Publication date: May 30, 2025

This study develops a deep-learning method for automatic segmentation of the interventricular septum (IS) in MR images to measure myocardial T2* and estimate cardiac iron deposition in patients with thalassemia. This retrospective study used multiple-gradient-echo cardiac MR scans from 419 thalassemia patients to develop and evaluate the segmentation network. The network was trained on 1. 5 T images from Center 1 and evaluated on 3. 0 T unseen images from Center 1, all data from Center 2, and the CHMMOTv1 dataset. Model performance was assessed using five metrics, and T2* values were obtained by fitting the network output. Bland-Altman analysis, coefficient of variation (CoV), and regression analysis were used to evaluate the consistency between automatic and manual methods. MA-BBIsegNet achieved a Dice of 0. 90 on the internal test set, 0. 85 on the external test set, and 0. 81 on the CHMMOTv1 dataset. Bland-Altman analysis showed mean differences of 0. 08 (95% LoA: -2. 79 ∼ 2. 63) ms (internal), 0. 29 (95% LoA: -4. 12 ∼ 3. 54) ms (external) and 0. 19 (95% LoA: -3. 50 ∼ 3. 88) ms (CHMMOTv1), with CoV of 8. 9%, 6. 8%, and 9. 3%. Regression analysis yielded r values of 0. 98 for the internal and CHMMOTv1 datasets, and 0. 99 for the external dataset (p < 0. 05). The IS segmentation network based on multiple-gradient-echo bright-blood images yielded T2* values that were in strong agreement with manual measurements, highlighting its potential for the efficient, non-invasive monitoring of myocardial iron deposition in patients with thalassemia.

Semantics

Original Article