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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhuang, Linghao, Zhang, Ying, Yuan, Gege, Zhao, Xingyue, Jiang, Zhiping
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915294552784896
author Zhuang, Linghao
Zhang, Ying
Yuan, Gege
Zhao, Xingyue
Jiang, Zhiping
author_facet Zhuang, Linghao
Zhang, Ying
Yuan, Gege
Zhao, Xingyue
Jiang, Zhiping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classification
Zhuang, Linghao
Zhang, Ying
Yuan, Gege
Zhao, Xingyue
Jiang, Zhiping
Computer Vision and Pattern Recognition
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.
title ActiveSSF: An Active-Learning-Guided Self-Supervised Framework for Long-Tailed Megakaryocyte Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.08200