Perelman School of Medicine at the University of Pennsylvania

Section for Biomedical Image Analysis (SBIA)

Cancer Imaging Phenomics Toolkit (CaPTk)

CaPTk is a software platform for analysis of radiographic cancer images, currently focusing on brain, breast, and lung cancer. CaPTk integrates advanced, validated tools performing various aspects of medical image analysis, that have been developed in the context of active clinical research studies and collaborations toward addressing real clinical needs. With emphasis given in its use as a very lightweight and efficient viewer, and with no prerequisites for substantial computational background, CaPTk aims to facilitate the swift translation of advanced computational algorithms into routine clinical quantification, analysis, decision making, and reporting workflow. Its long-term goal is providing widely used technology that leverages the value of advanced imaging analytics in cancer prediction, diagnosis and prognosis, as well as in better understanding the biological mechanisms of cancer development.

CaPTk Screenshot showing example annotated ROIs and initialized tumor (view larger)

Functionality

The core functionality of CaPTk is based on a two-level architecture (Fig.1). The first level targets image interaction, (pre)processing, and extraction of extensive panels of features capturing different aspects of local, regional and global imaging patterns, resulting in comprehensive quantitative imaging phenomic signatures. The second level focuses on specialized diagnostic analysis, by use of advanced computational methods to integrate these features into non-invasive diagnostic, prognostic and predictive models with clinically-oriented goals. Example applications include, i) precision diagnostics and risk assessment for developing cancer, ii) predictive models of patient survival and treatment response, and iii) detection of specialized imaging biomarkers of underlying cancer molecular characteristics (specific examples are given in “Science”, below). CaPTk has been designed as a modular adaptable platform, allowing for further extension, interoperability, and cross-platform usability.

Fig.1. Overview of all functions and applications of CaPTk, in its two-level architecture.

For more details, please visit our NIH-supported Project Page.

Close


Science

Here are examples of scientific findings utilizing CaPTk:


NON-INVASIVE IMAGING BIOMARKER OF EGFRvIII

Distributions of the Imaging Biomarker (the φ index) by EGFRvIII expression status.

References:

  1. S.Bakas, H.Akbari, J.Pisapia, M.Martinez-Lage, M.Rozycki, S.Rathore, N.Dahmane, D.M.O’Rourke, C.Davatzikos. "In vivo detection of EGFRvIII in glioblastoma via perfusion magnetic resonance imaging signature consistent with deep peritumoral infiltration: the φ index", Clin Cancer Res, 2017. [Epub ahead of print] DOI: 10.1158/1078-0432.CCR-16-1871
  2. S.Bakas, H.Akbari, J.Pisapia, M.Rozycki, D.M.O'Rourke, C.Davatzikos, "Identification of Imaging Signatures of the Epidermal Growth Factor Receptor Variant III (EGFRvIII) in Glioblastoma", Neuro Oncol, 17(Suppl.5):V154, 2015. DOI: 10.1093/neuonc/nov225.05

 

PREDICTION OF SURVIVAL / PROGNOSTIC STRATIFICATION

 Kaplan-Meier curves. Three survival groups based on predictions generated by the survival prediction index (SPI). HR: hazard ratio.

Reference:

  1. L.Macyszyn, H.Akbari, J.M.Pisapia, X.Da, M.Attiah, V.Pigrish, Y.Bi, S.Pal, R.V.Davuluri, L.Roccograndi, N.Dahmane, G.Biros, R.L.Wolf, M.Bilello, D.M.O’Rourke, C.Davatzikos. “Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques”, Neuro Oncol, 18(3):417-25, 2016 DOI: 10.1093/neuonc/nov127

 

PROBABILITY MAPS OF RECURRENCE

 Left panel presents an estimated map for tumor infiltration from pre-operative MRI analysis; yellow arrow points to a regions estimated to be relatively more infiltrated. Right panel represents the corresponding MR images after tumor resection and subsequent recurrence (red arrow) for the same patient. Recurrence occurred in the vicinity of peritumoral tissue originally estimated to be highly infiltrated.

Reference:

  1. H.Akbari, L.Macyszyn, X.Da, M.Bilello, R.L.Wolf, M.Martinez-Lage, G.Biros, M.Alonso-Basanta, D.M.O'Rourke, C.Davatzikos. “Imaging Surrogates of Infiltration Obtained Via Multiparametric Imaging Pattern Analysis Predict Subsequent Location of Recurrence of Glioblastoma”, Neurosurgery 78(4):572-580, 2016 DOI: 10.1227/NEU.0000000000001202

 

IMAGING BIOMARKERS RELATED TO CANCER RISK AND DEVELOPMENT

Quantitative imaging phenotypes of breast parenchymal complexity.

References:

  1. A.D.Williams, A.So, M.Synnestvedt, C.M.Tewksbury, D.Kontos, M.K.Hsieh, L.Pantalone, E.F.Conant, M.Schnall, K.Dumon, N.Williams, J.Tchou. “Mammographic breast density decreases after bariatric surgery” Breast Cancer Res Treat, 2017 DOI: 10.1007/s10549-017-4361-y
  2. E.F.Conant, B.M.Keller, L.Pantalone, A.Gastounioti, E.S.McDonald, D.Kontos. “Agreement between Breast Percentage Density Estimations from Standard-Dose versus Synthetic Digital Mammograms: Results from a Large Screening Cohort Using Automated Measures”, Radiology 283(3):673-80, 2017 DOI: 10.1148/radiol.2016161286
  3. A.M.McCarthy, B.M.Keller, L.M.Pantalone, M.K.Hsieh, M.Synnestvedt, E.F.Conant, K.Armstrong, D.Kontos. “Racial differences in quantitative measures of area and volumetric breast density”, J Natl Cancer Inst 108(10), 2016 DOI: 10.1093/jnci/djw104
  4. A.Gastounioti, A.Oustimov, B.M.Keller, L.Pantalone, M.K.Hsieh, E.F.Conant, D.Kontos. “Breast parenchymal patterns in processed versus raw digital mammograms: A large population study toward assessing differences in quantitative measures across image representations”, Med Phys 43(11):5862-77, 2016 DOI: 10.1118/1.4963810

 


Please cite the following when you use CaPTk in your research:

  • Sarthak Pati, Spryidon Bakas, Aristeidis Sotiras, Ratheesh Kalarot, Patmaa Sridharan, Mark Bergman, Saima Rathore, Hamed Akbari, Paul Yushkevich, Taki Shinohara, Yong Fan, Despina Kontos, Ragini Verma, Christos 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.
  • Sarthak Pati, Saima Rathore, Ratheesh Kalarot, Patmaa Sridharan, Mark Bergman, Taki Shinohara, Paul Yushkevich, Yong Fan, Ragini Verma, Despina Kontos, Christos 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

Close


Extendability

CaPTk is developed and maintained by the Center for Biomedical Image Computing and Analytics (CBICA) at the University of Pennsylvania, and draws upon research from several groups within the Center.

New applications, written in any programming language, can be integrated into CaPTk at different levels. These applications can then run within CaPTk, while having direct access to the full breadth of CaPTk’s interactive capabilities.

  • Source level integration:
    At this level, the new application source code (C++) is compiled alongside CaPTk, ensuring the most optimized integration. Source-level integration is straight-forward (only requiring additions to relevant CMake files and minor additions to the interactive base) if the new application relies on a subset of CaPTk’s dependencies (i.e., ITK, VTK, OpenCV, Qt).
  • Executable level integration:
    This level provides a graphical interface to an existing command-line application (not necessarily developed in C++), allowing users to leverage CaPTk’s functionality (e.g., interaction, feature extraction). Executable-level integration requires only minor additions to CaPTk to create a menu option for the new application.

Almost every application of CaPTk has an accompanying command-line executable. Those programs can be called directly, making the CaPTk applications available as components within a larger pipeline or for efficient batch processing of large numbers of images.

For detailed instructions and more information please visit the "For Developers" section in our NIH-supported NITRC page.

Close


Download

CaPTk is distributed as source code and pre-compiled installers for Windows 64-bit, Linux 64-bit (compiled under Ubuntu 12.04) and we are working on producing an installable package for macOS as well.

All the installer packages are self-contained and do not need administrative privileges for installation. Please direct any queries to software@cbica.upenn.edu.

To download the CaPTk source code along with various sample datasets, please visit our Download Page hosted in NIH-supported NITRC.

 

Supporting Grant: This work is developed through the NIH/NCI/ITCR-supported grant U24-CA189523.
Disclaimer: The software has been designed for research purposes and is not FDA-approved.


Please cite the following when you use CaPTk in your research:

  • Sarthak Pati, Spryidon Bakas, Aristeidis Sotiras, Ratheesh Kalarot, Patmaa Sridharan, Mark Bergman, Saima Rathore, Hamed Akbari, Paul Yushkevich, Taki Shinohara, Yong Fan, Despina Kontos, Ragini Verma, Christos 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.
  • Sarthak Pati, Saima Rathore, Ratheesh Kalarot, Patmaa Sridharan, Mark Bergman, Taki Shinohara, Paul Yushkevich, Yong Fan, Ragini Verma, Despina Kontos, Christos 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

Close


People

Advisors

Developers:

Collaborators:

Contact CBICA Software for questions, etc.

Close