Deep Learning-based sbORN Diagnostic Model

Nasopharyngeal Carcinoma Clinical Trial

Official title:

Development of Deep-Learning-Based Multimodal Post Radiotherapy Skull-Base Osteonecrosis and Recurrence of Nasopharyngeal Carcinoma Differential Diagnostic Model

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT06463392
• Other study ID #: SYSKY-2024-395-02
• Status: Not yet recruiting
• Start date: June 20, 2024
• Est. completion date: December 31, 2030

Study information

• Verified date: June 2024
• Source: Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
• Contact: Xiang-Wei Kong, Ph.D.
• Phone: 0086-020-34071439
• Email: kongxw8[@]mail.sysu.edu.cn
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Skull-base osteonecrosis (sbORN) is a severe long-term complication of nasopharyngeal carcinoma (NPC) post radiotherapy, which significantly diminish the quality of life, increase the risk of internal carotid artery rupture, and is frequently misdiagnosed as NPC recurrence. Novel diagnostic tools are therefore clinically significant. In this study, the investigators seek to ask if a deep-learning-based model shows a significantly higher sensitivity than radiologists. With a cross-sectional design, the investigators aim to recruit 312 participants in Sun Yat-sen Memorial Hospital, Guangzhou, China that meet the eligibility criteria.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 312
• Est. completion date: December 31, 2030
• Est. primary completion date: December 31, 2029
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Equal to or older than 18 years old.

• A history of histologically confirmed nonkeratinizing undifferentiated nasopharyngeal carcinoma.

• A history of radical radiotherapy at nasopharynx.

• Complete remission six months post radical radiotherapy according to RECIST 1.1.

• No evidence of distant metastasis upon recruitment.

• Diagnosis of sbORN given by senior radiologist with 2-4 Likert scores.

• Consent to biopsy awake or under general anesthesia.

• Consent to perform blood tests, EBV DNA, EBV IgAs, and MRI inspection of nasopharynx and neck.

• With a written consent.

Exclusion Criteria:

• MRI artifacts or other factors that interfere radiological diagnosis and region of interest contouring.

• Suspected lesion is not confined to nasopharynx and skull-base.

Related Conditions & MeSH terms

• Carcinoma
• Herpesvirus 4, Human
• Nasopharyngeal Carcinoma

Locations

Country	Name	City	State
China	Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University	Guangzhou	Guangdong

Sponsors (2)

Lead Sponsor	Collaborator
Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University	Sun Yat-sen University

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Other	The number of white blood cells in the peripheral blood.		Baseline
Other	The number of neutrophils in the peripheral blood.		Baseline
Other	The number of basophils in the peripheral blood.		Baseline
Other	The number of eosinophils in the peripheral blood.		Baseline
Other	The number of red blood cells in the peripheral blood.		Baseline
Other	The concentration of albumin in the peripheral blood.		Baseline
Other	The concentration of total protein in the peripheral blood.		Baseline
Other	The history of diabetes mellitus.		Baseline
Other	The history of hypertension.		Baseline
Other	The copy number of Epstein-Barr Virus (EBV) DNA.		Baseline
Other	The titer of EBV VCA IgA.		Baseline
Other	The titer of EBV EBNA1 IgA.		Baseline
Other	The titer of EBV EA IgA.		Baseline
Primary	Area under curve of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Primary	Area under curve of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	Sensitivity of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Secondary	Specificity of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Secondary	F1 score of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Secondary	Positive predictive value of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Secondary	Negative predictive value of the differential diagnosis of sbORN and NPC recurrence delivered by the deep-learning-based multimodal model.		Baseline
Secondary	Sensitivity of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	Specificity of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	F1 score of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	Positive predictive value of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	Negative predictive value of the differential diagnosis of sbORN and NPC recurrence delivered by the radiologists.		Baseline
Secondary	Dice similarity coefficient of the MRI contouring between the deep-learning-based multimodal model and the radiologists.		Baseline
Secondary	Average surface distance of the MRI contouring between the deep-learning-based multimodal model and the radiologists.		Baseline