Work

Brain-Mets-Seg UCSF External Validation

Year: 2026

Type: software

Abstract: Manuscript-supporting release for the UCSF external validation of SPIRS-P1. This release contains the analysis code, de-identified derived results, model provenance, patient-clustered sensitivity analyses, lesion-count reconciliation, boundary metrics, source-blinded clinician-review analysis, and supplementary-analysis outputs supporting the submitted manuscript, Size- and Burden-Stratified External Validation of Brain Metastasis Segmentation on 324 UCSF Imaging Studies. Imaging data and model weights are not redistributed in this repository. SPIRS-P1 model code and weights are available separately through QTIM-Lab/Brain-Mets-Seg. Licensed under the BSD 3-Clause License.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.22114219

Authors: Patel, Jay B., Quinones Alvarado, Raymond, Hanaoka, Mauro, Tu, Long, Marin, Thibault, Johnson, Jason M.

Topic: Medical Image Segmentation Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

OpenAlex ID: W7204261160

Cites:

Cited by:

Related to: