DICOM and Machine Learning

4 views (last 30 days)
Nitsa Herzog
Nitsa Herzog on 30 Mar 2017
Commented: Walter Roberson on 3 Apr 2017
Hi, I have a set of images of .dcm format (MRI). I would like to use some machine learning technique for data training and classification. Before I created classifier with .jpg, .png and ect image formats. Does Matlab has an option to create a classifier using .dcm images directly without conversion to other formats? Thank you,

Accepted Answer

Carl
Carl on 3 Apr 2017
Hi Nitsa, that depends on how you are working with the DICOM data. If you want to train with the image data directly from files, this usually requires you to construct an ImageDataStore. For this, you would need to convert the DCM files to another format, like JPG. You can use the 'dicomread' function to read in the image from a DCM file, and then save it afterwards as another format.
https://www.mathworks.com/help/images/ref/dicomread.html https://www.mathworks.com/help/matlab/ref/imwrite.html
However, if you are using the DICOM info and image in some other way, you can get that information with the 'dicominfo' and 'dicomread' functions, and structure your classifier however you like.
  1 Comment
Walter Roberson
Walter Roberson on 3 Apr 2017
I recommend PNG or TIFF, never JPEG for analysis work. JPEG is lossy which makes analysis difficult.

Sign in to comment.

More Answers (0)

Categories

Find more on Medical Physics in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!