Can you spot a deepfake X-ray? Neither can your radiologist

Certainly! Here are four key points from the article:

Impact of Deepfakes on Medical Imaging: Researchers found that deepfake X-rays generated by an AI model like ChatGPT can deceive radiologists, with only 41% able to detect that the images were fake during initial diagnosis efforts.
Ease of Generating Deepfake Medical Images: The study demonstrated that it’s relatively simple to generate radiographs using AI by providing basic prompts for anatomical details and disorders.
AI’s Limited Ability to Recognize Deepfakes: Even advanced multimodal models struggled to accurately identify the deepfake X-rays most of the time, distinguishing them correctly only between 57% and 85% of the time.
Broader Implications for Healthcare: The findings highlight potential risks and challenges posed by deepfake images in medical diagnosis, potentially impacting patient care and healthcare standards.

Note: For full access to the STAT+ exclusive article with more details, a subscription is required.