Cross-platform radiomics toolkit for predictive cancer imaging

This technology is a cross-platform imaging phenomics toolkit that enables the automated quantitative analysis of 2D and 3D cancer radiographic scans, supporting improved diagnosis, prediction, and clinical decision-making.

Unmet Need: Accessible platform for standardized quantitative cancer image analysis

Clinical imaging workflows rely heavily on manual interpretation or fragmented analysis tools, which makes quantitative imaging assessment inconsistent across institutions. Existing radiomics platforms often require advanced computational expertise, which limits their practicality for routine clinical or translational research applications. The field lacks an accessible, standardized system that can reliably extract and analyze quantitative imaging features at scale.

The Technology: Standardized radiomics toolkit for reproducible imaging analysis

This technology is a toolkit that analyzes radiographic cancer images through standardized pre-processing and feature extraction routines applied to 2D and 3D medical scans. Quantitative patterns in intensity, texture, and morphology are computed using integrated imaging libraries, and a streamlined interface enables automated, unbiased processing across subjects without requiring programming expertise. The resulting radiomic patterns reflect the underlying imaging phenotypes, and researchers can evaluate clinical or biological differences by comparing feature profiles across patients, time points, or tumor characteristics.

This technology has been validated with human samples.

Applications:

• Quantitative analysis of radiographic cancer imaging datasets
• Radiomic feature-based tumor characterization and phenotyping
• Development and evaluation of predictive imaging biomarkers
• Machine-learning model training for prognosis
• Standardized imaging workflows for multi-site or multi-scanner research studies
• Academic research tool for studying imaging phenomics in brain, breast, and lung cancers
• Platform for integrating new image analysis algorithms in clinical research settings
• Batch-processing and data-management support for high-throughput imaging studies

Advantages:

• Provides a unified, standardized platform for quantitative cancer image analysis
• Enables automated and reproducible radiomic feature extraction
• Integrates pre-processing, feature computation, and machine-learning preparation within a single workflow
• Offers a user-friendly interface that eliminates the need for advanced programming expertise
• Supports scalable batch processing
• Ensures cross-platform compatibility across Windows, macOS, and Linux systems
• Facilitates consistent imaging analysis across institutions
• Allows seamless incorporation of external algorithms

Lead Inventor:

Despina Kontos, Ph.D.

Related Publications:

• Davatzikos C, Rathore S, Bakas S, Pati S, Bergman M, Kalarot R, Sridharan P, Gastounioti A, Jahani N, Cohen E, Akbari H, Tunc B, Doshi J, Parker D, Hsieh M, Sotiras A, Li H, Ou Y, Doot RK, Bilello M, Fan Y, Shinohara RT, Yushkevich P, Verma R, Kontos D. “Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome.” J Med Imaging. 2018;5(1)

• Pati S, Singh A, Rathore S, Gastounioti A, Bergman M, Ngo P, Ha SM, Bounias D, Minock J, Murphy G, Li H, Bhattarai A, Wolf A, Sridaran P, Kalarot R, Akbari H, Sotiras A, Thakur SP, Verma R, Shinohara RT, Yushkevich P, Fan Y, Kontos D, Davatzikos C, Bakas S. “The Cancer Imaging Phenomics Toolkit (CaPTk): technical overview.” Brainlesion. 2020;11993:380-394.

Tech Ventures Reference:

• Licensing Contact: Joan Martinez