Beyond CLIP: Knowledge-Enhanced Multimodal Transformers for Cross-Modal Alignment in Diabetic Retinopathy Diagnosis

• URL: http://arxiv.org/abs/2512.19663v1
• Date: Mon, 22 Dec 2025 18:41:45 GMT
• Title: Beyond CLIP: Knowledge-Enhanced Multimodal Transformers for Cross-Modal Alignment in Diabetic Retinopathy Diagnosis
• Authors: Argha Kamal Samanta, Harshika Goyal, Vasudha Joshi, Tushar Mungle, Pabitra Mitra,
• Abstract summary: We propose a knowledge-enhanced joint embedding framework that integrates retinal fundus images, clinical text, and structured patient data.<n>Our framework achieves near-perfect text-to-image retrieval performance with Recall@1 of 99.94% compared to fine-tuned CLIP's 1.29%.
• Score: 7.945705180020063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diabetic retinopathy (DR) is a leading cause of preventable blindness worldwide, demanding accurate automated diagnostic systems. While general-domain vision-language models like Contrastive Language-Image Pre-Training (CLIP) perform well on natural image tasks, they struggle in medical domain applications, particularly in cross-modal retrieval for ophthalmological images. We propose a novel knowledge-enhanced joint embedding framework that integrates retinal fundus images, clinical text, and structured patient data through a multimodal transformer architecture to address the critical gap in medical image-text alignment. Our approach employs separate encoders for each modality: a Vision Transformer (ViT-B/16) for retinal images, Bio-ClinicalBERT for clinical narratives, and a multilayer perceptron for structured demographic and clinical features. These modalities are fused through a joint transformer with modality-specific embeddings, trained using multiple objectives including contrastive losses between modality pairs, reconstruction losses for images and text, and classification losses for DR severity grading according to ICDR and SDRG schemes. Experimental results on the Brazilian Multilabel Ophthalmological Dataset (BRSET) demonstrate significant improvements over baseline models. Our framework achieves near-perfect text-to-image retrieval performance with Recall@1 of 99.94% compared to fine-tuned CLIP's 1.29%, while maintaining state-of-the-art classification accuracy of 97.05% for SDRG and 97.97% for ICDR. Furthermore, zero-shot evaluation on the unseen DeepEyeNet dataset validates strong generalizability with 93.95% Recall@1 versus 0.22% for fine-tuned CLIP. These results demonstrate that our multimodal training approach effectively captures cross-modal relationships in the medical domain, establishing both superior retrieval capabilities and robust diagnostic performance.

Related papers

• A WDLoRA-Based Multimodal Generative Framework for Clinically Guided Corneal Confocal Microscopy Image Synthesis in Diabetic Neuropathy [8.701084151107652]
  Corneal Confocal Microscopy is a sensitive tool for assessing small-fiber damage in Diabetic Peripheral Neuropathy (DPN)<n>Development of robust, automated deep learning-based diagnostic models is limited by scarce labelled data and fine-grained variability in corneal nerve morphology.<n>We propose a Weight-Decomposed Low-Rank Adaptation (WDLoRA)-based multimodal generative framework for clinically guided CCM image synthesis.
  arXiv  Detail & Related papers  (2026-02-14T09:32:44Z)
• Quasi-multimodal-based pathophysiological feature learning for retinal disease diagnosis [4.437523386839875]
  A unified framework that integrates multimodal data synthesis and fusion is proposed for retinal disease classification and grading.<n>The proposed learning system is thoroughly interpreted through visualizations in both image and feature spaces.<n>This work not only enhances the accuracy and efficiency of retinal disease screening but also offers a scalable framework for data augmentation across various medical imaging modalities.
  arXiv  Detail & Related papers  (2026-02-03T15:13:57Z)
• One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training [45.49415063761575]
  EndoRare is a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image.<n>We validated the framework across four rare pathologies.<n>These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.
  arXiv  Detail & Related papers  (2025-12-30T15:07:09Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• DRetNet: A Novel Deep Learning Framework for Diabetic Retinopathy Diagnosis [8.234135343778993]
  Current DR detection systems struggle with poor-quality images, lack interpretability, and insufficient integration of domain-specific knowledge.<n>We introduce a novel framework that integrates three innovative contributions.<n>The framework achieves an accuracy of 92.7%, a precision of 92.5%, a recall of 92.6%, an F1-score of 92.5%, an AUC of 97.8%, a mAP of 0.96, and an MCC of 0.85.
  arXiv  Detail & Related papers  (2025-09-01T02:27:16Z)
• Metrics that matter: Evaluating image quality metrics for medical image generation [48.85783422900129]
  This study comprehensively assesses commonly used no-reference image quality metrics using brain MRI data.<n>We evaluate metric sensitivity to a range of challenges, including noise, distribution shifts, and, critically, morphological alterations designed to mimic clinically relevant inaccuracies.
  arXiv  Detail & Related papers  (2025-05-12T01:57:25Z)
• Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy [0.0]
  This paper proposes a framework for controllably generating high-fidelity and diverse DR fundus images. We achieve comprehensive control over DR severity and visual features within generated images. We manipulate the DR images generated conditionally on grades, further enhancing the dataset diversity.
  arXiv  Detail & Related papers  (2024-09-11T17:08:28Z)
• OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing [4.951748109810726]
  Optimal retinal image quality is mandated for accurate medical diagnoses and automated analyses. We propose an unpaired image-to-image translation scheme for mapping low-quality retinal CFPs to high-quality counterparts. We validated the integrated framework, OTRE, on three publicly available retinal image datasets.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)
• Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation [48.504790189796836]
  We present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe) We propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2% sim 9.4%$.
  arXiv  Detail & Related papers  (2020-05-27T06:58:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.