Addressing the Long-Tailed Data Distribution in Bone Marrow Cell Identification through Class Balance Deep Classification Model

The accurate classification of bone marrow cells has long been a critical component of diagnosing blood diseases. However, traditional methods rely on subjective human interpretation and lack standardized quantitative criteria. To address this challenge, this research proposes a Class Balance Deep Classification Model (CBDCM) designed to classify bone marrow cells using EfficientNet to handle the long-tailed data distribution problem. In order to validate the propose model by applying it to proper dataset and analyzing the experimental outcomes of the propose method. Notably, CBDCM attains impressive precision, sensitivity, and specificity values of 86.14%, 87.53%, and 99.45%, respectively. Simulation results show that CBDCM outperforms, demonstrating superior performance in a detailed comparison with both deep neural networks and traditional machine learning techniques. The findings of this study, with significant implications for addressing class imbalance in datasets, hold promise for standardizing the classification of bone marrow cells, potentially revolutionizing the diagnosis of blood diseases.