[论文解读] A New Deep Hybrid Boosted and Ensemble Learning-based Brain Tumor Analysis using MRI

Mirza Mumtaz Zahoor, Shahzad Ahmad Qureshi+2 more|arXiv (Cornell University)|Jan 14, 2022

Brain Tumor Detection and Classification被引用 5

一句话总结

本文提出了一种用于MRI扫描中脑肿瘤分析的两阶段深度混合提升与集成学习框架。首先通过深度提升特征和集成分类器（DBF-EC）检测肿瘤，准确率达到99.56%；随后通过融合动态（BRAIN-RENet）和静态（HOG）特征对肿瘤类型进行分类，准确率达到99.20%，在基准数据集上优于当前最先进方法。

ABSTRACT

Brain tumors analysis is important in timely diagnosis and effective treatment to cure patients. Tumor analysis is challenging because of tumor morphology like size, location, texture, and heteromorphic appearance in the medical images. In this regard, a novel two-phase deep learning-based framework is proposed to detect and categorize brain tumors in magnetic resonance images (MRIs). In the first phase, a novel deep boosted features and ensemble classifiers (DBF-EC) scheme is proposed to detect tumor MRI images from healthy individuals effectively. The deep boosted feature space is achieved through the customized and well-performing deep convolutional neural networks (CNNs), and consequently, fed into the ensemble of machine learning (ML) classifiers. While in the second phase, a new hybrid features fusion-based brain tumor classification approach is proposed, comprised of dynamic-static feature and ML classifier to categorize different tumor types. The dynamic features are extracted from the proposed BRAIN-RENet CNN, which carefully learns heteromorphic and inconsistent behavior of various tumors, while the static features are extracted using HOG. The effectiveness of the proposed two-phase brain tumor analysis framework is validated on two standard benchmark datasets; collected from Kaggle and Figshare containing different types of tumor, including glioma, meningioma, pituitary, and normal images. Experimental results proved that the proposed DBF-EC detection scheme outperforms and achieved accuracy (99.56%), precision (0.9991), recall (0.9899), F1-Score (0.9945), MCC (0.9892), and AUC-PR (0.9990). While the classification scheme, the joint employment of the deep features fusion of proposed BRAIN-RENet and HOG features improves performance significantly in terms of recall (0.9913), precision (0.9906), F1-Score (0.9909), and accuracy (99.20%) on diverse datasets.

研究动机与目标

• 解决由于形态差异、大小、位置和纹理不同导致的MRI扫描中脑肿瘤检测与分类的挑战。
• 通过结合基于深度学习的特征提取与集成机器学习分类器，提高检测准确率。
• 通过融合新型CNN（BRAIN-RENet）的动态特征与手工提取的HOG特征，提升肿瘤分类性能。
• 在包含胶质母细胞瘤、脑膜瘤、垂体瘤和正常病例的多样化公开MRI数据集上验证该框架。

提出的方法

• 提出一种两阶段框架：第一阶段进行肿瘤检测，第二阶段进行肿瘤类型分类。
• 在第一阶段，使用定制化的CNN提取深度提升特征，随后输入到一组机器学习分类器（DBF-EC）中进行肿瘤检测。
• 在第二阶段，从一种名为BRAIN-RENet的新型CNN中提取动态特征，该网络可建模异质性肿瘤行为，同时使用方向梯度直方图（HOG）提取静态特征。
• 将动态与静态特征进行融合，并输入到机器学习分类器中进行肿瘤类型分类。
• 该框架在来自Kaggle和Figshare的两个基准数据集上进行训练与评估，涵盖多种脑肿瘤类型。
• 第一阶段的集成分类器通过组合多个基学习器，提升肿瘤检测的鲁棒性与泛化能力。

实验结果

研究问题

• RQ1 与现有方法相比，混合深度学习与集成学习方法是否能提升MRI扫描中脑肿瘤检测的准确性？
• RQ2 动态特征（BRAIN-RENet）与静态特征（HOG）的融合在分类不同脑肿瘤类型方面效果如何？
• RQ3 所提出的DBF-EC方案在肿瘤检测中相较于单一分类器的性能提升程度如何？
• RQ4 该框架在具有不同肿瘤形态和成像协议的多样化MRI数据集上是否具备良好的泛化能力？

主要发现

• DBF-EC检测方案实现了99.56%的准确率、0.9991的精确率、0.9899的召回率、0.9945的F1-Score、0.9892的马修斯相关系数（MCC）以及0.9990的AUC-PR。
• 采用BRAIN-RENet与HOG特征融合的混合分类模型实现了99.20%的准确率、0.9906的精确率、0.9913的召回率以及0.9909的F1-Score。
• 所提出的框架在Kaggle和Figshare基准数据集上均表现出优越性能，证实了其鲁棒性与泛化能力。
• AUC-PR达到0.9990，表明肿瘤检测的精确率-召回率性能接近完美，凸显其高度可靠性。