We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us

Download Mobile App

Novel AI Image Generation Tool Has Promising Future in Radiology

By MedImaging International staff writers
Posted on 20 Mar 2023
Print article
Image: A study has found the use of generative models for augmenting and generating radiological data to be feasible (Photo courtesy of Charité University Berlin)
Image: A study has found the use of generative models for augmenting and generating radiological data to be feasible (Photo courtesy of Charité University Berlin)

DALL-E 2, an artificial intelligence (AI) tool that was unveiled in April 2022 by OpenAI, generates novel photorealistic images or artwork based on textual input. Trained on billions of text-image pairs available existing on the internet, DALL-E 2 boasts powerful generative capabilities. Now, new research indicates that the DALL-E 2 deep learning model for text-to-image generation could have a bright future in health care, particularly for image generation, augmentation, and manipulation.

Researchers at Charité University Berlin (Berlin, Germany) set out to examine whether generative models have sufficient medical domain knowledge to provide accurate and useful results and to understand if the capabilities of DALL-E 2 can be transferred to the medical domain in order to create or augment data. They analyzed DALL-E 2’s radiological knowledge in creating and manipulating X-ray, computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound images. The research team found that DALL-E 2 has learned relevant representations of X-ray images and has the potential for text-to-image generation. In particular, DALL-E 2 managed to create realistic X-ray images based on short text prompts, although it performed poorly when presented with specific CT, MRI, or ultrasound image prompts. Moreover, while it was able to reasonably reconstruct missing elements in radiological images, its ability to generate images with pathological abnormalities was limited. Additionally, DALL-E 2 could do much more, such as generating an entire, full-body radiograph using only one knee image.

Synthetic data generated by DALL-E 2 can significantly speed up the development of new deep-learning tools for radiology while resolving privacy concerns over data sharing between institutions. The researchers have suggested that the generated images must be subjected to quality control by domain experts in order to minimize the risk of incorrect information being integrated into a generated data set. According to the researchers, there is also a need for further research to tweak these models to medical data and integrate medical terminology in order to create powerful models for data generation and augmentation in radiology research. DALL-E 2 is unavailable to the public for fine-tuning, although other generative models such as Stable Diffusion can be tweaked by the public and adapted to generate a variety of medical images. The study indicates that AI image generation in radiology has a promising future and further R&D could pave the way for exciting new tools for radiologists and medical professionals.

Related Links:
Charité University Berlin

Print article



view channel
Image: The device creates microbubbles that temporarily disrupt the BBB, permitting the entry of immunotherapy into the brain (Photo courtesy of Northwestern)

Ultrasound Technology Breaks Blood-Brain Barrier for Glioblastoma Treatment

Despite extensive molecular studies, the outlook for patients diagnosed with the aggressive brain cancer known as glioblastoma (GBM) continues to be poor. This is partly due to the blood-brain barrier... Read more

Nuclear Medicine

view channel
Image: 68Ga-NC-BCH whole-body PET imaging rapidly targets an important gastrointestinal cancer biomarker in lesions in GI cancer patients (Photo courtesy of Qi, Guo, et al.; doi.org/10.2967/jnumed.123.267110)

New PET Radiotracer Enables Same-Day Imaging of Key Gastrointestinal Cancer Biomarker

Gastrointestinal cancers rank among the most prevalent cancers worldwide, contributing to over a quarter of all cancer cases and over one-third of cancer-related deaths annually. The initial symptoms of... Read more

General/Advanced Imaging

view channel
Image: The denoised image is less noisy and the defect is more detectable and visually clearer with DEMIST (Photo courtesy of Abhinav Jha/WUSTL)

Artificial Intelligence Tool Enhances Usability of Medical Images

Doctors use myocardial perfusion imaging (MPI) single-photon emission computed tomography (SPECT) images to evaluate blood flow to the heart muscle. To capture these images, patients are administered a... Read more

Imaging IT

view channel
Image: The new Medical Imaging Suite makes healthcare imaging data more accessible, interoperable and useful (Photo courtesy of Google Cloud)

New Google Cloud Medical Imaging Suite Makes Imaging Healthcare Data More Accessible

Medical imaging is a critical tool used to diagnose patients, and there are billions of medical images scanned globally each year. Imaging data accounts for about 90% of all healthcare data1 and, until... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.