Multi-center Application of an AI System for Diagnosis of Cervical Lesions Based on Colposcopy Images

NCT05281939 | Unknown

• 1 other identifier: AICC2203
• Study Type: interventional
• Target: 10,000
• Locations: 1 country
• Sites: 5

Brief Summary

The application of artificial intelligence in image recognition of cervical lesions diagnosis has become a research hotspot in recent years. The analysis and interpretation of colposcopy images play an important role in the diagnosis，prevention and treatment of cervical precancerous lesions and cervical cancer. At present, the accuracy of colposcopy detection is still affected by many factors. The research on the diagnosis system of cervical lesions based on multimodal deep learning of colposcopy images is a new and significant research topic. Based on the large database of cervical lesions diagnosis images and non-images, the research group established a multi-source heterogeneous cervical lesion diagnosis big data platform of non-image and image data. Research the lesions segmentation and classification model of colposcopy image based on convolutional neural network, explore the relevant medical data fusion network model that affects the diagnosis of cervical lesions, and realize a multi-modal self-learning artificial intelligence cervical lesion diagnosis system based on colposcopy images. The application efficiency of the artificial intelligence system in the real world was explored through the cohort, and the intelligent teaching model and method of cervical lesion diagnosis were further established based on the above intelligent system.

Conditions

Artificial Intelligence; Colposcopy; Cervical Lesions; Image

Outcome Measures

Primary Outcomes (5)

• HPV testing

  Cervical exfoliated cells were collected for HPV testing

  o month

• Cervical cytology testing

  Cervical exfoliated cells were collected for cytological and pathological examination.

  0 month

• Cervical histopathological examination

  Cervical tissue was collected for histopathological examination

  0 month

• Accuracy of CIN2+ diagnosis

  Accuracy in the diagnosis of cervical intraepithelial neoplasia grade 2 or worse.

  0 month

• Accuracy of CIN3+ diagnosis

  Accuracy in the diagnosis of cervical intraepithelial neoplasia grade 3 or worse.

  0 month

Study Arms (2)

Artificial intelligence diagnostic group

ACTIVE COMPARATOR

Women who show abnormalities in cervical cancer screening and require referral for colposcopy. Colposcopy was performed with the aid of an Artificial intelligence (AI) system.

Diagnostic Test: Artificial intelligence diagnosis

Gynecologist diagnostic Group

NO INTERVENTION

Women who show abnormalities in cervical cancer screening and require referral for colposcopy. Colposcopy is performed independently by a gynecologist without any external assistance.

Interventions

Artificial intelligence diagnosis DIAGNOSTIC_TEST

Participants were divided into the intervention group and the control group using a random number table. The intervention group participants' cervical colposcopic image data and non-image data as follow：age, the infection of high-risk human papillomavirus (HR-HPV),the type of HR-HPV infection,the duration of HR-HPV infection, cervical cytology (TCT) results, HIV/sexually transmitted infection history, marriage and childbearing history,first sexual life history, sexual partner history, smoking history,oral contraceptives history,the use of immune drug and possible clinical symptoms of cervical lesions such as postcoital bleeding, abnormal vaginal secretions, vaginal bleeding symptoms, etc.

Artificial intelligence diagnostic group

Eligibility Criteria

• Age: 18 Years+
• Sex: female
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Married woman
• Woman aged 18 and over
• Woman with an intact cervix
• Patients with abnormal results in cervical cancer screening
• Be able to understand this study and have signed a written informed consent

You may not qualify if:

• Woman with acute reproductive tract inflammation
• History of pelvic radiotherapy surgery
• Woman with mental disorder
• Patients with history of other malignant tumors
• Refuse to participate in this study

Sponsors & Collaborators

• Fujian Maternity and Child Health Hospital: lead

Study Sites (5)

Fujian Maternity and Child Health Hospital

Fuzhou, Fujian, 350001, China

RECRUITING

Mindong Hospital of Ningde City

Ningde, Fujian, 352000, China

RECRUITING

Jianou Maternal and child Health Care Hospital

Nanping, China

RECRUITING

Ningde Hospital affiliated to Ningde Normal University

Ningde, China

RECRUITING

Quanzhou First Hospital

Quanzhou, China

RECRUITING

Study Officials

• Pengming Sun, PhD

  Fujian Maternity and Child Health Hospital, Affiliated Hospital of Fujian Medical University

  STUDY CHAIR

Central Study Contacts

Binhua Dong

CONTACT

+8613599071900; dbh18-jy@126.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: TRIPLE
• Who Masked: PARTICIPANT, INVESTIGATOR, OUTCOMES ASSESSOR
• Masking Details: Masking was performed for all participants, colposcopists, and outcome assessor.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Model Details: Participants were randomly assigned to an Artificial intelligence (AI) group or a control group.

Study Record Dates

• First Submitted: March 7, 2022
• First Posted: March 16, 2022
• Study Start: August 1, 2021
• Primary Completion: August 1, 2024
• Study Completion: September 1, 2024
• Last Updated: November 18, 2023

Record last verified: 2023-11

Locations

CN (5)