Multimodality input: T1, T2, etc.

rezazad68 / BCDU-Net

BCDU-Net : Medical Image Segmentation

712 stars 264 forks source link

Multimodality input: T1, T2, etc. #20

Closed PinchukTS closed 4 years ago

PinchukTS commented 4 years ago

Good day to you. Is it possible to pass more than single channel (grayscale) arrays to model. I would like to train on my own dataset with MRI images: T1-wrighted, T2-weighted, T2 TIRM, DWI, SWI. All of images have same shape (512, 512, 1) and want to encode them as (512, 512, 5) input. Should I modify model exept input_size=(512, 512, 5) param of BCDU_net_D3 function?

P.S. Sorry for my english :(.

rezazad68 commented 4 years ago

Thanks for your interest. Yes, you can use any input shape for example (H, W, C) where C can be 1 channel (like Retina), 3 channels like Sking, to N channels(for your case 5 channels). Just make sure the model you are using does not load the pre-trained weights with 3 channels as input. Best.