[论文解读] CLEAR-Mamba:Towards Accurate, Adaptive and Trustworthy Multi-Sequence Ophthalmic Angiography Classification

Zhuonan Wang, Wenjie Yan+6 more|arXiv (Cornell University)|Jan 28, 2026

Retinal Imaging and Analysis被引用 0

一句话总结

CLEAR-Mamba通过结合基于超网络的自适应调节和证据性可靠性，对单模态眼科血管造影分类在43疾病的内部数据集上取得更好时序利用、泛化和校准不确定性的表现，优于基线方法。

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.

研究动机与目标

• 通过利用单模态FFA/ICGA序列中的时序信息，推动鲁棒的血管造影分类。
• 通过病例条件化参数生成提升跨域适应性。
• 通过校准的不确定性与风险感知拒绝来增强预测可靠性。
• 构建并利用一个包含43种疾病的大规模眼科血管造影数据集（FFA/ICGA）用于训练与评估。

提出的方法

• 使用MedMamba作为高效的时序骨干，通过Visual State Space Models (VSSMs)捕捉长程动力学。
• 引入HaC，一种基于HyperNetwork的自适应调节层，为实例条件化的特征调制生成病例特定参数。
• 引入RaP，一种基于证据学习的可靠性感知预测头，输出经过校准的概率与不确定性。
• 采用结合负对数似然与Dirichlet先验正则项的证据性目标函数用于不确定性估计的训练。
• 在三个尺度（T/S/B）上评估CLEAR-Mamba，并在内部数据集和公开数据集上与CNN/ViT/Mamba基线进行对比。

Figure 1: Automated pipeline for extracting, anonymizing, and aligning medical image–text data from raw PDF reports.

实验结果

研究问题

• RQ1 是否能通过利用时序动态显著改善单模态眼科血管造影（FFA/ICGA）在多疾病分类中的性能？
• RQ2 超网络自适应（HaC）与证据性可靠性（RaP）是否在域迁移下共同提升了准确性和预测标定？
• RQ3 与医疗专用与通用架构相比，CLEAR-Mamba在不同模型尺度（Tiny/Small/Big）上表现如何？
• RQ4 该方法是否提供可靠的不确定性估计，以支持风险感知的临床决策？
• RQ5 是否存在一个包含43种疾病的大型真实单模态血管造影数据集，可用于训练鲁棒模型？

主要发现

• CLEAR-Mamba在43疾病的内部数据集上，所有指标（OA、F1、AUC）均持续优于包括MedMamba在内的基线方法。
• HaC提升了特征调制能力，而RaP提供了经过校准的不确定性，完整模型达到最佳的OA/AUC。
• 完整的CLEAR在不同尺度（T/S/B）上实现比MedMamba-X更高的灵敏度与OA。
• 消融实验显示单独的HaC可能过于自信；单独的RaP可能过于保守；两者结合可获得更好的校准与判别能力。
• t-SNE嵌入显示CLEAR在类内聚类更紧凑、类间分离更清晰，相较于竞争模型。
• 不确定性指标（预测熵）可有效指示何时需要人工复核，支持风险感知的部署。

Figure 2: Dataset statistics. (a) Class distribution across 43 ocular categories showing a long-tailed pattern. (b) Modality proportion between FFA and ICGA images.