Ordinal Multi-Instance Learning for Automated Multi-Task Grading of Lumbar Degenerative Conditions on Sagittal MRI, with External Validation
- 1Department of Orthopedics, The First Hospital of Lanzhou University, Lanzhou, China
Abstract
PurposeLumbar spine MRI interpretation requires 25 structured severity judgments per examination -- five degenerative conditions at five disc levels, each on a three-level ordinal scale -- a time-consuming task with substantial inter-reader variability. We developed and externally validated a model that automates this complete scheme.
Materials and MethodsA full-sequence multi-instance learning (MIL) model -- ResNet34 backbone, bidirectional GRU, attention pooling over 24 uniformly sampled sagittal T2-weighted slices -- with 25 cumulative-logit ordinal heads was trained on 1,204 examinations from the multi-institutional RSNA 2024 LumbarDISC dataset and internally validated on 213 held-out examinations. External validation used 60 retrospectively collected patients from an independent Chinese university hospital (four scanner vendors, radiology reports as the reference standard, no fine-tuning). Agreement was assessed with exact accuracy, sensitivity, specificity, McNemar tests, and patient-clustered bootstrap confidence intervals.
ResultsThe ordinal model achieved 51.4% balanced accuracy internally (exact accuracy 65.1%), versus 16.3% for a single-slice baseline; severe-grade AUCs averaged 0.908 across conditions. Externally, it outperformed its softmax-weighted counterpart on exact accuracy (0.649 vs. 0.586; +6.3 percentage points, 95% CI +2.7 to +10.0) and sensitivity (0.868 vs. 0.833), with markedly fewer severe-grade false alarms (69 vs. 172 predicted severe cells; McNemar p<0.0001).
ConclusionA full-sequence MIL model with ordinal outputs automates the complete 25-task grading scheme on sagittal MRI and, in the first hospital external validation of such a model, reduced severe-grade over-prediction under domain shift without loss of sensitivity -- supporting its role as a screening and triage aid.
SummaryAn ordinal full-sequence multi-instance learning model graded all 25 lumbar MRI degeneration tasks and markedly reduced severe-grade false alarms in 60-patient hospital validation without loss of sensitivity.
Key PointsO_LIFull-sequence attention was indispensable: balanced accuracy rose from 16.3% (single-slice baseline) to 51.4% over 24 sagittal slices. C_LIO_LIIn external validation, ordinal outputs reduced severe-grade predictions from 172 to 69 of 900 cells (McNemar p<0.0001) with comparable ranking ability (AUC 0.835 vs. 0.829). C_LIO_LIThe Moderate grade remained the hardest class across all conditions (AUC 0.70-0.78), tracking known inter-reader variability at the mild-moderate boundary. C_LI
Related
- Preserving a decade of machine-learning validity across a ground-up refactoring: a five-tier automated validation of RCT-Reviewer, an independent modernization of RobotReviewer
- Automated quantitative computed tomography grading of lumbar facet joint degeneration: influence of segmentation errors on instance-level clinical assessment.
- Multimodal Multiple Instance Learning for Fibroepithelial Tumor Diagnosis in Breast Ultrasound
- Weakly-Supervised Detection of Facial Motor Tics in Video Data Using Score-Driven Top-k Multiple Instance Learning
- FragMIL: A Fragment-Token Multiple-Instance Learning Framework for Cancer Detection from Cell-Free DNA Fragmentomics
BibTeX
@misc{geng2026ordinal,
title = {{Ordinal Multi-Instance Learning for Automated Multi-Task Grading of Lumbar Degenerative Conditions on Sagittal MRI, with External Validation}},
author = {S. Geng and Q. Miao and Q. Qin and H. Guo and X. Wang},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.20.26366005},
url = {https://www.medrxiv.org/content/10.64898/2026.10.20.26366005v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Ordinal Multi-Instance Learning for Automated Multi-Task Grading of Lumbar Degenerative Conditions on Sagittal MRI, with External Validation
AU - S. Geng
AU - Q. Miao
AU - Q. Qin
AU - H. Guo
AU - X. Wang
PY - 2026
DA - 2026/10/20
PB - medRxiv
DO - 10.64898/2026.10.20.26366005
UR - https://www.medrxiv.org/content/10.64898/2026.10.20.26366005v1
AB - PurposeLumbar spine MRI interpretation requires 25 structured severity judgments per examination -- five degenerative conditions at five disc levels, each on a three-level ordinal scale -- a time-consuming task with substantial inter-reader variability. We developed and externally validated a model that automates this complete scheme. Materials and MethodsA full-sequence multi-instance learning (MIL) model -- ResNet34 backbone, bidirectional GRU, attention pooling over 24 uniformly sampled sagittal T2-weighted slices -- with 25 cumulative-logit ordinal heads was trained on 1,204 examinations from the multi-institutional RSNA 2024 LumbarDISC dataset and internally validated on 213 held-out examinations. External validation used 60 retrospectively collected patients from an independent Chinese university hospital (four scanner vendors, radiology reports as the reference standard, no fine-tuning). Agreement was assessed with exact accuracy, sensitivity, specificity, McNemar tests, and patient-clustered bootstrap confidence intervals. ResultsThe ordinal model achieved 51.4% balanced accuracy internally (exact accuracy 65.1%), versus 16.3% for a single-slice baseline; severe-grade AUCs averaged 0.908 across conditions. Externally, it outperformed its softmax-weighted counterpart on exact accuracy (0.649 vs. 0.586; +6.3 percentage points, 95% CI +2.7 to +10.0) and sensitivity (0.868 vs. 0.833), with markedly fewer severe-grade false alarms (69 vs. 172 predicted severe cells; McNemar p<0.0001). ConclusionA full-sequence MIL model with ordinal outputs automates the complete 25-task grading scheme on sagittal MRI and, in the first hospital external validation of such a model, reduced severe-grade over-prediction under domain shift without loss of sensitivity -- supporting its role as a screening and triage aid. SummaryAn ordinal full-sequence multi-instance learning model graded all 25 lumbar MRI degeneration tasks and markedly reduced severe-grade false alarms in 60-patient hospital validation without loss of sensitivity. Key PointsO_LIFull-sequence attention was indispensable: balanced accuracy rose from 16.3% (single-slice baseline) to 51.4% over 24 sagittal slices. C_LIO_LIIn external validation, ordinal outputs reduced severe-grade predictions from 172 to 69 of 900 cells (McNemar p<0.0001) with comparable ranking ability (AUC 0.835 vs. 0.829). C_LIO_LIThe Moderate grade remained the hardest class across all conditions (AUC 0.70-0.78), tracking known inter-reader variability at the mild-moderate boundary. C_LI
ER -