【使用cnn降低假正率】Pulmonary Nodule Detection in CT Images笔记
来源:互联网 发布:大数据可以研究什么 编辑:程序博客网 时间:2024/06/03 16:52
论文全文
INTRODUCTION
这篇文章提出了一种针对肺部结节的CAD系统(Computer-Aided Detection),不仅可以提高正确率,而且降低了假正率。
通常一个CAD系统由两部分组成:nodule candidates detection and false positive reduction. 并且False positives are subsequently reduced in a second stage, which determine most of the performance of CAD systems.
这个系统是由几个cnn网络组合而成。
MATERIALS
介绍训练和交叉验证数据集
LIDC-IDRI
ANODE09
DLCST
METHODS
Candidates Detection
determines the maximum detection sensitivity of subsequent stages.
因为结节形态和大小的差异,将其分成三种:solid nodules,subsolid nodules,Large solid nodules。不同的类有不同的算法,同一个目标三个算法都送入,最后合并三类的结果。
solid nodules
implemented the technique proposed by Murphy et al
具体来说,计算每个三维像素的shape index and curvedness,找出种子点,再将距离近的种子点合并成簇,最后丢弃小的簇。
subsolid nodules
implemented the technique proposed by Jacobs et al
key words:
density mask mask
Morphological opening 先腐蚀后膨胀的过程称为开运算。用来消除小物体、在纤细点处分离物体、平滑较大物体的边界的同时并不明显改变其面积
Large solid nodules
前面两种算法在这种肿瘤上表现不好。另外,由于它胸膜的对比度低,附着在胸膜上的大结节可以用lung segmentation algorithms来排除。we implemented a third detector that consists of three steps.
由于数据的不平衡,分类器可能会倾向常见的组织(比如血管)而忽略肿瘤。为防止过拟合,我们丢弃可能性低的。阈值根据经验设定。
Patches Extraction
从50* 50 * 50mm的立方体中提取图一(b)中的六个特定视角的二维图像
For each candidate,50*50mm,64 64 px;分辨率:0.78 mm,同时对灰度值也有要求。
False Positive Reduction: 2-D Convnets Configuration
The false positive reduction stage is constructed by combining various streams of ConvNets
卷积神经网络的number of views和fusion method在LIDC-IDRI上学习得到,结构是连续的三个卷积层加上一个全连接层。网络结构参见原文图2.
CNN介绍
False Positive Reduction: Convnets Fusion
这里作者调查了三种组合卷积神经网络的方式。注意Mixed-Fusion方法的输入必须是一组正交平面。
Training
888 LIDC-IDRI cases
Data Augmentation
- Training Data Augmentation
改变训练图像的大小以及对正样本过采样。 - Test-Data Augmentation
Test-data augmentation (TDA) is performed on each candidate (both nodule and non-nodule classes) by rescaling the patches to
40, 45, 50, and 55 mm
Evaluation
AUC和CMP(在不同误报次数下的召回率情况)
EXPERIMENTAL RESULTS
这一节介绍的是实验结果。
1. fusing models (late-fusion) 的结果比较好。
2. system trained with both contrast and non-contrast scans always
achieves better performance
3. performance of ConvNets improvement when more
views are considered in the architecture
DISCUSSION
这篇文章提出的CAD系统的创新之处在于,利用CNN避免了在降低假正率阶段的人工提取特征和分类。
1. 表1表明combining multiple candidate detection algorithms boosts the detection sensitivity from 85.7% to 93.3% while maintaining a similar number of false positives.
2. Fig. 3(c) shows that incorporating more views in the architecture allows the network to achieve better performance
3. combiner together with other parts of the network gives the best performance
进一步可以:
1. Improvement of the candidate detection algorithm can substantially increase the overall performance of CAD systems, which is planned as future work
2. At 4 FPs/scan, most of undetected nodules are subsolid nodules or nodules with irregular shape.Further data balancing on nodule categories is expected to significantly improve the performance
3. Information from 3-D input data could be exploited to train the ConvNets, even though this would increase the network complexity.
4. Another interesting direction that might also improve performance is by adding features that could not be extracted from patches
- 【使用cnn降低假正率】Pulmonary Nodule Detection in CT Images笔记
- 论文阅读笔记:DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
- 《Pedestrain detection in Infrared Images》
- 《Vehicle Detection in High-Resolution Aerial Images via Sparse Representation and Superpixels》论文笔记
- 《Vehicle Detection in High-Resolution Aerial Images Based on Fast Sparse Representation ...》论文笔记
- CT之cnn
- CT图之cnn
- USING DEEP LEARNING FOR ANOMALY DETECTION IN RADIOLOGICAL IMAGES
- (Paper)Robust Text Detection in Natural Scene Images
- Sliding Shapes for 3D Object Detection in Depth Images
- (Paper)Robust Text Detection in Natural Scene Images
- caffe学习笔记12 -- R-CNN detection
- 【object detection】R-cnn论文笔记
- 论文阅读:Automatic Detection and Classication of Teeth in CT Data
- saliency detection by forward and backward cues in deep-cnn
- Object Detection:R-CNN、Fast R-CNN、Faster R-CNN论文阅读笔记
- [深度学习论文笔记][Object Detection] Fast R-CNN
- 阅读笔记:Gated Bi-directional CNN for Object Detection
- java实现Excel将数据传进数据库中
- 简单日期类操作(c++)
- 互联网金融违约和个人信用的个人理解
- Hdu 1229 还是A+B
- Android中使用HelloChart开源库图表来实现折线图
- 【使用cnn降低假正率】Pulmonary Nodule Detection in CT Images笔记
- 正则匹配手机号中段
- c++动态内存管理
- windows下线程同步
- MySQL:ERROR 1820 (HY000)
- 以太网,IP,TCP,UDP数据包分析
- do{...}while(0)的意义
- 使用webpack搭建一个react项目
- 文章标题 HihoCoder