EUVIMEDEUVIMED entdecken
Crossref

Zero-shot segmentation of spinal vertebrae with metastatic lesions: an analysis of Meta’s Segment Anything Model 2 and factors affecting learning free segmentation

Rushmin Khazanchi, Sachin Govind, Rishi Jain, Rebecca Du, Nader S Dahdaleh, Christopher S Ahuja, Najib El Tecle

Neurosurgical Focus · 2025

DOI: 10.3171/2025.4.focus25234 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurosurgical Focus, 2025. Verfasst von Rushmin Khazanchi und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Spinal Neoplasms, Deep Learning, Spine. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE Accurate vertebral segmentation is an important step in imaging analysis pipelines for diagnosis and subsequent treatment of spinal metastases. Segmenting these metastases is especially challenging given their radiological heterogeneity. Conventional approaches for segmenting vertebrae have included manual review or deep learning; however, manual review is time-intensive with interrater reliability issues, while deep learning requires large datasets to build. The rise of generative AI, notably tools such as Meta’s Segment Anything Model 2 (SAM 2), holds promise in its ability to rapidly generate segmentations of any image without pretraining (zero-shot). The authors of this study aimed to assess the ability of SAM 2 to segment vertebrae with metastases. METHODS A publicly available set of spinal CT scans from The Cancer Imaging Archive was used, which included patient sex, BMI, vertebral locations, types of metastatic lesion (lytic, blastic, or mixed), and primary cancer type. Ground-truth segmentations for each vertebra, derived by neuroradiologists, were further extracted from the dataset. SAM 2 then produced segmentations for each vertebral slice without any training data, all of which were compared to gold standard segmentations using the Dice similarity coefficient (DSC). Relative performance differences were assessed across clinical subgroups using standard statistical techniques. RESULTS Imaging data were extracted for 55 patients and 779 unique thoracolumbar vertebrae, 167 of which had metastatic tumor involvement. Across these vertebrae, SAM 2 had a mean volumetric DSC of 0.833 ± 0.053. SAM 2 performed significantly worse on thoracic vertebrae relative to lumbar vertebrae, female patients relative to male patients, and obese patients relative to non-obese patients. CONCLUSIONS These results demonstrate that general-purpose segmentation models like SAM 2 can provide reasonable vertebral segmentation accuracy with no pretraining, with efficacy comparable to previously published trained models. Future research should include optimizations of spine segmentation models for vertebral location and patient body habitus, as well as for variations in imaging quality approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spinal NeoplasmsDeep LearningSpineHumansFemaleMaleTomography, X-Ray ComputedMiddle AgedAged

Stichwörter der Autor:innen

Dice similarity coefficientartificial intelligencecomputer visionmachine learningradiologyspinetumor

Zitieren

APA

Khazanchi, R., Govind, S., Jain, R., Du, R., Dahdaleh, N. S., Ahuja, C. S., & El Tecle, N. (2025). Zero-shot segmentation of spinal vertebrae with metastatic lesions: an analysis of Meta’s Segment Anything Model 2 and factors affecting learning free segmentation. Neurosurgical Focus. https://doi.org/10.3171/2025.4.focus25234

Vancouver

Khazanchi R, Govind S, Jain R, Du R, Dahdaleh NS, Ahuja CS, et al. Zero-shot segmentation of spinal vertebrae with metastatic lesions: an analysis of Meta’s Segment Anything Model 2 and factors affecting learning free segmentation. Neurosurgical Focus. 2025. doi:10.3171/2025.4.focus25234

BibTeX
@article{Khazanchi2025,
  author = {Khazanchi, Rushmin and Govind, Sachin and Jain, Rishi and Du, Rebecca and Dahdaleh, Nader S and Ahuja, Christopher S and El Tecle, Najib},
  title = {Zero-shot segmentation of spinal vertebrae with metastatic lesions: an analysis of Meta’s Segment Anything Model 2 and factors affecting learning free segmentation},
  journal = {Neurosurgical Focus},
  year = {2025},
  doi = {10.3171/2025.4.focus25234}
}
Kostenlos starten →