# Prompt-Conditioned FiLM and Multi-Scale Fusion on MedSigLIP for Low-Dose CT Quality Assessment

arXiv: https://arxiv.org/abs/2511.12256 · HTML: https://mlsanity.com/paper/2511.12256/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models](https://mlsanity.com/paper/2312.15663/) (2023)
- [A study of why we need to reassess full reference image quality assessment with medical images](https://mlsanity.com/paper/2405.19097/) (2024)
- [Low-dose CT Denoising with Language-engaged Dual-space Alignment](https://mlsanity.com/paper/2403.06128/) (2024)
- [LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models](https://mlsanity.com/paper/2507.06140/) (2025)
- [A-IDE : Agent-Integrated Denoising Experts](https://mlsanity.com/paper/2503.16780/) (2025)

## Abstract (arXiv)

We propose a prompt-conditioned framework built on MedSigLIP that injects textual priors via Feature-wise Linear Modulation (FiLM) and multi-scale pooling. Text prompts condition patch-token features on clinical intent, enabling data-efficient learning and rapid adaptation. The architecture combines global, local, and texture-aware pooling through separate regression heads fused by a lightweight MLP, trained with pairwise ranking loss. Evaluated on the LDCTIQA2023 (a public LDCT quality assessment challenge) with 1,000 training images, we achieve PLCC = 0.9575, SROCC = 0.9561, and KROCC = 0.8301, surpassing the top-ranked published challenge submissions and demonstrating the effectiveness of our prompt-guided approach.