Segmentation of human spermatozoa using improved Havrda-Chavrat entropy-based thresholding method

Abstract

The assisted method of fertilization has required an identification of sperm cells with normal morphological structure. The abnormal sperm cells cannot provide successful result in artificial fertilization. Nowadays the assessment of morphology of sperm cells is subjective and error prone hence creating automatic evaluation method for morphology assessment, it will improve the success ratio in infertility treatment. The first step in our proposed system is pre-processing where noise removal process is applied on microscopic medical images. In second step, adaptive alpha valued Havrda-Chavrat entropy-based threshold technique is proposed where the maximum probability distribution of foreground pixels or background pixels is assigned to alpha value. Further, existing state-of-art threshold-based segmentation methods are implemented and obtained results on the input images. These segmentation results are compared with the proposed method in terms of supervised and unsupervised evaluation metrics, in which our proposed thresholding method has given optimum threshold value for the segmentation of spermatozoa cells. The outcome of the segmented images and their metric values are indicating better segmentation by our proposed method. Furthermore, this proposed method can be implemented in the mobile applications for diagnosis with artificial intelligence techniques.