A WDLoRA-Based Multimodal Generative Framework for Clinically Guided Corneal Confocal Microscopy Image Synthesis in Diabetic Neuropathy

2026-02-14

AI Summary

This study addresses the challenge of limited annotated data and high morphological variability in corneal confocal microscopy (CCM) images for diabetic peripheral neuropathy (DPN), which hinders the development of deep learning–based diagnostic models. To overcome this, the authors propose a multimodal conditional diffusion generative framework based on Weight-Decomposed Low-Rank Adaptation (WDLoRA), which integrates clinical semantic prompts and nerve segmentation masks to guide the synthesis of anatomically plausible, multi-stage DPN CCM images. The method innovatively decouples the magnitude and direction of weight updates to separately model nerve topology and stromal contrast, substantially enhancing image realism and controllability. The generated images achieve state-of-the-art performance with an FID of 5.18 and SSIM of 0.630, and significantly improve downstream tasks—boosting diagnostic accuracy by 2.1% and segmentation performance by 2.2%.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Corneal Confocal Microscopy (CCM) is a sensitive tool for assessing small-fiber damage in Diabetic Peripheral Neuropathy (DPN), yet the development of robust, automated deep learning-based diagnostic models is limited by scarce labelled data and fine-grained variability in corneal nerve morphology. Although Artificial Intelligence (AI)-driven foundation generative models excel at natural image synthesis, they often struggle in medical imaging due to limited domain-specific training, compromising the anatomical fidelity required for clinical analysis. To overcome these limitations, we propose a Weight-Decomposed Low-Rank Adaptation (WDLoRA)-based multimodal generative framework for clinically guided CCM image synthesis. WDLoRA is a parameter-efficient fine-tuning (PEFT) mechanism that decouples magnitude and directional weight updates, enabling foundation generative models to independently learn the orientation (nerve topology) and intensity (stromal contrast) required for medical realism. By jointly conditioning on nerve segmentation masks and disease-specific clinical prompts, the model synthesises anatomically coherent images across the DPN spectrum (Control, T1NoDPN, T1DPN). A comprehensive three-pillar evaluation demonstrates that the proposed framework achieves state-of-the-art visual fidelity (Fr\'echet Inception Distance (FID): 5.18) and structural integrity (Structural Similarity Index Measure (SSIM): 0.630), significantly outperforming GAN and standard diffusion baselines. Crucially, the synthetic images preserve gold-standard clinical biomarkers and are statistically equivalent to real patient data. When used to train automated diagnostic models, the synthetic dataset improves downstream diagnostic accuracy by 2.1% and segmentation performance by 2.2%, validating the framework's potential to alleviate data bottlenecks in medical AI.

Problem

• Diabetic Peripheral Neuropathy
• Corneal Confocal Microscopy
• Medical Image Synthesis
• Data Scarcity
• Anatomical Fidelity

Innovation

• WDLoRA
• multimodal generative framework
• corneal confocal microscopy
• parameter-efficient fine-tuning
• clinically guided synthesis