Expert discusses ChatGPT's potential, limitations in radiology

May 16, 2023

AuntMinnie.com spoke with Rajesh Bhayana, MD, of the University of Toronto's department of medical imaging about ChatGPT's potential as a tool in radiology practice, as well as its dangerous tendency to produce so-called "hallucinations."


Latest in AI
2025 04 23 Ajr Vosshenrich Thumbnail
Deep-learning technique boosts diagnostic ability of fast knee MRI
April 24, 2025
Data Protection Nijat
Health data restrictions plague medtech AI developers
April 23, 2025
2025 04 22 Radiology Mrisegmenter Thumbnail
MRI tool segments over 60 abdominal organs, structures
April 22, 2025
Figure: Improved image quality with a generative adversarial network architecture for low- to high-field-strength image translation, called LowGAN. (A–C) Top: High-field-strength (3-T) and low-field-strength (64-mT) images and LowGAN outputs for a single participant across (A) fluid-attenuated inversion recovery (FLAIR), (B) T1-weighted (T1w), and (C) T2-weighted (T2w) contrasts. Bottom: Graphs demonstrate the structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and feature similarity index (FSIM) between high field strength and low field strength (64-mT) and high field strength and LowGAN outputs. a.u. = arbitrary units.****p ≤ 0.0001. Images and caption courtesy of Radiology and the RSNA.
AI produces synthetic 3T MR images from portable scans
April 22, 2025
Related Stories
187x200 Am Logo
Companies
AuntMinnie.com
2019 04 04 21 52 2230 Artificial Intelligence Ai Data 400
AI
Does ChatGPT really 'hallucinate'?
2020 04 01 22 35 2587 Patient Man 400
AI
Is ChatGPT more empathetic toward patient questions than physicians?
2022 09 09 22 43 4643 Computer Doctor Report Digital 400
AI
AI model identifies reports recommending additional patient imaging
More in AI
Deep-learning technique boosts diagnostic ability of fast knee MRI
By Kate Madden Yee
A new, fast deep learning-based MR imaging technique shows excellent performance for diagnosing knee injuries, researchers have reported.
April 24, 2025
2025 04 23 Ajr Vosshenrich Thumbnail
Health data restrictions plague medtech AI developers
By Liz Carey
Medtech industry and health leaders from big tech have introduced a new AI Policy Roadmap.
April 23, 2025
Data Protection Nijat
MRI tool segments over 60 abdominal organs, structures
By Amerigo Allegretto
An automated multiorgan tool can accurately segment T1-weighted abdominal MR images.
April 22, 2025
2025 04 22 Radiology Mrisegmenter Thumbnail
AI produces synthetic 3T MR images from portable scans
By Erik L. Ridley
Findings show that AI could potentially expand the utility of neuroimaging on portable MRI systems.
April 22, 2025
Figure: Improved image quality with a generative adversarial network architecture for low- to high-field-strength image translation, called LowGAN. (A–C) Top: High-field-strength (3-T) and low-field-strength (64-mT) images and LowGAN outputs for a single participant across (A) fluid-attenuated inversion recovery (FLAIR), (B) T1-weighted (T1w), and (C) T2-weighted (T2w) contrasts. Bottom: Graphs demonstrate the structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and feature similarity index (FSIM) between high field strength and low field strength (64-mT) and high field strength and LowGAN outputs. a.u. = arbitrary units.****p ≤ 0.0001. Images and caption courtesy of Radiology and the RSNA.
Cortechs.ai software gets Health Canada approval
By AuntMinnie.com staff writers
AI developer Cortechs.ai has received approval from Health Canada for its medical imaging analysis software suite.
April 22, 2025
Artificial Intelligence Ai Brain 400
More women welcome AI assistance for mammography exams
By Amerigo Allegretto
More women are willing to have AI assistance for their breast cancer screening exams.
April 18, 2025
Mammo Reading 400
How can AI best help in LDCT lung cancer screening?
By Will Morton
A commercially available AI-based tool appears effective as a prescreener in low-dose CT lung cancer screening.
April 16, 2025
Lung Cancer
Can LLMs help track interval changes on radiology reports?
By Erik L. Ridley
Large-language models (LLMs) show potential for tracking interval changes on longitudinal radiology reports.
April 14, 2025
Artificial Intelligence Ai Global Communication Network
AI-guided POCUS bests experts in detecting TB in underserved areas
By Amerigo Allegretto
AI-guided POCUS can accurately detect tuberculosis (TB), according to research presented at the ESCMID conference in Vienna, Austria.
April 13, 2025
Véronique Suttels, PhD, performs an ultrasound scan on a patient in Benin, West Africa, using a POCUS scanner connected to a smartphone. Her team studied how an AI-guided POCUS system can help diagnose tuberculosis in patients with respiratory symptoms. Image courtesy of Véronique Suttels, PhD.
Mimicking human vision: The new standard for medical image fidelity
By Ravinder Singh and Vaibhavi Sonetha, PhD
Ravinder Singh and Vaibhavi Sonetha, PhD, of Citius Healthcare Consulting, discuss a new method for assessing medical image fidelity.
April 11, 2025
Eye Pexels
Senators introduce medical AI reimbursement bill
By Amerigo Allegretto
A bill introduced in the U.S. Congress aims to establish a reimbursement pathway for FDA-authorized medical devices that rely on AI.
April 10, 2025
Business Computer Partners Handshake Techno 400
AI bests rads in finding breast cancer in women with personal history
By Amerigo Allegretto
AI may have a role in finding contralateral disease in women with a personal history of breast cancer.
April 8, 2025
Images depict a 65-year-old patient with contralateral second breast cancer 6.3 years after right mastectomy. (A) Left craniocaudal and (B) mediolateral oblique mammograms assessed as benign. (C) The AI algorithm outlined a lesion with a score of 31 on the craniocaudal view. (D) A supplemental axial ultrasound scan, which was obtained on the same day as the mammogram, shows an irregular hypoechoic mass (arrows) in the left upper central breast. (E) Preoperative sagittal contrast-enhanced T1-weighted MRI scan shows the corresponding enhancing mass (arrow) in the left upper center. The mass was proven to be ductal carcinoma in situ.
Page 1 of 376
Next Page