Develop

.gitignore

@@ -92,4 +92,5 @@ conda-pkg/meta.yaml
 !tests/sample_synthetic_data/*.csv
 secret_data/*
 secret_data/
-tmp_dcm2bids/*
+tmp_dcm2bids/*
+.Rproj.user

README.md

@@ -4,14 +4,14 @@
     <img style="width: 35%; height: 35%" src="image011.png">
 </p>
 
-brickstudy is an open source collaborative python library for analysis of data related to pediatric hematology patients, including and especially the neuroradiology data.
+brickstudy is an open source collaborative python library for analysis of data related to sickle cell disease patients, including and especially the neuroradiology data.
 
 brickstudy will include a main code library where the user can access the code.
 
 The library is under construction.
 
-Program files
-The core functions of brickstudy are in the folder brickstudy.
+Program Files
+The core functions of brickstudy are in the folder "brickstudy".
 
 Our guide to notebooks is under construction. To look around keep in mind the following distinction on folders:
 
@@ -21,13 +21,13 @@ These are a growing series of interactive notebooks that allow researchers to in
 
 notebooks/experi:
 
-This folder contains experimental work by core members of the BRICK team (Drs Candace Makeda Moore, Melanie Bruinooge and Aida Gebremeksel)
+This folder contains experimental work by core members of the BRICK team  Candace Makeda Moore,MD,  Melanie Bruinooge, MD and Aida Gebremeksel, MD)
 Data sets:
-The notebooks are configured to run on various datasets. Contact Dr. Melanie Bruinooge( 📫 m.bruinooge@erasmusmc.nl) to discuss any questions on data configuration for your datasets.
+The notebooks are configured to run on various datasets. Contact Melanie Bruinooge, MD (📫 m.bruinooge@erasmusmc.nl) to discuss any questions on data configuration for your datasets.
 
 notebooks/teaching:
 
-This folder contains teaching materials for learning the most basic basics of handeling data.
+This folder contains teaching materials for learning the most basic basics of handling data.
 
 A standardized dataset is under development.
 

brickstudy.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

brickstudy/foundation.py

@@ -29,7 +29,7 @@
 from functools import reduce
 import numpy as np
 from datetime import datetime, date
-# import pydicom as dicom
+import pydicom as pydicom
 import pandas as pd
 import openpyxl
 import skimage.io as io
@@ -181,6 +181,80 @@ def plot_slice(self, z):
             vmin=0,
             vmax=self.v[1],
         )
+
+
+def check_dimensions_of_voxel(image_string):
+    """
+    This function if given a dicom string will return the dimensions as
+    a tuple, and print a message about them
+
+    """
+    dcm_read = pydicom.dcmread(image_string)
+    voxel_width = dcm_read.PixelSpacing[0]
+    voxel_height = dcm_read.PixelSpacing[1]
+    slice_thickness = dcm_read.SliceThickness
+    print("Voxel dimensions are:",  voxel_width, voxel_height, slice_thickness)
+    return (voxel_width, voxel_height, slice_thickness)
+
+
+def map_for_commas(df):
+    """
+    checks if there are any string values with commas in a pandas DataFrame,
+    and return a datadrame with booleans, then a dataframe to show the values
+
+    :param df: The DataFrame to check.
+    :type df: :class:`~pd.dateframe`
+    :return: tuple of two dataframes one with bools for check, one with values
+    :rtype: :class: tuple
+    """
+    # apply a function to each element in the DataFrame to check for commas
+    bool_frame = df.applymap(lambda x: isinstance(x, str) and ',' in x)
+    bool_frame_applied = df[bool_frame]
+    return bool_frame, bool_frame_applied
+
+
+def map_for_commas_if_all_strings(df):
+    """
+    checks if there are any  values with commas in a pandas DataFrame,
+    and returns a datadrame with bools, then a dataframe which shows values
+
+    :param df: The DataFrame to check.
+    :type df: :class:`~pd.dateframe`
+    :return: tuple of two dataframes based on with bools for check
+    :rtype: :class: tuple
+
+    """
+    df = df.applymap(str)
+    # Apply a function to each element in the DataFrame to check for commas
+    bool_frame = df.applymap(lambda x: isinstance(x, str) and ',' in x)
+    bool_frame_applied = df[bool_frame]
+    return bool_frame, bool_frame_applied
+
+
+def check_and_print_commas(df):
+    """
+    converts all values in a DataFrame to strings,
+    then check if any values have commas.
+    If a value has a comma, print the location of the value.
+    Returns number of comma values
+
+    """
+    # convert all values to strings
+    df = df.applymap(str)
+
+    counter = 0
+    # check for commas and print the location
+    for row_index, row in df.iterrows():
+        for col_index, value in row.items():
+            if ',' in value:
+                print(
+                    f"Alert:comma row{row_index}, column{col_index}: {value}"
+                )
+                counter += 1
+
+    return counter
+
+
 # class PydicomDicomReader:
 #     """Class for reading DICOM metadata with pydicom."""
 

match_gen_r.sh

@@ -0,0 +1,15 @@
+for f in $(find /home/fsluser/pcasl_festival/json_holder_1/ -type f -name '*.nii.gz') ; do
+	out=pcasl_anat_output/$(basename $f)good2
+	stripped_basename=$(basename $f)
+	stripped_basename=${stripped_basename%.nii.gz}
+	anat=/home/fsluser/home_holder/$stripped_basename.anat
+	mkdir $out
+    # bolus duration not as in dicom data but as given by medical physics team
+    bolusDuration='0.22170496193,0.3720622289,1.18342832912'
+    # tistimes is a list of inflow times as specified by medical physics team (not DICOM)
+    tistimes='1.22170496193,2.15336425781,4.5'
+    # pvccorr adds partial volume correction
+	oxford_asl -i $f -o $out --fslanat $anat --tis=${tistimes} --bolus=${bolusDuration}  --casl --pvcorr & 
+break    	
+done
+wait

notebooks/Concatenate_volbrain_csvs_deeplesion.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Volbrain deeplesion verzamelen"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This code is for organizing the Volbrain.net output of the DeepLesion Algorythm. It runs over the zip files in a specific folder, and extracts necessary information from the enclosed CSVs and puts themm all together in a table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#load necessary libraries\n",
+    "import pandas as pd\n",
+    "import numpy as np \n",
+    "import zipfile\n",
+    "import os\n",
+    "from zipfile import ZipFile\n",
+    "import glob\n",
+    "from io import BytesIO"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#navigate to zipfolders and intended folder for output (change to commented out if on Windows)\n",
+    "# path_volbrain = 'Z:/processed_data/VolBrain'\n",
+    "# output_folder = \"Z:/processed_data/VolBrain/Separate_CSV_Deeplesion\"\n",
+    "path_volbrain = '/mnt/data/processed_data/VolBrain'\n",
+    "output_folder = \"/mnt/data/processed_data/VolBrain/Separate_CSV_Deeplesion\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#create a list to store the CSV headers in\n",
+    "all_data = []"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "dataframes = []\n",
+    "\n",
+    "for zip_file in glob.glob(os.path.join(path_volbrain, '*.zip')):\n",
+    "    # split by underscores\n",
+    "    participant_id = zip_file.split(\"_\")\n",
+    "    # concatenate BRICK with 00X\n",
+    "    participant_id = participant_id[1] + \"_\" + participant_id[2]\n",
+    "    with ZipFile(zip_file, \"r\") as zf:\n",
+    "        #get the list of files inside the zip (assumes 1 csv per zip folder)\n",
+    "        for entry_name in zf.namelist():\n",
+    "            if entry_name.endswith(\".csv\"):\n",
+    "                entry = zf.read(entry_name)\n",
+    "                df = pd.read_csv(BytesIO(entry), sep=';')\n",
+    "                df['Participant Id'] = participant_id\n",
+    "                dataframes.append(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "concat_df = pd.concat(dataframes)\n",
+    "concat_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#move the participant id row to the front. Now it's last. This is important for upload in castor.\n",
+    "concat_df = concat_df.loc[:, [concat_df.columns[-1]] + list(concat_df.columns[:-1])]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "concat_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#Now make the column names castor appropriate. Do not change the \"Participant Id\" column of course. dl stands for DeepLesion algorithm\n",
+    "concat_df.columns = [\n",
+    "    col if col == \"Participant Id\" else \"dl_\" + col.replace(\" \", \"_\") + \"_T0\"\n",
+    "    for col in concat_df.columns\n",
+    "]\n",
+    "\n",
+    "#For castor, male is 1 and female is 2. Replace these values\n",
+    "concat_df[\"dl_Sex_T0\"] = concat_df[\"dl_Sex_T0\"].replace({\"Female\": 2, \"Male\": 1})\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "concat_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# concat_df.to_csv('Z:/castor_proof_files/volbrains_castor.csv')\n",
+    "#(change to commented out if on Windows)\n",
+    "concat_df.to_csv('/mnt/data/castor_proof_files/volbrains_castor.csv')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}