Automated Glaucoma Report Generation via Dual-Attention Semantic Parallel-LSTM and Multimodal Clinical Data Integration

TL;DR

This work tackles automated glaucoma diagnostic report generation from multimodal data by introducing DA-SPL, a Dual-Attention Semantic Parallel-LSTM framework that jointly processes fundus imaging and supplementary clinical signals. DA-SPL combines a dual-attention encoder, a parallelized LSTM decoder, and a label enhancement module to produce concise, clinically faithful reports that align with ophthalmic terminology. Empirical results show DA-SPL outperforms state-of-the-art baselines across BLEU, CIDEr, and ROUGE-L metrics, with ablations confirming the contribution of each component and the benefit of integrating structured data. The approach advances interpretability and clinical relevance in glaucoma reporting and includes a multimodal corpus to support future research and reproducibility.

Abstract

Generative AI for automated glaucoma diagnostic report generation faces two predominant challenges: content redundancy in narrative outputs and inadequate highlighting of pathologically significant features including optic disc cupping, retinal nerve fiber layer defects, and visual field abnormalities. These limitations primarily stem from current multimodal architectures' insufficient capacity to extract discriminative structural-textural patterns from fundus imaging data while maintaining precise semantic alignment with domain-specific terminology in comprehensive clinical reports. To overcome these constraints, we present the Dual-Attention Semantic Parallel-LSTM Network (DA-SPL), an advanced multimodal generation framework that synergistically processes both fundus imaging and supplementary visual inputs. DA-SPL employs an Encoder-Decoder structure augmented with the novel joint dual-attention mechanism in the encoder for cross-modal feature refinement, the parallelized LSTM decoder architecture for enhanced temporal-semantic consistency, and the specialized label enhancement module for accurate disease-relevant term generation. Rigorous evaluation on standard glaucoma datasets demonstrates DA-SPL's consistent superiority over state-of-the-art models across quantitative metrics. DA-SPL exhibits exceptional capability in extracting subtle pathological indicators from multimodal inputs while generating diagnostically precise reports that exhibit strong concordance with clinical expert annotations.

Figures (2)

• Figure 1: The Architecture of DA-SPL
• Figure 2: Medical Report Generation of DA-SPL on Glaucoma & Nomal Eye