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

Carcinoma, Non-Small-Cell Lung

Carcinoma

Respiratory Tract Neoplasms

Thoracic Neoplasms

Lung Diseases

Respiratory Tract Diseases

Carcinoma, Bronchogenic

Bronchial Neoplasms

Patients who are receiving standard palliative radiotherapy planned under x-rays will also undergo 1 CT-simulation scan which they would otherwise not require. The planning x-rays and CT scan will then be compared dosimetrically

CT- simulation scan

Dr. Alysa Fairchild, MD FRCPC

Radiotherapy (RT) treatment to the chest is a standard way of trying to decrease symptoms like cough or shortness of breath. Before any RT can be delivered, it must be planned, either using conventional x-rays ("fluoroscopy") or using computer tomography ("CT") scanning. This study is being done because the investigators do not know which of these two common ways of RT planning is better for balancing both treating the cancer and decreasing side effects.

Standard RT planning will be performed under conventional simulation, followed by CT-simulation (for study purposes only). Retrospectively, 3D treatment fields will be designed using the CT-simulation data, and compared to the actual treatment fields planned using x-rays. Coverage of the tumour volume will be assessed, together with doses, field sizes and beam positions, to determine relative undercoverage of tumour and overcoverage of normal tissue between the two planning methods, if any.

CT-Based Versus Conventional Simulation for Palliative Radiotherapy of Non-Small Cell Lung Cancer

Comparison of Two-versus Three-Dimensional Treatment Planning for Patients Receiving Chest Radiotherapy for Symptom Control

Alberta Health services

Dr.Alysa Fairchild

Symptoms and General Pathology

Digestive System Diseases

Gland and Hormone Related Diseases

Rare Diseases

Recurrence

Pancreatic Neoplasms

Pancreatitis

Pancreatitis, Chronic

Pancreatic Diseases

Gastrointestinal Diseases

Chronic Disease

Disease Attributes

Gastrointestinal Neoplasms

Digestive System Neoplasms

Endocrine Gland Neoplasms

Endocrine System Diseases

Pancreatic Cancer

Chronic Graft Versus Host Disease

Acute Graft Versus Host Disease

Gastrointestinal Agents

All Drugs and Chemicals

Pancrelipase

Pancreatin

Patients undergo total pancreatectomy and autologous islet cell transplant IV over 15-60 minutes on day 1.

Pancreatectomy

Quality-of-Life Assessment

Undergo IV autologous islet cell transplant

Treatment Planning

Brett C. Sheppard

Brett C Sheppard

This phase I/II trial assesses the safety and effectiveness of total pancreatectomy with islet cell autotransplantation for the treatment of patients with long-term pancreatic inflammation (chronic pancreatitis) and non-cancerous (benign) pancreatic tumors. Total removal of the pancreas (pancreatectomy) can be used to treat chronic pancreatitis, but it may result in diabetes. An islet cell autotransplantation involves removing cells from a patient's pancreas (the islet cells) and infusing them into the liver. Islet cells are responsible for producing hormones like insulin, reducing the occurrence of diabetes in patients undergoing total pancreatectomy. Total pancreatectomy with autologous islet cell transplant is an accepted and Food and Drug Administration-approved treatment for patients with chronic pancreatitis. However, patients with chronic pancreatitis and pancreatic tumors have historically not been candidates for this procedure due to concerns of spreading potentially cancerous cells to other parts of the body. This clinical trial evaluates the safety and effectiveness of this treatment in patients with chronic pancreatitis and benign pancreatic tumors.

PRIMARY OBJECTIVE:

I. To evaluate the oncologic safety of total pancreatectomy with islet cell autotransplantation (TPIAT) in chronic pancreatitis patients with benign pancreatic neoplasms.

SECONDARY OBJECTIVES:

I. To evaluate postoperative insulin requirements in patients with presumed benign pancreatic neoplasms undergoing TPIAT.

II. To evaluate postoperative opiate requirements in patients with presumed benign pancreatic neoplasms undergoing TPIAT.

III. To evaluate the postoperative survival of patients with presumed benign pancreatic neoplasms undergoing TPIAT.

EXPLORATORY OBJECTIVES:

I. To evaluate quality of life outcomes in patients undergoing TPIAT with presumed benign pancreatic neoplasms.

II. To evaluate subjective pain-related outcomes in patients undergoing TPIAT with presumed benign pancreatic neoplasms.

OUTLINE:

Patients undergo total pancreatectomy and autologous islet cell transplant intravenously (IV) over 15-60 minutes on day 1.

After completion of study treatment, patients are followed up for 2 years.

A Surgical Procedure (Total Pancreatectomy) With a Transplant Procedure (Islet Cell Autotransplantation) for the Treatment of Chronic Pancreatitis and Benign Pancreatic Tumors

Total Pancreatectomy With Islet Cell Autotransplantation in Patients With Benign Pancreatic Neoplasms: A Pilot Study

QOL scores will be collected over time using the Short Form 12. Summary of QOL and its change over time will be presented graphically using box plot and spaghetti plots, in addition to a summary table of QOL over time.

Subjective pain-related outcomes will be collected using Patient Reported Outcomes Measurement Information System Bank Pain Interference Survey, version 1.1 and will be analyzed similar to the QOL survey.

AEs of grade 3 or greater will be collected and tabulated by the Medical Dictionary for Regulatory Activities version 21.1. By-patient listings will also be provided for the following: patient deaths, serious adverse events, and AEs leading to withdrawal.

The 95% confidence interval (CI) will be analyzed using the Clopper-Pearson exact interval method.

Defined as proportion not requiring insulin for blood glucose control for at least 14 days prior to the assessment date at 2 years. The 95% CI will be analyzed using Clopper-Pearson exact interval method.

Defined as proportion not receiving opiates for at least 14 days prior to the assessment date at 2 years.The 95% CI will be analyzed using Clopper-Pearson exact interval method.

The time to OS distribution will be characterized using the Kaplan-Meier method. Kaplan-Meier curves of OS rate at 2 years will be estimated from the survival curve along with the 95% CI.

Oregon Health and Science University

OHSU Knight Cancer Institute

Principal Investigator

Study title	NCT ID	Conditions	Interventions	Eligibility	Organization
ARtificial Intelligence for Gross Tumour vOlume Segmentation	NCT05775068	Lung Cancer	Radiotherapy	18 Years -	Maastricht Radiation Oncology
CT-Based Versus Conventional Simulation for Palliative Radiotherapy of Non-Small Cell Lung Cancer	NCT00862030	Non-small Cell ...	CT- simulation ...	18 Years -	AHS Cancer Control Alberta
A Surgical Procedure (Total Pancreatectomy) With a Transplant Procedure (Islet Cell Autotransplantation) for the Treatment of Chronic Pancreatitis and Benign Pancreatic Tumors	NCT05453851	Benign Pancreat... Chronic Pancrea... Recurrent Acute...	Pancreatectomy Quality-of-Life... Treatment Plann...	18 Years -	OHSU Knight Cancer Institute

Spots Global Cancer Trial Database for treatment planning