Renal Cancer Detection Using Convolutional Neural Networks (RCCCNN)

We aim to experiment and implement various deep learning architectures in order to achieve human-level accuracy in Computer-aided diagnosis (CAD) systems. In particular, we are interested in detecting renal tumors from CT urography scans in this project. We would like to classify renal tumor to cancer, non cancer, renal cyst I, renal cyst II, renal cyst III and renal cyst VI, with high sensitivity and low false positive rate using various types of convolutional neural networks (CNN). This task can be considered as the first step in building CAD systems for renal cancer diagnosis. Moreover, by automating this task, we can significantly reduce the time for the radiologists to create large-scale labeled datasets of CT-urography scans.

Study Overview

• Status: Recruiting
• Conditions: Kidney Cancer

Detailed Description

We aim to experiment and implement various deep learning architectures in order to achieve human-level accuracy in Computer-aided diagnosis (CAD) systems. In particular, we are interested in detecting renal tumors from CT urography scans in this project. We would like to classify renal tumor to cancer, non cancer, renal cyst I, renal cyst II, renal cyst III and renal cyst VI, with high sensitivity and low false positive rate using various types of convolutional neural networks (CNN). This task can be considered as the first step in building CAD systems for renal cancer diagnosis. Moreover, by automating this task, we can significantly reduce the time for the radiologists to create large-scale labeled datasets of CT-urography scans.

• Study Type: Observational
• Enrollment (Estimated): 5000

Contacts and Locations

• Study Contact: Name: Nessn Azawi, Phd; Phone Number: 004526393034; Email: nesa@regionsjaelland.dk

Study Locations

• Denmark
  • Roskilde, Denmark, 4000
    • Recruiting
    • Zealand University Hospital
    • Contact: Nessn H. Azawi, M.D.; Phone Number: 004526393034; Email: nesa@regionsjaelland.dk
    • Principal Investigator: Nessn Azawi, Ph.D

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Patients with RCC

Description

Inclusion Criteria:

• All patient with RCC, who underwent surgery

Exclusion Criteria:

• Patients with RCC, who did not underwent surgery

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Renal Cancer; Patients identified with RCC

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Predicting recurrences	Predicting recurrences of RCC	5 years

Collaborators and Investigators

• Sponsor: Nessn Azawi

Study record dates

Study Major Dates

• Study Start (Actual): February 1, 2019
• Primary Completion (Estimated): January 1, 2025
• Study Completion (Estimated): January 1, 2027

Study Registration Dates

• First Submitted: February 26, 2019
• First Submitted That Met QC Criteria: February 26, 2019
• First Posted (Actual): February 28, 2019

Study Record Updates

• Last Update Posted (Actual): January 30, 2024
• Last Update Submitted That Met QC Criteria: January 27, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Keywords: Renal Cancer; Machine Learning
• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Urologic Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Kidney Diseases; Urologic Diseases; Adenocarcinoma; Carcinoma; Neoplasms, Glandular and Epithelial; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Kidney Neoplasms; Carcinoma, Renal Cell
• Other Study ID Numbers: Zealand_UCRU

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No