Skip to main content

Main menu

  • About Us
    • Leadership
    • Our Team
    • Vision, Mission and Values
    • Health and Economic Impact
    • Strategic Plan
  • Our Research
    • Research Focus
      • Brain Health
      • Cancer
      • Cardiovascular Conditions and Diseases
      • Digital Health
      • Health Policy
      • Immunity and Infectious Diseases
      • Joint Health and Mobility
      • Respiratory and Lung Health
      • Spinal Cord Injury and Rehabilitation
    • Research Centres and Programs
      • BC Centre on Substance Use
      • Centre for Aging SMART
      • Centre for Cardiovascular Innovation
      • Centre for Clinical Epidemiology and Evaluation
      • Centre for Lung Health
      • Djavad Mowafaghian Centre for Brain Health
      • Immunity and Infection Research Centre
      • International Collaboration On Repair Discoveries
      • Ovarian Cancer Research Centre
      • Vancouver Prostate Centre
      • Community Research Program
      • Emergency Medicine Research Program
      • Hematology Research Program
      • Skin Research Program
      • Other Research Focus Areas
    • News and Stories
    • Researcher Directory
    • Events and Workshops
  • Research Services
    • New to VCHRI
      • Working at VCHRI
      • Regulations and Training
      • Membership with VCHRI
    • Starting Your Project
      • Research Facilitation
      • Awards and Funding
      • Grant Management
      • Operational Approval
    • Developing Your Project
      • Clinical Trials Administration
      • Clinical Research Unit
      • CST Cerner at VCH
      • Research Privacy
      • Financial Policies and Procedures
    • Additional Support
      • Education and Training
      • Communications and Branding
      • Media Relations
      • Study Recruitment Support
      • Innovation and Industry Partnership
    • Internal Awards
    • Clinical Research
    • Innovation and Partnership
  • Participate in Research
    • Reasons to Participate
    • Participant Stories
    • Find a Study
    • Recruitment Support

User menu

  • Log in

Breadcrumb

  1. Home
  2. Our Research
  3. News and Stories
  4. Enhancing ovarian cancer diagnostics using AI technology

Enhancing ovarian cancer diagnostics using AI technology

Stories Oct 13, 2022 3 minutes

Artificial intelligence algorithms could provide added support to remote communities and other areas that lack available specialists.

Ovarian cancer impacts over 3,100 Canadian women each year, making it the most lethal of all female reproductive cancers. A new study led by Vancouver Coastal Health Research Institute researcher Dr. Ali Bashashati is using artificial intelligence (AI) to aid pathologists in the diagnosis of ovarian cancer to improve patient outcomes.

Published in Modern Pathology in September 2022, Bashashati’s research builds on the understanding that ovarian cancer is not a single disease, but several distinct subtypes, called histotypes. 

Bashashati and his team compared ovarian cancer disease classifications made by an AI machine learning-based model against those of a team of expert gynecologic pathologists who specialize in the diagnosis of female reproductive cancers.

Using a cohort of 948 ovarian cancer tissue specimens from Vancouver General Hospital, Bashashati’s team developed a series of AI computer algorithms that can identify four histotypes of ovarian cancer with a high degree of accuracy.

“To the best of our knowledge, our AI model is the first of its kind to achieve the highest performance for ovarian carcinoma histotype diagnosis, approaching the performance level of expert gynecologic pathologists,” says Bashashati.

Each ovarian cancer histotype has unique characteristics and telltale signs that can nonetheless be difficult to identify in some cases.

There are several different subtypes, or histotypes, of ovarian cancer — shown under high magnification here — all of which hijack and alter healthy ovarian tissue cells.

Prior research has shown that general pathologists have weak to moderate interobserver agreement — the extent to which two or more experts agree — when it comes to ovarian cancer histotype classification, says Bashashati. Gynecologic pathologists, on the other hand, have strong to very accurate interobserver agreement.

Providing general pathologists with additional tools to achieve a higher interobserver agreement would support optimal diagnostics and the timeliest and best possible treatment approach. 

Advanced technology to extend the reach of specialist care

The AI algorithms Bashashati and his team developed were convolutional neural networks (CNNs) — highly advanced technology that attempts to mimic complex neurological connections in the human brain that support such thought processes as pattern recognition and deductive reasoning.

The research team’s CNNs overcame some of the challenges other similar CNNs previously faced, such as distinguishing between colours and other characteristics in tissue sample slides.

Dr. Ali Bashashati is the director of AI research at the Ovarian Cancer Research Program (OVCARE), as well as a faculty member in the School of Biomedical Engineering and the Department of Pathology and Laboratory Medicine at the University of British Columbia.

“When we tested our best-performing AI model using another cohort of 60 patients from a different Canadian hospital, the algorithm correctly diagnosed 52 of the cases,” says Bashashati. 

Expert gynecologic pathologists re-reviewed eight cases that were misclassified by the AI algorithm. In four of the eight cases, the experts ended up agreeing with the AI classification. 

“This means that the accuracy of our best-performing AI model approached 93 per cent, which is incredibly exciting.” 

Bashashati’s CNNs were designed to be transferable AI classification aids that could be used at various hospitals.

“Many community hospitals do not have a gynecologic pathologist on staff to assist a general pathologist with the classification of an ovarian cancer subtype,” says Bashashati. “As such, there is a great need to provide general pathologists with additional tools to aid them in ovarian cancer diagnosis, particularly given increased demand for specialists in remote communities and a limited number of available gynecologic pathologists across British Columbia.”

"Our AI models may provide a separate set of artificial eyes during clinical assessments to improve diagnostic performance when used alongside the assessment of a pathologist.”

Bashashati is now working to further validate these findings using an international cohort of 8,000 ovarian cancer tissue sample slides.

This research was supported by philanthropic funding from the Carraresi Foundation and Toigo Family through the VGH & UBC Hospital Foundation, along with a Canadian Institutes of Health Research grant.

 

Researchers

Ali Bashashati

Related Articles

B.C.-developed strategy reduces ovarian cancer risk: new study

Supporting women’s cancer journeys one listener at a time

Dry lab harnesses big data for gynecologic cancer research

Share:

  • Facebook
  • Linkedin
  • Twitter
  • Email

Related Research Centres/Programs

Ovarian Cancer Research Centre

Get the latest research headlines in your inbox

Subscribe

Recent News and Stories

Type
Announcement

Investigator Awards 2023 Recipients

Mar 21, 2023 award
Type
Stories

Ask an expert: Is my menstrual pain normal, or could I have endometriosis?

Mar 16, 2023 women, endometriosis, preventative
Type
Stories

Honing in on precision treatments for endometriosis

Mar 14, 2023 genetics, treatment options
See more news

Get updates!

Join our newsletter mailing list to stay up to date on features and releases.

Subscribe

Quick Links

  • News and Stories
  • Careers
  • Events
  • Media Enquiries

Follow Us

  • Twitter
  • LinkedIn

© 2023 VCHRI. All rights reserved.

  • Contact
  • Privacy Policy