SemEnrich enriches radiology reports with positive/neutral findings via self-supervised semantic clustering, yielding average gains of 5-7% on COMET, BERT score, Sentence BLEU, CheXbert-F1 and RadGraph-F1 after fine-tuning, plus further gains when cluster info is added to GRPO rewards.
Available: [https://arxiv.org/abs/2502.03333](https://arxiv.org/abs/2502.03333)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
LoFi adds location-aware captioning loss to jointly optimize fine-grained representations, yielding better retrieval and grounding on MIMIC-CXR and PadChest-GR.
Comparative evaluation of Qwen-VL-Max, Gemini 2.5 Pro, and Llama 4 Maverick on 100 blood report images using Sentence-BERT similarity indicates general-purpose VLMs show promise for preliminary patient-facing analysis.
citing papers explorer
-
SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning
SemEnrich enriches radiology reports with positive/neutral findings via self-supervised semantic clustering, yielding average gains of 5-7% on COMET, BERT score, Sentence BLEU, CheXbert-F1 and RadGraph-F1 after fine-tuning, plus further gains when cluster info is added to GRPO rewards.
-
LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray
LoFi adds location-aware captioning loss to jointly optimize fine-grained representations, yielding better retrieval and grounding on MIMIC-CXR and PadChest-GR.
-
Analysis of Blood Report Images Using General Purpose Vision-Language Models
Comparative evaluation of Qwen-VL-Max, Gemini 2.5 Pro, and Llama 4 Maverick on 100 blood report images using Sentence-BERT similarity indicates general-purpose VLMs show promise for preliminary patient-facing analysis.
- ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows