ScSAM: Debiasing Morphology and Distributional Variability in Subcellular Semantic Segmentation

TL;DR

ScSAM is a novel approach that combines pre-trained SAM with MAE-guided priors to improve subcellular segmentation by addressing morphological variability and data imbalance.

Contribution

It introduces a feature fusion module and a class prompt encoder to enhance feature robustness and specificity in subcellular segmentation tasks.

Findings

Outperforms existing methods on various datasets.

Effectively handles morphological and distributional variability.

Reduces bias caused by data imbalance.

Abstract

The significant morphological and distributional variability among subcellular components poses a long-standing challenge for learning-based organelle segmentation models, significantly increasing the risk of biased feature learning. Existing methods often rely on single mapping relationships, overlooking feature diversity and thereby inducing biased training. Although the Segment Anything Model (SAM) provides rich feature representations, its application to subcellular scenarios is hindered by two key challenges: (1) The variability in subcellular morphology and distribution creates gaps in the label space, leading the model to learn spurious or biased features. (2) SAM focuses on global contextual understanding and often ignores fine-grained spatial details, making it challenging to capture subtle structural alterations and cope with skewed data distributions. To address these challenges, we introduce ScSAM, a method that enhances feature robustness by fusing pre-trained SAM with Masked Autoencoder (MAE)-guided cellular prior knowledge to alleviate training bias from data imbalance. Specifically, we design a feature alignment and fusion module to align pre-trained embeddings to the same feature space and efficiently combine different representations. Moreover, we present a cosine similarity matrix-based class prompt encoder to activate class-specific features to recognize subcellular categories. Extensive experiments on diverse subcellular image datasets demonstrate that ScSAM outperforms state-of-the-art methods.