I have the matlab code for Hierarchical Centroid Shape Descriptor method. The image contains the steps .Please help me to correcte the codes for brain tumor detection.

3 次查看（过去 30 天）

sam CP 2017-2-7

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/323819-i-have-the-matlab-code-for-hierarchical-centroid-shape-descriptor-method-the-image-contains-the-ste

评论： sam CP 2017-2-28

Here by i attached the steps in the imaege and i have also attached the coding . this is the HCSD code for letters only. How can i modify the code by using the steps mentioned in my image..

8 个评论
显示 6更早的评论隐藏 6更早的评论

Walter Roberson 2017-2-27

It looks to me as if you could call the code directly, provided that you are passing in a 2D image.

sam CP 2017-2-28

Yes. It is the HCSD method for Letters. I want to make the code for brain tumor MRI input.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Image Analyst 2017-2-28

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/323819-i-have-the-matlab-code-for-hierarchical-centroid-shape-descriptor-method-the-image-contains-the-ste#answer_256568

See my tumor detection demo. Note: it works for this image but is not guaranteed to work with all images that have tumors, of course. But feel free to adapt it.

For what it's worth, I'm also attaching my kmeans demo, though I said in your other question it's not good as a complete method for finding tumors unless you know in advance there there is definitely one there.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

sam CP 2017-2-28

Thank you ..Yes, it is very sure that the kmeans may sometimes select tumor and some other sorrounding tissue, for extractiong such healthy tissues , the HCSD method will be used and it will worked based on this attached source code (have to modify the code for brain tumor).The HCSD is decompose the image in subimages. There will be five steps

1.Take the input I and compute the transpose of I. 2.Calculate the centroid for each input. 3.Divide the image into two sub images based on the centers of gravity. 4.Normalize the obtained vector by using[-0.5,0.5] 5.Concatenate the features extratced from I and transpose of I

Then the healthy tissues are removed from the mri and select the tumor section alone

请先登录，再进行评论。

请先登录，再回答此问题。