Metal artifact synthesis: Enabling inclusive Deep learning for patients with implants

Motivation: AI medical imaging solutions are impacted by the presence metal implants and a design of appropriate synthesis method can improve robustness of DL models. Goal(s): Simulation of patient medical condition like metal artifacts in MRI medical images. Approach: The proposed method blends regions from template images containing metal artifacts into target images by using metal segmentation mask for selection, blending this region into a chosen target image RoI . Results: Improvement in knee classification accuracy of 8% and decrease in spine plane distance error by 25-40% and plane angle error by 4-30% using the proposed approach. Impact: A data adaptive metal simulation method in semantically relevant regions in anatomy ensures robust of DL models in patients with metal implants who hitherto would not have benefitted from AI driven tasks .