AI Model for Cervical Cancer Detection From Colposcopy Images

NCT06644248 | Recruiting

• 1 other identifier: ISMC/Admin/2023/2149
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

Cervical cancer is a significant health issue, particularly in low-income countries, where late diagnosis and limited access to screenings contribute to high mortality rates. This study aims to develop and evaluate an artificial intelligence (AI) model to analyze colposcopic images for detecting cervical cancer more accurately and efficiently. Colposcopy, a procedure used to examine the cervix for signs of cancer, relies heavily on doctors' expertise, leading to inconsistent results. The current gold standard, colposcopy-directed biopsy, is invasive and can cause complications. The hypothesis is that an AI model can outperform traditional methods in identifying cervical abnormalities, providing a reliable and scalable solution for early detection, especially in underserved areas. By automating the analysis process, the AI model aims to reduce reliance on trained personnel, making cervical cancer screening more accessible and improving early diagnosis and treatment outcomes. The study will create a diverse dataset of colposcopy images from various sources and develop the AI model. The model's performance will be validated in clinical settings, assessing its accuracy in classifying cancer stages and identifying transformation zones. The impact on early detection, patient outcomes, and model usability will be evaluated, as well as its generalizability across different healthcare environments. The goal is to enhance the accuracy and efficiency of cervical cancer screening, ultimately reducing mortality rates and improving patient care.

Conditions

Uterine Cervical Neoplasms

Keywords

Cervical Cancer; Colposcopy; Deep Learning; Transformation Zones

Outcome Measures

Primary Outcomes (1)

• Swede Score Evaluation

  The Swede score will be used to evaluate the severity of cervical abnormalities identified in colposcopic images. This scoring system assesses various colposcopic findings, including acetowhiteness, lesion size, and vascular patterns, to determine the effectiveness of the AI model in evaluating cervical abnormalities.

  12 hours

Secondary Outcomes (1)

• Transformation Zone Classification Accuracy

  12 hours

Study Arms (1)

Self reported uterine distress undergoing colposcopic evaluation

The study group consists of women undergoing cervical cancer screening. This includes those with suspected cervical abnormalities identified through initial cytology or HPV tests and referred for colposcopy. The study group also includes women without apparent cervical abnormalities to ensure a comprehensive dataset. The aim is to develop an AI model capable of accurately diagnosing cervical cancer and identifying transformation zones in colposcopic images. This diverse group allows for the evaluation of the AI model across a wide range of conditions and exposures, enhancing its generalizability and clinical utility.

Diagnostic Test: Colposcopy

Interventions

Colposcopy DIAGNOSTIC_TEST

The intervention involves the use of colposcopy, a diagnostic procedure to visually examine the cervix using a colposcope. The procedure includes the application of saline, acetic acid, and iodine solutions to enhance the visualization of cervical tissues and identify abnormalities. The dosage form includes applying these solutions directly to the cervical area. The frequency of the intervention is typically a single session per patient, with the duration of the procedure lasting approximately 10-15 minutes. This study aims to utilize an AI model to analyze the colposcopic images obtained during the procedure to improve the accuracy and efficiency of cervical cancer detection.

Self reported uterine distress undergoing colposcopic evaluation

Eligibility Criteria

• Age: 18 Years+
• Gender Eligibility Details: The eligibility for this clinical study is based on gender, specifically targeting female participants. This criterion is due to the study's focus on cervical cancer, a condition that exclusively affects individuals with a cervix. Participants must be women who are referred for colposcopy due to abnormal cytology or HPV test results. The inclusion of only female participants ensures that the study accurately addresses the detection and diagnosis of cervical cancer through colposcopic examination and the evaluation of the AI model's performance in this context. No male participants are included as cervical cancer does not occur in the male population.
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The study cohort will consist of women referred to colposcopy clinics due to abnormal cytology, positive HPV tests, or self-reported cervical distress requiring evaluation. Participants will be sourced from listed primary care clinics, ensuring a diverse sample across age groups and socioeconomic backgrounds for comprehensive representation. The project aims to assess the AI model's efficacy in detecting cervical anomalies in a real-world clinical context, evaluating its performance across diverse populations and addressing the unique challenges of cervical cancer screening in varied healthcare settings.

You may qualify if:

• Female patients of age 18 years or older can be selectedas subjects.
• Individuals willing to participate in cervical cancerscreening.
• Availability for colposcopic examination.
• Women with no history of hysterectomy (total removalof the uterus).
• Women with no current or prior diagnosis of cervicalcancer.
• Availability of relevant medical records forconfirmation and comparison purposes.

You may not qualify if:

• Pregnant women, given the potential impact onscreening results and the need for specialconsiderations during pregnancy.
• Individuals with severe medical conditions orcircumstances that may make colposcopic examinationinappropriate or unsafe.
• Patients with conditions that could interfere with theaccuracy of the screening results, such as severevaginal bleeding.
• Follow-up screenings.

Sponsors & Collaborators

• Bangladesh University of Engineering and Technology: lead

Study Sites (1)

Ibn Sina Medical College Hospital

Dhaka, 1216, Bangladesh

RECRUITING

MeSH Terms

Conditions

Uterine Cervical Neoplasms

Interventions

Colposcopy

Condition Hierarchy (Ancestors)

Uterine Neoplasms; Genital Neoplasms, Female; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Uterine Cervical Diseases; Uterine Diseases; Genital Diseases, Female; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Genital Diseases

Intervention Hierarchy (Ancestors)

Diagnostic Techniques, Obstetrical and Gynecological; Diagnostic Techniques and Procedures; Diagnosis; Endoscopy; Diagnostic Techniques, Surgical; Minimally Invasive Surgical Procedures; Surgical Procedures, Operative; Obstetric Surgical Procedures; Gynecologic Surgical Procedures; Urogenital Surgical Procedures

Study Officials

• Taufiq Hasan, Taufiq

  Department of Biomedical Engineering, BUET, Dhaka - 1205.

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Taufiq Hasan, PhD

CONTACT

+8801817579844; taufiq@bme.buet.ac.bd

Raiyun Kabir, B.Sc.

CONTACT

+8801521525834; razeenraiyun99@gmail.com

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Study Record Dates

• First Submitted: July 30, 2024
• First Posted: October 16, 2024
• Study Start: January 11, 2024
• Primary Completion: January 11, 2025
• Study Completion: February 11, 2025
• Last Updated: October 16, 2024

Record last verified: 2024-10

Data Sharing

• IPD Sharing: Will not share

Locations

BA (1)