jung diagnostics GmbH, Hamburg, Germany.
Institute of Diagnostic and Interventional Neuroradiology, University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.
Eur Radiol. 2023 Mar;33(3):1852-1861. doi: 10.1007/s00330-022-09170-y. Epub 2022 Oct 20.
OBJECTIVES: To develop an automatic method for accurate and robust thalamus segmentation in T1w-MRI for widespread clinical use without the need for strict harmonization of acquisition protocols and/or scanner-specific normal databases. METHODS: A three-dimensional convolutional neural network (3D-CNN) was trained on 1975 T1w volumes from 170 MRI scanners using thalamus masks generated with FSL-FIRST as ground truth. Accuracy was evaluated with 18 manually labeled expert masks. Intra- and inter-scanner test-retest stability were assessed with 477 T1w volumes of a single healthy subject scanned on 123 MRI scanners. The sensitivity of 3D-CNN-based volume estimates for the detection of thalamus atrophy was tested with 127 multiple sclerosis (MS) patients and a normal database comprising 4872 T1w volumes from 160 scanners. The 3D-CNN was compared with a publicly available 2D-CNN (FastSurfer) and FSL. RESULTS: The Dice similarity coefficient of the automatic thalamus segmentation with manual expert delineation was similar for all tested methods (3D-CNN and FastSurfer 0.86 ± 0.02, FSL 0.87 ± 0.02). The standard deviation of the single healthy subject's thalamus volume estimates was lowest with 3D-CNN for repeat scans on the same MRI scanner (0.08 mL, FastSurfer 0.09 mL, FSL 0.15 mL) and for repeat scans on different scanners (0.28 mL, FastSurfer 0.62 mL, FSL 0.63 mL). The proportion of MS patients with significantly reduced thalamus volume was highest for 3D-CNN (24%, FastSurfer 16%, FSL 11%). CONCLUSION: The novel 3D-CNN allows accurate thalamus segmentation, similar to state-of-the-art methods, with considerably improved robustness with respect to scanner-related variability of image characteristics. This might result in higher sensitivity for the detection of disease-related thalamus atrophy. KEY POINTS: • A three-dimensional convolutional neural network was trained for automatic segmentation of the thalamus with a heterogeneous sample of T1w-MRI from 1975 patients scanned on 170 different scanners. • The network provided high accuracy for thalamus segmentation with manual segmentation by experts as ground truth. • Inter-scanner variability of thalamus volume estimates across different MRI scanners was reduced by more than 50%, resulting in increased sensitivity for the detection of thalamus atrophy.
目的：开发一种自动方法，以便在不严格协调采集协议和/或扫描仪特定正常数据库的情况下，在广泛的临床应用中准确、稳健地对 T1w-MRI 中的丘脑进行分割。
方法：使用 FSL-FIRST 生成的丘脑掩模作为地面实况，在来自 170 台 MRI 扫描仪的 1975 个 T1w 容积上训练三维卷积神经网络（3D-CNN）。使用 18 个手动标记的专家掩模评估准确性。使用单个健康受试者的 477 个 T1w 容积评估扫描仪内和扫描仪间的测试-再测试稳定性，该受试者在 123 台 MRI 扫描仪上进行了扫描。使用 127 名多发性硬化症（MS）患者和包含来自 160 台扫描仪的 4872 个 T1w 容积的正常数据库测试基于 3D-CNN 的体积估计对丘脑萎缩的检测灵敏度。将 3D-CNN 与公开可用的 2D-CNN（FastSurfer）和 FSL 进行比较。
结果：与所有测试方法（3D-CNN 和 FastSurfer 0.86 ± 0.02，FSL 0.87 ± 0.02）相比，自动丘脑分割与手动专家勾画的 Dice 相似系数相似。同一 MRI 扫描仪上重复扫描时，单个健康受试者的丘脑体积估计的标准偏差最低（3D-CNN 为 0.08 mL，FastSurfer 为 0.09 mL，FSL 为 0.15 mL），在不同扫描仪上重复扫描时（3D-CNN 为 0.28 mL，FastSurfer 为 0.62 mL，FSL 为 0.63 mL）。3D-CNN 检测到的 MS 患者丘脑体积显著减少的比例最高（24%，FastSurfer 为 16%，FSL 为 11%）。
结论：新型 3D-CNN 可实现准确的丘脑分割，与最先进的方法相似，但对图像特征与扫描仪相关的可变性具有显著提高的稳健性。这可能导致对疾病相关的丘脑萎缩的检测灵敏度更高。
关键点： • 基于来自 1975 名患者的 T1w-MRI 的异质样本，使用三维卷积神经网络对丘脑进行自动分割，这些患者在 170 台不同的扫描仪上进行了扫描。 • 该网络提供了以专家手动分割作为地面实况的高精度丘脑分割。 • 通过减少超过 50%的跨不同 MRI 扫描仪的丘脑体积估计的扫描仪间可变性，提高了对丘脑萎缩的检测灵敏度。
Brain Struct Funct. 2024-6
Neuroimage Clin. 2018-12-10
Hum Brain Mapp. 2024-12-15
Fluids Barriers CNS. 2024-7-12
Int J Comput Assist Radiol Surg. 2024-9
Brain Struct Funct. 2024-6
Front Neurol. 2021-2-5
Neuroimage. 2020-10-1
Neuroimage. 2020-10-1
Zotero 插件
