irAEMM/pythonScripts/preprocess.py

import os
import json
import re
import subprocess
import nibabel
import shutil
import sys

shome=os.path.expanduser('~nixUser')
fhome=os.path.expanduser('~')
with open(os.path.join(fhome,".labkey","setup.json")) as f:
    setup=json.load(f)

sys.path.insert(0,setup["paths"]["labkeyInterface"])
import labkeyInterface
import labkeyDatabaseBrowser
import labkeyFileBrowser

sys.path.insert(0,setup["paths"]["orthancInterface"])
import orthancInterface
import orthancFileBrowser

#sys.path.insert(1,shome+'/software/src/IPNUMM/dicomUtils')
#import loadDicom


fconfig=os.path.join(fhome,'.labkey','network.json')

#matlab=os.path.join("/","data","software","install","matlab","bin","matlab")
matlab=setup["paths"]["matlab"]
#os.path.join(fhome,"software","install","matlab","bin","matlab")
generalCodes=setup["paths"]["generalCodes"]
#ios.path.join(fhome,"software","src","generalCodes")
niftiTools=setup["paths"]["niftiTools"]
#niftiTools=os.path.join(fhome,"software","src","NifTiScripts")

net=labkeyInterface.labkeyInterface()
net.init(fconfig)
db=labkeyDatabaseBrowser.labkeyDB(net)
fb=labkeyFileBrowser.labkeyFileBrowser(net)


onet=orthancInterface.orthancInterface()
onet.init(fconfig)
ofb=orthancFileBrowser.orthancFileBrowser(onet)

hi=0
project='iPNUMMretro/Study'
#for prospective, set
project='IPNUMMprospektiva/Study'
dataset='Imaging1'
tempBase=os.path.join(fhome,'temp')


participantField='PatientId'
#for prospective set
participantField='ParticipantId'

#all images from database
ds=db.selectRows(project,'study',dataset,[])
#imageSelector={"CT":"CT","PET":"PETWB"};
imageSelector={"CT":"CT_orthancId","PET":"PETWB_orthancId"}
#output
imageResampledField={"CT":"ctResampled","PET":"petResampled","patientmask":"ROImask"}

#projectNIfTIBase=os.path.join(labkeyBase,'files',project,'@files/nifti')
#use webdav to transfer file (even though it is localhost)


def getPatientLabel(row,participantField='PatientId'):
    return row[participantField].replace('/','_') 

def getVisitLabel(row):
    return 'VISIT_'+str(int(row['SequenceNum']))

def getStudyLabel(row,participantField='PatientId'):
    return getPatientLabel(row,participantField)+'-'+getVisitLabel(row)

def runPreprocess_DM(matlab,generalCodes,niftiTools,studyDir):

    #run after all directories have been assembled
    script="addpath('"+generalCodes+"');"
    script+="addpath('"+niftiTools+"');"
    script+="preprocess_DM('"+studyDir+"',0,0);"
    script+="test;"
    script+="quit();"
    #outText=subprocess.check_output(["/bin/echo",script])
    try: 
        outText=subprocess.check_output([matlab,"-nojvm","-r",script])
    except subprocess.CalledProcessError as e:
        print("Failed with:\n{}".format(e.output.decode('utf-8')))
        return False
    print(outText.decode('utf-8'))
    return True


def getDicom(ofb,row,zipDir,rawDir,im,imageSelector,\
        participantField='PatientId'):

    #Load the dicom zip file and unzips it. If zip file is already at the expected path, it skips the loading step

    #Return True for valid outcome and False for troubles in row formating or unzip failures

    seriesId=row[imageSelector[im]];
    if seriesId=="0":
        return False

    print("{}: {}".format(im,seriesId))
    fname=os.path.join(zipDir,\
            getStudyLabel(row,participantField)+'_'+im+".zip");

    #copy data from orthanc
    if os.path.isfile(fname):
        print("Data already loaded. Skipping")
    else:
        print("Loading data from orthanc")
        ofb.getZip('series',seriesId,fname)

    #unzip the zipped dicom series

    unzipDir=os.path.join(rawDir,im)

    if os.path.isdir(unzipDir):
        print("Data already unzipped")
        return True
    
    try:
        os.mkdir(unzipDir)
    except FileExistsError:
        shutil.rmtree(unzipDir)
    
    try:
        outTxt=subprocess.check_output(["unzip","-d",unzipDir,"-xj",fname])
    except subprocess.CalledProcessError:
        print("unzip failed for {}".format(fname))
        return False

    return True    

def updateRow(project,dataset,row,imageResampledField,gzFileNames,\
        participantField='PatientId'):
    row['patientCode']=getPatientLabel(row,participantField)
    row['visitCode']=getVisitLabel(row)
    for im in imageResampledField:
        row[imageResampledField[im]]=gzFileNames[im]
    db.modifyRows('update',project,'study',dataset,[row])
 


i=0
for row in ds["rows"]:

    #interesting files are processedDir/studyName_CT_notCropped_2mmVoxel.nii
    #asn processedDir/studyName_PET_notCropped_2mmVoxel.nii
    volumeFileNames={im:\
            getStudyLabel(row,participantField)+'_'+im+
            '_notCropped_2mmVoxel.nii'\
                for im in imageResampledField}
    gzFileNames={im:f+".gz" \
            for (im,f) in volumeFileNames.items()}
    
    #build/check remote directory structure
    remoteDir=fb.buildPathURL(project,['preprocessedImages',\
            getPatientLabel(row,participantField),getVisitLabel(row)])

    gzRemoteFiles={im:remoteDir+'/'+f\
            for (im,f) in gzFileNames.items()}

    remoteFilePresent=[fb.entryExists(f)\
            for f in gzRemoteFiles.values()]

    for f in gzRemoteFiles.values():
        print("[{}]: [{}]".format(f,fb.entryExists(f)))


    if all(remoteFilePresent):
        print("Entry for row done.")
        updateRow(project,dataset,row,imageResampledField,\
                gzFileNames,participantField)
        continue

    
    #setup the directory structure for preprocess_DM
    studyDir=os.path.join(tempBase,getStudyLabel(row,participantField))
    if not os.path.isdir(studyDir):
        os.mkdir(studyDir)

    rawDir=os.path.join(studyDir,'Raw')
    if not os.path.isdir(rawDir):
        os.mkdir(rawDir)

    zipDir=os.path.join(studyDir,'Zip')
    if not os.path.isdir(zipDir):
        os.mkdir(zipDir)

    processedDir=os.path.join(studyDir,'Processed')
    if not os.path.isdir(processedDir):
        os.mkdir(processedDir)

    #specify local file names with path 
    volumeFiles={im:os.path.join(processedDir,f)\
            for (im,f) in volumeFileNames.items()}
    gzFiles={im:f+".gz"\
            for (im,f) in volumeFiles.items()}

    filesPresent=[os.path.isfile(f) for f in gzFiles.values()]
    
    
    if not all(filesPresent):

        #use imageSelector -> inputs
        for im in imageSelector:
            #checks if raw files are already loaded
            getDicom(ofb,row,zipDir,rawDir,im,imageSelector,\
                    participantField)


    
        #preprocess and zip
        ok=runPreprocess_DM(matlab,generalCodes,niftiTools,studyDir)
        if not ok:
            shutil.rmtree(studyDir)
            continue


        for f in volumeFiles.values():
            print("Running gzip {}".format(f))
            outText=subprocess.check_output(["/bin/gzip",f])
            print(outText.decode('utf-8'))

    #upload local files to remote
    for im in gzFiles:
    #for local,remote in zip(gzFiles,gzRemoteFiles):
        local=gzFiles[im]
        remote=gzRemoteFiles[im]
        print("Uploading {}".format(local))
        fb.writeFileToFile(local,remote)


    #update row and let it know where the processed files are
    updateRow(project,dataset,row,imageResampledField,gzFileNames,\
            participantField)
   

    #cleanup
    shutil.rmtree(studyDir)
    

    if i==-1:
        break
    i=i+1


print("Done")