# Semantically Calibrated Evidence Composition for CT Vision-Language Learning

arXiv: https://arxiv.org/abs/2608.00239 · HTML: https://mlsanity.com/paper/2608.00239/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training](https://mlsanity.com/paper/2209.07098/) (2022)
- [Joint Learning of Localized Representations from Medical Images and Reports](https://mlsanity.com/paper/2112.02889/) (2021)
- [Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports](https://mlsanity.com/paper/2111.03452/) (2021)
- [Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes](https://mlsanity.com/paper/2002.04752/) (2020)
- [Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding](https://mlsanity.com/paper/2501.14548/) (2025)
- [Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge](https://mlsanity.com/paper/2209.07118/) (2022)
- [Vision Foundation Models for Computed Tomography](https://mlsanity.com/paper/2501.09001/) (2025)
- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering](https://mlsanity.com/paper/2105.00136/) (2021)
- [Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models](https://mlsanity.com/paper/2404.04936/) (2024)
- [Comprehensive language-image pre-training for 3D medical image understanding](https://mlsanity.com/paper/2510.15042/) (2025)
- [Curia: A Multi-Modal Foundation Model for Radiology](https://mlsanity.com/paper/2509.06830/) (2025)
- [T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency](https://mlsanity.com/paper/2312.01529/) (2023)
- [Intensity Confusion Matters: An Intensity-Distance Guided Loss for Bronchus Segmentation](https://mlsanity.com/paper/2406.16150/) (2024)
- [BCNet: Bronchus Classification via Structure Guided Representation Learning](https://mlsanity.com/paper/2205.06947/) (2022)

## Abstract (arXiv)

Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods typically emphasize either global CT-report alignment or fine-grained anatomy-level correspondence. Global alignment preserves broad study context but leaves the contribution of localized evidence implicit, whereas anatomy-level alignment explicitly grounds local findings but does not specify how independently represented evidence should interact, acquire study-level meaning, and contribute to a global CT representation. To address this gap, we propose SCOPE (Semantic Calibration Of comPosed Evidence), a framework for semantically calibrated evidence composition in CT vision-language learning. Under organ-specific report supervision, mask-guided queries with fixed anatomical identities extract context-aware organ evidence from shared, uncropped volumetric features, while an unrestricted global query retains access to whole-volume context. The global query then drives Local-Global Coupling to compose the organ evidence into a unified evidence representation. The composed evidence is subsequently calibrated using the diagnostic summary, providing study-level semantic supervision beyond local organ descriptions, and is finally integrated as a controlled residual into a context-preserving whole-volume representation aligned with the complete report. This progressive pathway connects localized evidence with study-level semantics without reducing the CT representation to a predefined set of organs. On CT-RATE and RadChestCT, SCOPE achieves macro AUCs of 85.0 and 72.2, respectively, outperforming the previous SOTA by 7.2 and 4.2, while also yielding substantial gains in linear probing and cross-modal retrieval. These results demonstrate the effectiveness of semantically calibrated evidence composition.