ARtificial Intelligence for Gross Tumour vOlume Segmentation

NCT05775068 | Active Not Recruiting

• 1 other identifier: ARGOS
• Study Type: observational
• Target: 2,000
• Locations: 1 country
• Sites: 1

Brief Summary

Identifying the outline of a Gross Tumour Volume (GTV) in lung cancer is an essential step in radiation treatment. Clinical research, such as radiomics and image-based prognostication, requires the GTV to be pre-defined on massive imaging datasets. The ARGOS community creates an open-source and vendor-agnostic federated learning infrastructure that makes it possible to train a deep learning neural network to automatically segment Lung Cancer GTV on computed tomography images. To reduce risks associated with sharing of patient data, we have used a data-secure Federated Learning paradigm known as the "Personal Health Train" that has been jointly developed by MAASTRO Clinic and the Dutch Comprehensive Cancer Organization (IKNL). The successful completion of this project will deliver a highly scalable and readily-reusable framework where multiple clinics anywhere in the world - large or small - can equitably collaborate and solve complex clinical problems with the help of artificial intelligence and massive amounts of data, while reducing the barriers associated with moving sensitive patient data across borders.

Conditions

Lung Cancer

Keywords

artificial intelligence; deep learning; federated learning; computed tomography; tumor segmentation; radiation dosimetry; treatment planning

Outcome Measures

Primary Outcomes (1)

• As-treated primary GTV delineation in lung

  Gross Tumor Volume as delineated by a medical professional on a treatment planning computed tomography scan for the purpose of radiation planning/dosimetry but not re-drawn/re-edited for this research study.

  Before radiotherapy

Interventions

Radiotherapy RADIATION

Radiotherapy

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Retrospectively archive/registry-extracted adult lung cancer patients treated with external beam radiotherapy, having a GTV mass in the lung (not exclusively mediastinal disease) on radiotherapy planning CT, such that a Primary Lung GTV has been delineated by a human expert physician (i.e. radiation oncologist).

You may qualify if:

• Primary lung cancer, either small-cell or non-small cell
• Any stage of primary disease
• Radiotherapy planning Computed Tomography (CT) series taken before the commencement of radiotherapy
• Gross Tumor Volume delineated (see primary outcome above)
• CT series in DICOM format
• Primary GTV delineation (not including respiratory motion) in RT-Structure DICOM format for one matching CT series
• Any type of external beam radiotherapy treatment received
• Combinations with other therapies permitted

You may not qualify if:

• Not a primary in the lung
• Exclusively nodal disease in mediastinum with no visible hyperintense mass within the outlines of the lung parenchyma
• Only has CT series taken after lung resection
• CT reconstructed pixel spacing (spatial resolution) exceeding 1.1 mm per pixel
• CT reconstructed slice thickness is greater than 3 mm per slice

Sponsors & Collaborators

• Maastricht Radiation Oncology: lead
• Universitaire Ziekenhuizen KU Leuven: collaborator
• Radboud University Medical Center: collaborator
• The Netherlands Cancer Institute: collaborator
• University Hospital, Basel, Switzerland: collaborator
• University of Zurich: collaborator
• University Medical Center Groningen: collaborator
• Isala: collaborator
• Tianjin Medical University Cancer Institute and Hospital: collaborator
• Fondazione Policlinico Universitario Agostino Gemelli IRCCS: collaborator
• Cardiff University: collaborator
• The Leeds Teaching Hospitals NHS Trust: collaborator
• The Christie NHS Foundation Trust: collaborator
• Cambridge University Hospitals NHS Foundation Trust: collaborator
• Hospital Israelita Albert Einstein: collaborator
• University of Pennsylvania: collaborator
• Liverpool Hospital, South Western Sydney Local Health District: collaborator
• MVR Cancer Centre and Research Institute India: collaborator
• H. Lee Moffitt Cancer Center and Research Institute: collaborator
• Oslo University Hospital: collaborator
• Christian Medical College, Vellore, India: collaborator
• Fudan University: collaborator
• Swiss Institute of Bioinformatics: collaborator
• Guangdong Provincial People's Hospital: collaborator
• National Institute of Technology Calicut: collaborator
• Maastricht University: collaborator

Study Sites (1)

Maastro Clinic

Maastricht, Limburg, 6229ET, Netherlands

Location

Related Publications (1)

• Choudhury A, Volmer L, Martin F, Fijten R, Wee L, Dekker A, Soest JV. Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train: Federated Deep Learning Study. JMIR AI. 2025 Feb 6;4:e60847. doi: 10.2196/60847.

  PMID: 39912580 DERIVED

Related Links

• \[1\] The Personal Health Train

MeSH Terms

Conditions

Lung Neoplasms

Interventions

Radiotherapy

Condition Hierarchy (Ancestors)

Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases

Intervention Hierarchy (Ancestors)

Therapeutics

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor of Clinical Data Science

Study Record Dates

• First Submitted: March 7, 2023
• First Posted: March 20, 2023
• Study Start: July 1, 2021
• Primary Completion: September 30, 2023
• Study Completion: December 1, 2024
• Last Updated: March 27, 2024

Record last verified: 2024-03

Data Sharing

• IPD Sharing: Will not share

Locations

NL (1)