# Deep learning-based automated quantification system for abdominal aortic calcification: multicenter cohort study for algorithm development and clinical validation

## TL;DR

This study developed an automated system using deep learning to measure abdominal aortic calcification, validated across multiple centers for accuracy and reliability in clinical settings.

## Contribution

A novel deep learning-based system for automated abdominal aortic calcification quantification with clinical validation across multiple centers.

## Key findings

- The automated system showed strong correlation with expert ratings (Spearman's ρ = 0.923 internally and 0.888 externally).
- The system achieved high inter-rater reliability (intraclass correlation coefficients of 0.913 internally and 0.874 externally).
- Stratification by calcification severity demonstrated high sensitivity and specificity across categories.

## Abstract

To establish an automated scoring system for abdominal aortic calcification (AAC) to facilitate standardized quantitative imaging analysis in support of clinical decision-making in atherosclerosis management.

x-ray images of the abdominal aorta were obtained for 2,941 individuals from five medical centers in Zhejiang Province. Calcification severity was graded manually using the Kauppila scoring system, and cases were stratified into three groups based on total calcification burden. The automated assessment framework comprised two sequential components: a lumbar spine segmentation model based on nnUnet and an AAC score regression model based on ResNet. Model development was conducted using 1,737 training cases, with internal validation in 471 cases and external validation in 733 cases from independent centers. A retrospective matched cohort study was conducted in 200 AAC patients from Center B (100 dialysis-dependent and 100 not dialysis-dependent cases), to investigate associations with major adverse cardiovascular events.

The developed automated quantification system demonstrated mean absolute errors of 1.686 (internal validation set) and 1.920 (external validation set), with strong correlation to expert ratings (Spearman's ρ = 0.923 and 0.888, respectively, both P < 0.001). Inter-rater reliability analysis revealed excellent agreement with manual scoring (intraclass correlation coefficients of 0.913 internally and 0.874 externally). Stratification based on calcification severity showed optimal sensitivity for the moderate calcification category (88.6%), with superior specificity for the non/mild (94.2%) and severe (91.5%) categories.

The established automated quantification system for AAC exhibits good assessment efficiency and measurement accuracy, offering a standardized approach to refine cardiovascular risk stratification in clinical practice.