EUVIMEDEUVIMED entdecken
Crossref

Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation

Venkatesh S Madhugiri, Dheerendra Prasad

Journal of Neuro-Oncology · 2025

DOI: 10.1007/s11060-024-04851-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neuro-Oncology, 2025. Verfasst von Venkatesh S Madhugiri und 1 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gamma Knife Radiosurgery, Department of Radiation Medicine, Roswell Park Cancer Institute, Elm and Carlton Streets, Buffalo, NY, 14203, U…. Hauptthemen laut MEDLINE: Brain Neoplasms, Artificial Intelligence, Magnetic Resonance Imaging. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: - Accurate detection, segmentation, and volumetric analysis of brain lesions are essential in neuro-oncology. Artificial intelligence (AI)-based models have improved the efficiency of these processes. This study evaluated an AI-based module for detecting and segmenting brain metastases, comparing it with manual detection and segmentation. METHODS: - MRIs from 51 patients treated with Gamma Knife radiosurgery for brain metastases were analyzed. Manual lesion identification and contouring on Leksell Gamma Plan at the time of treatment served as the gold standard. The same MRIs were processed through an AI-based module (Brainlab Smart Brush), and lesion detection and volumes were compared. Discrepancies were analyzed to identify possible sources of error. RESULTS: - Among 51 patients, 359 brain metastases were identified. The AI module achieved a sensitivity of 79.2% and a positive predictive value of 95.6%, compared to a 93.3% sensitivity for manual detection. However, for lesions > 0.1 cc, the AI's sensitivity rose to 97.5%, surpassing manual detection at 93%. Volumetric agreement between AI and manual segmentations was high (Spearman's ρ = 0.997, p < 0.001). Most lesions missed by the AI (53.8%) were near anatomical structures that complicated detection. CONCLUSIONS: - The AI module demonstrated higher sensitivity than manual detection for metastases larger than 0.1 cc, with robust volumetric accuracy. However, human expertise remains critical for detecting smaller lesions, especially near complex anatomical areas. AI offers significant potential to enhance neuro-oncology practice by improving the efficiency and accuracy of lesion management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsArtificial IntelligenceMagnetic Resonance ImagingHumansRadiosurgeryImage Processing, Computer-AssistedFemaleMaleMiddle Aged

Stichwörter der Autor:innen

Artificial intelligenceBrain metastasesLesion detectionSegmentationVolumetry

Autor:innen und Institutionen

  • Division of Gamma Knife Radiosurgery, Department of Radiation Medicine, Roswell Park Cancer Institute, Elm and Carlton Streets, Buffalo, NY, 14203, USA.
  • Division of Gamma Knife Radiosurgery, Department of Radiation Medicine, Roswell Park Cancer Institute, Elm and Carlton Streets, Buffalo, NY, 14203, USA. d.prasad@roswellpark.org.
  • Department of Neurosurgery, Roswell Park Comprehensive Cancer Center, Buffalo, USA. d.prasad@roswellpark.org.
  • Department of Neruosurgery, UB Jacobs School of Medicine and Biomedical Sciences, Buffalo, USA. d.prasad@roswellpark.org.

Zitieren

APA

Madhugiri, V. S., & Prasad, D. (2025). Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation. Journal of Neuro-Oncology. https://doi.org/10.1007/s11060-024-04851-8

Vancouver

Madhugiri VS, Prasad D. Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation. Journal of Neuro-Oncology. 2025. doi:10.1007/s11060-024-04851-8

BibTeX
@article{Madhugiri2025,
  author = {Madhugiri, Venkatesh S and Prasad, Dheerendra},
  title = {Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation},
  journal = {Journal of Neuro-Oncology},
  year = {2025},
  doi = {10.1007/s11060-024-04851-8}
}
Kostenlos starten →