Friday, September 30, 2022

Count records in csv file and group duplicates in PowerShell

#
#  Output number of images per study form input file list
#   used to validate data in PACS Export and Transfer in October 2022
#   Why:  Needed to process a 400K item list of images files and group by study accession number with total of images see dicom files with python.


$dicomimages = Import-Csv  -Delimiter "," -Path .\DicomFilelist-20220928-135709.csv

$studylistcount = $dicomimages |Group-Object -Property AccessionNumber

[System.Collections.ArrayList]$dicomtruth = @{}



$studylistcount |ForEach-Object {

    $studygrp=$_.Group



     $count= $_.count

     $acc = $_.name

     $mrn = $studygrp| Select-Object -ExpandProperty PatientID -First 1

     $description =  $studygrp| Select-Object -ExpandProperty SeriesDescription -First 1

     $StudyDate =  $studygrp| Select-Object -ExpandProperty StudyDate -First 1

     $StudyInstanceUID  =  $studygrp| Select-Object -ExpandProperty StudyInstanceUID -First 1

     

    $line = [pscustomobject]@{  

            StudyUID = $StudyInstanceUID

            PatientMRN = $mrn

            AccessionNumber = $acc

            StudyDate = $StudyDate

            StudyDescription = $description

            NumberofImages = $count

            }

        $dicomtruth.add($line)|Out-Null    

        }

     $truthfile = "c:\support\dicomtruth-" + $(get-date -f yyyyMMddhhmm) + ".csv"

     $truthfile

     $dicomtruth |Export-Csv -Path $truthfile

No comments:

Post a Comment