当前位置:网站首页>[paper reading] cavemix: a simple data augmentation method for brain vision segmentation
[paper reading] cavemix: a simple data augmentation method for brain vision segmentation
2022-07-04 23:54:00 【xiongxyowo】
[ Address of thesis ][ Code ][MICCAI 21]
Abstract
Segmentation of brain lesions (Brain Lesion Segmentation) It provides a valuable tool for clinical diagnosis , Convolutional neural networks (CNN) We have achieved unprecedented success in this task . Data enhancement is a widely used strategy , Can improve CNN Training effect , The design of enhancement methods for brain lesion segmentation is still an open problem . In this work , We propose a simple data enhancement method , go by the name of CarveMix, Used based on CNN Segmentation of brain lesions . With others based on " blend " The same way , Such as Mixup and CutMix,CarveMix Randomly combine two existing marker images to generate new marker samples . However , Different from these image combination based enhancement strategies ,CarveMix It is disease perception , Pay attention to pathological changes when combining , And create appropriate annotations for the generated image . say concretely , According to the location and geometry of the lesion , Carve a region of interest from a marked image (ROI),ROI The size of is sampled from a probability distribution . then , Carved ROI It replaces the corresponding voxel in the second marked image , The annotation of the second image is also replaced accordingly . In this way , We generate new tagged images for network training , And the lesion information is preserved . In order to evaluate the proposed method , We conducted experiments on two brain lesion datasets . It turns out that , Compared with other simple data enhancement methods , Our method improves the accuracy of segmentation .
Method
This paper is a data enhancement method specially proposed for brain lesion segmentation ——CarveMix. This method is also a method based on label fusion , such as MixUp(ICLR 18) Is to fuse the two labels linearly , and CarveMix(ICCV 19) It is a kind of nonlinear fusion . It should be noted that , These classical methods are used for image classification tasks , Therefore, there is a lack of label fusion methods for segmentation tasks .CarveMix The integration process of is as follows :
First look at the formula directly : Fused image X \mathbf{X} X And the label obtained by fusion Y \mathbf{Y} Y The final calculation process of is as follows : X = X i ⊙ M i + X j ⊙ ( 1 − M i ) \mathbf{X}=\mathbf{X}_{i} \odot \mathbf{M}_{i}+\mathbf{X}_{j} \odot\left(1-\mathbf{M}_{i}\right) X=Xi⊙Mi+Xj⊙(1−Mi) Y = Y i ⊙ M i + Y j ⊙ ( 1 − M i ) \mathbf{Y}=\mathbf{Y}_{i} \odot \mathbf{M}_{i}+\mathbf{Y}_{j} \odot\left(1-\mathbf{M}_{i}\right) Y=Yi⊙Mi+Yj⊙(1−Mi) For the sake of intuition , We take label fusion as an example to show the specific fusion process , The fusion of image itself is consistent with the fusion of label . Seen from the figure , The fusion of labels is basically equivalent to directly merging two original images mask Y i \mathbf{Y}_i Yi and Y j \mathbf{Y}_j Yj Add it up directly :
In fact, it is Y i \mathbf{Y}_i Yi Multiplied by a factor a a a After and Y j \mathbf{Y}_j Yj Multiplied by a factor b b b And then add up , Yes a + b = 1 a+b=1 a+b=1. In the figure "⊙" The symbol represents pixel by pixel , So you can even put M i \mathbf{M}_i Mi As a spatial attention map .
The problem now is actually how to calculate M i \mathbf{M}_i Mi 了 . As you can see from the diagram , M i \mathbf{M}_i Mi And Y i \mathbf{Y}_i Yi In fact, it is very similar , It's a bit like in M i \mathbf{M}_i Mi An expansion operation is carried out on the basis of . say concretely , M i \mathbf{M}_i Mi pass the civil examinations j j j A pixel value M i v \mathbf{M}_i^v Miv The calculation method is as follows : M i v = { 1 , D v ( Y i ) ≤ λ 0 , otherwise \mathbf{M}_{i}^{v}=\left\{\begin{array}{l} 1, D^{v}\left(\mathbf{Y}_{i}\right) \leq \lambda \\ 0, \text { otherwise } \end{array}\right. Miv={ 1,Dv(Yi)≤λ0, otherwise D v ( Y i ) = { − d ( v , ∂ Y i ) , if Y i v = 1 d ( v , ∂ Y i ) , if Y i v = 0 D^{v}\left(\mathbf{Y}_{i}\right)=\left\{\begin{aligned} -d\left(v, \partial \mathbf{Y}_{i}\right), & \text { if } \mathbf{Y}_{i}^{v}=1 \\ d\left(v, \partial \mathbf{Y}_{i}\right), & \text { if } \mathbf{Y}_{i}^{v}=0 \end{aligned}\right. Dv(Yi)={ −d(v,∂Yi),d(v,∂Yi), if Yiv=1 if Yiv=0 This d ( v , ∂ Y i ) d(v, \partial \mathbf{Y}_{i}) d(v,∂Yi) Refers to the current pixel v v v And " Lesion boundary " ∂ Y i \partial \mathbf{Y}_{i} ∂Yi Distance of . You can see , If v v v Itself is in the lesion area , that D v ( Y i ) D^{v}\left(\mathbf{Y}_{i}\right) Dv(Yi) Just give a negative number , So as to ensure that it has a greater probability of being selected ( That is less than λ \lambda λ); And if it is outside the lesion area , We think that the closer we are, the more we should be selected . It is worth noting that , This λ \lambda λ It's positive and negative , So as to ensure the pathological area " inflation " perhaps " shrinkage ". λ \lambda λ The specific calculation process of is more complex , Interested readers can read the original .
边栏推荐
- Acrel-EMS综合能效平台在校园建设的意义
- Pict generate orthogonal test cases tutorial
- S32 design studio for arm 2.2 quick start
- Jar batch management gadget
- 【雅思阅读】王希伟阅读P4(matching2段落信息配对题【困难】)
- Hong Kong Jewelry tycoon, 2.2 billion "bargain hunting" Giordano
- 人脸识别5- insight-face-paddle-代码实战笔记
- MariaDB's Galera cluster application scenario -- multi master and multi active databases
- French scholars: the explicability of counter attack under optimal transmission theory
- OSEK standard ISO_ 17356 summary introduction
猜你喜欢
Solution record of jamming when using CAD to move bricks in high configuration notebook
壁仞科技研究院前沿技术文章精选
机器人强化学习——Learning Synergies between Pushing and Grasping with Self-supervised DRL (2018)
"Xiaodeng" domain password policy enhancer in operation and maintenance
QT addition calculator (simple case)
A new method for analyzing the trend chart of London Silver
[论文阅读] CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation
企业公司项目开发好一部分基础功能,重要的事保存到线上第一a
Observable time series data downsampling practice in Prometheus
What is the difference between port mapping and port forwarding
随机推荐
Face recognition 5- insight face padding code practice notes
js如何实现数组转树
[path planning] RRT adds dynamic model for trajectory planning
取得PMP证书需要多长时间?
蓝天NH55系列笔记本内存读写速度奇慢解决过程记录
人生无常,大肠包小肠, 这次真的可以回家看媳妇去了。。。
Chinese verification of JS regular expressions (turn)
壁仞科技研究院前沿技术文章精选
Application of machine learning in housing price prediction
XML的解析
QT addition calculator (simple case)
Paddleocr tutorial
ECCV 2022 | 腾讯优图提出DisCo:拯救小模型在自监督学习中的效果
Jar batch management gadget
Go pit - no required module provides Package: go. Mod file not found in current directory or any parent
[论文阅读] CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation
Recommended collection: build a cross cloud data warehouse environment, which is particularly dry!
[kotlin] the third day
Design of emergency lighting evacuation indication system for urban rail transit station
微服务(Microservice)那点事儿