Converting Data#
In this example, the preprocessing and conversion of DICOM data is demonstrated. These are essential first steps before data can be analysed using PyDicer.
[1]:
try:
from pydicer import PyDicer
except ImportError:
!pip install pydicer
from pydicer import PyDicer
from pathlib import Path
from pydicer.input.test import TestInput
Setup PyDicer#
As in the Getting Started example, we must first define a working directory for our dataset. We also create a PyDicer object.
[2]:
directory = Path("./working")
pydicer = PyDicer(directory)
Fetch some data#
A TestInput class is provided in pydicer to download some sample data to work with. Several other input classes exist if you’d like to retrieve DICOM data for conversion from somewhere else. See the docs for information on how the PyDicer input classes work.
Most commonly, if you have DICOM files stored within a folder on your file system you can simply pass the path to your DICOM directory to the pydicer.add_input() function.
[3]:
dicom_directory = directory.joinpath("dicom")
test_input = TestInput(dicom_directory)
test_input.fetch_data()
# Add the input DICOM location to the pydicer object
pydicer.add_input(dicom_directory)
Preprocess#
With some DICOM data ready to work with, we must first use the PyDicer preprocess module. This module will crawl over all DICOM data available and will index all information required for conversion of the data.
[4]:
pydicer.preprocess()
100%|██████████| 1309/1309 [00:03<00:00, 415.00files/s, preprocess]
Inspect Preprocessed Data#
Here we load the data that was indexed during preprocessing and output the first rows. This data will be used by the following step of data conversion.
[5]:
df_preprocessed = pydicer.read_preprocessed_data()
df_preprocessed.head()
[5]:
| patient_id | study_uid | series_uid | modality | sop_class_uid | sop_instance_uid | for_uid | file_path | slice_location | referenced_uid | referenced_for_uid | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1207 | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.797724702538... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | CT | 1.2.840.10008.5.1.4.1.1.2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.418136430763... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | working/dicom/HNSCC/HNSCC-01-0019/07-04-1998-N... | -807.0 | NaN | NaN |
| 1268 | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.797724702538... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | CT | 1.2.840.10008.5.1.4.1.1.2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.206018114826... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | working/dicom/HNSCC/HNSCC-01-0019/07-04-1998-N... | -804.0 | NaN | NaN |
| 1206 | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.797724702538... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | CT | 1.2.840.10008.5.1.4.1.1.2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.100785615013... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | working/dicom/HNSCC/HNSCC-01-0019/07-04-1998-N... | -801.0 | NaN | NaN |
| 1230 | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.797724702538... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | CT | 1.2.840.10008.5.1.4.1.1.2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.113351005230... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | working/dicom/HNSCC/HNSCC-01-0019/07-04-1998-N... | -798.0 | NaN | NaN |
| 1247 | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.797724702538... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | CT | 1.2.840.10008.5.1.4.1.1.2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.112029189313... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | working/dicom/HNSCC/HNSCC-01-0019/07-04-1998-N... | -795.0 | NaN | NaN |
Convert Data#
With the DICOM data having been indexed during preprocessing, we are now ready to convert this data into NIfTI format which will be stored within the PyDicer standard directory structure.
Running the following cell will begin the conversion process. While this cell is running, take a look inside the working/data directory to see how the converted data is being stored.
Notice the converted.csv file stored for each patient. This tracks each converted data object. This will be loaded as a Pandas DataFrame for use throughout PyDicer.
[6]:
pydicer.convert.convert()
Conversion Progress: 24%|██▍ | 5/21 [00:51<03:11, 11.95s/it]WARNING: In /tmp/SimpleITK-build/ITK-prefix/include/ITK-5.3/itkImageSeriesReader.hxx, line 477
ImageSeriesReader (0x7f22b853e2b0): Non uniform sampling or missing slices detected, maximum nonuniformity:0.000641026
Conversion Progress: 29%|██▊ | 6/21 [00:53<02:07, 8.48s/it]WARNING: In /tmp/SimpleITK-build/ITK-prefix/include/ITK-5.3/itkImageSeriesReader.hxx, line 477
ImageSeriesReader (0x7f22b853e2b0): Non uniform sampling or missing slices detected, maximum nonuniformity:0.000641026
Conversion Progress: 100%|██████████| 21/21 [04:02<00:00, 11.54s/it]
Load Converted DataFrame#
Once data is converted, we can load a Pandas DataFrame which contains a description of each object converted.
The most useful columns in the DataFrame for working with this data in PyDicer are: - hashed_uid: This is a 6 character hexidecimal hash of the associated DICOM SeriesInstanceUID. PyDicer refers to objects using this hashed identifier for a more consice representation. - modality: The modality of the data object. - patient_id: The ID of the patient this data object belongs to. - path: The path within the working directory where files for this data object are stored.
[7]:
df = pydicer.read_converted_data()
df
[7]:
| sop_instance_uid | hashed_uid | modality | patient_id | series_uid | for_uid | referenced_sop_instance_uid | path | |
|---|---|---|---|---|---|---|---|---|
| 0 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.334001018535... | c4ffd0 | CT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.151938046710... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.120880328745... | NaN | working/data/HNSCC-01-0176/images/c4ffd0 |
| 1 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.107072817915... | 8e0da9 | CT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.176143398282... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.216161306702... | NaN | working/data/HNSCC-01-0176/images/8e0da9 |
| 2 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.133948865586... | ec4aec | CT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.192899726585... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.216161306702... | NaN | working/data/HNSCC-01-0176/images/ec4aec |
| 3 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.469610481459... | 33c44a | CT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.244362210503... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.310630617866... | NaN | working/data/HNSCC-01-0176/images/33c44a |
| 4 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.169033525924... | 833a74 | RTDOSE | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.279793773343... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.706719210726... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.470253980284... | working/data/HNSCC-01-0176/doses/833a74 |
| 5 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.267291308489... | bf3fba | RTDOSE | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.283706688235... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.566662631858... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.173917268454... | working/data/HNSCC-01-0176/doses/bf3fba |
| 6 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.173917268454... | 6f7db7 | RTPLAN | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.120111576192... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.566662631858... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.323156708629... | working/data/HNSCC-01-0176/plans/6f7db7 |
| 7 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.470253980284... | a6b346 | RTPLAN | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.318927873561... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.706719210726... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.403955456521... | working/data/HNSCC-01-0176/plans/a6b346 |
| 8 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.403955456521... | cbbf5b | RTSTRUCT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.276897558084... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.120880328745... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.334001018535... | working/data/HNSCC-01-0176/structures/cbbf5b |
| 9 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.323156708629... | 6d2934 | RTSTRUCT | HNSCC-01-0176 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.495627765798... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.310630617866... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.469610481459... | working/data/HNSCC-01-0176/structures/6d2934 |
| 10 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.240263316258... | 72b0f9 | CT | HNSCC-01-0199 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.261759476368... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.870916135819... | NaN | working/data/HNSCC-01-0199/images/72b0f9 |
| 11 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.264264397186... | c16e76 | RTDOSE | HNSCC-01-0199 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233527028792... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.870916135819... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.287865632112... | working/data/HNSCC-01-0199/doses/c16e76 |
| 12 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.287865632112... | 664e96 | RTPLAN | HNSCC-01-0199 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.137463901488... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.870916135819... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.166429645421... | working/data/HNSCC-01-0199/plans/664e96 |
| 13 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.166429645421... | 06e49c | RTSTRUCT | HNSCC-01-0199 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.243934637013... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.870916135819... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.240263316258... | working/data/HNSCC-01-0199/structures/06e49c |
| 14 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.418136430763... | b281ea | CT | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.233510441938... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | NaN | working/data/HNSCC-01-0019/images/b281ea |
| 15 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.242809596262... | 309e1a | RTDOSE | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.777975715563... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.254865609982... | working/data/HNSCC-01-0019/doses/309e1a |
| 16 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.254865609982... | 57b99f | RTPLAN | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.202542618630... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.168221415040... | working/data/HNSCC-01-0019/plans/57b99f |
| 17 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.168221415040... | 7cdcd9 | RTSTRUCT | HNSCC-01-0019 | 1.3.6.1.4.1.14519.5.2.1.1706.8040.103450757970... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.290727775603... | 1.3.6.1.4.1.14519.5.2.1.1706.8040.418136430763... | working/data/HNSCC-01-0019/structures/7cdcd9 |
Data Quarantine#
If anything goes wrong while converting a DICOM object during either the preprocess step or the conversion step, the problematic DICOM data will be copied to the working/quarantine directory.
It’s a good idea to regularly check your quarantine directory to ensure that no critical data objects are being quarantine. If so you may want to consider rectifying the issue and running the preprocess and conversion steps again.
As can be seen by running the cell below, there were several DICOM objects moved to the quarantine during for our test dataset. This was due to there being multiple slices at the same location with differing pixel data in one CT image series.
[8]:
df_quarantine = pydicer.read_quarantined_data()
df_quarantine
[8]:
| file | error | quarantine_dttm | PatientID | Modality | SOPInstanceUID | SeriesDescription | |
|---|---|---|---|---|---|---|---|
| 0 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location 0.0 containing different ... | 2025-03-13 20:34:21.029463 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.181695106907... | SCOUT/NECK-ORAL/NASO W/CON |
| 1 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location 0.0 containing different ... | 2025-03-13 20:34:21.034055 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.258957568007... | SCOUT/NECK-ORAL/NASO W/CON |
| 2 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:21.048307 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.308207714344... | BONE |
| 3 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:21.053672 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.189167578552... | BONE |
| 4 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:21.058698 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.146032766668... | BONE |
| ... | ... | ... | ... | ... | ... | ... | ... |
| 607 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:25.587872 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.190466192108... | CONTRAST120CC@3CC/S,90S DELAY |
| 608 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:25.597725 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.209452648754... | CONTRAST120CC@3CC/S,90S DELAY |
| 609 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:25.607680 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.174557835738... | CONTRAST120CC@3CC/S,90S DELAY |
| 610 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:25.617611 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.113716820433... | CONTRAST120CC@3CC/S,90S DELAY |
| 611 | working/dicom/HNSCC/HNSCC-01-0176/03-05-2004-N... | 2 slices at location -155.0 containing differe... | 2025-03-13 20:34:25.627458 | HNSCC-01-0176 | CT | 1.3.6.1.4.1.14519.5.2.1.1706.8040.141027169157... | CONTRAST120CC@3CC/S,90S DELAY |
612 rows × 7 columns
[ ]: