Machine-learning Optimization for Prostate Brachytherapy Planning

NCT02943824 | Completed DMC

• 1 other identifier: 1.1.1
• Study Type: interventional
• Target: 42
• Locations: 1 country
• Sites: 1

Brief Summary

The proposed, mono-institutional, randomized-controlled trial aims to determine whether the dosimetric outcomes following prostate Low-Dose-Rate (LDR) brachytherapy, planned using a novel machine learning (ML-LDR) algorithm, are equivalent to manual treatment planning techniques. Forty-two patients with low-to-intermediate-risk prostate cancer will be planned using ML-LDR and expert manual treatment planning over the course of the 12-month study. Expert radiation oncology (RO) physicians will then evaluate and modify blinded, randomized plans prior to implantation in patients. Planning time, pre-operative dosimetry, and plan modifications will be assessed before treatment, and post-operative dosimetry will be evaluated 1-month following the implant, respectively.

Conditions

Prostatic Neoplasms

Keywords

brachytherapy; machine learning; treatment planning; Low-Dose-Rate brachytherapy

Outcome Measures

Primary Outcomes (1)

• post-operative prostate V100%

  After receiving treatment patients are discharged. Over the coming month prostate edema decreases. Approximately 1 month following treatment patients have a CT scan and the plan dosimetry is re-computed from actual radioactive seed positions. One of the key dosimetry metrics used to assess the quality of the outcomes is the prostate V100%. This metric will be compared between ML and RT groups.

  1 month

Secondary Outcomes (3)

• Pre-operative planning time

  1 min to 1 hour

• Pre-operative dosimetry

  1 min to 1 hour

• Frequency & magnitude of plan modifications

  1-5 min

Study Arms (2)

Machine Learning Planning

EXPERIMENTAL

Patients will be pre-operatively planned using a machine-learning computer program. An expert radiation oncologist will evaluate the plan prior to implantation. The prescription dose is 145 Gy for monotherapy LDR brachytherapy.

Other: Machine Learning Planning

Radiation Therapist Planning

ACTIVE COMPARATOR

Patients will be pre-operatively planned manually by an expert radiation therapist (\> 60 cases planned). An expert radiation oncologist will evaluate the plan prior to implantation.The prescription dose is 145 Gy for monotherapy LDR brachytherapy.

Other: Radiation Therapist Planning

Interventions

Machine Learning Planning OTHER

The intervention being tested is a novel approach to planning LDR treatment plans using a machine learning computer algorithm.

Machine Learning Planning

Radiation Therapist Planning OTHER

The intervention being compared to the experimental arm is conventional manual planning by a human expert LDR brachytherapy planner.

Radiation Therapist Planning

Eligibility Criteria

• Sex: male
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Diagnosed low- or intermediate-risk prostate cancer patients opting for I-125 LDR brachytherapy at the Sunnybrook Odette Cancer Centre.
• Prostate volume on TRUS \< 60 cc.
• Ability to give informed consent to participate in the study

You may not qualify if:

• Locally advanced or metastatic disease.
• Prior Trans Urethral Resection of the Prostate (TURP).
• International Prostate Symptom Score (IPSS) \> 18
• Patients receiving salvage or boost treatments after primary external radiation or brachytherapy.
• Patients on study protocols with prescription doses other than 145 Gy.

Sponsors & Collaborators

• Sunnybrook Health Sciences Centre: lead

Study Sites (1)

Sunnybrook Odette Cancer Centre

Toronto, Ontario, M4N3M5, Canada

Location

MeSH Terms

Conditions

Prostatic Neoplasms

Condition Hierarchy (Ancestors)

Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Genital Diseases; Urogenital Diseases; Prostatic Diseases; Male Urogenital Diseases

Study Officials

• Ananth Ravi, PhD

  Toronto Sunnybrook Regional Cancer Centre

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: OTHER
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: October 21, 2016
• First Posted: October 25, 2016
• Study Start: August 24, 2017
• Primary Completion: August 24, 2018
• Study Completion: September 4, 2018
• Last Updated: September 6, 2018

Record last verified: 2018-03

Data Sharing

• IPD Sharing: Will not share

Locations

CA (1)