Thesis I · Sacral MRI · Sep 2025 – Mar 2026
Automatic lumbosacral vertebra localization in variable field-of-view pelvic MRI
A Deep Learning Approach for Variable Field-of-View Pelvic Imaging
4.21 mm
Mean Localization Error
257 landmarks, multi-center
3.77 mm
S1 Anchor Error
100% within 10 mm
3.54 mm
Median Error
Across all protocols
222
Training Cases
Protocol II + III
The Problem This Work Solves
Accurate lumbosacral vertebrae localization in pelvic MRI is clinically critical for spinal surgery planning, radiation therapy field definition, endometriosis staging, and large-scale morphometric studies. Yet existing automated methods fundamentally fail in this setting — they assume full spinal visibility from C2 or T1, which is never available in pelvic MRI.
In pelvic imaging, the spine appears only incidentally: 84.7% of cases show partial or sacral-only coverage. No prior work had addressed individual S1–S5 sacral vertebra detection in this context, leaving a critical gap in automated pelvic MRI analysis.
The Innovation: S1-Anchored Detection
The core insight is that pelvic MRI always captures the S1 vertebra — it is the anatomical bridge between the sacrum and the pelvis. Rather than requiring a superior reference (the conventional approach), this work proposes making S1 the anchor point for bidirectional vertebral labeling, implemented through a novel two-stage system:
Dual-Head 3D U-Net: A lightweight architecture (~400K parameters) with a shared encoder-decoder and two task-specific output heads — one detecting all vertebral centers, one dedicated to S1 morphology. Joint training enables the model to learn both global vertebral patterns and S1-specific anatomy simultaneously.
S1-Anchored Post-Processing: A multi-stage inference pipeline that detects S1 from its dedicated heatmap, then propagates labels bidirectionally — cranially through lumbar vertebrae and caudally through sacral segments — without any need for upper vertebrae to be present in the scan.
Biased Patch Sampling: 70% of training patches are drawn from high-activity heatmap regions, forcing the model to learn from challenging anatomical boundaries rather than uniform sampling.
Architecture
Inference Pipeline
Dual-Head 3D U-Net
Shared Encoder
Head 1 · All Vertebrae
Head 2 · S1 Dedicated
S1-Anchored Post-Processing
Per-Vertebra Results
| Vertebra | Mean Error | ≤5 mm | ≤10 mm | Bar |
|---|---|---|---|---|
| L4 | 4.36 mm | 70.0% | 90.0% | |
| L5 | 3.65 mm | 78.9% | 97.4% | |
| S1 (Anchor) | 3.77 mm | 75.0% | 100% | |
| S2 | 4.33 mm | 75.0% | 97.7% | |
| S3 | 3.54 mm | 83.7% | 97.7% | |
| S4 | 4.79 mm | 69.2% | 89.7% | |
| S5 | 5.25 mm | 62.5% | 87.5% |
S1 anchor achieved 100% detection within 10 mm across all 44 test instances. S4–S5 show higher variance due to progressive developmental fusion.
Contextualized Against Prior Work
| Method | Setting | Performance |
|---|---|---|
| Existing methods | Require full spinal visibility (C2/T1 reference) | Not applicable |
| Glocker et al. (CT) | Full-spine CT, regression forests | 8.6 mm |
| Windsor et al. (MRI) | Spine-dedicated MRI, full FOV | 2–4 mm (lumbar only) |
| This work | Pelvic MRI, partial FOV, all sacral levels | 4.21 mm (L1–S5, multi-center) |
Results are within the range of spine-dedicated methods despite operating on a fundamentally harder problem: partial spinal coverage, lower through-plane resolution, and variable patient positioning.
Clinical Impact & Future Directions
This is the first published method for individual S1–S5 sacral vertebra detection in pelvic MRI, enabling:
Reproducible lumbosacral morphometry in gynecological imaging workflows — reducing inter-reader variability in surgical and radiotherapy planning.
Observer-independent spinal measurements at population scale unlocking large-scale epidemiological studies previously blocked by manual bottlenecks.
A modular building block for joint pelvic analysis systems that co-localize vertebral and uterine anatomy from a single MRI acquisition.
Future work is planned toward a unified pelvic MRI framework that jointly predicts both spinal and uterine landmarks, leveraging the geometric relationship between the sacrum and uterus to mutually constrain predictions.