Automatic segmentation, classification, and follow-up of optic pathway gliomas using deep learning and fuzzy c-means clustering based on MRI
Automatic segmentation, classification, and follow-up of optic pathway gliomas using deep learning and fuzzy c-means clustering based on MRI
复制标题
DOI：
10.1002/mp.14489
复制
发表时间：
2020-10-08
期刊：
影响因子：
3.8
通讯作者：
Ben Bashat, Dafna
中科院分区：
文献类型：
--
作者：
Artzi, Moran;Gershov, Sapir;Ben Bashat, Dafna
目的视神经胶质瘤（Optic pathway glioma，OPG）是一种低度恶性的毛细胞型星形细胞瘤，占儿童颅内肿瘤的3-5%。使用磁共振成像（MRI）对OPG进行准确和定量随访对于治疗决策至关重要，但由于这些肿瘤的复杂形状和异质组织模式，因此具有挑战性。本研究的目的是实现基于MRI的OPG及其组分的自动分割和分类方法。方法回顾性分析29例视交叉OPG患者的202例MRI表现。数据包括T（2）和增强后T（1）加权图像。由高级神经放射科医师手动注释整个肿瘤体积及其组成部分，并在扫描子集中评估整个肿瘤体积的评估者间和评估者内变异性。使用U-Net+ResNet架构的深度学习方法进行自动肿瘤分割。一个五重交叉验证计划被用来评估相对于手动分割的自动结果。使用模糊c均值聚类将肿瘤基于体素分类为增强、非增强和囊性成分。结果肿瘤自动分割结果为：验证数据的平均骰子得分= 0.736 +/- 0.025，精确度= 0.918 +/- 0.014，召回率= 0.635 +/- 0.039，骰子得分= 0.761 +/- 0.011，精确度= 0.794 +/- 0.028，并且对于测试数据，召回率= 0.742 +/-0.012。基于体素的肿瘤成分分类的准确性为0.94，对于非增强、增强和囊性成分，精确度分别为0.89、0.97和0.85，召回率分别为1.00、0.79和0.94。结论本研究提出了一种基于常规MRI的视交叉OPG肿瘤自动分割和分类的方法。这些肿瘤的自动定量纵向评估可以改善放射学监测，促进疾病进展的早期检测和优化治疗管理。
Purpose Optic pathway gliomas (OPG) are low-grade pilocytic astrocytomas accounting for 3-5% of pediatric intracranial tumors. Accurate and quantitative follow-up of OPG using magnetic resonance imaging (MRI) is crucial for therapeutic decision making, yet is challenging due to the complex shape and heterogeneous tissue pattern which characterizes these tumors. The aim of this study was to implement automatic methods for segmentation and classification of OPG and its components, based on MRI. Methods A total of 202 MRI scans from 29 patients with chiasmatic OPG scanned longitudinally were retrospectively collected and included in this study. Data included T(2)and post-contrast T(1)weighted images. The entire tumor volume and its components were manually annotated by a senior neuro-radiologist, and inter- and intra-rater variability of the entire tumor volume was assessed in a subset of scans. Automatic tumor segmentation was performed using deep-learning method with U-Net+ResNet architecture. A fivefold cross-validation scheme was used to evaluate the automatic results relative to manual segmentation. Voxel-based classification of the tumor into enhanced, non-enhanced, and cystic components was performed using fuzzy c-means clustering. Results The results of the automatic tumor segmentation were: mean dice score = 0.736 +/- 0.025, precision = 0.918 +/- 0.014, and recall = 0.635 +/- 0.039 for the validation data, and dice score = 0.761 +/- 0.011, precision = 0.794 +/- 0.028, and recall = 0.742 +/- 0.012 for the test data. The accuracy of the voxel-based classification of tumor components was 0.94, with precision = 0.89, 0.97, and 0.85, and recall = 1.00, 0.79, and 0.94 for the non-enhanced, enhanced, and cystic components, respectively. Conclusion This study presents methods for automatic segmentation of chiasmatic OPG tumors and classification into the different components of the tumor, based on conventional MRI. Automatic quantitative longitudinal assessment of these tumors may improve radiological monitoring, facilitate early detection of disease progression and optimize therapy management.