# Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming

arXiv: https://arxiv.org/abs/2605.21652 · HTML: https://mlsanity.com/paper/2605.21652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge](https://mlsanity.com/paper/2304.06975/) (2023)
- [GRIT: Teaching MLLMs to Think with Images](https://mlsanity.com/paper/2505.15879/) (2025)
- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models](https://mlsanity.com/paper/2503.02623/) (2025)
- [Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectives](https://mlsanity.com/paper/2307.05545/) (2023)
- [SteerConf: Steering LLMs for Confidence Elicitation](https://mlsanity.com/paper/2503.02863/) (2025)
- [Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning](https://mlsanity.com/paper/2505.19213/) (2025)
- [U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding](https://mlsanity.com/paper/2505.17779/) (2025)
- [Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data](https://mlsanity.com/paper/2507.06828/) (2025)
- [A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories](https://mlsanity.com/paper/2509.17046/) (2025)
- [EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence](https://mlsanity.com/paper/2509.14977/) (2025)

## Abstract (arXiv)

Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal. In clinical practice, sonographers explicitly focus on lesion regions to formulate reports, though diagnostic interpretations sometimes vary due to inherent subjectivity. However, existing VLMs are not explicitly structured to interactively zoom into lesions prior to diagnosis; moreover, they typically treat annotations as unbiased ground truths, failing to account for their inherent subjectivity and ambiguity. In this paper, we propose a framework specifically designed to consider the sonographer's cognitive workflow. We first introduce a structured Zoom-then-Diagnose paradigm, which replicates the interactive search process to enable lesion-focused reasoning. Furthermore, within the Group Relative Policy Optimization (GRPO) framework, we introduce an uncertainty-aware reward derived from stochastic group-wise rollouts to estimate prediction consistency as a proxy for model confidence. Together, these two components encourage the model to reinforce accurate predictions on clear cases while remaining cautious under ambiguity. Experiments across liver, breast, and thyroid datasets show that our framework improves lesion localization by 39.3%, demonstrating that our model has learned the ability to actively look closer and diagnose.