当前位置: X-MOL 学术Concurr. Comput. Pract. Exp. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Brain tumor segmentation and overall survival period prediction in glioblastoma multiforme using radiomic features
Concurrency and Computation: Practice and Experience ( IF 2 ) Pub Date : 2021-07-21 , DOI: 10.1002/cpe.6501
Suchismita Das 1, 2 , Srijib Bose 2 , Gopal K. Nayak 1 , Suresh Chandra Satapathy 2 , Sanjay Saxena 1
Affiliation  

Glioblastoma multiforme (GBM or glioblastoma) is a fast-growing glioma that are the most invasive type of glial tumors, rapidly growing and commonly spreading into nearby brain tissue. Due to its aggressive and fast growing nature, patients suffer from high grade glioma (GBM) survive very less time as compare to other tumors. Prediction of patient survival (OS) time helps the radiologist for better systematic treatment planning and clinical decision making. The OS rate depends on the tumor size, shape, and different imaging features of brain. In this study, the OS period prediction was performed using Random Forest, SVM, XgBoost, and LGBM taking radiomic features which represents fused deep features and hand crafted features of the tumor. Efficiency of the prediction depends on the tumor volume that is segmented from the different MRI modalities. Hence the whole tumor and its sub tumor are extracted from multi-modal MR images using U-Net++ deep model and stacked together for deep features extraction using convolutional neural networks. To increase the accuracy, the features are reduced using PCA and then this radiomic feature set was used for OS period prediction. Prediction performance was evaluated for both 2-class and 3-class survival groups. The experiment was performed on well-known dataset BraTS 2017 and achieved a classification AUC value as 63% for 3-class classification and 2-class group using different classifier. Segmentation DOR is computed as 1269.29, 2033.99, and 648.00 for complete tumor, enhancing tumor, and necrotic tumor extraction, respectively. To achieve even more accuracy, bio inspired optimization methods GA and PSO are used on fused feature set. Finally, the method achieves the AUC score of 0.66 using fused feature+SVM+GA (3-class group) and 0.70 using fused feature+SVM+PSO (2-class group) which outperforms the state-of-the-art.

中文翻译:

利用放射组学特征对多形性胶质母细胞瘤进行脑肿瘤分割和总生存期预测

多形性胶质母细胞瘤(GBM 或胶质母细胞瘤)是一种快速生长的胶质瘤,是最具侵袭性的胶质瘤类型,生长迅速并通常扩散到附近的脑组织。由于其侵袭性和快速生长的性质,与其他肿瘤相比,患有高级别胶质瘤 (GBM) 的患者存活时间非常短。患者生存 (OS) 时间的预测有助于放射科医生更好地进行系统的治疗计划和临床决策。OS 率取决于肿瘤大小、形状和脑部不同的成像特征。在这项研究中,使用 Random Forest、SVM、XgBoost 和 LGBM 进行 OS 周期预测,采用放射组学特征表示融合的肿瘤深层特征和手工制作的特征。预测的效率取决于从不同 MRI 模式中分割出来的肿瘤体积。因此,使用 U-Net++ 深度模型从多模态 MR 图像中提取整个肿瘤及其子肿瘤,并使用卷积神经网络堆叠在一起以进行深度特征提取。为了提高准确性,使用 PCA 减少了这些特征,然后将此放射组学特征集用于 OS 周期预测。对 2 级和 3 级生存组的预测性能进行了评估。该实验在著名的数据集 BraTS 2017 上进行,使用不同分类器的 3 类分类和 2 类组的分类 AUC 值为 63%。对于完整肿瘤、增强肿瘤和坏死肿瘤提取,分割 DOR 分别计算为 1269.29、2033.99 和 648.00。为了获得更高的准确性,在融合特征集上使用了受生物启发的优化方法 GA 和 PSO。最后,
更新日期:2021-07-21
down
wechat
bug