Abstract: Systems/techniques that facilitate improved ease of image annotation via curved planar reformation are provided. In various embodiments, a system can access a first image depicting an original version of a tubular anatomical structure. In various aspects, the system can generate a second image, by straightening the first image about a centerline of the tubular anatomical structure, such that the second image depicts a straightened version of the tubular anatomical structure. In various instances, the system can generate a third image, by inserting an annotation into the second image, such that the third image depicts the annotation and the straightened version of the tubular anatomical structure. In various cases, the system can generate a fourth image, by un-straightening the third image about the centerline of the tubular anatomical structure, such that the fourth image depicts both the original version of the tubular anatomical structure and an un-straightened version of the annotation.

Abstract: Systems/techniques that facilitate curve-conditioned medical image synthesis are provided. In various embodiments, a system can access a user-specified geometric curve. In various aspects, the system can generate, via execution of a first deep learning neural network on the user-specified geometric curve, a synthetic medical image whose visual characteristics are based on the user-specified geometric curve. In various instances, the system can render the synthetic medical image on an electronic display.