Skip to content
Open access

ncLVMass-Net: dedicated AI for left ventricular myocardium segmentation and hypertrophy detection from non-contrast cardiac CT

Oct 2026 · European Heart Journal · Vol 47 · 0 citations

Abstract

On non-contrast cardiac CT (NCCT) images, the left ventricular (LV) myocardium and blood pool share nearly identical attenuation, rendering endocardial boundary delineation infeasible. Publicly available AI models trained on contrast-enhanced CT (CECT) have been applied to NCCT for LV mass estimation, but their segmentation accuracy on this fundamentally different modality has not been rigorously validated. To develop and comprehensively evaluate ncLVMass-Net, a dedicated AI model for LV myocardium segmentation in NCCT, with respect to segmentation accuracy, LV mass estimation, subgroup consistency, and LV hypertrophy (LVH) detection. CECT-based myocardial annotations from 1,529 patients were transferred to paired NCCT images through rigorous three-dimensional non-rigid registration with systematic quality verification, creating a large-scale training dataset with pixel-level ground truth. ncLVMass-Net was developed using the nnU-Net framework and evaluated against TotalSegmentator, MOOSE 3.0, and Mask R-CNN on internal (N=190) and external (N=308, three hospitals) testing sets. Performance was assessed for both thick- and thin-slice NCCT images. ncLVMass-Net achieved a Dice similarity coefficient (DSC) of up to 0.88 in both internal and external testing, substantially outperforming TotalSegmentator (DSC: 0.78–0.83), MOOSE (DSC: 0.67–0.78), and Mask R-CNN (DSC: 0.74–0.77). For LV mass estimation, ncLVMass-Net achieved the lowest mean absolute error (internal: 4%; external: 6%), while other models demonstrated persistent over- or underestimation with errors exceeding 12%. ncLVMass-Net reduced bias magnitude by up to 91.5% and mean absolute error by up to 78.5% relative to CECT-trained models applied directly to NCCT. Unlike TotalSegmentator and MOOSE, which exhibited progressive underestimation with increasing LV mass, ncLVMass-Net demonstrated no mass-dependent bias and maintained consistent performance across subgroups dichotomized by LV size and myocardial volume (variation < 2.3% in mean absolute error). ncLVMass-Net achieved excellent agreement with ground truth (ICC > 0.9) and yielded a superior LVH detection F1-score of up to 0.9. A dedicated AI model can achieve accurate myocardial segmentation and quantification from NCCT despite the invisible endocardial boundary. ncLVMass-Net substantially outperforms publicly available models in segmentation, LV mass quantification, and LVH detection, enabling reliable LV mass quantification and LVH detection from routine NCCT.Figure

Read PDF

Similar papers

Conference Open access Oct 2026

Performance Comparison of Deep Learning Models for Multi-Structure Cardiac Segmentation in Two-Chamber Echocardiography Images

Two-dimensional echocardiography is a widely adopted non-invasive medical imaging modality for the assessment of cardiac structure and function. However, manual delineation of cardiac boundaries remains a time-consuming task requiring substantial clinical expertise. This study presents a comparative evaluation of three...

Atithep Kaone, Phichamon Intra, Theerasak Chanwimalueang et al. · 0 citations
Open access Oct 2026

Cardiac CT foundation model for whole-heart segmentation: integrating human-in-the-loop and self-supervised learning

Cardiac computed tomography (CCT) provides high-resolution data essential for personalized medicine and clinical evaluations; however, manual segmentation of cardiac structures is prohibitively time-consuming and prone to intra- and inter-observer variability. To manually label a comprehensive, multi-cente...

P. M. Kazaj, L. Weber, W. Xie et al. · 0 citations
Sep 2026

Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation

The approach enabled low-error NWU quantification from baseline NCCT without advanced imaging, supporting further prospective clinical evaluation and targeting NCCT-only infarct segmentation across heterogeneous external cohorts, although performance varied across domains.

Linus Britt, M. Nielsen, S. Klapproth et al. · 0 citations
Open access Nov 2026

Machine Learning Multiclass Models Based on Cardiac Segmentation Quantitative Parameters from Non-Contrast and Contrast-Enhanced Chest CT for the Differential Diagnosis of Acute Chest Pain

Objectives: Acute coronary syndrome (ACS), pulmonary embolism (PE), and aortic dissection (AD) present with overlapping symptoms but require markedly different treatments. We investigated whether cardiac quantitative parameters obtained by automated segmentation of non-contrast and contrast-enhanced chest CT can suppor...

Shuo Liang, Zhong-Yun Liu, Dan Li et al. · 0 citations
Open access Nov 2026

An End-to-End Cardiac MRI Segmentation and Multi-Class Pathology Classification Pipeline Using Ensemble U-Net Models and Explainable Machine Learning

Accurate delineation of cardiac structures in cardiac magnetic resonance (CMR) images is a prerequisite for quantifying cardiac function. This paper presents an end-to-end pipeline for automated cardiac segmentation and five-class pathology classification, evaluated on the 150 patients of the Automated Cardiac Diagnosi...

Alina Georgiana Badea, I. Tache, Lidia Băjenaru et al. · 0 citations
Open access Oct 2026

Opportunistic volume assessment of left ventricular volume from coronary CT angiography: agreement with cardiac MRI

Heart failure frequently remains undiagnosed until advanced stages. Automated extraction of cardiac chamber volumes from routine CCTA may enable opportunistic identification of patients at risk of ventricular remodeling without additional imaging or radiation. However, large-scale validation studies against cardi...

H. Lind, J. Kragballe, F. Fossan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.