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

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