I'm currently working on tumor detection project using dicom images as I'm beginner in it currently having a difficulty in segmenting each part in image and giving each segment a new colour.

  • $\begingroup$ Can you give us a detailed description of your scientific problem! Analyse your question title,we can give a full book here. $\endgroup$ – quintumnia Oct 1 '18 at 16:27
  • $\begingroup$ I'm working on tumor detection having a difficulty by using watershed algo as it only segment the part of interest which have tumor but i have asked to segment each part in it as im beginner in matlab and image processing so facing a bit difficulty after when i will done with it.i will do feature extraction and svm classification also.i will appropriate if you recommend book $\endgroup$ – Shehnaz Ameer Oct 1 '18 at 16:43

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.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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