Barón Jaime Rafael, Bernabé Gregorio, González-Férez Pilar, García José Manuel, Casas Guillem, González-Carrillo Josefa
Computer Engineering Department, University of Murcia, 30100 Murcia, Spain.
Hospital Universitari Vall d'Hbron, 08035 Barcelona, Spain.
J Clin Med. 2025 Jan 6;14(1):271. doi: 10.3390/jcm14010271.
Accurate segmentation of the left ventricular myocardium in cardiac MRI is essential for developing reliable deep learning models to diagnose left ventricular non-compaction cardiomyopathy (LVNC). This work focuses on improving the segmentation database used to train these models, enhancing the quality of myocardial segmentation for more precise model training. We present a semi-automatic framework that refines segmentations through three fundamental approaches: (1) combining neural network outputs with expert-driven corrections, (2) implementing a blob-selection method to correct segmentation errors and neural network hallucinations, and (3) employing a cross-validation process using the baseline U-Net model. Applied to datasets from three hospitals, these methods demonstrate improved segmentation accuracy, with the blob-selection technique boosting the Dice coefficient for the Trabecular Zone by up to 0.06 in certain populations. Our approach enhances the dataset's quality, providing a more robust foundation for future LVNC diagnostic models.
在心脏磁共振成像（MRI）中准确分割左心室心肌对于开发可靠的深度学习模型以诊断左心室致密化不全心肌病（LVNC）至关重要。这项工作专注于改进用于训练这些模型的分割数据库，提高心肌分割质量以进行更精确的模型训练。我们提出了一个半自动框架，通过三种基本方法来优化分割：（1）将神经网络输出与专家驱动的校正相结合；（2）实施一种斑点选择方法来纠正分割错误和神经网络幻觉；（3）使用基线U-Net模型进行交叉验证过程。将这些方法应用于来自三家医院的数据集，结果表明分割准确性得到了提高，在某些人群中，斑点选择技术使小梁区的Dice系数提高了多达0.06。我们的方法提高了数据集的质量，为未来的LVNC诊断模型提供了更坚实的基础。
