# Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches

arXiv: https://arxiv.org/abs/2607.18882 · HTML: https://mlsanity.com/paper/2607.18882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 21 Jul 2026.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks](https://mlsanity.com/paper/1807.10225/) (2018)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Explaining Classifiers with Causal Concept Effect (CaCE)](https://mlsanity.com/paper/1907.07165/) (2019)
- [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://mlsanity.com/paper/2211.12737/) (2022)
- [Scrutinizing XAI using linear ground-truth data with suppressor variables](https://mlsanity.com/paper/2111.07473/) (2021)
- [Multitask Brain Tumor Inpainting with Diffusion Models: A Methodological Report](https://mlsanity.com/paper/2210.12113/) (2022)
- [LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models](https://mlsanity.com/paper/2403.14066/) (2024)
- [Denoising Diffusion Models for Inpainting of Healthy Brain Tissue](https://mlsanity.com/paper/2402.17307/) (2024)
- [Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables](https://mlsanity.com/paper/2306.01464/) (2023)
- [The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting](https://mlsanity.com/paper/2305.08992/) (2023)
- [Benchmarking the Influence of Pre-training on Explanation Performance in MR Image Classification](https://mlsanity.com/paper/2306.12150/) (2023)
- [XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance](https://mlsanity.com/paper/2306.12816/) (2023)
- [FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI](https://mlsanity.com/paper/2511.15481/) (2025)
- [Feature salience - not task-informativeness - drives machine learning model explanations](https://mlsanity.com/paper/2602.09238/) (2026)

## Abstract (arXiv)

Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches rely on expert annotations, which are prone to labeling errors, or on hand-crafted artificial perturbations superimposed onto healthy images to mimic lesions or malignant features, which lack clinical realism. We present Local Label-Informed Feature Transfer (LLIFT), a framework for generating semi-synthetic brain magnetic resonance images with realistic lesions placed in user-controlled regions, which does not require pixel-level lesion annotations during training. We implement LLIFT with two generative paradigms: LLIFT-GAN, a custom GAN that learns pathological features from binary class labels alone, and LLIFT-DM, a diffusion-based inpainting pipeline conditioned on bounding-box masks via ControlNet. Both approaches are evaluated on brain magnetic resonance imaging data derived from the Human Connectome Project. In evaluations, both achieve Fr'echet Inception Distance scores, with respect to the real pathological distribution, that are comparable to the inter-class reference between healthy and pathological images in the given dataset. Furthermore, qualitative inspection confirms the realism of lesion structures. The resulting benchmark datasets provide spatially controlled ground truth data for evaluating XAI methods in medical imaging.