HematoNet: Expert Level Classification of Bone Marrow Cytology Morphology in Hematological Malignancy with Deep Learning

Abstract

There have been few efforts made to automate the cytomorphological categorization of bone marrow cells. For bone marrow cell categorization, deep-learning algorithms have been limited to a small number of samples or disease classifications. In this paper, we proposed a pipeline to classify the bone marrow cells despite these limitations. Data augmentation was used throughout the data to resolve any class imbalances. Then, random transformations such as rotating between 0° to 90°, zooming in/out, flipping horizontally and/or vertically, and translating were performed. The model used in the pipeline was a CoAtNet and that was compared with two baseline models, EfficientNetV2 and ResNext50. We then analyzed the CoAtNet model using SmoothGrad and Grad-CAM, two recently developed algorithms that have been shown to meet the fundamental requirements for explainability methods. After evaluating all three models’ performance for each of the distinct morphological classes, the proposed CoAtNet model was able to outperform the EfficientNetV2 and ResNext50 models due to its attention network property that increased the learning curve for the algorithm which was represented using a precision-recall curve.

Determination of bone marrow cell morphology in rat

“…In this morphological classification, bone marrow cells had a similar structure. The classes were arranged into blood lineages (27). According to the standard method, the main physiological classes of myelopoiesis and lymphopoiesis, as well as common pathological classes, were included in the classification (Fig 3).…”

Radiobioinformatics: A novel bridge between basic research and clinical practice for clinical decision support in diffuse liver diseases

“…Tripathi et al. [162] used CoAtNet for the cytomorphological classification of bone marrow cells and found that the CoAtNet model outperformed the EfficientNetV2 and ResNext50 models. Diffuse liver diseases are difficult to distinguish in the early stages by medical imaging and naked eye classification [163].…”

“…Kvak [161] used CoAtNet to classify malignant and benign melanoma and obtained an accuracy of 0.901, which is better than the accuracies obtained with other state-of-the-art algorithms. Tripathi et al [162] used CoAtNet for the cytomorphological classification of bone marrow cells and found that the CoAtNet model outperformed the EfficientNetV2 and ResNext50 models. Diffuse liver diseases are difficult to distinguish in the early stages by medical imaging and naked eye classification [163].…”