# Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions

arXiv: https://arxiv.org/abs/2507.00670 · HTML: https://mlsanity.com/paper/2507.00670/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [Robust Compressed Sensing MRI with Deep Generative Priors](https://mlsanity.com/paper/2108.01368/) (2021)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models](https://mlsanity.com/paper/2402.12336/) (2024)
- [Adversarial Robustness on In- and Out-Distribution Improves Explainability](https://mlsanity.com/paper/2003.09461/) (2020)
- [Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction](https://mlsanity.com/paper/2203.03623/) (2022)
- [nnDetection: A Self-configuring Method for Medical Object Detection](https://mlsanity.com/paper/2106.00817/) (2021)
- [SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation](https://mlsanity.com/paper/2203.06823/) (2022)
- [Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems](https://mlsanity.com/paper/2407.10641/) (2024)
- [CLIPAG: Towards Generator-Free Text-to-Image Generation](https://mlsanity.com/paper/2306.16805/) (2023)
- [From Posterior Sampling to Meaningful Diversity in Image Restoration](https://mlsanity.com/paper/2310.16047/) (2023)
- [Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations](https://mlsanity.com/paper/2208.03161/) (2022)
- [Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics](https://mlsanity.com/paper/2502.11725/) (2025)
- [Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction](https://mlsanity.com/paper/2406.04318/) (2024)
- [fastMRI Breast: A publicly available radial k-space dataset of breast dynamic contrast-enhanced MRI](https://mlsanity.com/paper/2406.05270/) (2024)
- [Segmentation-guided MRI reconstruction for meaningfully diverse reconstructions](https://mlsanity.com/paper/2407.18026/) (2024)

## Built on by (most cited first, 2 of 2)

- [CUTE-MRI: Conformalized Uncertainty-based framework for Time-adaptivE MRI](https://mlsanity.com/paper/2508.14952/) (2025)
- [Measured-Subspace Consistency: A Plug-and-Play Operator for Diffusion Posterior Sampling in Accelerated MRI Reconstruction](https://mlsanity.com/paper/2606.28448/) (2026)

## Abstract (arXiv)

In recent years, accelerated MRI reconstruction based on deep learning has led to significant improvements in image quality with impressive results for high acceleration factors. However, from a clinical perspective image quality is only secondary; much more important is that all clinically relevant information is preserved in the reconstruction from heavily undersampled data. In this paper, we show that existing techniques, even when considering resampling for diffusion-based reconstruction, can fail to reconstruct small and rare pathologies, thus leading to potentially wrong diagnosis decisions (false negatives). To uncover the potentially missing clinical information we propose ``Semantically Diverse Reconstructions'' (SDR), a method which, given an original reconstruction, generates novel reconstructions with enhanced semantic variability while all of them are fully consistent with the measured data. To evaluate SDR automatically we train an object detector on the fastMRI+ dataset. We show that SDR significantly reduces the chance of false-negative diagnoses (higher recall) and improves mean average precision compared to the original reconstructions. The code is available on https://github.com/NikolasMorshuis/SDR