Work

Low-Power Quantized Convolutional Neural Network for Early Breast Cancer Detection in Remote Communities

Year: 2025

Type: conference-paper

Abstract: Breast cancer remains a leading cause of mortality in low-resource communities due to late diagnosis and limited access to specialized healthcare facilities. Leveraging recent advancements in deep learning, this study presents a low-power, cost-effective solution for early breast cancer detection tailored to resource-constrained environments. We developed a quantized convolutional neural network (CNN) using Brevitas and deployed it on a PYNQ-Z1 development board via the FINN framework. The CNN efficiently classifies ultrasonic topography images into three categories: normal, benign, or malignant. Achieving up to 91.2% accuracy on the BUSI dataset, our results highlight the effectiveness of 4-bit quantization, offering a viable trade-off between computational efficiency and accuracy. This makes it viable for real-time medical image classification in underserved communities, potentially facilitating early diagnosis and timely referrals, and ultimately contributing to improved healthcare outcomes.

DOI: 10.1109/ssd64182.2025.10989970

Authors: Kawthar Dellel, Emanuel Trabes, Hana Ben Fredj, Carlos Valderrama, Hassene Faiedh

Institutions: University of Mons, National University of San Luis, University of Monastir

Language: English

Topic: AI in cancer detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDGs: Good health and well-being, Reduced inequalities, Industry, innovation and infrastructure

Open Access status: green

OpenAlex ID: W4410538734

FWCI:

Cites: 22

Cited by:

Related to: 10