当前位置: X-MOL 学术Med. Biol. Eng. Comput. › 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.)
An efficient brain tumor image classifier by combining multi-pathway cascaded deep neural network and handcrafted features in MR images
Medical & Biological Engineering & Computing ( IF 2.6 ) Pub Date : 2021-06-29 , DOI: 10.1007/s11517-021-02370-6
Abhishek Bal 1 , Minakshi Banerjee 2 , Rituparna Chaki 1 , Punit Sharma 3
Affiliation  

Accurate segmentation and delineation of the sub-tumor regions are very challenging tasks due to the nature of the tumor. Traditionally, convolutional neural networks (CNNs) have succeeded in achieving most promising performance for the segmentation of brain tumor; however, handcrafted features remain very important in identification of tumor’s boundary regions accurately. The present work proposes a robust deep learning–based model with three different CNN architectures along with pre-defined handcrafted features for brain tumor segmentation, mainly to find out more prominent boundaries of the core and enhanced tumor regions. Generally, automatic CNN architecture does not use the pre-defined handcrafted features because it extracts the features automatically. In this present work, several pre-defined handcrafted features are computed from four MRI modalities (T2, FLAIR, T1c, and T1) with the help of additional handcrafted masks according to user interest and fed to the convolutional features (automatic features) to improve the overall performance of the proposed CNN model for tumor segmentation. Multi-pathway CNN is explored in this present work along with single-pathway CNN, which extracts simultaneously both local and global features to identify the accurate sub-regions of the tumor with the help of handcrafted features. The present work uses a cascaded CNN architecture, where the outcome of a CNN is considered as an additional input information to next subsequent CNNs. To extract the handcrafted features, convolutional operation was applied on the four MRI modalities with the help of several pre-defined masks to produce a predefined set of handcrafted features. The present work also investigates the usefulness of intensity normalization and data augmentation in pre-processing stage in order to handle the difficulties related to the imbalance of tumor labels. The proposed method is experimented on the BraST 2018 datasets and achieved promising results than the existing (currently published) methods with respect to different metrics such as specificity, sensitivity, and dice similarity coefficient (DSC) for complete, core, and enhanced tumor regions. Quantitatively, a notable gain is achieved around the boundaries of the sub-tumor regions using the proposed two-pathway CNN along with the handcrafted features.



中文翻译:

通过结合多通路级联深度神经网络和 MR 图像中的手工特征,一种高效的脑肿瘤图像分类器

由于肿瘤的性质,亚肿瘤区域的准确分割和描绘是非常具有挑战性的任务。传统上,卷积神经网络 (CNN) 在脑肿瘤分割方面取得了最有希望的性能;然而,手工制作的特征在准确识别肿瘤边界区域方面仍然非常重要。目前的工作提出了一个强大的基于深度学习的模型,该模型具有三种不同的 CNN 架构以及用于脑肿瘤分割的预定义手工特征,主要是为了找出核心和增强肿瘤区域的更突出边界。通常,自动 CNN 架构不使用预定义的手工特征,因为它会自动提取特征。在目前的工作中,几个预定义的手工特征是根据用户兴趣从四种 MRI 模态(T2、FLAIR、T1c 和 T1)计算出来的,借助额外的手工掩模根据用户兴趣并馈送到卷积特征(自动特征)以提高整体性能提出了用于肿瘤分割的CNN模型。在目前的工作中探索了多通路 CNN 和单通路 CNN,单通路 CNN 同时提取局部和全局特征,以在手工特征的帮助下识别肿瘤的准确子区域。目前的工作使用级联 CNN 架构,其中 CNN 的结果被视为下一个后续 CNN 的附加输入信息。为了提取手工制作的特征,在几个预定义掩码的帮助下,将卷积运算应用于四种 MRI 模态,以产生一组预定义的手工特征。目前的工作还研究了强度归一化和数据增强在预处理阶段的有用性,以处理与肿瘤标签不平衡相关的困难。所提出的方法在 BraST 2018 数据集上进行了实验,并在完整、核心和增强的肿瘤区域的特异性、灵敏度和骰子相似系数 (DSC) 等不同指标方面取得了比现有(当前发布的)方法有希望的结果。从数量上讲,使用所提出的双通路 CNN 以及手工制作的特征,在亚肿瘤区域的边界周围实现了显着的增益。目前的工作还研究了强度归一化和数据增强在预处理阶段的有用性,以处理与肿瘤标签不平衡相关的困难。所提出的方法在 BraST 2018 数据集上进行了实验,并在完整、核心和增强的肿瘤区域的特异性、灵敏度和骰子相似系数 (DSC) 等不同指标方面取得了比现有(当前发布的)方法有希望的结果。从数量上讲,使用所提出的双通路 CNN 以及手工制作的特征,在亚肿瘤区域的边界周围实现了显着的增益。目前的工作还研究了强度归一化和数据增强在预处理阶段的有用性,以处理与肿瘤标签不平衡相关的困难。所提出的方法在 BraST 2018 数据集上进行了实验,并在完整、核心和增强的肿瘤区域的特异性、灵敏度和骰子相似系数 (DSC) 等不同指标方面取得了比现有(当前发布的)方法有希望的结果。从数量上讲,使用所提出的双通路 CNN 以及手工制作的特征,在亚肿瘤区域的边界周围实现了显着的增益。所提出的方法在 BraST 2018 数据集上进行了实验,并在完整、核心和增强的肿瘤区域的特异性、灵敏度和骰子相似系数 (DSC) 等不同指标方面取得了比现有(当前发布的)方法有希望的结果。从数量上讲,使用所提出的双通路 CNN 以及手工制作的特征,在亚肿瘤区域的边界周围实现了显着的增益。所提出的方法在 BraST 2018 数据集上进行了实验,并在完整、核心和增强的肿瘤区域的特异性、灵敏度和骰子相似系数 (DSC) 等不同指标方面取得了比现有(当前发布的)方法有希望的结果。从数量上讲,使用所提出的双通路 CNN 以及手工制作的特征,在亚肿瘤区域的边界周围实现了显着的增益。

更新日期:2021-06-29
down
wechat
bug