State Key Laboratory of Brain and Cognitive Science, Institute of Biophysics, Chinese Academy of Sciences, 100101, Beijing, China.
Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, 230088, Hefei, China.
Eur Radiol Exp. 2024 Nov 5;8(1):126. doi: 10.1186/s41747-024-00512-7.
We developed a framework for segmenting and modeling lenticulostriate arteries (LSAs) on 7-T time-of-flight magnetic resonance angiography and tested its performance on cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) patients and controls.
We prospectively included 29 CADASIL patients and 21 controls. The framework includes a small-patch convolutional neural network (SP-CNN) for fine segmentation, a random forest for modeling LSAs, and a screening model for removing wrong branches. The segmentation performance of our SP-CNN was compared to competitive networks. External validation with different resolution was performed on ten patients with aneurysms. Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each network and manual segmentation were calculated. The modeling results of the centerlines, diameters, and lengths of LSAs were compared against manual labeling by four neurologists.
The SP-CNN achieved higher DSC (92.741 ± 2.789, mean ± standard deviation) and lower HD (0.610 ± 0.141 mm) in the segmentation of LSAs. It also outperformed competitive networks in the external validation (DSC 82.6 ± 5.5, HD 0.829 ± 0.143 mm). The framework versus manual difference was lower than the manual inter-observer difference for the vessel length of primary branches (median -0.040 mm, interquartile range -0.209 to 0.059 mm) and secondary branches (0.202 mm, 0.016-0.537 mm), as well as for the offset of centerlines of primary branches (0.071 mm, 0.065-0.078 mm) and secondary branches (0.072, 0.064-0.080 mm), with p < 0.001 for all comparisons.
Our framework for LSAs modeling/quantification demonstrated high reliability and accuracy when compared to manual labeling.
NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ).
The proposed automatic segmentation and modeling framework offers precise quantification of the morphological parameters of lenticulostriate arteries. This innovative technology streamlines diagnosis and research of cerebral small vessel disease, eliminating the burden of manual labeling, facilitating cohort studies and clinical diagnosis.
The morphology of LSAs is important in the diagnosis of CSVD but difficult to quantify. The proposed algorithm achieved the performance equivalent to manual labeling by neurologists. Our method can provide standardized quantitative results, reducing radiologists' workload in cohort studies.
我们开发了一种在 7T 时飞磁共振血管造影上分割和建模纹状体动脉（LSAs）的框架，并在 CADASIL 患者和对照组中对其进行了测试。
我们前瞻性纳入了 29 名 CADASIL 患者和 21 名对照。该框架包括用于精细分割的小补丁卷积神经网络（SP-CNN）、用于建模 LSAs 的随机森林以及用于去除错误分支的筛选模型。我们的 SP-CNN 的分割性能与竞争网络进行了比较。对十名患有动脉瘤的患者进行了不同分辨率的外部验证。计算了每个网络与手动分割之间的 Dice 相似系数（DSC）和 Hausdorff 距离（HD）。将 LSAs 的中心线、直径和长度的建模结果与四名神经科医生的手动标记进行了比较。
SP-CNN 在 LSAs 的分割中实现了更高的 DSC（92.741±2.789，平均值±标准差）和更低的 HD（0.610±0.141mm）。它在外部验证中的表现也优于竞争网络（DSC 82.6±5.5，HD 0.829±0.143mm）。与手动标记相比，框架与手动标记之间的差异低于手动观察者之间的差异，用于主支的血管长度（中位数-0.040mm，四分位距-0.209 至 0.059mm）和次支（0.202mm，0.016 至 0.537mm），以及主支中心线的偏移量（0.071mm，0.065 至 0.078mm）和次支（0.072，0.064 至 0.080mm），所有比较的 p 值均小于 0.001。
与手动标记相比，我们用于 LSAs 建模/量化的框架表现出较高的可靠性和准确性。
NCT05902039（https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039）。
所提出的自动分割和建模框架提供了纹状体动脉形态参数的精确量化。这项创新技术简化了脑小血管疾病的诊断和研究，消除了手动标记的负担，促进了队列研究和临床诊断。
LSAs 的形态在 CSVD 的诊断中很重要，但很难量化。所提出的算法通过神经科医生实现了与手动标记相当的性能。我们的方法可以提供标准化的定量结果，减轻放射科医生在队列研究中的工作量。
