Skip to main content
An official website of the United States government
Email

Quantitative Imaging Network (QIN)

Members of the Quantitative Imaging Network sit at desks while attending the network’s annual meeting.

The Quantitative Imaging Network (QIN) promotes research, development, and clinical validation of quantitative imaging tools and methods for the measurement or prediction of tumor response to therapies in clinical trial settings. Its overall goal is facilitating clinical decision making.

Background on Quantitative Imaging and the QIN

The goal of quantitative imaging is to enable clinical imaging devices to behave as measurement instruments. Such tools provide clinicians with reliable and reproducible numeric (i.e., quantitative) information so they can predict or measure the health status of patients, or plan treatment strategies.

Unfortunately, clinical oncologists lack access to quantitative imaging analysis tools to measure or predict therapeutic response/outcome during clinical trials. The QIN program was initiated to support the development, optimization, and validation of quantitative imaging software tools and imaging methods that will give oncologists the confidence that imaging can provide valuable clinical decision support for reliable patient care.

NCI launched the QIN in 2008, and through several program announcements, it grew into an organized network of 40 U.S. research teams at its maximum. Currently nine U.S. teams and 10 international associate member networks from nine countries are engaged in activities. NCI will provide its final funding to the last remaining QIN team in 2027.

QIN Mission, Goals, and Project Objectives

Mission

The QIN works to improve the role of quantitative imaging for clinical decision-making in oncology by developing and validating data acquisition, analysis methods, and tools to:

  • Tailor treatment to individual patients
  • Predict or monitor the response to drug or radiation therapy

Goals

  • Translate quantitative imaging methods and algorithms as clinical decision support tools into clinical utility
  • Implement all imaging scanners to perform as measuring instruments

Project Objectives

  • Develop, adapt, and implement quantitative imaging methods, imaging protocols, and software solutions/tools (used with existing commercial imaging platforms and instrumentation) for application in current and planned clinical therapy trials
  • Focus on image-derived quantitative measurements of responses to drugs and/or radiation therapy during clinical trials or standard of care

QIN Structure

QIN Research Teams

The QIN consists of multidisciplinary research teams that include oncologists and basic and clinical imaging scientists. The teams entered the QIN through the NIH peer review process in which a research application was submitted in response to a program announcement (e.g., PAR-18-248). A Notice of Special Interest in 2021 (NOT-CA-21-032)  was the last QIN funding announcement.

The nine current research teams are listed below with links to their project’s information.

PIInstitutionProject Name and Information
Ashley StokesBarrow Neurological InstituteMulti-parametric Perfusion MRI for Therapy Response Assessment in Brain Cancer

Robert Avery

Marius Linguraru

Children’s Hospital of Philadelphia

Children’s National Hospital (Washington, DC)

MRI for Pediatric Optic Pathway Glioma Treatment Response
Kathleen SchmaindaMedical College of WisconsinQuantitative (Perfusion & Diffusion) MRI Biomarkers to Measure Glioma Response
Gene KimWeill Medical College of Cornell UniversityDiffusion MRI of Treatment Response for De-escalation of Radiation Therapy

Eric Sigmund

Sunitha Thakur

New York University School of Medicine

Memorial Sloan Kettering Cancer Center

Breast Cancer Intravoxel-incoherent-motion MRI Multisite (BRIMM) Study

Wei Huang

James Holmes

Savannah Partridge

Oregon Health & Science University 

University of Iowa

University of Washington

Shutter-Speed Model DCE-MRI for Assessment of Response to Cancer Therapy

Yevgeniy (Jenia) Vinogradskiy

Richard Castillo

Edward Castillo

Thomas Jefferson University

Emory University

Beaumont Health System

Quantitative Lung Function Imaging to Reduce Toxicity for patients treated with Radiation and Immunotherapy
Harrison KimUniversity of Alabama at BirminghamDisposable Perfusion Phantom for Accurate DCE-MRI Measurement of Pancreatic Cancer Therapy Response
Lubomir HadjiyskiUniversity of MichiganBiomarkers for Staging and Treatment Response Monitoring of Bladder Cancer

Executive Committee (EC)

  • Comprises principal investigators from each research team and several program directors from the NCI Cancer Imaging Program
  • Oversees the network
  • Establishes guidelines on network interactions with professional societies, methods for data sharing, publication and promotion material for the network, and the conduct of tool challenges

Associate Members

The QIN includes associate members from around the globe who are interested in or working on exploring the clinical utility of quantitative imaging tools and methods to predict or measure response to cancer therapy. Associate members do not receive NIH financial support, but they receive QIN collaborative opportunities, participate in QIN tool challenges and WG discussions, and may attend the annual QIN meeting.

As of November 2024, there are 28 associate members and 25 emeritus research teams.

Recent QIN Activities

Interactions between QIN and the National Clinical Trials Network (NCTN)

The QIN developed a pathway for directing quantitative methods in clinical trials. Collaborations between the QIN and the NCTN groups (ECOG-ACRIN, Alliance for Clinical Trials in Oncology, NRG Oncology, and SWOG) worked to determine the best ways to test quantitative imaging tools in national clinical trial settings.

QIN Challenges and Collaborative Projects

QIN members have examined various quantitative imaging and image-assessment parameters through network-wide cooperative projects. Challenges and Collaborative Projects (CCPs) were divided into Technical and Clinical CCPs. The CCPs aimed to:

  • Benchmark advanced software tools for clinical decision support
  • Explore new imaging biomarkers for therapeutic assessment
  • Establish consensus on a range of methods and protocols in support of the use of quantitative imaging to predict and assess response to cancer therapy.

CCPs often resulted in publication of manuscripts in peer-reviewed journals that described the design, implementation, and results of the collaborative effort. 

Selected QIN Publications

QIN team members have published nearly 500 peer-reviewed articles in various imaging journals resulting from QIN work. Below are a few selected publications.

  • Sun, D., Hadjiiski,L., et al. Computerized Decision Support for Bladder Cancer Treatment Response Assessment in CT Urography: Effect on Diagnostic Accuracy in Multi-Institution Multi-Specialty Study. Tomography, 2022 March; 8(2) 644-656. PubMed
  • Jones EF, Buatti JM, Shu H-K, et al. Clinical Trial Design and Development Work Group Within the Quantitative Imaging Network. Tomography. 2020 Jun;6(2):60-64. PubMed
  • Tomography Special Issue on Quantitative Imaging Network. Tomography. 2019;5(1): 27 articles. Full Issue
  • Journal of Medical Imaging Special Issue on Quantitative Imaging Honoring Larry Clarke. on Quantitative Imaging Network. J Med Imaging. 2018 Jan;5(1): 21 articles. Full Issue
  • Tomography Special Issue on Quantitative Imaging Network. Tomography. 2016;2(4): 26 articles. Full Issue
  • Yankeelov TE. The Quantitative Imaging Network: A Decade of Achievement. Tomography. 2019 Mar;5(1):A8  PubMed
  • Farahani K, Tata D, and Nordstrom RJ. QIN Benchmarks for Clinical Translation of Quantitative Imaging Tools. Tomography. 2019 Mar;5(1)1-6. PubMed

Validating QIN Tools

QIN researchers work to enhance quantitative imaging in clinical trials for prediction and/or measurement of response to cancer therapies, such as:

  • Emphasizing the development, optimization, and validation of state-of-the-art quantitative imaging methods and software tools for potential implementation in single or multi-site clinical trials
  • Enhancing quantitative imaging methods to address the challenges of integrating existing and or new quantitative imaging methods as required for multicenter clinical trials.
  • Evaluating a range of multimodal imaging approaches, harmonizing image data collection, analysis, display and clinical workflow methods across imaging platforms, or testing their performance across different cancer site.

A few recent, mature QIN tools involved in prospective clinical trials are listed below.

Institution Tool Name/Type Image Modality Tool Capabilities Tool Description
Columbia University Solid Tumor Segmentation/Algorithm: segmentation methods for solid tumors CT, MRI, and /or PET Solid tumor segmentation Software for segmentation of solid tumors – tumors in lung, liver, and lymph nodes
Emory University Spectroscopic MRI clinical interface/Web-based sMRI clinical interface to analyze, visualize, and integrate sMRI data into patient management. MRI spectroscopy Integrates automated spectral filtering to enable ad-hoc and post-hoc filtering of any data imported into the web applications; Rigid registration of the sMRI maps with clinical images; Automated segmentation of regions-of-interest in metabolite maps. Useful and intuitive framework to help end-users to display, evaluate, and manipulate sMRI metabolic information alongside standard clinical images, enabling integration of volumetric metabolic data into the clinical workflow.
Medical College of Wisconsin IB Clinic/FDA-cleared and CE-marked suite of post-processing software algorithms for quantitative analysis and decision support MRI and CT Processing DSC-MRI, Perfusion-CT, DWI-MRI, and DCE-MRI data as well as automated determination of regions of enhancement from pre- and post-contrast T1-weighted MRI IB Neuro uses an enhanced contrast agent leakage correction algorithm for MR DSC perfusion analysis; IB Delta Suite has fundamental radiology tools (image co-registration, image subtraction, class map exporting, and image intensity calibration); and generates "Delta T1" maps using pre- and post-contrast T1 images.
Johns Hopkins University AutoPERCIST/A working software application for quantitative analysis, translation of QIN research into practice, or decision support PET, PET/CT Clinical decision support, Image Quantitation - Static, Image segmentation, Image viewer/visualization, Response assessment Software for semi-automated PERCIST-based analysis of FDG-PET image studies
University of California, San Francisco Aegis SER/Software Application and Algorithm for Volumetric analysis of Breast Cancer response to neoadjuvant chemotherapy MRI, DCE-MRI Image Quantitation - Dynamic, Image reconstruction, Image registration, Image segmentation, Image viewer/visualization; Commercial version used by approximately 20 sites in the I- SPY 2 TRIAL. Image processing and analysis package for breast MRI; primary application is volumetric analysis of breast tumors based on DCE-MRI contrast kinetics.
University of Michigan Mi Viewer/ Versatile software tool can annotate, outline, and measure lesions in the bladder, lung, head & neck and most other solid tumor sites. CT, PET/CT, MRI and Ultrasound Automatically segments lesions in 3D; estimates lesion volume and change based on radiomic features (gray level, shape, and texture features); has utility in clinical decision support, image quantitation, static image segmentation, image viewer/visualization, volume assessment, radiomics feature analysis, and response assessment. The clinician can view the anatomical site slice by slice for possible lesions, mark a volume of interest (VOI), outline the lesion, identify the lesion center and measure the lesion dimensions. The tool performs automatic 3D lesion volume segmentation within an interactively marked bounding box of the lesion.

Contacts

Dr. Darrell Tata
Director, QIN
Darrell.Tata@nih.gov

Dr. Pushpa Tandon
Deputy Director, QIN
Associate Membership
tandonp@mail.nih.gov

  • Updated:

If you would like to reproduce some or all of this content, see Reuse of NCI Information for guidance about copyright and permissions. In the case of permitted digital reproduction, please credit the National Cancer Institute as the source and link to the original NCI product using the original product's title; e.g., “Quantitative Imaging Network (QIN) was originally published by the National Cancer Institute.”

Email