The model was developed and validated specifically for liver, spleen and pancreas segmentation, and outperformed a publicly available segmentation model already in use.

Although these tools have proven themselves valuable in numerous settings, they must be used with caution, especially by patients and nonradiologist providers who may be seeking clarification on imaging reports. 

Image-based questions were significantly more challenging for the large language model to answer, despite the latest version now being capable of accepting image prompts.

Automated AI-generated measurements combined with annotated CT images can improve treatment planning and help referring physicians and patients better understand their disease, explained Sarah Jane Rinehart, MD, director of cardiac imaging with Charleston Area Medical Center.

Finding such discrepancies is critical to the continuity of patient care, as medical records and reports are often utilized across multiple providers and facilities. 

This could be especially helpful when timely clinical decisions relative to the use of a contrast agent need to be made.

Two advanced algorithms—one for CAC scores and another for segmenting cardiac chamber volumes—outperformed radiologists when assessing low-dose chest CT scans. 

Apparently, it isn’t just humans who occasionally struggle to work under stress. According to a recent study, the performance of AI flounders, too.