Bone Marrow Cytomorphology Cell Detection using InceptionResNetV2

TL;DR

This paper introduces a transfer learning model using InceptionResNetV2 for bone marrow cell detection, aiming to improve accuracy and reduce diagnostic delays in hematology.

Contribution

A novel transfer learning approach with InceptionResNetV2 for bone marrow cytology analysis, achieving high accuracy and addressing current diagnostic challenges.

Findings

Achieved 96.19% accuracy in cell detection

Potential to assist in faster, more reliable hematological diagnoses

Applicable to other medical image analyses in hematology

Abstract

Critical clinical decision points in haematology are influenced by the requirement of bone marrow cytology for a haematological diagnosis. Bone marrow cytology, however, is restricted to reference facilities with expertise, and linked to inter-observer variability which requires a long time to process that could result in a delayed or inaccurate diagnosis, leaving an unmet need for cutting-edge supporting technologies. This paper presents a novel transfer learning model for Bone Marrow Cell Detection to provide a solution to all the difficulties faced for the task along with considerable accuracy. The proposed model achieved 96.19\% accuracy which can be used in the future for analysis of other medical images in this domain.