# Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining

arXiv: https://arxiv.org/abs/2304.14204 · HTML: https://mlsanity.com/paper/2304.14204/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 60 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 30 of 48)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Bilinear Attention Networks](https://mlsanity.com/paper/1805.07932/) (2018)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)
- [On the Automatic Generation of Medical Imaging Reports](https://mlsanity.com/paper/1711.08195/) (2017)
- [ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph](https://mlsanity.com/paper/2006.16934/) (2020)
- [When Radiology Report Generation Meets Knowledge Graph](https://mlsanity.com/paper/2002.08277/) (2020)

## Built on by (most cited first, 11 of 11)

- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation](https://mlsanity.com/paper/2312.08078/) (2023)
- [Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation](https://mlsanity.com/paper/2405.09586/) (2024)
- [MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations](https://mlsanity.com/paper/2503.01019/) (2025)
- [A Survey of Pre-trained Language Models for Processing Scientific Text](https://mlsanity.com/paper/2401.17824/) (2024)
- [A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture](https://mlsanity.com/paper/2305.05352/) (2023)
- [Grounded Knowledge-Enhanced Medical Vision-Language Pre-training for Chest X-Ray](https://mlsanity.com/paper/2404.14750/) (2024)
- [Medical Report Generation Is A Multi-label Classification Problem](https://mlsanity.com/paper/2409.00250/) (2024)
- [Augmented Vision-Language Models: A Systematic Review](https://mlsanity.com/paper/2507.22933/) (2025)
- [Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering](https://mlsanity.com/paper/2602.23676/) (2026)
- [Anatomy-Aware Conditional Image-Text Retrieval](https://mlsanity.com/paper/2503.07456/) (2025)

## Abstract (arXiv)

Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks, which is very practical in the medical domain. It can significantly reduce the requirement of large amounts of task-specific data by sufficiently sharing medical knowledge among different tasks. However, due to the challenges of designing strongly generalizable models with limited and complex medical data, most existing approaches tend to develop task-specific models. To take a step towards MAGI, we propose a new paradigm called Medical-knOwledge-enhanced mulTimOdal pretRaining (MOTOR). In MOTOR, we combine two kinds of basic medical knowledge, i.e., general and specific knowledge, in a complementary manner to boost the general pretraining process. As a result, the foundation model with comprehensive basic knowledge can learn compact representations from pretraining radiographic data for better cross-modal alignment. MOTOR unifies the understanding and generation, which are two kinds of core intelligence of an AI system, into a single medical foundation model, to flexibly handle more diverse medical tasks. To enable a comprehensive evaluation and facilitate further research, we construct a medical multimodal benchmark including a wide range of downstream tasks, such as chest x-ray report generation and medical visual question answering. Extensive experiments on our benchmark show that MOTOR obtains promising results through simple task-oriented adaptation. The visualization shows that the injected knowledge successfully highlights key information in the medical data, demonstrating the excellent interpretability of MOTOR. Our MOTOR successfully mimics the human practice of fulfilling a "medical student" to accelerate the process of becoming a "specialist". We believe that our work makes a significant stride in realizing MAGI.