Application of innovative image processing methods and AdaBound-SE-DenseNet to optimize the diagnosis performance of meningiomas and gliomas. (May 2020)

• Record Type: Journal Article
• Authors: Huang, Zheng; Zhao, Yiwen; Li, Xin; Zhao, Xingang; Liu, Yunhui; Song, Guoli; Luo, Yang
• Is Part Of: Biomedical signal processing and control. Volume 59(2020)
• Publication Date: 2020-05
• Subjects: Brain tumors -- Brain region extraction -- Iterative gamma correction -- AdaBound-SE-DenseNet; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.101926
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel multi-directional brain region extraction method (MDBRE) method is proposed to remove the disturbances of skulls and background. A novel iterative gamma correction based on two peaks (TPGC) is proposed to narrow the illumination variances among brain images. The advantages of DenseNet, SE blocks and AdaBound are combined to form an AD-SE-DenseNet that can contribute to improving the diagnosis performance. More than 4800 original brain images are employed to diagnosis meningiomas, gliomas and normal for the first time. The experimental results indicate that the proposed system can achieve the state-of-the-art performance. Abstract: With the development of artificial intelligence, numerous computer-aided diagnosis systems (CADSs) have been proposed to diagnosis meningiomas and gliomas automatically. However, most current systems not only ignore the large intra-class variances among original brain images, but also employ small databases with expensive labeling costs; as a result, the performances of most CADSs are well below expectations. To optimize the diagnosis performance of meningiomas and gliomas, novel image processing methods, including a novel multi-directional brain region extraction (MDBRE) method and an iterative gamma correction based on two peaks (TPGC), are proposed to narrow the intra-class variances, and a pre-trained AdaBound-SE-DenseNet (AD-SE-DenseNet) is presented to avoid over-fitting. First, innovative image processing methods, including a novel MDBER and a novel TPGC, are applied to remove the disturbances of skulls and brightness variances. Then, data augmentation technologies are applied to produce a larger database and a pretrained AD-SE-DenseNet is introduced to train the classifier. The experimental results indicate that the accuracy of this system can reach 96.87%. Implementing the innovative image processing methods and AD-SE-DenseNet can lead to a nearly 8% and 1.7% accuracy improvement, respectively.