# Quantifying central canal stenosis prediction uncertainty in SpineNet with conformal prediction

## TL;DR

This paper uses conformal prediction to assess uncertainty in classifying spinal canal narrowing, finding that one method provides reliable and clinically useful results.

## Contribution

The study introduces conformal prediction for uncertainty quantification in central canal stenosis classification, comparing multiple methods and identifying the most effective one.

## Key findings

- Class-conditional conformal prediction achieved desired coverage with minimal prediction set size.
- Top-k and LAC/APS methods produced larger or less reliable prediction sets, especially for moderate and severe cases.
- Uncertainty was higher for less frequent moderate and severe grades, reflected in larger prediction sets.

## Abstract

This study applies conformal prediction (CP) to SpineNet to quantify prediction uncertainty in the classification of central canal stenosis (CCS) into four grades: normal, mild, moderate, and severe. CP provides prediction sets rather than singleton predictions with a guaranteed probability of containing the true class, offering a transparent way to assess model reliability. This makes CP particularly useful in the medical field, where reliable predictions are critical for decision-making. We analysed 1689 vertebral levels (L1/L2 to L5/S1) from 340 patients who underwent T2-weighted MRI examinations and evaluated four CP methods across multiple significance level. (α). Bootstrap resampling was used to assess robustness across calibration/test splits. Among the evaluated CP methods, the class-conditional CP method consistently achieved the desired coverage while producing the smallest prediction set siss. Top-k produced larger, uninformative prediction sets (~ 4), and Least Ambiguous Set-Valued Classifiers (LAC) and Adaptive Prediction Sets (APS) showed reduced performance, particularly in moderate and severe cases. A class- and level-specific analysis with class-conditional CP (α = 0.15) revealed smaller prediction sets for normal and mild grades (~ 1.5) and larger sets (~ 2.7–3) for less frequent moderate and severe grades, reflecting higher uncertainty in these categories. Overall class-conditional CP emerged as the most reliable and clinically informative approach for estimating uncertainty in CCS grading.

The online version contains supplementary material available at 10.1038/s41598-026-35343-6.