Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Local Label-Informed Feature Transfer (LLIFT), a novel framework for generating semi-synthetic brain MRI images with realistic lesions without requiring pixel-level annotations. By employing two generative approaches—LLIFT-GAN and LLIFT-DM—both of which utilize binary class labels and bounding-box masks, the authors demonstrate that their methods produce high-quality images that closely resemble real pathological distributions. The resulting datasets not only enhance the evaluation of Explainable AI methods in medical imaging but also mitigate the issues associated with expert annotation errors and artificial perturbations.
Generating realistic brain MRI lesions without pixel-level annotations could revolutionize the validation of Explainable AI in medical imaging.
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.