OpenSpineConsortium: An Open-Source Framework for Medical Student Engagement in Computational Spine Imaging Research.

INTRODUCTION: Research experience is heavily weighted in competitive specialties, yet preclinical schedules constrain student bandwidth. Prior work shows students acquire coding skills quickly and that imaging-based curricula engage them in scholarship, but programs are institution-bound and rarely couple anatomical learning with authentic computational contribution. This initiative combines open-source spine imaging datasets, Python coding, and a consortium model targeting a clinically high-impact anatomic region. METHODS: OpenSpineConsortium (OSC) is a distributed, open-source collaborative unifying public imaging collections into documented, openly licensed datasets, supporting anatomy-aware machine learning for the spine and pelvis. For medical students, this translated into analyzing spine CTs, annotating anatomical structures, and learning to automatically extract clinically useful parameters. Onboarding covers spine anatomy, segmentation, Python, and reproducible workflows. Students completed scoped sub-projects with senior-trainee mentorship. A post-participation survey assessed self-reported skill gains, scholarly output, and specialty interest. RESULTS: A total of 10 sub-projects span 16 contributors. Self-reported comfort (five-point scale) improved significantly across all six domains (Wilcoxon, all p<0.05), with the largest gains in CT spine interpretation (1.8-3.3, p<0.001), anatomic landmark/pathology identification (2.0-3.2, p<0.001), and Python coding (1.3-2.6, p<0.001). Conference submission, abstract writing, and literature reading also improved significantly. Eight of 16 reported increased interest in neurosurgery and 11 of 16 in research-oriented careers. All 16 would recommend OSC. CONCLUSIONS: OSC produced significant gains in spine anatomy, computational proficiency, and scientific communication alongside 10 scholarly projects, supporting a scalable, low-cost model bridging anatomical education, computational training, and authentic contribution within medical school's time constraints.