What Does DALL-E 2 Know About Radiology?
This work addresses the potential for using generative models in radiology for data augmentation and generation, though it is incremental as it highlights current limitations and the need for fine-tuning.
The study investigated DALL-E 2's ability to generate and manipulate radiological images, finding it capable of zero-shot text-to-image generation, image continuation, and element removal for X-rays, but limited in pathology generation and other modalities like CT and MRI.
Generative models such as DALL-E 2 could represent a promising future tool for image generation, augmentation, and manipulation for artificial intelligence research in radiology provided that these models have sufficient medical domain knowledge. Here we show that DALL-E 2 has learned relevant representations of X-ray images with promising capabilities in terms of zero-shot text-to-image generation of new images, continuation of an image beyond its original boundaries, or removal of elements, while pathology generation or CT, MRI, and ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if further fine-tuning and adaptation of these models to the respective domain is required beforehand.