Skip to main content
An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted.

The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov.

Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

EASTER Project Phase 1: Advancing Affordable AI-Driven Systems for Cervical Cancer Screening, Triage, and Treatment

  • Date: Monday, June 16, 2025
  • Time: 11:00am EDT to 12:00pm EDT

On This Page

  • All Heading 2s will automatically be pulled in to this list.
  • Do not edit the content on this template.

Speaker

Mary Luz Rol, Ph.D.

Mary Luz Rol, Ph.D.
Scientist
Early Detection, Prevention & Infections Branch
IARC-WHO

Biography

I am Dr. Mary Luz Rol. In 2017, I joined the World Health Organization's International Agency for Research on Cancer (IARC-WHO), motivated to improve equal access to high-quality healthcare for everyone. Currently, I lead an IARC team dedicated to eliminating cervical cancer as a public health priority in accordance with WHO targets. I manage the EASTER project, which tests novel, low-cost AI-based screening, triage, and treatment methods for cervical cancer and precancer in low- and middle-income countries.

Furthermore, I coordinate the "Cancer Screening in Five Continents" (CanScreen5) training effort in 27 countries, including 17 francophone African countries and 10 Asian countries. CanScreen5 aims to help countries collect and use cancer screening data in order to assess and improve the quality of national screening programs.

Previously, I oversaw the ESTAMPA clinical trial. ESTAMPA evaluated several approaches for implementing primary HPV screening and triage of HPV-positive women throughout nine Latin American countries.

Abstract

EASTER project aims to develop and validate an affordable, AI-driven dual system for cervical cancer screening, triage, and treatment. Phase 1, launched in Harare, Zimbabwe, enrolled 1,100 women by December 2024. Participants aged 25-49 provided self-collected vaginal and urine samples. Vaginal samples were tested with ScreenFire, and urine samples are being analyzed with COBAS and AI-driven FTIR spectroscopy. During colposcopy, cervical images were captured using the nGyn system, the second AI-tool under development to predict precancers and guide treatment. Of 1,090 valid vaginal HPV results, 28% were HPV-positive. FTIR signals were successfully collected locally. Colposcopy attendance is 74%, cervical images were collected, and follow-up is ongoing. External histology review has confirmed 40 HSIL cases. Initial AI training for spectroscopy achieved 82% concordance with HPV ScreenFire results. Further analysis, including urine COBAS and nGyn image data, is ongoing. While FTIR spectroscopy shows promise, additional data is needed to enhance model robustness.