Evaluating AI‐powered text‐to‐image generators for anatomical illustration: A comparative study
Anatomical Sciences Education · 2024-07 · 17 (5) · 979-983
DOI: 10.1002/ase.2336 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Anatomical Sciences Education, online erschienen am 11.09.2023. Verfasst von Geoffroy P J C Noel. Beteiligte Einrichtung: Division of Anatomy, Department of Surgery, University of California, San Diego, La Jolla, California, USA. Hauptthemen laut MEDLINE: Anatomy. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Medical illustration, which involves the creation of visual representations of anatomy, has long been an essential tool for medical professionals and educators. The integration of AI and medical illustration has the potential to revolutionize the field of anatomy education, providing highly accurate, customizable images. The authors evaluated three AI‐powered text‐to‐image generators in producing anatomical illustrations of the human skulls, heart, and brain. The generators were assessed for their accurate depiction of foramina, suture lines, coronary arteries, aortic and pulmonary trunk branching, gyri, sulci, and the relationship between the cerebellum and temporal lobes. None of the generators produced illustrations with comprehensive anatomical details. Foramina, such as the mental and supraorbital foramina, were frequently omitted, and suture lines were inaccurately represented. The illustrations of the heart failed to indicate proper coronary artery origins, and the branching of the aorta and pulmonary trunk was often incorrect. Brain illustrations lacked accurate gyri and sulci depiction, and the relationship between the cerebellum and temporal lobes remained unclear. Although AI generators tended toward esoteric imagery, they exhibited significant speed and cost advantages over human illustrators. However, improving their accuracy necessitates augmenting the training databases with anatomically correct images. The study emphasizes the ongoing role of human medical illustrators, especially in ensuring the provision of accurate and accessible illustrations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Anatomy, Department of Surgery, University of California, San Diego, La Jolla, California, USA.
- Division of Anatomical Sciences, Department of Anatomy and Cell Biology, McGill University, Montreal, Québec, Canada.
- Institute of Health Sciences Education, Faculty of Medicine, McGill University, Montreal, Québec, Canada.
ORCID-Profile: Geoffroy P J C Noel
Zitieren
APA
Noel, G. P. J. C. (2024). Evaluating AI‐powered text‐to‐image generators for anatomical illustration: A comparative study. Anatomical Sciences Education, 17(5), 979-983. https://doi.org/10.1002/ase.2336
Vancouver
Noel GPJC. Evaluating AI‐powered text‐to‐image generators for anatomical illustration: A comparative study. Anatomical Sciences Education. 2024;17(5):979-983. doi:10.1002/ase.2336
BibTeX
@article{Noel2024,
author = {Noel, Geoffroy P J C},
title = {Evaluating AI‐powered text‐to‐image generators for anatomical illustration: A comparative study},
journal = {Anatomical Sciences Education},
year = {2024},
volume = {17},
number = {5},
pages = {979--983},
doi = {10.1002/ase.2336}
}
EUVIMED