# MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images

arXiv: https://arxiv.org/abs/2604.13970 · HTML: https://mlsanity.com/paper/2604.13970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 26 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining](https://mlsanity.com/paper/2204.14095/) (2022)
- [Joint Learning of Localized Representations from Medical Images and Reports](https://mlsanity.com/paper/2112.02889/) (2021)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification](https://mlsanity.com/paper/2307.15254/) (2023)
- [DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2206.08861/) (2022)
- [PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning](https://mlsanity.com/paper/2403.08967/) (2024)
- [Using Multiple Instance Learning to Build Multimodal Representations](https://mlsanity.com/paper/2212.05561/) (2022)

## Abstract (arXiv)

In diagnostic reports, experts encode complex imaging data into clinically actionable information. They describe subtle pathological findings that are meaningful in their anatomical context. Reports follow relatively consistent structures, expressing diagnostic information with few words that are often associated with tiny but consequential image observations. Standard vision language models struggle to identify the associations between these informative text components and small locations in the images. Here, we propose "MApLe", a multi-task, multi-instance vision language alignment approach that overcomes these limitations. It disentangles the concepts of anatomical region and diagnostic finding, and links local image information to sentences in a patch-wise approach. Our method consists of a text embedding trained to capture anatomical and diagnostic concepts in sentences, a patch-wise image encoder conditioned on anatomical structures, and a multi-instance alignment of these representations. We demonstrate that MApLe can successfully align different image regions and multiple diagnostic findings in free-text reports. We show that our model improves the alignment performance compared to state-of-the-art baseline models when evaluated on several downstream tasks. The code is available at https://github.com/cirmuw/MApLe.