0
$\begingroup$

I'm currently working on a tumour detection project using Dicom images. As I'm a beginner, I don't know how to segment each part in the image and give each segment a new different colour. I'm using the Watershed segmentation algorithm in Matlab, which only segments the part of interest (the ones that have tumour).

$\endgroup$
0
2
$\begingroup$

Deep learning based image segmentation is basically pixel-wise image classification.

So instead of predicting a $C$ dimensional vector $\vec{x}$ where $C$ corresponds to the number of class labels, you predict a tensor $x\in\mathbb{R}^{h\times w \times C}$ of the same height and width dimensions as your input image, and with $C$ channels which correspond to the different classes.

The paper "U-Net: Convolutional Networks for Biomedical Image Segmentation" provides a good overview of the current methods.

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.