Valdo2021 - vascular space segmentation in vascular disease detection challenge (2)

Today we will share Segmentation of cerebral vascular space Of The second step is the complete implementation process of binary classification , In order to facilitate everyone to learn and understand the whole process , The whole process steps are sorted out , And give the detailed results of the steps . If you are interested, please give it a try .

One 、 Data analysis and preprocessing

First, the effective data of intracranial vascular space area in training is extracted , There are some data without vascular space areas , Not as training data , Only tag values are analyzed here 1, Other labels are 0. In total 40 Example data , There are data of vascular space 22 example .

Analyze this 22 Basic information of example data ： Average image size [243.27777778, 298.5, 168.16666667], Images Spacing Average size [0.63042518,0.63042518,0.85555538], Average size of vascular space [5.05882353,5.62745098,3.70588235]. You can see Vascular space The area of is very small , So using spacing Zoom the original image and Mask The image is unified to （0.3,0.3,0.3）.

For non vascular interstitial areas , Throughout Three modes Cut out randomly on the image 200 individual （64,64,64）, For the vascular space area , According to the connected domain analysis Mask Get the boundingbox, Randomly obtain points in this area , And take this as the center to cut （64,64,64）, The number of cuts is 200/ Number of connected domains . Then cut the image （5,95） The mean of 0, The variance of 1 Normalization of .

Finally, divide the data into training sets , Validation set and test set , The ratio is 80%,10%,10% size .

Two 、 Dichotomous networks

The main body of the network adopts VGG16 Residual connection network , The loss function uses binary cross entropy , The learning rate is 0.001,droupout yes 0.5, The number of iterations is 20epochs,batchsize yes 12. The training data totaled 4551 example , The total test data is 500 example , The validation data are 500 example , The optimizer is AdamOptimizer.

3、 ... and 、 Network training and testing

Training loss results and accuracy results

Verify set loss results and accuracy results

Test on test data

The confusion matrix is

305	2
4	189

ROC The curve is 0.9938988371504278, The curve is as follows ：

Other evaluation indicators ：

	precision	recall	f1-score	support
0.0	0.99	0.99	0.99	307
1.0	0.99	0.98	0.98	193
avg / total	0.99	0.99	0.99	500