DeepMIB: features and updates in MIB 2.80

[@alexshevelkin3711]

Great tutorial! Thank you, Ilya. Is it possible to use cDNN to train for segmentation of brain tissue to study morphology of neurons?

[@ajaxel]

Thank you, Alex! it is definitely possible, but in this case it may be better to start with some simpler segmentations as membranes. I guess the typical workflow for neuroscience is to assemble several networks starting from segmentation of membranes and continue after that to segment cells and their organelles

[@aslanturkhan1825]

Where are the Dataset ? please. you are good teacher

[@ajaxel]

all details for datasets are in the supporting information at journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008374 direct link: journals.plos.org/ploscompbiol/article/file?type=supplementary&id=info:doi/10.1371/journal.pcbi.1008374.s002

[@aslanturkhan1825]

@@ajaxel Hi Ilya. I trained the images I obtained from the normal microscope with U-net and Segnet. I used 15 images for the tutorial. I could not get results after training in U-net. but I got a segmented result. Why didn't U-net produce results? I can send images and training results to your e-mail address.

[@aslanturkhan1825]

I got a SegNet result

[@ajaxel]

@@aslanturkhan1825 sure, I am at work this week, so we can chat about it if you want

[@HenrikSahlinPettersen]

Excellent tutorial, Ilya! For a tutorial on how to use DeepMIB seamlessly with QuPath (for annotation of whole slide images) and FastPathology (for direct prediction on whole slide images), Ilya and I (and co-workers) have published and arXiv preprint of this and published a tutorial video here: kzbin.info/www/bejne/b5W3l4ito7FpsLs