当前位置: X-MOL 学术Cogn. Syst. Res. › 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.)
Convolutional Neural Network for Brain Tumor Detection using MRI
Cognitive Systems Research ( IF 2.1 ) Pub Date : 2020-01-01 , DOI: 10.1016/j.cogsys.2019.10.002
Javaria Amin , Muhammad Sharif , Muhammad Almas Anjum , Mudassar Raza , Syed Ahmad Chan Bukhari

Abstract Accurate glioma detection using magnetic resonance imaging (MRI) is a complicated job. In this research, deep learning model is presented for glioma and stroke lesion detection. The proposed architecture consists of 14 layers. The first input layer is followed by three convolutional layers while 5th, 6th and 7th layers correspond to batch normalization, followed by next three layers of rectified linear unit (ReLU). Eleventh layer is average pooling 2D which is followed by fully connected (FC), softmax and classification layers respectively. The presented method is verified on six MICCAI databases namely multimodal brain tumor segmentation (BRATS) 2013, 2014, 2015, 2016, 2017 and sub-acute ischemic stroke lesion segmentation (SISS-ISLES) 2015. The computational time is also measured across each benchmark dataset such as 53 s on BRATS 2013, 26 s on BRATS 2014, 41 s on BRATS 2015, 36 s on BRATS 2016, and 38 s on BRATS 2017 and 4.13 s on ISLES 2015 proving that the proposed technique has less processing time. The proposed method achieved 0.9943 ACC, 1.00 SP, 0.9839 SE on BRATS 2013, 0.9538 ACC, 0.9991 SP, 0.7196 SE on BRATS 2014, 0.9978 ACC, 1.00 SP, 0.9919 SE on BRATS 2015, 0.9569 ACC, 0.9491 SP, 0.9755 SE on BRAST 2016, 0.9778 ACC, 0.9770 SP, 0.9789 SE on BRATS 2017 and 0.9227 ACC, 1.00 SP, 0.8814 SP on ISLES 2015 datasets respectively.

中文翻译:

使用 MRI 进行脑肿瘤检测的卷积神经网络

摘要 使用磁共振成像 (MRI) 进行准确的胶质瘤检测是一项复杂的工作。在这项研究中,提出了用于神经胶质瘤和中风病变检测的深度学习模型。建议的架构由 14 层组成。第一个输入层之后是三个卷积层,而第 5、6 和 7 层对应于批量归一化,然后是接下来的三层整流线性单元 (ReLU)。第十一层是平均池化 2D,其后分别是全连接 (FC)、softmax 和分类层。所提出的方法在六个 MICCAI 数据库上得到验证,即多模式脑肿瘤分割 (BRATS) 2013、2014、2015、2016、2017 和亚急性缺血性中风病变分割 (SISS-ISLES) 2015。计算时间也在每个基准上进行测量数据集,例如 BRATS 2013 上的 53 s,BRATS 2014 为 26 秒,BRATS 2015 为 41 秒,BRATS 2016 为 36 秒,BRATS 2017 为 38 秒,ISLES 2015 为 4.13 秒,证明所提出的技术具有更少的处理时间。所提出的方法在 BRATS 2013 上实现了 0.9943 ACC,1.00 SP,0.9839 SE,在 BRATS 2014 上实现了 0.9538 ACC,0.9991 SP,0.7196 SE,在 BRATS 2014 上实现了 0.9978 ACC,1.00 SP,2095 上 SE095, SE095 ACC.SE905.SE。 2016 年,BRATS 2017 上的 0.9778 ACC、0.9770 SP、0.9789 SE 和 ISLES 2015 数据集上的 0.9227 ACC、1.00 SP、0.8814 SP。
更新日期:2020-01-01
down
wechat
bug