Beyond Labels: Visual Representations for Bone Marrow Cell Morphology Recognition
This addresses the challenge of analyzing bone marrow cell morphology for hematopathology diagnosis, which is complex and time-consuming, by improving recognition tasks with a novel approach.
The paper tackles the problem of bone marrow cell recognition by moving beyond reliance on labeled data and using self-supervision, resulting in significant performance improvements over state-of-the-art methods.
Analyzing and inspecting bone marrow cell cytomorphology is a critical but highly complex and time-consuming component of hematopathology diagnosis. Recent advancements in artificial intelligence have paved the way for the application of deep learning algorithms to complex medical tasks. Nevertheless, there are many challenges in applying effective learning algorithms to medical image analysis, such as the lack of sufficient and reliably annotated training datasets and the highly class-imbalanced nature of most medical data. Here, we improve on the state-of-the-art methodologies of bone marrow cell recognition by deviating from sole reliance on labeled data and leveraging self-supervision in training our learning models. We investigate our approach's effectiveness in identifying bone marrow cell types. Our experiments demonstrate significant performance improvements in conducting different bone marrow cell recognition tasks compared to the current state-of-the-art methodologies.