Context-Aware Asymmetric Ensembling for Interpretable Retinopathy of Prematurity Screening via Active Query and Vascular Attention

TL;DR

This paper introduces a novel, interpretable ensemble model for retinopathy of prematurity screening that combines clinical reasoning with active learning and vascular attention, achieving state-of-the-art results on imbalanced datasets.

Contribution

The proposed CAA Ensemble integrates specialized streams for structural and vascular analysis, utilizing active query and attention mechanisms to improve generalization and interpretability in ROP screening.

Findings

Achieved Macro F1-Score of 0.93 for ROP staging

Attained AUC of 0.996 for Plus Disease detection

Demonstrated model transparency with attention heatmaps

Abstract

Retinopathy of Prematurity (ROP) is among the major causes of preventable childhood blindness. Automated screening remains challenging, primarily due to limited data availability and the complex condition involving both structural staging and microvascular abnormalities. Current deep learning models depend heavily on large private datasets and passive multimodal fusion, which commonly fail to generalize on small, imbalanced public cohorts. We thus propose the Context-Aware Asymmetric Ensemble Model (CAA Ensemble) that simulates clinical reasoning through two specialized streams. First, the Multi-Scale Active Query Network (MS-AQNet) serves as a structure specialist, utilizing clinical contexts as dynamic query vectors to spatially control visual feature extraction for localization of the fibrovascular ridge. Secondly, VascuMIL encodes Vascular Topology Maps (VMAP) within a gated Multiple Instance Learning (MIL) network to precisely identify vascular tortuosity. A synergistic meta-learner ensembles these orthogonal signals to resolve diagnostic discordance across multiple objectives. Tested on a highly imbalanced cohort of 188 infants (6,004 images), the framework attained State-of-the-Art performance on two distinct clinical tasks: achieving a Macro F1-Score of 0.93 for Broad ROP staging and an AUC of 0.996 for Plus Disease detection. Crucially, the system features `Glass Box' transparency through counterfactual attention heatmaps and vascular threat maps, proving that clinical metadata dictates the model's visual search. Additionally, this study demonstrates that architectural inductive bias can serve as an effective bridge for the medical AI data gap.