Neoplasms

Respiratory Tract (Lung and Bronchial) Diseases

All Conditions

Lung Neoplasms

Radiotherapy

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.

Lung cancer (LC) is the single leading cancer cause of death worldwide (age-standardized rate of 18.5 per 100,000 population), outstripping the mortality from cancers of the breast, gastro-intestinal tract and reproductive organs. Radiotherapy (RT), often in combination with other treatments, has an essential role in managing LC. An essential step in the RT process is to draw the outline of the Gross Tumor Volume (GTV) in the lung on axial computed tomography (CT) scans. The step is required for precisely directing tumoricidal radiation to the target, and simultaneously avoiding irradiation of adjacent healthy tissue as much as reasonably achievable.

However, tumor outlining by hand consumes a large amount of expert physician time, and has demonstrably high levels of inter- and intra-observer variability. Part of a clinical solution would require validated automated systems that work well for complex GTVs in a wide variety of clinical settings. In recent times, a subclass of artificial intelligence known as deep learning neural networks (DLNNs) has shown promising potential to assist clinicians for such image processing tasks. The immense appeal of DLNN-based tools, if they can be safely shown to add value into radiotherapy clinical workflow, is easily understandable - these have the potential to significantly boost the productivity of clinicians by automating a portion of labor-intensive work.

In respect to LC, models trained on selective data from few institutions are the norm. What the field lacks is not simply large sample size, but sufficient diversity and heterogeneity of subjects to represent the real world, and the means to train a DLNN on such a population. That such a population exists among all the RT clinics around the world is indisputable, however the question is how do we utilize data from all over the world for such a purpose.

"Federated Learning" very clearly addresses this by side-stepping a few of the administrative complication of transferring individual-patient level data across national borders. Federated learning is an implementation of the Personal Health Train (PHT) paradigm, where we send research questions to each other in the form of software and exchange anonymous statistical results (such as a DLNN model) instead of sending patient data around. Hence PHT addresses two of the major challenges of using large-scale cancer data at a single stroke: (a) using data for a good purpose in spite of the geographic dispersion of oncology data, and (b) reducing privacy concerns associated sharing of private patient data across borders.

Objective

Project ARGOS will demonstrate how some of the infrastructural challenges of federated deep learning and early clinical feasibility barriers to an LC GTV DLNN-based automated segmentation model might be developed using a PHT approach. ARGOS adopts a global, cooperative, vendor-agnostic and inter-disciplinary approach to AI development using decentralized imaging datasets. As our first starting step, we will focus on less complex clinical cases where the LC primary GTV is mostly contained inside the lung.

ARGOS plans to use existing radiotherapy planning CT delineations from several leading radiotherapy centres throughout Europe, Asia, Oceania and North America. No new patient data will be required because all the existing data already resides inside RT clinics as a result of standard-of-care treatment.

The initial objective will be to train a DLNN that automatically segments the LC primary GTV that is mostly or entirely contained in the lung parenchyma. The ARGOS partners will also independently validate the globally-trained model on holdout validation and external test datasets.

Sub-objectives

1. Share know-how among radiotherapy centres around the world for setting up the required radiotherapy imaging data and metadata as "FAIR imaging data stations".
2. Offer a vendor-neutral and platform-agnostic open-source architecture for global federated deep learning ("secure tracks").
3. Provide a registration and credentialing procedure for packaging deep learning algorithms as a docker container software application ("docker trains").
4. Define a project governance structure and standardized operational principles, including collaborative research agreements, data protection and intellectual property valorization.

ARtificial Intelligence for Gross Tumour vOlume Segmentation

Federated learning does not require transfer of patient data to the leading investigator.

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.

Universitaire Ziekenhuizen KU Leuven

Radboud University Medical Center

The Netherlands Cancer Institute

University Hospital, Basel, Switzerland

University of Zurich

University Medical Center Groningen

Isala

Tianjin Medical University Cancer Institute and Hospital

Fondazione Policlinico Universitario Agostino Gemelli IRCCS

Cardiff University

The Leeds Teaching Hospitals NHS Trust

The Christie NHS Foundation Trust

Cambridge University Hospitals NHS Foundation Trust

Hospital Israelita Albert Einstein

University of Pennsylvania

Liverpool Hospital, South Western Sydney Local Health District

MVR Cancer Centre and Research Institute India

H. Lee Moffitt Cancer Center and Research Institute

Oslo University Hospital

Christian Medical College, Vellore, India

Fudan University

Swiss Institute of Bioinformatics

Guangdong Provincial People's Hospital

National Institute of Technology Calicut

Maastricht University

Maastricht Radiation Oncology

Professor of Clinical Data Science

Symptoms and General Pathology

Hypoxia

All Drugs and Chemicals

Fluoroazomycin arabinoside

Radiopharmaceuticals

First 5 consecutive 18F-FAZA avid subjects that undergo up to 5 PET scans, 13 blood and 2 urine samples over 4.5 hours

Next 5 consecutive 18F-FAZA avid subjects that undergo up to 4 PET scans, 8 blood and 2 urine samples over 5.5 hours

Radioactive dose of 110-600 MBq per injection. A single pre-treatment injection of 18F-FAZA will be permitted per patient

18F-FAZA

Alexander McEwan, MB, FRCPC

Hypoxia (little of no oxygen) is considered to be an important characteristic of a patient's tumour that may help predict patient outcomes and/or help inform patient management decisions. 18F-FAZA Positron Emission Tomography (PET) can detect hypoxic tumours because 18F-FAZA accumulates in hypoxic tissues. This study is being done to learn more about the processes by which 18F-FAZA is absorbed, distributed, metabolized (built-up and broken down) and eliminated by the body.

A Phase I Radiopharmacokinetic and Radiodosimetric study of 18F-FAZA. Prior to treatment, subjects will receive a single injection of 18F-FAZA. Subjects will undergo a series of 5-5 PET scans, and will have 8-13 blood samples and 2 urine samples taken at specified time points over a 4.5-5.5 hour period. 18F-FAZA PET images will be reviewed to develop a dynamic uptake model, and blood and urine samples will be analyzed for unchanged 18F-FAZA and its metabolites.

A Radiopharmacokinetic and Radiodosimetric Phase I Imaging Study of 18F-FAZA

AHS Cancer Control Alberta

Urinary Tract, Sexual Organs, and Pregnancy Conditions

Prostatic Neoplasms

Neoplasm Metastasis

Neoplastic Processes

Antineoplastic Agents

Radium Ra 223 dichloride

The patients will receive Radium-223 chloride as an escalating dose of either 50, 100 or 200 kBq/kg b.w. (0.0014, 0.0027 or 0.0054 mCi/kg).

The required volume of study drug to be administered to a patient was calculated using the patient's body weight.

Radium-223 chloride (BAY88-8223)

Michael J. Morris, MD

The purpose of the study is to investigate the safety, biodistribution, radiation dosimetry and pharmacokinetics of three intravenous escalating dose levels of Xofigo (Alpharadin).

Within the U.S., the trial is conducted under an IND sponsored by Bayer.

Alpharadin™ (Radium-223 Chloride) Safety and Dosimetry With HRPC That Has Metastasized to the Skeleton

Phase 1, Open-label, Single Ascending-dose Study to Assess Safety, Pharmacokinetics, Biodistribution and Radiation Dosimetry of Intravenous Doses of Alpharadin™ Injection (Radium-223 Chloride) in Patients With HRPC and Skeletal Metastases

Bayer

Rare Diseases

Neuroendocrine Tumors

Pheochromocytoma

Paraganglioma

Carcinoid Tumor

Neuroectodermal Tumors

Neuroectodermal Tumors, Primitive

Neoplasms, Germ Cell and Embryonal

Neoplasms by Histologic Type

Adenocarcinoma

Carcinoma

Neoplasms, Glandular and Epithelial

Neoplasms, Nerve Tissue

Neuroendocrine Tumor

Paragangliomas 1

Neuroepithelioma

Micronutrients

Anti-Infective Agents

Iodine

Cadexomer iodine

3-Iodobenzylguanidine

Enzyme Inhibitors

Ultratrace iobenguane I 131

Ralph E Coleman, MD

The purpose of this study is to test the safety of a drug called Ultratrace iobenguane I 131 that has radioactivity, to measure how long it takes for the drug to be absorbed and passed out of the body, and to measure how much radioactivity is absorbed into different tissues of the body.

Iobenguane, which is also known as MIBG, has been used in many patients who have types of cancers caused by what are known as neuroendocrine tumors, such as pheochromocytoma, paraganglioma, and carcinoid. Iobenguane is absorbed by neuroendocrine tumor cells. The radioactive portion of the study drug, Ultratrace iobenguane, is a form of iodine called I 131. The I 131 is absorbed into the tumor with the iobenguane, and the radioactivity should kill the tumors. The type of iobenguane being studied is called Ultratrace because of the new way in which this form of iobenguane is made. This study is the first time in which Ultratrace iobenguane will be given to patients. The purpose of the study is to give a low dose of iobenguane just to find out if the drug is safe, to measure how long it takes the drug to be absorbed and passed out of the body, and to see how much radioactivity is absorbed by different types of tissues of the body.

ULTRATRACE Iobenguane I 131 in Patients With Malignant Pheochromocytoma, Paraganglioma, or Metastatic Carcinoid

Phase 1 Study Evaluating the Safety, Distribution, Metabolism, and Radiation Dosimetry of ULTRATRACE Iobenguane I 131 in Patients With Malignant Pheochromocytoma/Paraganglioma or Metastatic Carcinoid

Molecular Insight Pharmaceuticals, Inc.

Carcinoma, Non-Small-Cell Lung

Respiratory Tract Neoplasms

Thoracic Neoplasms

Lung Diseases

Respiratory Tract Diseases

Carcinoma, Bronchogenic

Bronchial Neoplasms

Fluorodeoxyglucose F18

Deoxyglucose

Antimetabolites

Antiviral Agents

one injection of Technetium ethylenedicysteine-deoxyglucose to yield a target activity of 20 mCi (range 20-30 mCi) to be given by slow IV push (over 3-5 minutes) 1mg of EC-DG will be injected

Radiolabeled (99Tc) EC-DG (ethylenedicysteine-deoxyglucose)

99mTc EC-DG injection, single dose, slow IV push over 3-5 minutes, yielding a target activity of 20 mCi (range 20-30 mCi)

Technetium 99m ethylenedicysteine-deoxyglucose

single injection of 18F FDG (range 10-20 mCi)

18 F fluorodeoxyglucose

Donald Blaufox, MD

This is a multi-center Phase 1 b study designed to expand the patient safety using 99mTc-EC-DG with SPECT/CT imaging and to expand the patient radiation dosimetry and pharmacokinetic database using 99mTc-EC-DG in patients who have non-incisional biopsy definitive evidence of Non-small Cell Lung Cancer as compared to 18F-FDG PET/CT imaging.

Male and female patients at least 18 years old with untreated Non-small Cell Lung Cancer who have non-incisional biopsy definitive evidence of disease (or cytology results from a bronchoscope procedure confirming NSCLC) and who have been previously certified (per Centers for Medicare and Medicaid Services requirements)by their physicians will be consented for the study. The study consists of a screening visit, gold-standard 18F-FDG PET/CT imaging followed by the investigational agent 99mTc-EC-DG with SPECT/CT(if the PET/CT was performed as part of the pre-study activities on a qualified PET camera for this study, the SPECT/CT must be done within 45 days of the PET/CT imaging procedures). The study procedures can be performed within 5-7 days of signing the informed consent. During the 99mTc-EC-DG SPECT/CT visit of the study, pharmacokinetic (PK) blood draws and urine collection will be taken and radiation dosimetry (Planar Imaging) will be performed at specified time points post 99mTc-EC-DG injection. Patients will be seen 24 hours after the 99mTc-EC-DG injection for safety and final PK blood and urine collection. A 21-day follow-up period (after the SPECT/CT image) will allow the investigator to acquire additional imaging, surgical, pathology and treatment documentation (an actual patient visit is not required at the 21 day follow-up time point).

Pharmacokinetic and Radiation Dosimetry Study Evaluating 99m TC-EC-DG SPECT/CT in Patients With Non-small Cell Lung Cancer (NSCLC)

A Multi-Center Phase 1b Pharmacokinetic and Radiation Dosimetry Study Evaluating 99mTc-EC-DG SPECT/CT in Patients With Non-small Cell Lung Cancer (NSCLC)

Numoda

Venn Life Sciences

Camargo Pharmaceutical Services

Biomedical Systems

Cell>Point LLC

Skin and Connective Tissue Diseases

Musculoskeletal Diseases

Nervous System Diseases

Skin Neoplasms

Muscle Rigidity

Skin Diseases

Both rigid and flexible 3D printed boluses made for each patient. Each is used on alternate days during radiation therapy.

Biopolymer used for 3D-printing of rigid bolus

Ingeo Biopolymer (PLA)

Polymer used for the 3D-printed flexible bolus

Ecoflex 030

Lara R Best, MD, FRCPC

This study compares two types of 3D-printed skin bolus (rigid and flexible) used to optimize the treatment of tumors/cancers involving the skin. Each patient will have both types of bolus made, with each will be used on alternating days. The goal is to determine if one type of bolus provides a better fit and thus radiotherapy plan, the ease of use of each type of bolus, and patient reported feedback.

Need for Skin Bolus during Radiotherapy for Cancers that Involve the Skin Using standard megavoltage (MV) radiotherapy to treat tumors that involve the skin is technically challenging as without modification, the high-energy radiotherapy machines under-dose the superficial tissue. This is a problem, as this may lead to an inadequate radiation dose being delivered to the skin, thus compromising tumor control. To compensate for this, a flexible polymer material ("bolus") measuring 5-10mm in thickness is placed over the skin during radiotherapy.

There are many types of boluses used internationally from rubber to candle wax slabs. The bolus allows the radiation dose to build up so that a sufficient dose is deposited at the skin. Use of bolus for cancers involving the skin is considered the standard of care when using conventional MV radiotherapy.

Challenges of Using Conventional Bolus Many standard boluses are slightly flexible, but are not able to follow significant changes in the underlying contours. When a bolus is not able to follow an individual's unique 'peaks and valleys' in contour, it can lead to air gaps between the bolus and the skin. An air gap, which is easily seen during imaging, can also vary on a day-to-day basis due to slight changes in positioning of the bolus prior to radiotherapy treatment. The varying air gaps can affect how much radiation dose is getting to the skin, and can potentially lead to under-dosing of the cancer cells in the skin. Even small air gaps (i.e. 5mm in thickness), can cause a 5% error in dose, which exceeds the safe tolerance for treatment.

Areas where this can be a problem are where the patient's anatomy undergoes significant topographical changes in a small area. Examples of this include the ear, nose, top of head. Patients with metastatic cancer can also have large lymph nodes or masses that are growing towards the skin that can be difficult to accommodate with standard bolus materials.

3D-Printed Bolus One method to overcome challenging anatomy for cases that require skin bolus for radiotherapy is the use of 3D-printed bolus. This technology uses data acquired from a CT scan of the affected area. The patients contour can then be used to create an individualized bolus that matches the patient contour for the treatment field. This technology has been demonstrated to improve fit (less air gaps) and decreased radiotherapy treatment time. The bolus used in this study was rigid.

Trial design and Rationale Other than the chestwall study, the literature on 3D-printed bolus for radiotherapy has focused on the dosimetry and feasibility of using this technology. However, it is used in an ad hoc method in many centers, using various workflows. There are no studies examining which type of bolus provides the best radiotherapy plan, is the easiest to use at the radiation therapy machines or which is preferred by patients.

To fill this gap, this study will aim to answer a few questions. It will compare the use of rigid 3D-printed bolus (most commonly used and reported in the literature) versus a flexible silicone 3D-printed bolus. Both types of bolus will be used to treat patients with cancers involving the skin. This will allow comparison of radiotherapy plans for each patient between the two types of bolus where each subject is his/her own control. The study will also collect data about real-time set-up using each bolus and feedback from radiation therapists (deliver radiation treatments) about the ease of use of each. Lastly, patients will complete a short survey to provide feedback about comfort with use of each type of bolus and to determine if one type of bolus is favored over the other.

This data will be instrumental is determining the standard of care of the use of 3D-printed bolus as it will assess two types of bolus in three domains: ability to help generate an adequate radiotherapy plan, ease of use by the specialists that deliver the radiotherapy (radiation therapists) and patient reported feedback.

All patients will have both the rigid and flexible 3D printed boluses made. Each will be used on alternate days during radiation therapy treatments.

3D Printed Rigid Bolus Versus Silicone Bolus for Treatment of Tumors Involving the Skin: A Comparative Study

3D Printed Rigid Bolus Versus Silicone Bolus: A Comparative Study

Measurement of the gap between the bolus and the surface of the patient

Comparison of the planned radiation dose at skin, and that measured during radiation therapy treatment

Time required to place bolus in proper location prior to each radiation therapy treatment

Radiation therapists asked to rate ease of use for each type of bolus

Comparison of the number of times each bolus could not be adequately applied prior to radiation therapy treatment

Patients asked about comfort associated with each bolus, their preference between the two, and any other feedback on the boluses

Comparison of average fabrication time for each type of bolus

Comparison of percentage of cases for which an acceptable bolus could be created for each type of bolus

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
ARtificial Intelligence for Gross Tumour vOlume Segmentation	NCT05775068	Lung Cancer	Radiotherapy	18 Years -	Maastricht Radiation Oncology
A Radiopharmacokinetic and Radiodosimetric Phase I Imaging Study of 18F-FAZA	NCT00756691	Hypoxic Tumours	18F-FAZA	18 Years -	AHS Cancer Control Alberta
Alpharadin™ (Radium-223 Chloride) Safety and Dosimetry With HRPC That Has Metastasized to the Skeleton	NCT00748046	Prostate Cancer Metastases Pharmacokinetic...	Radium-223 chlo...	18 Years -	Bayer
ULTRATRACE Iobenguane I 131 in Patients With Malignant Pheochromocytoma, Paraganglioma, or Metastatic Carcinoid	NCT00339131	Pheochromocytom... Paraganglioma Carcinoid	Ultratrace iobe...	18 Years -	Molecular Insight Pharmaceuticals, Inc.
Pharmacokinetic and Radiation Dosimetry Study Evaluating 99m TC-EC-DG SPECT/CT in Patients With Non-small Cell Lung Cancer (NSCLC)	NCT00864110	Non Small Cell ...	Radiolabeled (9... Technetium 99m ... 18 F fluorodeox...	18 Years -	Cell>Point LLC
3D Printed Rigid Bolus Versus Silicone Bolus for Treatment of Tumors Involving the Skin: A Comparative Study	NCT04176900	Skin Neoplasm M... Skin Cancer	Ingeo Biopolyme... Ecoflex 030	18 Years -	Nova Scotia Cancer Centre

Spots Global Cancer Trial Database for radiation dosimetry