ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classification

TL;DR

ActiveSSF is a novel framework combining active learning and self-supervised pretraining to improve classification of megakaryocytes, especially rare subtypes, in stained slides with complex backgrounds and morphological variability.

Contribution

This work introduces ActiveSSF, integrating advanced region extraction, adaptive sample selection, and prototype clustering to address challenges in megakaryocyte classification.

Findings

Achieves state-of-the-art accuracy on clinical datasets.

Significantly improves recognition of rare megakaryocyte subtypes.

Demonstrates practical potential for clinical diagnosis.

Abstract

Precise classification of megakaryocytes is crucial for diagnosing myelodysplastic syndromes. Although self-supervised learning has shown promise in medical image analysis, its application to classifying megakaryocytes in stained slides faces three main challenges: (1) pervasive background noise that obscures cellular details, (2) a long-tailed distribution that limits data for rare subtypes, and (3) complex morphological variations leading to high intra-class variability. To address these issues, we propose the ActiveSSF framework, which integrates active learning with self-supervised pretraining. Specifically, our approach employs Gaussian filtering combined with K-means clustering and HSV analysis (augmented by clinical prior knowledge) for accurate region-of-interest extraction; an adaptive sample selection mechanism that dynamically adjusts similarity thresholds to mitigate class imbalance; and prototype clustering on labeled samples to overcome morphological complexity. Experimental results on clinical megakaryocyte datasets demonstrate that ActiveSSF not only achieves state-of-the-art performance but also significantly improves recognition accuracy for rare subtypes. Moreover, the integration of these advanced techniques further underscores the practical potential of ActiveSSF in clinical settings.