FissureNet: A Deep Learning Approach For Pulmonary Fissure Detection in CT Images.
FissureNet: A Deep Learning Approach For Pulmonary Fissure Detection in CT Images.
复制标题
DOI：
10.1109/tmi.2018.2858202
复制
发表时间：
2019-01
影响因子：
10.6
通讯作者：
Reinhardt JM
中科院分区：
文献类型：
--
作者：
Gerard SE;Patton TJ;Christensen GE;Bayouth JE;Reinhardt JM
CT肺裂检测是肺自动分割的重要组成部分。大多数裂缝检测方法使用的特征描述符是手工制作的，低级别的，并具有局部空间范围。这种特征检测器的设计通常针对正常的裂隙解剖结构，对临床数据集中常见的弱和异常裂隙产生低灵敏度。此外，局部特征通常具有低特异性，因为当不考虑全局背景时，肺中的复杂纹理可能无法与裂隙区分开。我们提出了一个监督判别学习框架，同时进行特征提取和分类。所提出的框架称为FissureNet，是两个卷积神经网络的粗到细级联。从粗到细的策略消除了与训练网络以分割代表图像体素的一小部分的薄结构相关联的挑战。对来自COPDGene临床试验的吸气和呼气3DCT扫描的3706名受试者的队列和来自肺癌临床试验的4DCT扫描的20名受试者的队列评价了FissureNet。在这两个数据集上，与使用U-Net架构的深度学习方法和基于Hessian的裂缝检测方法相比，FissureNet在精确率-召回率曲线下的面积（PR-AUC）方面表现出上级性能。在COPDGene（肺癌）数据集上，FissureNet、U-Net和Hessian的总体PR-AUC分别为0.980（0.966）、0.963（0.937）和0.158（0.182）。在30个COPDGene扫描的子集上，将FissureNet与最近提出的称为棒的衍生物（DoS）的高级裂缝检测方法进行比较，并显示出上级性能，PR-AUC为0.991，而DoS为0.668。
Pulmonary fissure detection in computed tomography (CT) is a critical component for automatic lobar segmentation. The majority of fissure detection methods use feature descriptors that are hand-crafted, low-level, and have local spatial extent. The design of such feature detectors is typically targeted towards normal fissure anatomy, yielding low sensitivity to weak and abnormal fissures that are common in clinical datasets. Furthermore, local features commonly suffer from low specificity, as the complex textures in the lung can be indistinguishable from the fissure when global context is not considered. We propose a supervised discriminative learning framework for simultaneous feature extraction and classification. The proposed framework, called FissureNet, is a coarse-to-fine cascade of two convolutional neural networks. The coarse-to-fine strategy alleviates the challenges associated with training a network to segment a thin structure that represents a small fraction of the image voxels. FissureNet was evaluated on a cohort of 3706 subjects with inspiration and expiration 3DCT scans from the COPDGene clinical trial and a cohort of 20 subjects with 4DCT scans from a lung cancer clinical trial. On both datasets, FissureNet showed superior performance compared to a deep learning approach using the U-Net architecture and a Hessian-based fissure detection method in terms of area under the precision- recall curve (PR-AUC). The overall PR-AUC for FissureNet, U-Net, and Hessian on the COPDGene (lung cancer) dataset was 0.980 (0.966), 0.963 (0.937), and 0.158 (0.182), respectively. On a subset of 30 COPDGene scans, FissureNet was compared to a recently proposed advanced fissure detection method called derivative of sticks (DoS) and showed superior performance with a PR-AUC of 0.991 compared to 0.668 for DoS.