Hussain Lal, Saeed Sharjil, Awan Imtiaz Ahmed, Idris Adnan, Nadeem Malik Sajjad Ahmed, Chaudhry Qurat-Ul-Ain
Department of Computer Sciences & Information Technology, University of Azad Jammu and Kashmir, City Campus 13100, Muzaffarabad, Azad Kashmir, Pakistan.
Department of Computer Sciences & Information Technology, University of Poonch Rawalakot, Rawalakot, Pakistan.
Curr Med Imaging Rev. 2019;15(6):595-606. doi: 10.2174/1573405614666180718123533.
Brain tumor is the leading cause of death worldwide. It is obvious that the chances of survival can be increased if the tumor is identified and properly classified at an initial stage. MRI (Magnetic Resonance Imaging) is one source of brain tumors detection tool and is extensively used in the diagnosis of brain to detect blood clots. In the past, many researchers developed Computer-Aided Diagnosis (CAD) systems that help the radiologist to detect the abnormalities in an efficient manner.
The aim of this research is to improve the brain tumor detection performance by proposing a multimodal feature extracting strategy and employing machine learning techniques.
In this study, we extracted multimodal features such as texture, morphological, entropybased, Scale Invariant Feature Transform (SIFT), and Elliptic Fourier Descriptors (EFDs) from brain tumor imaging database. The tumor was detected using robust machine learning techniques such as Support Vector Machine (SVM) with kernels: polynomial, Radial Base Function (RBF), Gaussian; Decision Tree (DT), and Naïve Bayes. Most commonly used Jack-knife 10-fold Cross- Validation (CV) was used for testing and validation of dataset.
The performance was evaluated in terms of specificity, sensitivity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Positive Rate (FPR), Total Accuracy (TA), Area under the receiver operating Curve (AUC), and P-value. The highest performance of 100% in terms of Specificity, Sensitivity, PPV, NPV, TA, AUC using Naïve Bayes classifiers based on entropy, morphological, SIFT and texture features followed by Decision Tree classifier with texture features (TA=97.81%, AUC=1.0) and SVM polynomial kernel with texture features (TA=94.63%). The highest significant p-value was obtained using SVM polynomial with texture features (P-value 2.65e-104) followed by SVM RB with texture features (P-value 1.96e-98).
The results reveal that Naïve Bayes followed by Decision Tree gives highest detection accuracy based on entropy, morphological, SIFT and texture features.
脑肿瘤是全球主要的死亡原因。显然，如果在初始阶段识别并正确分类肿瘤，生存几率会增加。磁共振成像（MRI）是脑肿瘤检测工具的一种来源，广泛用于脑部诊断以检测血凝块。过去，许多研究人员开发了计算机辅助诊断（CAD）系统，帮助放射科医生高效检测异常。
本研究的目的是通过提出多模态特征提取策略并采用机器学习技术来提高脑肿瘤检测性能。
在本研究中，我们从脑肿瘤成像数据库中提取了多模态特征，如纹理、形态学、基于熵的、尺度不变特征变换（SIFT）和椭圆傅里叶描述符（EFD）。使用强大的机器学习技术检测肿瘤，如支持向量机（SVM），其核函数包括多项式、径向基函数（RBF）、高斯；决策树（DT）和朴素贝叶斯。最常用的留一法10折交叉验证（CV）用于数据集的测试和验证。
根据特异性、敏感性、阳性预测值（PPV）、阴性预测值（NPV）、假阳性率（FPR）、总准确率（TA）、受试者工作特征曲线下面积（AUC）和P值评估性能。基于熵、形态学、SIFT和纹理特征的朴素贝叶斯分类器在特异性、敏感性、PPV、NPV、TA、AUC方面表现最佳，达到100%，其次是具有纹理特征的决策树分类器（TA = 97.81%，AUC = 1.0）和具有纹理特征的SVM多项式核（TA = 94.63%）。使用具有纹理特征的SVM多项式获得最高的显著p值（P值2.65e - 104），其次是具有纹理特征的SVM RB（P值1.96e - 98）。
结果表明，基于熵、形态学、SIFT和纹理特征，朴素贝叶斯其次是决策树具有最高的检测准确率。
