Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia.
Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia.
Eur Radiol. 2024 Sep;34(9):5816-5828. doi: 10.1007/s00330-024-10630-w. Epub 2024 Feb 10.
To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI.
Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4.
The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data.
A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development.
A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection.
• A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.
开发并分享一种深度学习方法，以便能够从多供应商、多机构和多场强反转预扫描（TI 预扫描）序列中准确识别心脏 MRI 晚期钆增强的最佳反转时间（TI）。
对来自四个中心和三个扫描仪供应商的 1136 例 1.5T 和 3T 心脏 MRI 检查进行回顾性多中心研究。深度学习模型由卷积神经网络（CNN）和长短时记忆网络（LSTM）组成，在中心 1 至 3 的 TI 预扫描像素数据上进行训练，以识别最佳 TI，使用两位读者的地面真实注释。准确性在 50ms 以内，平均绝对误差（MAE）、Lin 的一致性系数（LCCC）和简化主要轴回归（RMAR）用于从验证结果中选择最佳模型，并应用于保留测试数据。还在中心 4 的成像数据上测试了表现最佳模型的稳健性。
最佳模型（SE-ResNet18-LSTM）在保留测试集上的准确率为 96.1%，MAE 为 22.9ms，LCCC 为 0.47，与地面真实值相比；在对未见的外部（中心 4）数据进行测试时，准确率为 97.3%，MAE 为 15.2ms，LCCC 为 0.64。观察到供应商性能的差异，在训练数据中最常见的供应商的准确性最高。
开发了一种深度学习模型，可以从多供应商数据的 TI 预扫描图像中以高精度识别最佳反转时间，包括以前未见的外部数据。我们将此模型提供给科学界进行进一步评估或开发。
一种用于晚期钆增强成像的稳健自动反转时间选择工具，可以实现跨供应商的可重复和高效反转时间选择。
开发了一种由卷积和递归神经网络组成的模型，用于从 TI 预扫描图像中提取最佳 TI。
在多供应商保留和外部数据上，模型的准确性分别达到了 50ms 以内的地面真实值，分别为 96.1%和 97.3%。
该模型可以提高工作流程效率，并为一致的 LGE 成像标准化最佳 TI 选择。
