CaPTk is currently distributed in the form of pre-compiled (executable) Windows, Linux (compiled on Ubuntu 16.04) and macOS (compiled on 10.13) installers with all dependencies integrated in the package.
Check the Installation guide for details on installation.
-
-Please make sure that whenever you use and/or refer to CaPTk in your research, you should always cite the following papers:
+Note: Please make sure that whenever you use and/or refer to CaPTk in your research, you should always cite the following papers:
- C.Davatzikos, S.Rathore, S.Bakas, S.Pati, M.Bergman, R.Kalarot, P.Sridharan, A.Gastounioti, N.Jahani, E.Cohen, H.Akbari, B.Tunc, J.Doshi, D.Parker, M.Hsieh, A.Sotiras, H.Li, Y.Ou, R.K.Doot, M.Bilello, Y.Fan, R.T.Shinohara, P.Yushkevich, R.Verma, D.Kontos, "Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome", J Med Imaging, 5(1):011018, 2018, DOI:10.1117/1.JMI.5.1.011018
- S.Pati, A.Singh, S.Rathore, A.Gastounioti, M.Bergman, P.Ngo, S.M.Ha, D.Bounias, J.Minock, G.Murphy, H.Li, A.Bhattarai, A.Wolf, P.Sridaran, R.Kalarot, H.Akbari, A.Sotiras, S.P.Thakur, R.Verma, R.T.Shinohara, P.Yushkevich, Y.Fan, D.Kontos, C.Davatzikos, S.Bakas, "The Cancer Imaging Phenomics Toolkit (CaPTk): Technical Overview", Springer - BrainLes 2019 - LNCS, Vol.11993, 380-394, 2020, DOI:10.1007/978-3-030-46643-5_38 @@ -79,7 +78,7 @@
- S.Pati, S.Rathore, R.Kalarot, P.Sridharan, M.Bergman, T.Shinohara, P.Yushkevich, Y.Fan, R.Verma, D.Kontos, C.Davatzikos. "Cancer and Phenomics Toolkit (CaPTk): A Software Suite for Computational Oncology and Radiomics", 102nd Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA), Nov.27-Dec.2, 2016, Chicago IL. archive.rsna.org/2016/16014589.html
-
+
License
By installing the CaPTk, the user agrees to the following licenses, which pertain to the code and its different constituents:
-
diff --git a/docs/ITCR_Connectivity.html b/docs/ITCR_Connectivity.html
new file mode 100644
index 000000000..d15791777
--- /dev/null
+++ b/docs/ITCR_Connectivity.html
@@ -0,0 +1,112 @@
+
+
+
+
+
+
+
+
- Download the ".msi" installer file and double click to open. @@ -69,7 +69,7 @@
- If a security prompt comes up after opening the installer, click on "Run Anyway".
- Follow prompts for installation.
- Linux users have a CaPTk AppImage available called
CaPTk_${Version}.bin.
@@ -82,7 +82,7 @@ - Follow prompts to install.
- Users will download the ".pkg" file from NITRC; double-click the file. diff --git a/docs/People.html b/docs/People.html index 434e5cd9b..edfd28f4b 100644 --- a/docs/People.html +++ b/docs/People.html @@ -61,7 +61,7 @@
- Christos Davatzikos @@ -72,7 +72,7 @@
- Aimilia Gastounioti
- Spyridon Bakas
- Sarthak Pati: v.0.0.1 - present @@ -92,7 +92,7 @@
- Spyridon Bakas: v.0.0.1
- Mark Bergman diff --git a/docs/ReleaseNotes.html b/docs/ReleaseNotes.html index a95ff7e5b..d958d5e35 100644 --- a/docs/ReleaseNotes.html +++ b/docs/ReleaseNotes.html @@ -62,6 +62,19 @@
- New training module +
- Updated documentation +
- Miscellaneous bug fixes +
- Fixes to Preprocessing
- NIfTI to DICOM writing improvements
- Registration improvements (rigid and deformable added to CLI and GUI) @@ -92,21 +105,15 @@
- Added Collage radiomic features to Feature Extraction module
- Documentation updates
For a full list, please see https://github.com/CBICA/CaPTk/issues?q=is%3Aissue+is%3Aclosed
--Known Issues
-https://github.com/CBICA/CaPTk/issues
--Older Versions
--1.7.6
++
- New model and data for Pseudo-Progression Estimator
- Generic bug fixes and improvements
- Documentation updates
-1.7.5
++
- GUI improvements
- Algorithmic fixes for Neuro applications @@ -114,8 +121,8 @@
- Linux installation updates
- Generic bug fixes and improvements
-1.7.3
++
- Light/Dark mode and font switcher
- Lots of new Utilities (NIfTI to DICOM & DICOM-Seg object conversion, Orientation change, Thresholding, File format conversion) @@ -123,8 +130,8 @@
- Automated Docker builds
- Generic bug fixes and improvements
-1.7.2
++
- Preferences dialog added (see File > Preferences)
- DICOM reading updates on the GUI @@ -132,15 +139,15 @@
- Comparison mode works on 2 images
- Generic bug fixes and improvements
-1.7.1
++
- Better high DPI support for all supported platforms
- Updated documentation for whole package
- Generic bug fixes and improvements
-1.7.0
++
--1.6.1
++
- Generic bug fixes in several applications
- Feature Extraction fixes on par with IBSI
- OpenGL rendering added to better handle scaling issues
- New "Preprocessing" executable added which has a bunch of generic functionality
-1.6.0
++
- New applications have been added: Lung Cancer Segmentation/Analysis, Pseudo-Progression, EGFRvIII-SVM, Training Module, DeepMedic Segmentation, Greedy Registration
- Updates to Feature Extraction Panel (Lattice-based computation, new feature families)
- macOS package has been added
- Lots of bug-fixes and improvements
-1.5.0
++
- New applications added: Perfusion derivatives (ap-rCBV, PSR, PH), Diffusion derivatives (FA, AX, RAD, TR), PCA Volume Extraction, GBM Molecular Subtype Prediction, GBM Population Atlas
- Performance and UI improvements @@ -188,8 +195,8 @@
- Updated implementation of Directionality Estimation
-1.3.0
++
- Labels updated to support GLISTR and GLISTRboost outputs
- Added a way to invoke CaPTk from the command line to make QC of multiple subjects easier @@ -197,56 +204,56 @@
- New applications added
- Performance and UI improvements
-1.2.0
++
- New applications added
- Interactive functionality updated
- Added central core for statistical analyses
- Bug fixes
-1.1.0
++
- Added functionality to drawing
- Documentation updated with more illustrative screenshots
-1.0.1
++
- Updated documentation outside and inside the application
- Random bug-fixes
-2017.02.01
++
- First public release of CaPTk_Full (version 1.0.0)
- Applications populated using highlighted algorithms from CBICA
- Feature Panel added to generate a comprehensive radiomic feature set for training
- More optimizations and bug-fixes in interaction
-2016.10.14
++
- Release for MICCAI 2016
- UI optimizations
- Seed point selector updated
-2016.09.05
++
- Move to a date-based versioning system for more clarity and coherence
- SeedSelector version for GLISTR, GLISTRboost, PORTR added to compilation
- Major UI overhaul with more dynamic elements
-0.0.2
++
- Bug fixes in the seed points are saved
- Generic interactive improvements
-0.0.1
++
- First (internal) release of CaPTk
- Mostly a prototype at this stage diff --git a/docs/Training_Module.html b/docs/Training_Module.html index 094dbdac5..b3c341aaf 100644 --- a/docs/Training_Module.html +++ b/docs/Training_Module.html @@ -61,28 +61,30 @@
Miscellaneous: Training Module - Launch the application from "Applications" -> "Training Module".
- Specify the features (.csv) file and the corresponding target (.csv) file. -
- Specify the kernel of SVM using either of the two radio buttons. -
- Specify the cross-validation method which could be either k-fold cross-validation, split-train-test, training only, or inference only. -
- In case of k-fold cross-validation, specify the number of folds in the corresponding edit box. In case of split-train-test method, specify the number of training samples X. The starting X entries (out of the total N) of the feature and target file will be used for training and the remaining n-X entries will be used for testing. For training only option, no additional parameter is required in 'Configuration' section. For testing only option, the directory containing the trained model files should be provided. +
- Specify the mode you wish to run the application in. You can train a model, test an existing model, or perform k-fold cross-validated training and testing. +
- If training a model, specify the classifier you wish to use and the feature selection approach, as well as other options. -Classifier options include SVMs (with Linear, RBF, Polynomial, Sigmoid, Chi-squared, and Histogram Intersection kernels), stochastic-gradient-descent based SVM, and decision trees (Random Forests and Boosted Trees). -You can also enable hyperparameter optimization for C and Gamma parameters. You can optionally enable internal cross-validation during individual training steps. -Feature selection options include forward sequential feature selection, recursive feature elimination, Effect-size-based feature selection, RELIEF-F based feature selection, and Random-Forest-based feature selection. +
- In the case of k-fold cross-validation, specify the number of folds in the corresponding edit box. +
- If testing an existing model, you may optionally provide a labels file to be used as ground truth. Performance metrics will be calculated and placed in the output directory. +
- Select an output directory.
- Press "Confirm" button.
- The model or the predicted output, depending on the configuration, will be calculated and saved in the output directory.
- This application is also available as with a stand-alone CLI for data analysts to build pipelines around, and can run in the following formats:
-
-
- K-Fold CrossValidation option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -c 1 -n 1 -k 10
- - Split Train-Test option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -c 1 -n 2 -k 40
- - Train only option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -c 1 -n 3 -k 10
- - Test only option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -c 1 -n 4 -k 10 -m C:/ModelDirectory
+ - K-Fold CrossValidation option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -t crossvalidate -c 1 -k 10
+ - Training option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -l C:/TestLabels.csv -o C:/OutputDirectory -t train -c 2 -s 5 -n 2
+ - Testing option:
${CaPTk_InstallDir}/bin/TrainingModule -f C:/TestFeatures.csv -m C:/ModelDirectory/ -o C:/OutputDirectory -t test 3
- K-Fold CrossValidation option:
- S.Pati, S.Bakas, A.Sotiras, R.Kalarot, P.Sridharan, M.Bergman, S.Rathore, H.Akbari, P.Yushkevich, T.Shinohara, Y.Fan, D.Kontos, R.Verma, C.Davatzikos. "Cancer Imaging Phenomics Toolkit (CaPTk): A Radio(geno)mics Software Platform Leveraging Quantitative Imaging Analytics for Computational Oncology", 103rd Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA), Nov.26-Dec.1, 2017, Chicago IL.
- S.Pati, S.Rathore, R.Kalarot, P.Sridharan, M.Bergman, T.Shinohara, P.Yushkevich, Y.Fan, R.Verma, D.Kontos, C.Davatzikos. "Cancer and Phenomics Toolkit (CaPTk): A Software Suite for Computational Oncology and Radiomics", 102nd Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA), Nov.27-Dec.2, 2016, Chicago IL. archive.rsna.org/2016/16014589.html
- The software has been designed for research purposes only and has neither been reviewed nor approved for clinical use by the Food and Drug Administration (FDA) or by any other federal/state agency.
- This code (excluding dependent libraries) is governed by the license provided in https://www.med.upenn.edu/sbia/software-agreement.html unless otherwise specified.
- The minimum recommended resolution is 1024x768. We have seen some issues with high DPI screens and bug reports related to it will be appreciated.
- B.Gaonkar, L.Shu, G.Hermosillo, Y.Zhan, "Adaptive geodesic transform for segmentation of vertebrae on CT images", Proceedings Volume 9035, Medical Imaging 2014: Computer-Aided Diagnosis; 9035:16, 2014, DOI:10.1117/12.2043527.
|
+ Cancer Imaging Phenomics Toolkit (CaPTk)
+ 1.8.2.Alpha
+
+ |
+
Table of Contents
+ +This section includes a reference of all ongoing and existing connections between CaPTk and other projects funded under the [Informatics Technology for Cancer Research (ITCR)]() program.
+A connectivity map featuring all ITCR projects can be found here.
++Existing Connections
++DCMT
+CaPTk uses DCMTK - DICOM ToolKit (DCMTK) for DICOM file handling.
++DCMQI
+CaPTk leverages DICOM for Quantitative Imaging (DCMQI) for generating DICOM-Seg files from NIfTI files.
++Synapse PACS
+CaPTk’s performance evaluation metrics are used by Synapse PACS.
+
+TCIA and IDC
+Enriching The Cancer Imaging Archive (TCIA) and Imaging Data Commons (IDC) data collections with segmentations and radiomic features. Robustness analysis on radiomic features on TCIA data has also been posted back to TCIA.
++Ongoing Development
++RADxTools
+CaPTk provides the CoLlAGe features through its feature extraction functionality.
+Contact software [at] cbica.upenn.edu with any questions.
+-
+
.
+
+
Windows
-
+
Linux
-
+
macOS
People (Credits)
Windows
+
Linux
-
+
macOS
People (Credits)
macOS
+
Advisors:
-
+
Developers:
More details are available from our repository's Insights page.
-
+
Collaborators:
+
+For a full list, please see https://github.com/CBICA/CaPTk/issues?q=is%3Aissue+is%3Aclosed
+
+Issues
+https://github.com/CBICA/CaPTk/issues
+
+Versions
+
+
+
-This application allows training/testing using Support Vector Machine
- REQUIREMENTS: Input features file (CSV) and a target label file (CSV).
+This application allows training and cross-validation of machine learning models, as well as inference functionality to generate predictions. Currently, it supports a variety of classifiers for binary classification tasks. It also provides several approaches for feature selection.
+ REQUIREMENTS: Input features file (CSV) and a target label file (CSV) (if training).
USAGE:parameterize
-c is the classifier type (-c 1 for Linear SVM, -c 2 for RBF SVM) n is the configuration type (-n 1 for cross-validation, -n 2 for split train-test, -n 3 for training only, -n 4 for testing only) k is the # of folds for cross-validation configuration, and size of train dataset for split train-test configuration
-
+c is the classifier type (-c 1 for Linear SVM, -c 2 for RBF SVM, -c 3 for Polynomial SVM, -c 4 for Sigmoid SVM, -c 5 Chi-squared SVM, -c 6 Intersection SVM, -c 7 Random Forest, -c 8 SGD SVM, -c 9 Boosted Trees ) s is the feature selection type (-s 1 for Effect-size FS, -s 2 for Forward FS, -s 3 for Recursive Feature Elimination, -s 4 for Random Forest based FS, -5 for RELIEF-F FS). t is the execution mode ('cv' or 'crossvalidate' for cross-validation, 'train' for model training only, 'test' for testing only) k is the # of folds for cross-validation configuration. x is the maximum number of features to select during feature selection. Up to that many features can be included. A value of 0 produces different behavior depending on the feature selection method used. For Forward FS, Effect-size FS, and Recursive Feature Elimination, produces the best set overall. For Random Forest FS and RELIEF-F FS, selects all features but in the order of importance.
+
+See the usage option of the TrainingModule application (-u, –usage) for more information.
diff --git a/docs/index.html b/docs/index.html
index 69d6f0b41..f6d1dabb4 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -75,13 +75,13 @@
Fig.1. Overview of all functions and applications of CaPTk, in its two-level architecture
-
+
Bug Tracker and Feature Request
We coordinate our bugs and feature requests via out GitHub page: https://github.com/CBICA/CaPTk/issues
-
+
Frequently Asked Questions (FAQ)
Please see our FAQ Section.
-
+
Citations
Please make sure that whenever you use and/or refer to CaPTk in your research, you should always cite the following papers:
@@ -95,18 +95,18 @@
-
+
Supporting Grant
This work is supported by the NIH/NCI/ITCR* grant U24-CA189523.
* National Institutes of Health / National Cancer Institute / Informatics Technology for Cancer Research
-
+
Disclaimer
-
+
Contact
For more information, please contact software@cbica.upenn.edu.
diff --git a/docs/index.qhp b/docs/index.qhp
index 3ecf3afec..900f93009 100644
--- a/docs/index.qhp
+++ b/docs/index.qhp
@@ -7,12 +7,12 @@
-
-
-
-
-
-
+
+
+
+
+
+
@@ -61,102 +61,98 @@
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
-
-
-
-
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -208,6 +204,7 @@
tabs.css
@@ -273,6 +270,7 @@
Installation.html
ReleaseNotes.html
People.html
+ ITCR_Connectivity.html
index.html
pages.html
diff --git a/docs/navtreedata.js b/docs/navtreedata.js
index 8f3071a5f..92c53fa7c 100644
--- a/docs/navtreedata.js
+++ b/docs/navtreedata.js
@@ -33,12 +33,12 @@ var NAVTREE =
[ "Image Visualization", "Getting_Started.html#gs_imageVisualization", null ],
[ "Tab Docking", "Getting_Started.html#gs_tabDocking", null ],
[ "Coordinate definition (Seed-point initialization)", "Getting_Started.html#gs_seedpoints", [
- [ "Bug Tracker and Feature Request", "index.html#autotoc_md131", null ],
- [ "Frequently Asked Questions (FAQ)", "index.html#autotoc_md132", null ],
- [ "Citations", "index.html#autotoc_md133", null ],
- [ "Supporting Grant", "index.html#autotoc_md134", null ],
- [ "Disclaimer", "index.html#autotoc_md135", null ],
- [ "Contact", "index.html#autotoc_md136", null ],
+ [ "Bug Tracker and Feature Request", "index.html#autotoc_md103", null ],
+ [ "Frequently Asked Questions (FAQ)", "index.html#autotoc_md104", null ],
+ [ "Citations", "index.html#autotoc_md105", null ],
+ [ "Supporting Grant", "index.html#autotoc_md106", null ],
+ [ "Disclaimer", "index.html#autotoc_md107", null ],
+ [ "Contact", "index.html#autotoc_md108", null ],
[ "Tumor Points", "Getting_Started.html#gs_seedpoints_tumor", null ],
[ "Tissue Points", "Getting_Started.html#gs_seedpoints_tissue", null ]
] ],
@@ -79,7 +79,27 @@ var NAVTREE =
[ "Download Instructions", "Download.html", null ],
[ "Installation Instructions", "Installation.html", null ],
[ "Changelog: Release Notes", "ReleaseNotes.html", null ],
- [ "People (Credits)", "People.html", null ]
+ [ "People (Credits)", "People.html", null ],
+ [ "ITCR Connectivity", "ITCR_Connectivity.html", [
+ [ "Existing Connections", "ITCR_Connectivity.html#itcr_existing", [
+ [ "License", "Download.html#lic", null ],
+ [ "Windows", "Installation.html#Windows", null ],
+ [ "Linux", "Installation.html#Linux", null ],
+ [ "macOS", "Installation.html#macOS", null ],
+ [ "Issues", "ReleaseNotes.html#Known", null ],
+ [ "Versions", "ReleaseNotes.html#Older", null ],
+ [ "Advisors:", "People.html#advisors", null ],
+ [ "Developers:", "People.html#devs", null ],
+ [ "Collaborators:", "People.html#collabs", null ],
+ [ "DCMT", "ITCR_Connectivity.html#itcr_dcmtk", null ],
+ [ "DCMQI", "ITCR_Connectivity.html#itcr_dcmqi", null ],
+ [ "Synapse PACS", "ITCR_Connectivity.html#itcr_synapse", null ],
+ [ "TCIA and IDC", "ITCR_Connectivity.html#itr_tcia_idc", null ]
+ ] ],
+ [ "Ongoing Development", "ITCR_Connectivity.html#itcr_ongoing", [
+ [ "RADxTools", "ITCR_Connectivity.html#itcr_radxtools", null ]
+ ] ]
+ ] ]
] ]
];
diff --git a/docs/navtreeindex0.js b/docs/navtreeindex0.js
index 06885bb40..cc9fc9ce1 100644
--- a/docs/navtreeindex0.js
+++ b/docs/navtreeindex0.js
@@ -6,6 +6,7 @@ var NAVTREEINDEX0 =
"BreastCancer_texture.html":[3,3,10],
"Diffusion_Derivatives.html":[3,3,14],
"Download.html":[6],
+"Download.html#lic":[0],
"FAQ.html":[2],
"FAQ.html#gs_FAQ_1":[2,0],
"FAQ.html#gs_FAQ_10":[2,9],
@@ -47,13 +48,29 @@ var NAVTREEINDEX0 =
"Glioblastoma_Survival.html":[3,3,5],
"Glioblastoma_WhiteStripe.html":[3,3,0],
"How_To_Guides.html":[3],
+"ITCR_Connectivity.html":[10],
+"ITCR_Connectivity.html#itcr_dcmqi":[10,0,10],
+"ITCR_Connectivity.html#itcr_dcmtk":[10,0,9],
+"ITCR_Connectivity.html#itcr_existing":[10,0],
+"ITCR_Connectivity.html#itcr_ongoing":[10,1],
+"ITCR_Connectivity.html#itcr_radxtools":[10,1,0],
+"ITCR_Connectivity.html#itcr_synapse":[10,0,11],
+"ITCR_Connectivity.html#itr_tcia_idc":[10,0,12],
"Installation.html":[7],
+"Installation.html#Linux":[2],
+"Installation.html#Windows":[1],
+"Installation.html#macOS":[3],
"LungCancer_SBRT.html":[3,3,11],
"PCA_Extraction.html":[3,3,16],
"People.html":[9],
+"People.html#advisors":[6],
+"People.html#collabs":[8],
+"People.html#devs":[7],
"Perfusion_Alignment.html":[3,3,13],
"Perfusion_Derivatives.html":[3,3,15],
"ReleaseNotes.html":[8],
+"ReleaseNotes.html#Known":[4],
+"ReleaseNotes.html#Older":[5],
"Science.html":[4],
"Science.html#jcoCancer":[4,3],
"Science.html#libraPapers":[4,4],
@@ -69,12 +86,12 @@ var NAVTREEINDEX0 =
"ht_utilities.html":[3,4],
"index.html":[],
"index.html":[0],
-"index.html#autotoc_md131":[0],
-"index.html#autotoc_md132":[1],
-"index.html#autotoc_md133":[2],
-"index.html#autotoc_md134":[3],
-"index.html#autotoc_md135":[4],
-"index.html#autotoc_md136":[5],
+"index.html#autotoc_md103":[0],
+"index.html#autotoc_md104":[1],
+"index.html#autotoc_md105":[2],
+"index.html#autotoc_md106":[3],
+"index.html#autotoc_md107":[4],
+"index.html#autotoc_md108":[5],
"pages.html":[],
"preprocessing_bias.html":[3,0,3],
"preprocessing_brats.html":[3,0,6],
diff --git a/docs/pages.html b/docs/pages.html
index a1072803f..019b5fb49 100644
--- a/docs/pages.html
+++ b/docs/pages.html
@@ -109,6 +109,7 @@
Installation Instructions Changelog: Release Notes People (Credits) ITCR Connectivity
diff --git a/docs/seg_GeoTrain.html b/docs/seg_GeoTrain.html
index 5c46c0b83..69ce297b0 100644
--- a/docs/seg_GeoTrain.html
+++ b/docs/seg_GeoTrain.html
@@ -76,7 +76,8 @@
Advisors:
+
Developers:
More details are available from our repository's Insights page.
-
+
Collaborators:
-
+
For a full list, please see https://github.com/CBICA/CaPTk/issues?q=is%3Aissue+is%3Aclosed
++Issues
+https://github.com/CBICA/CaPTk/issues
++Versions
++
+This application allows training/testing using Support Vector Machine
-REQUIREMENTS: Input features file (CSV) and a target label file (CSV).
+This application allows training and cross-validation of machine learning models, as well as inference functionality to generate predictions. Currently, it supports a variety of classifiers for binary classification tasks. It also provides several approaches for feature selection.
+REQUIREMENTS: Input features file (CSV) and a target label file (CSV) (if training).
USAGE:parameterize
c is the classifier type (-c 1 for Linear SVM, -c 2 for RBF SVM) n is the configuration type (-n 1 for cross-validation, -n 2 for split train-test, -n 3 for training only, -n 4 for testing only) k is the # of folds for cross-validation configuration, and size of train dataset for split train-test configuration
-+
c is the classifier type (-c 1 for Linear SVM, -c 2 for RBF SVM, -c 3 for Polynomial SVM, -c 4 for Sigmoid SVM, -c 5 Chi-squared SVM, -c 6 Intersection SVM, -c 7 Random Forest, -c 8 SGD SVM, -c 9 Boosted Trees ) s is the feature selection type (-s 1 for Effect-size FS, -s 2 for Forward FS, -s 3 for Recursive Feature Elimination, -s 4 for Random Forest based FS, -5 for RELIEF-F FS). t is the execution mode ('cv' or 'crossvalidate' for cross-validation, 'train' for model training only, 'test' for testing only) k is the # of folds for cross-validation configuration. x is the maximum number of features to select during feature selection. Up to that many features can be included. A value of 0 produces different behavior depending on the feature selection method used. For Forward FS, Effect-size FS, and Recursive Feature Elimination, produces the best set overall. For Random Forest FS and RELIEF-F FS, selects all features but in the order of importance.
++See the usage option of the TrainingModule application (-u, –usage) for more information.
diff --git a/docs/index.html b/docs/index.html index 69d6f0b41..f6d1dabb4 100644 --- a/docs/index.html +++ b/docs/index.html @@ -75,13 +75,13 @@
+
Bug Tracker and Feature Request
We coordinate our bugs and feature requests via out GitHub page: https://github.com/CBICA/CaPTk/issues
-
+
Frequently Asked Questions (FAQ)
Please see our FAQ Section.
-
+
Citations
Please make sure that whenever you use and/or refer to CaPTk in your research, you should always cite the following papers:
-
@@ -95,18 +95,18 @@
+
Supporting Grant
This work is supported by the NIH/NCI/ITCR* grant U24-CA189523.
* National Institutes of Health / National Cancer Institute / Informatics Technology for Cancer Research
+
Disclaimer
-
+
Contact
Contact
For more information, please contact software@cbica.upenn.edu.
diff --git a/docs/index.qhp b/docs/index.qhp index 3ecf3afec..900f93009 100644 --- a/docs/index.qhp +++ b/docs/index.qhp @@ -7,12 +7,12 @@
You have to draw the ROI image somewhere else to use the CLI executable. This image should be zero everywhere, except for the voxels that you have drawn. These voxels should be the same value if they belong to the same area. For instance in the example we discussed before, you can use value 1 for tumor core, value 2 for edema and value 3 for healthy tissue. If you don't want the output to contain the healthy tissue you can use parameter "-cl 3/0" which means that value 3 will be changed to 0. Keep in mind that values for healthy tissue are still needed, they just not going to show up in the output segmentation. If you want to iterate (correct mistakes in the segmentation), it's a bit harder to do with the CLI. You have to add new values to the input ROI (not the output segmentation) and run again. If you are going to use the CLI it is recommended to spend a little bit more time when you draw your input ROI so the first segmentation you get is good and you don't have to iterate the algorithm often.
-+
+Note that the CLI allows users to configure a pixel limit. Images above this size (after normalization) will be downsampled for processing, then upsampled when done. This produces a faster, but less precise, result. The GUI does not currently perform this downscaling step.
References: