Computer Vision Based Kidney’s (HK-2) Damaged Cells Classification with Reconfigurable Hardware Accelerator (FPGA)

Ghani, A; Hodeify, R.; See, Chan Hwang; Keates, S.; Lee, D.J.; Bouridane, A.

Abstract

In medical and health sciences, detection of cell injury plays an important role in diagnosis, personal treatment and disease prevention. Despite recent advancements in tools and methods for image classification, it is challenging to classify cell images with higher precision and accuracy. Cell classification based on computer vision offers significant benefits in biomedicine and healthcare. There have been studies reported where cell classification techniques have been complemented by Artificial Intelligence-based classifiers such as Convolutional Neural Networks. These classifiers suffer from the drawback of the scale of computational resources required for training and hence do not offer real-time classification capabilities for an embedded system plat-form. Field Programmable Gate Arrays (FPGAs) offer the flexibility of hardware reconfiguration and have emerged as a viable platform for algorithm acceleration. Given that the logic resources and on-chip memory available on a single device are still limited, hardware/software co-design is proposed where image pre-processing and network training was performed in software and trained architectures were mapped onto an FPGA device (Nexys4DDR) for real-time cell classification. This paper demonstrates that the embedded hardware-based cell classifier performs with almost 100% accuracy in detecting different types of damaged kidney cells.

Citation

Ghani, A., Hodeify, . R., See, C. H., Keates, S., Lee, D., & Bouridane, A. (2022). Computer Vision Based Kidney’s (HK-2) Damaged Cells Classification with Reconfigurable Hardware Accelerator (FPGA). Electronics, 11(24), Article 4234. https://doi.org/10.3390/electronics11244234

• Journal Article Type: Article
• Acceptance Date: Dec 15, 2022
• Online Publication Date: Dec 19, 2022
• Publication Date: 2022
• Deposit Date: Dec 15, 2022
• Publicly Available Date: Dec 19, 2022
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 11
• Issue: 24
• Article Number: 4234
• DOI: https://doi.org/10.3390/electronics11244234
• Keywords: artificial neural networks; cell classification; FPGAs; hardware accelerators; human kidney-damaged cells
• Public URL: http://researchrepository.napier.ac.uk/Output/2983821