Bone marrow examination has become increasingly important for the diagnosis and treatment of hematologic and other illnesses. The present methods for analyzing bone marrow biopsy samples involve subjective and inaccurate assessments by visual estimation by pathologists. Thus, there is a need to develop automated tools to assist in the analysis of bone marrow samples. However, there is a lack of publicly available standardized and high-quality datasets that can aid in the research and development of automated tools that can provide consistent and objective measurements. In this paper, we present a comprehensive Bone Marrow Biopsy (BaMBo) dataset consisting 185 semantic-segmented bone marrow biopsy images, specifically designed for the automated calculation of bone marrow cellularity. Our dataset comprises high-resolution, generalized images of bone marrow biopsies, each annotated with precise semantic segmentation of different haematological components. These components are divided into 4 classes: Bony trabeculae, adipocytes, cellular region and Background (BG). The annotations were performed with the help of two experienced hematopathologists that were supported by state-of-the-art Deep Learning (DL) models and image processing techniques. We then used our dataset to train a custom U-Net based DL model that performs multi-class semantic segmentation of the images (Dice Score: 0.831± 0.099) and predicts the cellularity of these images with an error of 5.9% ± 8.8%. This shows the applicability of our data for future research in this domain. Our code is available at https://github.com/AI-in-Medicine-IIT-Ropar/BaMbo-Bone-Marrow-Biopsy
Singh et al. (Wed,) studied this question.