Efficacy and Safety of AI-assisted Radiotherapy Contouring Software for Thoracic Organs at Risk

Breast Cancer Clinical Trial

Official title:

Prospective, Multicenter and Controlled Evaluation of Efficacy and Safety of AI-assisted Radiotherapy Contouring Software in CT Images for Thoracic Organs at Risk

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT05787522
• Other study ID #: PVMEDCT202201
• Status: Recruiting
• Start date: September 30, 2022
• Est. completion date: June 30, 2023

Study information

• Verified date: March 2023
• Source: Tianjin Medical University Cancer Institute and Hospital
• Contact: Yong Guan, MD
• Phone: +862223340123
• Email: alan099015[@]163.com
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The goal of this clinical trial is to evaluate efficacy and safety of AI-assisted radiotherapy contouring software in CT images for thoracic organs at risk. After screening, qualified participants' thoracic CT images will be anonymized and randomized to two sequences, one with independent investigator contouring of thoracic organs at risk, followed by washout period and software-assisted contouring, and the other in reverse sequence. The washout period lasts for at least 4 weeks. Investigators will not only contour organs at risk in their own center, but also organs in the previous center. The anonymized images will be contoured by independent expert team as the golden standard. The experimental group refers to software-assisted contouring, while the control group refers to independent investigator contouring. Judged by the golden standard, the two groups will be compared to evaluate efficacy and safety of software-assisted contouring of thoracic organs at risk.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 500
• Est. completion date: June 30, 2023
• Est. primary completion date: April 30, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

1. =18 years old, no gender limit;

2. patients suffering from breast cancer or lung cancer or esophageal cancer, undergoing thoracic CT scan, ready for radiotherapy;

3. CT slice thickness =5mm;

4. patients understand the goal of the trial, are willing to attend the trial and sign the informed consent.

Exclusion Criteria:

1. congenital malformation or anatomical anomaly in scanned sites;

2. artifact, prosthesis or implantation causing images undistinguishable;

3. CT images not conforming to DICOM standards;

4. investigators consider not suitable.

Related Conditions & MeSH terms

• Breast Cancer
• Esophageal Cancer
• Lung Cancer

Intervention

Device:
• contouring of thoracic organs at risk
The thoracic organs at risk will be contoured by investigators independently, and by investigators assisted with software, at different time points. Judged by the golden standards established by the expert team, the contours will be evaluated. But the contoured organs in any group will not be applied in radiotherapy.

Locations

Country	Name	City	State
China	Tianjin Medical University Cancer Institute and Hospital, Tianjin Key Laboratory of Cancer Prevention and Therapy	Tianjin	Tianjin

Sponsors (6)

Lead Sponsor	Collaborator
Tianjin Medical University Cancer Institute and Hospital	Fifth Affiliated Hospital, Sun Yat-Sen University, Guangzhou Perception Vision Medical Technology Co. Ltd, Nanxishan Hospital of Guangxi Zhuang Autonomous Region, Shanxi Province Cancer Hospital, Wuhan Union Hospital, China

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	adverse events	adverse events during CT scanning	during CT 1 day scanning
Other	device defect	software malfunction	1 day (during the process of contouring)
Primary	DICE	DICE= 2×(AnB)/(A+B), A refers to golden standard, B refers to control or experimental group	through study completion, an average of 6 months
Primary	contouring time	from time of CT loaded to end of contouring	through study completion, an average of 6 months
Secondary	difference of volume, DV	DV = (A-B) /B× 100%, A refers to golden standard, B refers to control or experimental group	through study completion, an average of 6 months
Secondary	recall, Rec	Rec = | AnB| / A, A refers to golden standard, B refers to control or experimental group	through study completion, an average of 6 months
Secondary	precision, Pre	Pre= |AnB| / B, A refers to golden standard, B refers to control or experimental group	through study completion, an average of 6 months
Secondary	rate of efficiency improvement	rate of efficiency improvement= (duration of independent investigator contouring-duration of software-assisted contouring)/ duration of independent investigator contouring*100%	through study completion, an average of 6 months
Secondary	satisfaction for AI contouring	satisfaction assessment utilizing Likert scale: 1, very unsatisfied; 2, somewhat unsatisfied; 3, modest; 4, somewhat satisfied; 5, very satisfied.	through study completion, an average of 6 months