Response Prediction to Neoadjuvant Chemoradiation in Esophageal Cancer Using Artificial Intelligence & Machine Learning

NCT04489368 | Unknown

• 1 other identifier: RGCIRC/IRB/80/2020
• Study Type: observational
• Target: 150
• Locations: 2 countries
• Sites: 2

Brief Summary

In esophageal carcinoma, neoadjuvant concurrent chemo-radiotherapy (NA-CCRT) followed by surgery is the current standard of care and ample evidence has accumulated supporting the view that complete pathological response (pCR) is a positive prognostic marker for improved outcomes. Predicting the probability of achieving pCR prior to neoadjuvant treatment could permit modification of treatment protocols for those patients unlikely to achieve pCR. Radiomics is a new entrant in the field of imaging where specific features are derived from the intensity and distribution pattern of pixels based on a region-of-interest (ROI). The features thus extracted can then be used for prediction modelling similar to other -omics datasets. Preliminary investigations examining its utility have been performed and its applications have thus far focused on screening and survival prediction after treatment. Due to the multi-dimensional nature of data extracted using radiomics, Artificial Intelligence (AI) methods are ideally suited for analysing and modelling radiomic features. Machine Learning (ML) and Deep Learning (DL)\[utilising Convolutional Neural Networks (CNN)\] are both part of the AI framework. In contrast to ML, DL is a new entrant and has been utilised by some medical researchers for modelling using prediction-type algorithms. Besides significantly reducing the workflow associated with Radiomics-based research, feature engineering and modelling using DL are immune to the effects of incorrect ROI delineation. However, the main limitation of DL is the 'blackbox' effect, in which the underlying basis of a CNN is not known. This has been mitigated in part by the visualisation of activation maps directly on the image dataset to prove biological plausibility of predictions. The comparative performance of both types of modelling is also not known. Our objective is to investigate pCR probability in our study population using radiomics-based ML and AI-based modelling. We will also investigate the comparative performance of both modelling techniques. For DL based prediction modelling, we will attempt to provide biological plausibility on the basis of activation maps.

Conditions

Esophageal Neoplasm

Keywords

Artificial Intelligence; Deep Learning; Neoadjuvant Chemoradiation; Pathologic Response; Radiomics; Radiotherapy

Outcome Measures

Primary Outcomes (2)

• Develop models to predict pCR based on pre-neoadjuvant imaging modalities

  August 2021

• Perform a clinical audit of patient outcomes (OS, RFS, pCR rate) after new-adjuvant chemoradiation and esophagectomy

  January 2020

Study Arms (1)

Study Group

Patients undergoing NA-CCRT followed by Surgery

Radiation: Neo-Adjuvant Radiotherapy; Drug: Neo-Adjuvant Chemotherapy; Procedure: Esophagectomy

Interventions

Neo-Adjuvant Radiotherapy RADIATION

Neo-Adjuvant Radiotherapy via any technique, delivered concurrently with Neo-Adjuvant Chemotherapy.

Study Group

Neo-Adjuvant Chemotherapy DRUG

Neo-Adjuvant Chemotherapy, delivered concurrently with Neo-Adjuvant Radiotherapy.

Study Group

Esophagectomy PROCEDURE

Esophagectomy, performed 4-6 weeks after completion of Neo-Adjuvant Concurrent ChemoRadiation

Study Group

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

Patient records in each participating research center from January 2011 to 1st May 2020

You may qualify if:

• ECOG Performance Status: 0-2
• Patients with histopathological or cytopathological confirmed malignancy of the esophagus
• Histology: Squamous Cell Carcinoma and Adenocarcinoma
• Patients should have received NeoAdjuvant Concurrent Chemoradiation (NACCRT) followed by Surgery
• All therapeutic interventions (Radiotherapy, Chemotherapy \& Surgery) delivered within participating institutions
• At least one pre-NACCRT DICOM imaging dataset (HRCT/ 18-FDG PET-CT/ Radiotherapy planning CT) for each patient

You may not qualify if:

• Patients with any metallic implants in the region of interest
• Patient with locally advanced disease or metastatic disease (T4 disease, Fistula, metastases)
• Patients with prior history of radiotherapy in the same region
• Patients developing a second malignancy in the esophagus

Sponsors & Collaborators

• Dr Kundan Singh Chufal: lead

Study Sites (2)

Illawarra Cancer Care Centre

Wollongong, 2500, Australia

Location

Rajiv Gandhi Cancer Institute & Research Center

New Delhi, National Capital Territory of Delhi, 110019, India

Location

MeSH Terms

Conditions

Esophageal Neoplasms

Interventions

Esophagectomy

Condition Hierarchy (Ancestors)

Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Head and Neck Neoplasms; Digestive System Diseases; Esophageal Diseases; Gastrointestinal Diseases

Intervention Hierarchy (Ancestors)

Digestive System Surgical Procedures; Surgical Procedures, Operative

Study Officials

• Kundan S Chufal, MD

  Rajiv Gandhi Cancer Institute & Research Center

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Senior Consultant & Chief of Thoracic Radiation Oncology, Department of Radiation Oncology

Study Record Dates

• First Submitted: July 23, 2020
• First Posted: July 28, 2020
• Study Start: January 16, 2020
• Primary Completion: July 1, 2023
• Study Completion: July 1, 2023
• Last Updated: December 28, 2022

Record last verified: 2022-12

Data Sharing

• IPD Sharing: Will not share

Locations

AU (1); IN (1)