# Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend

arXiv: https://arxiv.org/abs/2311.13717 · HTML: https://mlsanity.com/paper/2311.13717/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (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)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [The Role of ImageNet Classes in Fr'echet Inception Distance](https://mlsanity.com/paper/2203.06026/) (2022)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [ConvNets vs. Transformers: Whose Visual Representations are More Transferable?](https://mlsanity.com/paper/2108.05305/) (2021)
- [How Transferable Are Self-supervised Features in Medical Image Classification Tasks?](https://mlsanity.com/paper/2108.10048/) (2021)
- [medigan: a Python library of pretrained generative models for medical image synthesis](https://mlsanity.com/paper/2209.14472/) (2022)
- [TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation](https://mlsanity.com/paper/2105.08993/) (2021)
- [Evaluating the Performance of StyleGAN2-ADA on Medical Images](https://mlsanity.com/paper/2210.03786/) (2022)

## Built on by (most cited first, 24 of 24)

- [Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets](https://mlsanity.com/paper/2412.01496/) (2024)
- [MRI-CORE: A Foundation Model for Magnetic Resonance Imaging](https://mlsanity.com/paper/2506.12186/) (2025)
- [Metrics that matter: Evaluating image quality metrics for medical image generation](https://mlsanity.com/paper/2505.07175/) (2025)
- [A Pragmatic Note on Evaluating Generative Models with Fr'echet Inception Distance for Retinal Image Synthesis](https://mlsanity.com/paper/2502.17160/) (2025)
- [Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models](https://mlsanity.com/paper/2505.05573/) (2025)
- [Cross-modality image synthesis from TOF-MRA to CTA using diffusion-based models](https://mlsanity.com/paper/2409.10089/) (2024)
- [MedLoRD: A Medical Low-Resource Diffusion Model for High-Resolution 3D CT Image Synthesis](https://mlsanity.com/paper/2503.13211/) (2025)
- [Scalable next-scale autoregression for medical image generation across anatomical regions](https://mlsanity.com/paper/2602.14512/) (2026)
- [Interpretable Similarity of Synthetic Image Utility](https://mlsanity.com/paper/2512.17080/) (2025)
- [Image Synthesis with Class-Aware Semantic Diffusion Models for Surgical Scene Segmentation](https://mlsanity.com/paper/2410.23962/) (2024)
- [Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Score](https://mlsanity.com/paper/2501.00744/) (2025)
- [Improving Medical Image Generative Models with Fr'echet Distance Loss](https://mlsanity.com/paper/2607.13300/) (2026)
- [Tokenizer-Generator Coupling in Medical Image Generation](https://mlsanity.com/paper/2608.07713/) (2026)
- [Generating Novel Brain Morphology by Deforming Learned Templates](https://mlsanity.com/paper/2503.03778/) (2025)
- [Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis](https://mlsanity.com/paper/2508.06021/) (2025)
- [MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography](https://mlsanity.com/paper/2508.09616/) (2025)
- [MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification](https://mlsanity.com/paper/2510.22070/) (2025)
- [Evaluating the trustworthiness of the Fr'echet Inception Distance with stochastic embedding representations](https://mlsanity.com/paper/2601.21979/) (2026)
- [DMD-augmented Unpaired Neural Schr"odinger Bridge for Ultra-Low Field MRI Enhancement](https://mlsanity.com/paper/2603.03769/) (2026)
- [VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers](https://mlsanity.com/paper/2603.25181/) (2026)
- [A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI](https://mlsanity.com/paper/2606.18970/) (2026)
- [Through the Schr"odinger Bridge: Benchmarking Antemortem Image Restoration from Postmortem Autolysis to Enhance Forensic Diagnostics](https://mlsanity.com/paper/2608.21813/) (2026)
- [Anguinus Sculpturae: Compositional Synthesis of Peak-Enhancement Breast DCE-MRI Scans](https://mlsanity.com/paper/2609.33611/) (2026)
- [M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image Models](https://mlsanity.com/paper/2609.33769/) (2026)

## Abstract (arXiv)

Fr'echet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images. Our study challenges this practice by demonstrating that ImageNet-based extractors are more consistent and aligned with human judgment than their RadImageNet counterparts. We evaluated sixteen StyleGAN2 networks across four medical imaging modalities and four data augmentation techniques with Fr'echet distances (FDs) computed using eleven ImageNet or RadImageNet-trained feature extractors. Comparison with human judgment via visual Turing tests revealed that ImageNet-based extractors produced rankings consistent with human judgment, with the FD derived from the ImageNet-trained SwAV extractor significantly correlating with expert evaluations. In contrast, RadImageNet-based rankings were volatile and inconsistent with human judgment. Our findings challenge prevailing assumptions, providing novel evidence that medical image-trained feature extractors do not inherently improve FDs and can even compromise their reliability. Our code is available at https://github.com/mckellwoodland/fid-med-eval.