Conus Medullaris Position in 9,808 Pediatric Lumbosacral MRI Examinations: A Large-Cohort Reference Distribution and the Normally Positioned Conus in Surgically Treated Tethered Cord

Background

Tethered cord syndrome (TCS) is classically associated with a low-lying conus medullaris, yet many surgically treated children have a normally positioned conus (“occult” TCS). Large-scale normative data on conus position in children, and the diagnostic value of quantitative conus assessment, are limited.

Purpose

To establish a large-cohort reference distribution for conus medullaris termination level in children, to quantify conus position in children surgically treated for presumed (occult) TCS, and to test whether automated conus segmentation and radiomics can distinguish TCS from normal.

Materials and Methods

In this retrospective single-center study, conus termination level was extracted from structured radiology reports of consecutive pediatric lumbosacral MRI examinations and encoded numerically (L1 = 1, L2 = 2, …). Children surgically treated for tethered cord were identified by linkage to an operative registry (name and date of birth) and restricted to preoperative examinations. A deep-learning model (nnU-Net) was trained for conus segmentation on axial T2-weighted images. IBSI-compliant radiomic features were extracted; reproducibility was assessed by intra- and inter-observer intraclass correlation (ICC). A case–control radiomics analysis used batch-only ComBat harmonization and cross-validated L1-penalized logistic regression; discrimination was compared with conus level by paired bootstrap.

Results

Among 9,808 examinations with a parseable conus level (98.5% of reports; parser validated against dual blinded annotation, 99.4% agreement, κ 0.946), the conus terminated in the L1 region in 85.7% and the L2 region in 14.3% of the reference cohort (postoperative examinations excluded, n = 9,655); a low-lying conus (≥L3) occurred in only 0.05% (5/9,655), and remained rare (0.14%, 14/9,808) including operated examinations (median L1; mean 1.13 ± 0.33). A slightly more cephalad position was seen with increasing age (negligible correlation). Among 475 preoperative children surgically treated for tethered cord, 99.6% had a normally positioned conus (≤L2) and only 0.4% were low-lying. Automated conus segmentation achieved a held-out Dice of 0.85. Conus radiomics likewise did not distinguish TCS from controls (equivalence-tested null; full segmentation/radiomics pipeline reported in the companion methodological paper).

Conclusion

In children, the conus medullaris terminates at L1–L2 in more than 99% of cases and is normally positioned in virtually all children surgically treated for TCS. Within the conus, neither position nor texture (radiomics) identifies tethered cord; whether the filum terminale carries a diagnostic signal was not tested here.

Key Results

• In a reference cohort of 9,655 children (postoperative examinations excluded; conus level by a validated parser), the conus terminated in the L1 region (85.7%) or L2 region (14.3%); a low-lying conus (≥L3) occurred in only 0.05% (0.14% including operated examinations).

• Among 475 preoperative children surgically treated for tethered cord, 99.6% had a normally positioned conus, consistent with a radiologically occult presentation.

• Automated conus segmentation (Dice 0.85) was deployed cohort-wide; quantitative conus texture (radiomics) likewise did not discriminate tethered cord (full pipeline in the companion paper).