What Does DALL-E 2 Know About Radiology?

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Adams, Lisa C., Busch, Felix, Truhn, Daniel, Makowski, Marcus R., Aerts, Hugo JWL., Bressem, Keno K.
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909204419182592
author Adams, Lisa C.
Busch, Felix
Truhn, Daniel
Makowski, Marcus R.
Aerts, Hugo JWL.
Bressem, Keno K.
author_facet Adams, Lisa C.
Busch, Felix
Truhn, Daniel
Makowski, Marcus R.
Aerts, Hugo JWL.
Bressem, Keno K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2209_13696
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle What Does DALL-E 2 Know About Radiology?
Adams, Lisa C.
Busch, Felix
Truhn, Daniel
Makowski, Marcus R.
Aerts, Hugo JWL.
Bressem, Keno K.
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
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.
title What Does DALL-E 2 Know About Radiology?
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2209.13696