Clinical Validation of AI-Assisted Radiotherapy Contouring Software for Thoracic Organs At Risk

Completed

• Conditions: Breast Cancer; Esophageal Cancer; Lung Cancer
• Interventions: Device: contouring of thoracic organs at risk

• Registration Number: NCT05787522
• Lead Sponsor: Tianjin Medical University Cancer Institute and Hospital

Brief Summary

The goal of this clinical trial is to evaluate performance and clinical applicability of AI-assisted radiotherapy contouring software for thoracic organs at risk. The main question it aims to answer is:

• Does AI-assisted contouring (AI contouring with manual modification) offer greater accuracy and time efficiency compared to manual contouring? After screening, the qualified participants' thoracic CT images will be anonymized and segmented using three methods: manual, AI (AI-only), and AI-assisted contouring. The researchers will compare the results generated by the three different contouring methods with the ground truth established by expert consensus, in order to evaluate both accuracy and time-related parameters

Detailed Description

Not available

Study Timeline

• Study Start: 2022-09-30
• Study First Submitted: 2023-03-02
• Study First Submitted QC: 2023-03-27
• Study First Posted: 2023-03-28
• Primary Completion: 2023-07-27
• Status Verified: 2024-03
• Study Completion: 2024-03-06
• Last Update Submitted: 2024-10-25
• Last Update Posted: 2024-10-29

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 500

Inclusion Criteria

1. ≥18 years old, no gender limit.
2. Patients diagnosed with breast cancer, lung cancer, or esophageal cancer, who are scheduled for chest CT scanning followed by thoracic 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 malformations or abnormal anatomical structures resulting from non-tumor factors in the scan area.
2. Artifact, prosthesis or implantation causing images undistinguishable.
3. CT images not conforming to DICOM standards.
4. Investigators consider not suitable.

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
control group	contouring of thoracic organs at risk	independent investigator contouring of thoracic organs at risk
experimental group	contouring of thoracic organs at risk	software-assisted contouring of thoracic organs at risk
golden standard group	contouring of thoracic organs at risk	contouring of thoracic organs at risk by a team of experts, in which contours by two experts separately will be arbitrated by the third expert as the golden standard

Primary Outcome Measures

Name	Time	Method
DICE similarity coefficient, DSC	Within 6 months after enrollment	DSC= 2×（A∩B）/(A+B), A refers to the volume of ground-truth, B refers to the volume of manual, AI, or AI-assisted contouring.
Contouring time (min)	Within 6 months after enrollment	Manual contouring time is recorded from the time the CT is loaded on the contouring platform to the completion of contouring. AI-assisted contouring time is defined as the sum of the auto-segmentation model runtime, the transfer to the contouring platform, and the subsequent manual modification.

Secondary Outcome Measures

Name	Time	Method
Volumetric revision index, VRI	Within 6 months after enrollment	VRI = \[(A- A∩B) + (B- A∩B)\] /A, A refers to the volume of ground-truth, B refers to the volume of manual, AI, or AI-assisted contouring
Rate of time efficiency improvement	Within 6 months after enrollment	Rate of efficiency time improvement= (manual contouring duration - AI-assisted contouring duration)/ manual contouring duration\*100%
Rate of volume difference, DV	Within 6 months after enrollment	DV = (A-B) /B, A refers to the volume of ground-truth, B refers to the volume of manual, AI, or AI-assisted contouring
Recall, Rec	Within 6 months after enrollment	Rec = \| A∩B\| / A, A refers to the volume of ground-truth, B refers to the volume of manual, AI, or AI-assisted contouring
Precision, Pre	Within 6 months after enrollment	Pre= \|A∩B\| / B, A refers to the volume of ground-truth, B refers to the volume of manual, AI, or AI-assisted contouring
Investigators satisfaction score for AI contouring	Within 6 months after enrollment	Evaluated on a 1-5 Likert scale: 1 - very dissatisfied, 2 - somewhat dissatisfied, 3 - neutral, 4 - somewhat satisfied, 5 - very satisfied. Assessment conducted after AI-assisted contouring by the investigators.

Trial Locations

Locations (1)

Tianjin Medical University Cancer Institute and Hospital, Tianjin Key Laboratory of Cancer Prevention and Therapy; 🇨🇳 Tianjin, Tianjin, China