# Hallucination Index: An Image Quality Metric for Generative Reconstruction Models

arXiv: https://arxiv.org/abs/2407.12780 · HTML: https://mlsanity.com/paper/2407.12780/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

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

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction](https://mlsanity.com/paper/2203.03623/) (2022)
- [How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control](https://mlsanity.com/paper/2302.03791/) (2023)
- [Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction](https://mlsanity.com/paper/2006.06270/) (2020)
- [How should a fixed budget of dwell time be spent in scanning electron microscopy to optimize image quality?](https://mlsanity.com/paper/1801.04085/) (2018)

## Built on by (most cited first, 26 of 26)

- [Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS](https://mlsanity.com/paper/2503.01075/) (2025)
- [Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography](https://mlsanity.com/paper/2503.00136/) (2025)
- [Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation](https://mlsanity.com/paper/2508.09177/) (2025)
- [Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities](https://mlsanity.com/paper/2508.07031/) (2025)
- [Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2409.18872/) (2024)
- [RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models](https://mlsanity.com/paper/2507.12201/) (2025)
- [Conformal Bounds on Full-Reference Image Quality for Imaging Inverse Problems](https://mlsanity.com/paper/2505.09528/) (2025)
- [Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problems](https://mlsanity.com/paper/2511.13533/) (2025)
- [HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration](https://mlsanity.com/paper/2512.03345/) (2025)
- [CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing](https://mlsanity.com/paper/2512.09806/) (2025)
- [Cortex-Grounded Diffusion Models for Brain Image Generation](https://mlsanity.com/paper/2601.19498/) (2026)
- [sFRC for assessing hallucinations in medical image restoration](https://mlsanity.com/paper/2603.04673/) (2026)
- [Managing Diabetic Retinopathy with Deep Learning: A Data Centric Overview](https://mlsanity.com/paper/2604.02448/) (2026)
- [Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models](https://mlsanity.com/paper/2605.05026/) (2026)
- [High-Fidelity 3D Lung CT Synthesis in ARDS Swine Models Using Score-Based 3D Residual Diffusion Models](https://mlsanity.com/paper/2410.10826/) (2024)
- [Converting T1-weighted MRI from 3T to 7T quality using deep learning](https://mlsanity.com/paper/2507.13782/) (2025)
- [Hallucinations in medical devices](https://mlsanity.com/paper/2508.14118/) (2025)
- [PAINT: Pathology-Aware Integrated Next-Scale Transformation for Virtual Immunohistochemistry](https://mlsanity.com/paper/2601.16024/) (2026)
- [Volumetric Directional Diffusion: Anchoring Uncertainty Quantification in Anatomical Consensus for Ambiguous Medical Image Segmentation](https://mlsanity.com/paper/2603.04024/) (2026)
- [On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods](https://mlsanity.com/paper/2605.13146/) (2026)
- [Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates](https://mlsanity.com/paper/2606.02331/) (2026)
- [Learning to Distort: Weakly-Supervised Image Quality Transfer for Prostate DWI Correction](https://mlsanity.com/paper/2606.18869/) (2026)
- [Multilevel Stochastic Plug-and-Play for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2606.24567/) (2026)
- [Residual-Guided Expert Specialization for Incomplete Multimodal Learning](https://mlsanity.com/paper/2606.30355/) (2026)
- [One-Step Is Optimal: Unconditional Rectified Flows are Noise2Noise Denoisers, and Multi-Step Integration Provably Hurts---A Benchmark and Task-Based Detectability Study on Low-Dose CT](https://mlsanity.com/paper/2609.31670/) (2026)
- [QuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG](https://mlsanity.com/paper/2609.33351/) (2026)

## Abstract (arXiv)

Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs with the appearance of high SNR. However, the outputs can have a new type of error called hallucinations. In medical imaging, these hallucinations may not be obvious to a Radiologist but could cause diagnostic errors. Generally, hallucination refers to error in estimation of object structure caused by a machine learning model, but there is no widely accepted method to evaluate hallucination magnitude. In this work, we propose a new image quality metric called the hallucination index. Our approach is to compute the Hellinger distance from the distribution of reconstructed images to a zero hallucination reference distribution. To evaluate our approach, we conducted a numerical experiment with electron microscopy images, simulated noisy measurements, and applied diffusion based reconstructions. We sampled the measurements and the generative reconstructions repeatedly to compute the sample mean and covariance. For the zero hallucination reference, we used the forward diffusion process applied to ground truth. Our results show that higher measurement SNR leads to lower hallucination index for the same apparent image quality. We also evaluated the impact of early stopping in the reverse diffusion process and found that more modest denoising strengths can reduce hallucination. We believe this metric could be useful for evaluation of generative image reconstructions or as a warning label to inform radiologists about the degree of hallucinations in medical images.