Inpainting Pathology in Lumbar Spine MRI with Latent Diffusion
This work addresses data augmentation challenges for medical imaging, specifically for lumbar spine MRI, by enabling more accurate synthesis of complex pathologies, though it is incremental as it builds on existing inpainting and diffusion techniques.
The paper tackles the problem of insufficient and imbalanced datasets for automated radiology diagnosis by proposing an efficient method to inpaint pathological features onto healthy MRI scans using a latent diffusion model with voxelwise noise scheduling. It achieves superior Frechet Inception Distance scores compared to state-of-the-art methods when inserting disc herniation and central canal stenosis in lumbar spine MRI.
Data driven models for automated diagnosis in radiology suffer from insufficient and imbalanced datasets due to low representation of pathology in a population and the cost of expert annotations. Datasets can be bolstered through data augmentation. However, even when utilizing a full suite of transformations during model training, typical data augmentations do not address variations in human anatomy. An alternative direction is to synthesize data using generative models, which can potentially craft datasets with specific attributes. While this holds promise, commonly used generative models such as Generative Adversarial Networks may inadvertently produce anatomically inaccurate features. On the other hand, diffusion models, which offer greater stability, tend to memorize training data, raising concerns about privacy and generative diversity. Alternatively, inpainting has the potential to augment data through directly inserting pathology in medical images. However, this approach introduces a new challenge: accurately merging the generated pathological features with the surrounding anatomical context. While inpainting is a well established method for addressing simple lesions, its application to pathologies that involve complex structural changes remains relatively unexplored. We propose an efficient method for inpainting pathological features onto healthy anatomy in MRI through voxelwise noise scheduling in a latent diffusion model. We evaluate the method's ability to insert disc herniation and central canal stenosis in lumbar spine sagittal T2 MRI, and it achieves superior Frechet Inception Distance compared to state-of-the-art methods.