EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research-based clinical deployment of artificial intelligence algorithm for prostate MRI

Stephanie A Harmon, Jesse Tetreault, Omer Tarik Esengur, Ming Qin, Enis C Yilmaz, Victor Chang, Dong Yang, Ziyue Xu, Gregg Cohen, Jeff Plum, Testi Sherif, Ron Levin und 10 weitere

Abdominal Radiology · 2025

DOI: 10.1007/s00261-025-05014-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, 2025. Verfasst von Stephanie A Harmon und 21 weiteren Autor:innen. Beteiligte Einrichtung: National Institutes of Health, Bethesda, USA. stephanie.harmon@nih.gov. Hauptthemen laut MEDLINE: Artificial Intelligence, Prostatic Neoplasms, Algorithms, Magnetic Resonance Imaging. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

A critical limitation to deployment and utilization of Artificial Intelligence (AI) algorithms in radiology practice is the actual integration of algorithms directly into the clinical Picture Archiving and Communications Systems (PACS). Here, we sought to integrate an AI-based pipeline for prostate organ and intraprostatic lesion segmentation within a clinical PACS environment to enable point-of-care utilization under a prospective clinical trial scenario.

Methods

A previously trained, publicly available AI model for segmentation of intra-prostatic findings on multiparametric Magnetic Resonance Imaging (mpMRI) was converted into a containerized environment compatible with MONAI Deploy Express. An inference server and dedicated clinical PACS workflow were established within our institution for evaluation of real-time use of the AI algorithm. PACS-based deployment was prospectively evaluated in two phases: first, a consecutive cohort of patients undergoing diagnostic imaging at our institution and second, a consecutive cohort of patients undergoing biopsy based on mpMRI findings. The AI pipeline was executed from within the PACS environment by the radiologist. AI findings were imported into clinical biopsy planning software for target definition. Metrics analyzing deployment success, timing, and detection performance were recorded and summarized.

Results

In phase one, clinical PACS deployment was successfully executed in 57/58 cases and were obtained within one minute of activation (median 33 s [range 21–50 s]). Comparison with expert radiologist annotation demonstrated stable model performance compared to independent validation studies. In phase 2, 40/40 cases were successfully executed via PACS deployment and results were imported for biopsy targeting. Cancer detection rates for prostate cancer were 82.1% for ROI targets detected by both AI and radiologist, 47.8% in targets proposed by AI and accepted by radiologist, and 33.3% in targets identified by the radiologist alone.

Conclusions

Integration of novel AI algorithms requiring multi-parametric input into clinical PACS environment is feasible and model outputs can be used for downstream clinical tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceProstatic NeoplasmsAlgorithmsMagnetic Resonance ImagingImage Interpretation, Computer-AssistedMultiparametric Magnetic Resonance ImagingHumansMaleRadiology Information SystemsProspective StudiesProstate

Stichwörter der Autor:innen

Artificial intelligenceDeep learningDeploymentMRIPACSProstate cancer

Autor:innen und Institutionen

  • National Institutes of Health, Bethesda, USA. stephanie.harmon@nih.gov.
  • Nvidia (United States), Santa Clara, USA.
  • National Institutes of Health, Bethesda, USA.
  • Philips (United States), Andover, USA.
  • National Institutes of Health, Bethesda, USA. turkbeyi@mail.nih.gov.

Förderung

  • National Institutes of Health

Zitieren

APA

Harmon, S. A., Tetreault, J., Esengur, O. T., Qin, M., Yilmaz, E. C., Chang, V., Yang, D., Xu, Z., Cohen, G., Plum, J., Sherif, T., Levin, R., Schmidt-Richberg, A., Thompson, S., Coons, S., Chen, T., Choyke, P. L., Xu, D., Gurram, S., …, & Turkbey, B. (2025). Research-based clinical deployment of artificial intelligence algorithm for prostate MRI. Abdominal Radiology. https://doi.org/10.1007/s00261-025-05014-7

Vancouver

Harmon SA, Tetreault J, Esengur OT, Qin M, Yilmaz EC, Chang V, et al. Research-based clinical deployment of artificial intelligence algorithm for prostate MRI. Abdominal Radiology. 2025. doi:10.1007/s00261-025-05014-7

BibTeX
@article{Harmon2025,
  author = {Harmon, Stephanie A and Tetreault, Jesse and Esengur, Omer Tarik and Qin, Ming and Yilmaz, Enis C and Chang, Victor and Yang, Dong and Xu, Ziyue and Cohen, Gregg and Plum, Jeff and Sherif, Testi and Levin, Ron and Schmidt-Richberg, Alexander and Thompson, Scott and Coons, Samuel and Chen, Te and Choyke, Peter L and Xu, Daguang and Gurram, Sandeep and Wood, Bradford J and Pinto, Peter A and Turkbey, Baris},
  title = {Research-based clinical deployment of artificial intelligence algorithm for prostate MRI},
  journal = {Abdominal Radiology},
  year = {2025},
  doi = {10.1007/s00261-025-05014-7}
}
Kostenlos starten →