CLEAR-Mamba:Towards Accurate, Adaptive and Trustworthy Multi-Sequence Ophthalmic Angiography Classification

TL;DR

CLEAR-Mamba is a novel framework that enhances ophthalmic angiography classification by improving cross-domain adaptability and prediction reliability, addressing limitations of existing methods in generalization and high-confidence predictions.

Contribution

The paper introduces HaC, a hypernetwork-based adaptive layer, and RaP, a reliability-aware prediction scheme, to improve accuracy and trustworthiness in multi-sequence ophthalmic image classification.

Findings

Outperforms baseline models in multi-disease classification

Enhances model reliability and stability

Demonstrates superior generalization across modalities

Abstract

Medical image classification is a core task in computer-aided diagnosis (CAD), playing a pivotal role in early disease detection, treatment planning, and patient prognosis assessment. In ophthalmic practice, fluorescein fundus angiography (FFA) and indocyanine green angiography (ICGA) provide hemodynamic and lesion-structural information that conventional fundus photography cannot capture. However, due to the single-modality nature, subtle lesion patterns, and significant inter-device variability, existing methods still face limitations in generalization and high-confidence prediction. To address these challenges, we propose CLEAR-Mamba, an enhanced framework built upon MedMamba with optimizations in both architecture and training strategy. Architecturally, we introduce HaC, a hypernetwork-based adaptive conditioning layer that dynamically generates parameters according to input feature distributions, thereby improving cross-domain adaptability. From a training perspective, we develop RaP, a reliability-aware prediction scheme built upon evidential uncertainty learning, which encourages the model to emphasize low-confidence samples and improves overall stability and reliability. We further construct a large-scale ophthalmic angiography dataset covering both FFA and ICGA modalities, comprising multiple retinal disease categories for model training and evaluation. Experimental results demonstrate that CLEAR-Mamba consistently outperforms multiple baseline models, including the original MedMamba, across various metrics-showing particular advantages in multi-disease classification and reliability-aware prediction. This study provides an effective solution that balances generalizability and reliability for modality-specific medical image classification tasks. Our project can be accessed at https://github.com/ZJU4HealthCare/CLEAR-Mamba.