AI Science Tracker
EN

An MRI system classifies lumbar disc herniation in held-out patients

Tianjin Medical University General Hospital · 30 May 2024 · medicine

Discovery

An MRI system classifies lumbar disc herniation in held-out patients

Source check: Source checked. Not independent scientific confirmation.

Finding: A learned MRI pipeline localized discs, detected herniation and assigned severity categories using data from 217 patients, including 33 held-out patients. The study reported high internal agreement with expert reference labels. Its reader experiment sampled images from both development and test data, so it does not provide independent evidence that clinical readers benefit from the system. External validation remains needed.

Technology: Faster R-CNN; convolutional neural network; U-Net

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Faster R-CNN localizes discs, a neural classifier detects herniation and U-Net-derived regions support severity classification.
Test and result
Patient-separated development/test diagnostic classification against expert MRI labels.
Limitation / still unknown
External accuracy and independent reader-assistance benefit remain unestablished; reader-study images overlapped the development pool.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11137648/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 21 Nov 2026. Review scope: Primary relevant Methods/results/limitations and exact front/canonical identity; current primary PubMed linked correction/retraction metadata checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.