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.
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).
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.
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.
Case-control
Retrospective
Colposcopy
Diagnostic testThe 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.
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.
Transformation Zone Classification Accuracy
The metric used includes accuracy, precision, recall, and F1-score for the classification of the transformation zone (TZ) in colposcopic images by the AI model. These metrics will assess the effectiveness of the AI model in identifying and classifying the transformation zone in colposcopic images.
Click on the lead sponsor to view all of their trials.
