# Rethinking Artificial Intelligence in Medical Imaging: Assumptions, Reality, and Reframing

arXiv: https://arxiv.org/abs/2607.27428 · HTML: https://mlsanity.com/paper/2607.27428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [Vision Foundation Models for Computed Tomography](https://mlsanity.com/paper/2501.09001/) (2025)
- [Artificial Intelligence-Based Methods for Fusion of Electronic Health Records and Imaging Data](https://mlsanity.com/paper/2210.13462/) (2022)
- [Objective task-based evaluation of artificial intelligence-based medical imaging methods: Framework, strategies and role of the physician](https://mlsanity.com/paper/2107.04540/) (2021)
- [A brief history of AI: how to prevent another winter (a critical review)](https://mlsanity.com/paper/2109.01517/) (2021)
- [AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets](https://mlsanity.com/paper/2307.13897/) (2023)
- [Artificial Intelligence in Healthcare: Lost In Translation?](https://mlsanity.com/paper/2107.13454/) (2021)
- [Nuclear Medicine AI in Action: The Bethesda Report (AI Summit 2024)](https://mlsanity.com/paper/2406.01044/) (2024)
- [What is Implementation Science; and Why It Matters for Bridging the Artificial Intelligence Innovation-to-Application Gap in Medical Imaging](https://mlsanity.com/paper/2510.13006/) (2025)

## Abstract (arXiv)

Medical imaging has served as primary proving ground for clinical artificial intelligence (AI), yet a decade of intense research has not translated into proportionate bedside impact. We argue that this gap is not primarily a product of insufficient algorithmic performance, inadequate regulation, or limited explainability. Rather, it reflects a structural misalignment, between how AI systems are designed and evaluated, and how clinical decisions are made. This Perspective identifies six interconnected dimensions of this misalignment: the dominance of pixel-only models in a multimodal clinical world; the erosion of physician trust through opaque and inflexible systems; the unfulfilled promise of foundation models in data-sparse medical domains; the persistent bottleneck of non-shareable, under-curated datasets; the gap between validated algorithms and deployable clinical platforms; and the failure of prediction-centric AI to generate actionable clinical guidance. For each dimension, we reframe the problem and propose a path forward, culminating in a vision of agentic, physician-aligned AI that extends, rather than replaces, clinical judgment.