EUVIMEDEUVIMED entdecken
Crossref

Clinical Application of Large Language Models in Generating Pathologic Images

Lingxuan Zhu, Yancheng Lai, Na Ta, Weiming Mou iD, Rodolfo Montironi iD, Katrina Collins iD, Kenneth A Iczkowski iD, Fei Chen iD, Antonio Lopez-Beltran iD, Rui Zhou iD, Huang He iD, Gyan Pareek und 10 weitere

JCO Clinical Cancer Informatics · 2025

DOI: 10.1200/cci-24-00267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Lingxuan Zhu und 21 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Artificial Intelligence, Image Processing, Computer-Assisted, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 11 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE This study investigates the potential of DALL·E 3, an artificial intelligence (AI) model, to generate synthetic pathologic images of prostate cancer (PCa) at varying Gleason grades. The aim is to enhance medical education and research resources, particularly by providing diverse case studies and valuable teaching tools. METHODS This study uses DALL·E 3 to generate 30 synthetic images of PCa across various Gleason grades, guided by standard Gleason pattern descriptions. Nine uropathologists evaluated these images for realism and accuracy compared with actual hematoxylin and eosin (H&E)–stained slides using a scoring system. RESULTS The average realism and representativeness scores were 6.04 and 6.17, indicating satisfactory quality. Scores varied significantly among Gleason patterns ( P < .05), with Gleason 5 images achieving the highest scores and accurately depicting critical pathologic characteristics. Limitations included a lack of fine nuclear detail, essential for identifying malignancy, which may affect the images' diagnostic utility. CONCLUSION DALL·E 3 shows promise in generating customized pathologic images that can aid in education and resource expansion within pathology. However, ethical concerns, such as the potential misuse of AI-generated images for data falsification, highlight the need for responsible oversight. Collaboration between technology firms and pathologists is essential for the ethical integration of AI in pathology practices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsArtificial IntelligenceImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansMaleNeoplasm GradingLarge Language Models

Autor:innen und Institutionen

  • Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Department of Oncology, Zhujiang Hospital, Southern Medical University, Guangzhou, China.
  • The First Clinical Medical School, Southern Medical University, Guangdong, China.
  • Department of Pathology, Shanghai Changhai Hospital, Second Military Medical University, Shanghai, China.
  • Department of Urology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • Molecular Medicine and Cell Therapy Foundation, Polytechnic University of the Marche Region, Ancona, Italy.

ORCID-Profile: Weiming Mou, Rodolfo Montironi, Katrina Collins, Kenneth A Iczkowski, Fei Chen, Antonio Lopez-Beltran, Rui Zhou, Huang He, Borivoj Golijanin, Kamil Malshy, Alessia Cimadamore, Tao Yang, Liang Cheng, Rui Chen

Zitieren

APA

Zhu, L., Lai, Y., Ta, N., Mou, W., Montironi, R., Collins, K., Iczkowski, K. A., Chen, F., Lopez-Beltran, A., Zhou, R., He, H., Pareek, G., Hyams, E., Golijanin, D., Khaleel, S., Golijanin, B., Malshy, K., Cimadamore, A., Ni, X., …, & Chen, R. (2025). Clinical Application of Large Language Models in Generating Pathologic Images. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-24-00267

Vancouver

Zhu L, Lai Y, Ta N, Mou W, Montironi R, Collins K, et al. Clinical Application of Large Language Models in Generating Pathologic Images. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-24-00267

BibTeX
@article{Zhu2025,
  author = {Zhu, Lingxuan and Lai, Yancheng and Ta, Na and Mou, Weiming and Montironi, Rodolfo and Collins, Katrina and Iczkowski, Kenneth A and Chen, Fei and Lopez-Beltran, Antonio and Zhou, Rui and He, Huang and Pareek, Gyan and Hyams, Elias and Golijanin, Dragan and Khaleel, Sari and Golijanin, Borivoj and Malshy, Kamil and Cimadamore, Alessia and Ni, Xiang and Yang, Tao and Cheng, Liang and Chen, Rui},
  title = {Clinical Application of Large Language Models in Generating Pathologic Images},
  journal = {JCO Clinical Cancer Informatics},
  year = {2025},
  doi = {10.1200/cci-24-00267}
}
Kostenlos starten →