Hardware deployment of deep learning model for classification of breast carcinoma from digital mammogram images

• Published in: Medical & biological engineering & computing 2023-11, Vol.61 (11), p.2843-2857
• Main Authors: R, Kayalvizhi, H, Heartlin Maria, S, Malarvizhi, Venkatraman, Revathi, Patil, Shantanu
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Breast cancer; Breast carcinoma; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Cancer; Classification; Cognitive ability; Complexity; Computational neuroscience; Computer Applications; Computers; Datasets; Deep Learning; Diagnosis; Digital imaging; Female; Field programmable gate arrays; Hardware; Human Physiology; Humans; Illnesses; Imaging; Machine Learning; Mammography; Mammography - methods; Medical diagnosis; Model accuracy; Neural networks; Original Article; Power consumption; Power management; Radiology
• ISSN: 0140-0118; 1741-0444
• DOI: 10.1007/s11517-023-02883-2

Cancer is an illness that instils fear in many individuals throughout the world due to its lethal nature. However, in most situations, cancer may be cured if detected early and treated properly. Computer-aided diagnosis is gaining traction because it may be used as an initial screening test for many illnesses, including cancer. Deep learning (DL) is a CAD-based artificial intelligence (AI) powered approach which attempts to mimic the cognitive process of the human brain. Various DL algorithms have been applied for breast cancer diagnosis and have obtained adequate accuracy due to the DL technology’s high feature learning capabilities. However, when it comes to real-time application, deep neural networks (NN) have a high computational complexity in terms of power, speed, and resource usage. With this in mind, this work proposes a miniaturised NN to reduce the number of parameters and computational complexity for hardware deployment. The quantised NN is then accelerated using field-programmable gate arrays (FPGAs) to increase detection speed and minimise power consumption while guaranteeing high accuracy, thus providing a new avenue in assisting radiologists in breast cancer diagnosis using digital mammograms. When evaluated on benchmark datasets such as DDSM, MIAS, and INbreast, the suggested method achieves high classification rates. The proposed model achieved an accuracy of 99.38% on the combined dataset. Graphical Abstract