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.

翻译：医学图像分类是计算机辅助诊断（CAD）中的核心任务，在疾病早期检测、治疗规划及患者预后评估中发挥着关键作用。在眼科实践中，荧光素眼底血管造影（FFA）和吲哚菁绿血管造影（ICGA）能够提供传统眼底摄影无法捕捉的血流动力学及病灶结构信息。然而，由于模态单一性、病灶模式细微性以及设备间显著差异性，现有方法在泛化性与高置信度预测方面仍面临局限。为应对这些挑战，我们提出了CLEAR-Mamba，一个基于MedMamba构建的增强框架，在架构与训练策略上均进行了优化。在架构层面，我们引入了HaC，一种基于超网络的自适应条件层，能够根据输入特征分布动态生成参数，从而提升跨域适应能力。从训练角度出发，我们开发了RaP，一种基于证据不确定性学习的可靠性感知预测方案，促使模型关注低置信度样本，提升整体稳定性与可靠性。我们进一步构建了一个涵盖FFA与ICGA模态的大规模眼科血管造影数据集，包含多种视网膜疾病类别，用于模型训练与评估。实验结果表明，CLEAR-Mamba在多项指标上持续优于多个基线模型（包括原始MedMamba），在多疾病分类及可靠性感知预测方面展现出显著优势。本研究为特定模态医学图像分类任务提供了一种兼顾泛化性与可靠性的有效解决方案。