Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.04281 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909825790640128 |
|---|---|
| author | Gao, Zhuangzhi Qin, Hongyi Zhao, He Yu, Qinkai Zhou, Feixiang Shantsila, Eduard Alam, Uazman Shantsila, Alena El-Bouri, Wahbi Lip, Gregory Y. H. Zheng, Yalin |
| author_facet | Gao, Zhuangzhi Qin, Hongyi Zhao, He Yu, Qinkai Zhou, Feixiang Shantsila, Eduard Alam, Uazman Shantsila, Alena El-Bouri, Wahbi Lip, Gregory Y. H. Zheng, Yalin |
| contents | Multimodal large language models (MLLMs) hold promise for integrating diverse data modalities, but current medical adaptations such as LLaVA-Med often fail to fully exploit the synergy between color fundus photography (CFP) and optical coherence tomography (OCT), and offer limited interpretability of quantitative biomarkers. We introduce GROK, a grounded multimodal large language model that jointly processes CFP, OCT, and text to deliver clinician-grade diagnoses of ocular and systemic disease. GROK comprises three core modules: Knowledge-Guided Instruction Generation, CLIP-Style OCT-Biomarker Alignment, and Supervised Instruction Fine-Tuning, which together establish a quantitative-to-qualitative diagnostic chain of thought, mirroring real clinical reasoning when producing detailed lesion annotations. To evaluate our approach, we introduce the Grounded Ophthalmic Understanding benchmark, which covers six disease categories and three tasks: macro-level diagnostic classification, report generation quality, and fine-grained clinical assessment of the generated chain of thought. Experiments show that, with only LoRA (Low-Rank Adaptation) fine-tuning of a 7B-parameter Qwen2 backbone, GROK outperforms comparable 7B and 32B baselines on both report quality and fine-grained clinical metrics, and even exceeds OpenAI o3. Code and data are publicly available in the GROK repository. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04281 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GROK: From Quantitative Biomarkers to Qualitative Diagnosis via a Grounded MLLM with Knowledge-Guided Instruction Gao, Zhuangzhi Qin, Hongyi Zhao, He Yu, Qinkai Zhou, Feixiang Shantsila, Eduard Alam, Uazman Shantsila, Alena El-Bouri, Wahbi Lip, Gregory Y. H. Zheng, Yalin Artificial Intelligence Multimodal large language models (MLLMs) hold promise for integrating diverse data modalities, but current medical adaptations such as LLaVA-Med often fail to fully exploit the synergy between color fundus photography (CFP) and optical coherence tomography (OCT), and offer limited interpretability of quantitative biomarkers. We introduce GROK, a grounded multimodal large language model that jointly processes CFP, OCT, and text to deliver clinician-grade diagnoses of ocular and systemic disease. GROK comprises three core modules: Knowledge-Guided Instruction Generation, CLIP-Style OCT-Biomarker Alignment, and Supervised Instruction Fine-Tuning, which together establish a quantitative-to-qualitative diagnostic chain of thought, mirroring real clinical reasoning when producing detailed lesion annotations. To evaluate our approach, we introduce the Grounded Ophthalmic Understanding benchmark, which covers six disease categories and three tasks: macro-level diagnostic classification, report generation quality, and fine-grained clinical assessment of the generated chain of thought. Experiments show that, with only LoRA (Low-Rank Adaptation) fine-tuning of a 7B-parameter Qwen2 backbone, GROK outperforms comparable 7B and 32B baselines on both report quality and fine-grained clinical metrics, and even exceeds OpenAI o3. Code and data are publicly available in the GROK repository. |
| title | GROK: From Quantitative Biomarkers to Qualitative Diagnosis via a Grounded MLLM with Knowledge-Guided Instruction |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04281 |