Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification

TL;DR

This paper introduces a novel domain-invariant representation learning framework using the Segment Anything Model for blood cell classification, effectively addressing domain shifts and improving cross-domain performance.

Contribution

The paper proposes a new framework combining LoRA-finetuned SAM and a cross-domain autoencoder to extract domain-invariant features for blood cell classification.

Findings

Achieves state-of-the-art cross-domain classification performance.

Outperforms existing methods significantly on multiple datasets.

Demonstrates robustness to domain shifts in blood cell imaging.

Abstract

Accurate classification of blood cells is of vital significance in the diagnosis of hematological disorders. However, in real-world scenarios, domain shifts caused by the variability in laboratory procedures and settings, result in a rapid deterioration of the model's generalization performance. To address this issue, we propose a novel framework of domain-invariant representation learning (DoRL) via segment anything model (SAM) for blood cell classification. The DoRL comprises two main components: a LoRA-based SAM (LoRA-SAM) and a cross-domain autoencoder (CAE). The advantage of DoRL is that it can extract domain-invariant representations from various blood cell datasets in an unsupervised manner. Specifically, we first leverage the large-scale foundation model of SAM, fine-tuned with LoRA, to learn general image embeddings and segment blood cells. Additionally, we introduce CAE to learn domain-invariant representations across different-domain datasets while mitigating images' artifacts. To validate the effectiveness of domain-invariant representations, we employ five widely used machine learning classifiers to construct blood cell classification models. Experimental results on two public blood cell datasets and a private real dataset demonstrate that our proposed DoRL achieves a new state-of-the-art cross-domain performance, surpassing existing methods by a significant margin. The source code can be available at the URL (https://github.com/AnoK3111/DoRL).