcia, and N. Pombo, “Internet of things architectures, technologies, applications, challenges, and future directions for enhanced living environments and healthcare systems: A review,” Electronics, vol. 8, no. 10, p. 1081, 2019, doi: https://doi.org/10.3390/electronics8101081
M. Junaid, S. Arslan, T. Lee, and H. Kim, “Optimal architecture of floating-point arithmetic for neural network training processors,” Sensors, vol. 22, no. 3, p. 1230, Feb. 2022, doi: https://doi.org/10.3390/s22031230
Q. Wang, P. Li, and Y. Kim, “A parallel digital VLSI architecture for integrated support vector machine training and classification,” in IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 23, no. 8, pp. 1471-1484, Aug. 2015, doi: https://doi.org/10.1109/TVLSI.2014.2343231
M. A. Talib, S. Majzoub, Q. Nasir, and D. Jamal, “A systematic literature review on the hardware implementation of artificial intelligence algorithms,” J. Supercomput., vol. 77, no. 2, pp. 1897–1938, Feb. 2021, doi: https://doi.org/10.1007/s11227-020-03325-8
K. Pande, P. T. Karule and P. M. Palsodkar, “Design of floating-point arithmetic computational units for non-linear applications,” 2024 International Conference on Innovations and Challenges in Emerging Technologies (ICICET), Nagpur, India, 2024, pp. 1-5, doi: https://doi.org/10.1109/ICICET59348.2024.10616278
H. Saadat, “Design and optimization of approximate multipliers and dividers for integer and floating-point arithmetic.” UNSW Sydney, 2021, doi: http://dx.doi.org/https://dorg/10.26190/unsworks/22719
A. Siddique, M. A. Iqbal, M. Aleem, and J. C.-W. Lin, “A high-performance, hardware-based deep learning system for disease diagnosis,” PeerJ Computer Science, vol. 8, p. e1034, Jul. 2022, doi: https://doi.org/10.7717/peerj-cs.1034
M. M. Islam, H. Iqbal, M. R. Haque, and M. K. Hasan, “Prediction of breast cancer using support vector machine and K-Nearest neighbors,” 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, Bangladesh, 2017, pp. 226-229, doi: https://doi.org/10.1109/R10-HTC.2017.8288944
M. Bansal, A. Goyal, and A. Choudhary, “A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning,” Decision Analytics Journal, vol. 3, p. 100071, Jun. 2022, doi: https://doi.org/10.1016/j.dajour.2022.100071
H. Rajaguru and S. C. SR, “Analysis of decision tree and k-nearest neighbor algorithm in the classification of breast cancer,” Asian Pacific Journal Cancer Prevention (APJCP), vol. 20, no. 12, p. 3777-3781, Dec. 2019, doi: https://doi.org/10.31557/APJCP.2019.20.12.3777
M. M. Islam, M. R. Haque, H. Iqbal, M. M. Hasan, M. Hasan, and M. N. Kabir, “Breast cancer prediction: A comparative study using machine learning techniques,” SN Comput. Sci., vol. 1, no. 5, p. 290, 2020, doi: https://doi.org/10.1007/s42979-020-00305-w
A. Sathiya, B. Prabhavathy, A. Balasupramani, A. A, L. Kavitha and R. Saravanakumar, “Low-power approximate computing-based VLSI architecture for biomedical signal processing,” 2025 International Conference on Visual Analytics and Data Visualization (ICVADV), Tirunelveli, India, 2025, pp. 541-548, doi: https://doi.org/10.1109/ICVADV63329.2025.10961086
J. Han and M. Orshansky, “Approximate computing: An emerging paradigm for energy-efficient design,” 2013 18th IEEE European Test Symposium (ETS), Avignon, France, 2013, pp. 1-6, doi: https://doi.org/10.1109/ETS.2013.6569370
S. Venkatachalam and S. -B. Ko, “Design of power and area efficient approximate multipliers,” in IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 25, no. 5, pp. 1782-1786, May 2017, doi: https://doi.org/10.1109/TVLSI.2016.2643639
M. Brand, F. Hannig, O. Keszocze and J. Teich, “Precision- and accuracy-reconfigurable processor architectures—An overview,” in IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 69, no. 6, pp. 2661-2666, June 2022, doi: https://doi.org/10.1109/TCSII.2022.3173753
M. Kanojia, “Malignancy detection in breast histo-images using multi-layer perceptron,” in International Conference on Soft Computing and Pattern Recognition, Springer, vol. 417, pp. 553–562, Feb. 2022, doi: https://doi.org/10.1007/978-3-030-96302-6_52
A. Medina-Santiago, C. A. Hernández-Gracidas, L. A. Morales-Rosales, I. Algredo-Badillo, M. Amador García, and J. A. Orozco Torres, “CMOS implementation of ANNs based on analog optimization of N-dimensional objective functions,” Sensors, vol. 21, no. 21, p. 7071, 2021, doi: https://doi.org/10.3390/s21217071
S. T. Chandrasekaran, R. Hua, I. Banerjee, and A. Sanyal, “A fully-integrated analog machine learning classifier for breast cancer classification,” Electronics, vol. 9, no. 3, p. 515, Mar. 2020, doi: https://doi.org/10.3390/electronics9030515
