Hardware Accelerator for Nuclei Detection in Histopathology Images

Abstract

In pathology based Computer Aided Diagnosis, accurate detection of cell nuclei is an important step. Accurate and efficient detection of cell nuclei in high resolution histopathological images is a highly compute intensive task. Hence, nuclei detection algorithms take a significant amount of processing time on general purpose processors. To reduce the processing time and assist the doctors in real-time, a special hardware accelerator which can process the complex computational tasks in parallel can be helpful. In this paper, we propose an FPGA based accelerator architecture for nuclei detection in Whole Slide Images using generalized Laplacian of Gaussian filters. The experimental results show that the implemented architecture provides a significant improvement in processing time without losing detection accuracy.