Introduction
The original project for MIB version 2.70 included as a supplementary Figure 2 from
DeepMIB: User-friendly and open-source software for training of deep learning network for biological image segmentation
I. Belevich, and E. Jokitalo
PLoS Comput Biol. 2021 Mar 2;17(3):e1008374. doi: 10.1371/journal.pcbi.1008374
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1008374

The updated version for the recent release of MIB is available from 
https://mib.helsinki.fi/tutorials/deepmib/2_2DLM_Files.zip

Used dataset
The training and test datasets were acquired from 
Broad Bioimage Benchmark Collection 
https://data.broadinstitute.org/bbbc/BBBC039/

References:
Ljosa V, Sokolnicki KL, Carpenter AE.
Annotated high-throughput microscopy image sets for validation
Nat Methods. 2012 Jun 28;9(7):637. doi: 10.1038/nmeth.2083.

Project details
It consisted of 197 16-bit annotated images (3 empty images without cells were removed) 
with dimensions (height x width) of 520 x 696 pixels and 1 color channel. 
The dataset was randomly split into the training (143 images) and prediction 
sets (54 images). Training was done using 2D U-Net.

Structure of the project:
valid_252px_32patches_50ep.mibCfg - configuration file
valid_252px_32patches_50ep.mibDeep - trained network
progress_plot.png - figure with the training progress
1_Training - images (TIF format) and the model (1_Labels_TrainingSet.model) used for training
2_Prediction - images for prediction (TIF format) and the ground-truth model (Labels_PredictionSet.model)
3_Result\PredictionImages\GroundTruthLabels - converted to *.mat format ground truth models for evaluation of prediction
3_Result\PredictionImages\ResultsModels - predicted models and evaluation results in XLS (EvaluationResults.xls) and Matlab (EvaluationResults.mat) formats
3_Result\PredictionImages\ResultsScores - probability scores, 4 color channels: 
	- channel 1: probability of exterior; 
	- channel 2: probability of nuclei
	- channel 3: probability of boundaries
	- channel 4: probability of touching bounaries
3_Result\PredictionImages\ - converted to *.mat format images from 2_Prediction
3_Result\ScoreNetwork - accuracy and loss scores from the training
3_Result\TrainImages - converted to *.mat format images used for training
3_Result\TrainLabels - converted to *.mat format models used for training
3_Result\ValidationImages - converted to *.mat format images used for validation
3_Result\ValidationLabels - converted to *.mat format models used for validation
