A Fully Unsupervised Instance Segmentation Technique for White Blood Cell Images

TL;DR

This paper introduces a novel fully unsupervised instance segmentation method specifically designed for accurately segmenting white blood cells, including nucleus and cytoplasm, from microscopic bone marrow images, aiding medical diagnosis.

Contribution

It presents a new unsupervised segmentation technique tailored for WBCs in microscopic images, eliminating the need for labeled training data.

Findings

Effective segmentation of WBCs including nucleus and cytoplasm

Potential to assist in medical diagnosis without labeled data

Improves accuracy over traditional methods

Abstract

White blood cells, also known as leukocytes are group of heterogeneously nucleated cells which act as salient immune system cells. These are originated in the bone marrow and are found in blood, plasma, and lymph tissues. Leukocytes kill the bacteria, virus and other kind of pathogens which invade human body through phagocytosis that in turn results immunity. Detection of a white blood cell count can reveal camouflaged infections and warn doctors about chronic medical conditions such as autoimmune diseases, immune deficiencies, and blood disorders. Segmentation plays an important role in identification of white blood cells (WBC) from microscopic image analysis. The goal of segmentation in a microscopic image is to divide the image into different distinct regions. In our paper, we tried to propose a novel instance segmentation method for segmenting the WBCs containing both the nucleus and the cytoplasm, from bone marrow images.