We've updated our Privacy Policy to make it clearer how we use your personal data.

We use cookies to provide you with a better experience. You can read our Cookie Policy here.

Paving the way to Better Ovarian Cancer Diagnosis

Paving the way to Better Ovarian Cancer Diagnosis

Paving the way to Better Ovarian Cancer Diagnosis

Paving the way to Better Ovarian Cancer Diagnosis

Read time:

Want a FREE PDF version of This News Story?

Complete the form below and we will email you a PDF version of "Paving the way to Better Ovarian Cancer Diagnosis"

First Name*
Last Name*
Email Address*
Company Type*
Job Function*
Would you like to receive further email communication from Technology Networks?

Technology Networks Ltd. needs the contact information you provide to us to contact you about our products and services. You may unsubscribe from these communications at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy

Overseen by her thesis supervisor and in collaboration with B.C. Cancer Agency scientists, a Simon Fraser University doctoral student is developing a faster, more reliable way to diagnose ovarian cancer.

Computing science student Aïcha BenTaieb is designing a computer-aided diagnostic system at SFU’s Medical Image Analysis Lab that will more accurately and more quickly identify ovarian cancer’s many subtypes than the current technique.

Currently, before treatment can begin, pathologists use a microscope to identify tissue samples from cancerous ovarian tumours. According to OVCARE, a B.C.-based ovarian cancer research team, every three-and-a-half-hours in Canada a woman is diagnosed with ovarian cancer—one of the most fatal and least understood cancers. Time is of the essence.

With research help from SFU computing science professor Ghassan Hamarneh and B.C. Cancer Agency pathologists Drs. David Huntsman and Hector Li Chang, BenTaieb’s automated system will speed up decision-making on appropriate chemo- or radiation therapies.

“Traditional classification can be easily impaired by technical factors such as lighting and the pathologist’s experience,” explains BenTaieb. “Despite having guidelines for diagnosis, each pathologist has his or her own understanding of the disease, and the act of visually classifying something remains subjective. Classification can also be costly, as non-expert pathologists require long hours of training and additional testing might be needed.”

BenTaieb’s computer prototype is programmed to classify the appropriate cancer subtype using expert-annotated tissue-sample images. They have an agreed-upon subtype verified through biological testing.

The system’s built-in artificial intelligence is then able to interpret tissue samples and identify the appropriate cancer subtype by comparing the sample’s visual appearance to annotated images.

So far, the results have been promising. The system is already correctly classifying the subtypes in more than 92 per cent of cases.