Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Editorial
. 2024 Mar 19;1(1):umae006.
doi: 10.1093/radadv/umae006. eCollection 2024 May.

ChatGPT-4: a breakthrough in ultrasound image analysis

Laith R Sultan  1 , Mohamed Kh Mohamed  1 , Savvas Andronikou  1   2
Affiliations
Editorial

ChatGPT-4: a breakthrough in ultrasound image analysis

Laith R Sultan et al. Radiol Adv. .
No abstract available

Keywords: ChatGPT-4; artificial intelligence; computer aided diagnosis; quantitative image analysis; ultrasound.

PubMed Disclaimer

Conflict of interest statement

Please see ICMJE form(s) for author conflicts of interest. These have been provided as supplementary materials. All authors have no conflicts of interest.

Figures

Figure 1.
Figure 1.
ChatGPT-4 analysis of a grayscale ultrasound image of the thyroid gland containing a nodule. The process begins with a query to ChatGPT-4 for (A) locating the nodule within the image (indicated by a rectangular box), and (B) generating a differential diagnosis for the nodule. Images of ChatGPT-4 outputs to request for delineation (outlined) of (C) the entire thyroid gland including the nodule and of the nodule specifically.
Figure 2.
Figure 2.
Capability of ChatGPT-4 in accurately classifying renal ultrasound images as either normal or pathological and offering diagnoses. (A) A collection of ultrasound images, encompassing both healthy kidneys and those exhibiting various degrees of urinary tract dilation (UTD). (B) Process by which ChatGPT-4 is tasked to classify these ultrasound images. (C) ChatGPT-4 accurately distinguishing normal from abnormal findings offers correct diagnoses of pathologies.
See this image and copyright information in PMC

References

    1. Oren O, Gersh BJ, Bhatt DL.. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. Lancet Digit Health. 2020;2(9):e486-e488. 10.1016/s2589-7500(20)30160-6 - DOI - PubMed
    1. Le MPT, Voigt L, Nathanson R, et al. Comparison of four handheld point-of-care ultrasound devices by expert users. Ultrasound J. 2022;14(1):27. - PMC - PubMed
    1. Di Serafino M, Iacobellis F, Schillirò ML, et al. Common and uncommon errors in emergency ultrasound. Diagnostics (Basel). 2022;12(3):631. 10.3390/diagnostics12030631 - DOI - PMC - PubMed
    1. Kim YH. Artificial intelligence in medical ultrasonography: driving on an unpaved road. Ultrasonography. 2021;40(3):313-317. 10.14366/usg.21031 - DOI - PMC - PubMed
    1. Biswas SS. Role of ChatGPT in radiology with a focus on pediatric radiology: proof by examples. Pediatr Radiol. 2023;53(5):818-822. 10.1007/s00247-023-05675-w - DOI - PubMed

Publication types

LinkOut - more resources