AI diagnoses major cancer with near perfect accuracy | Charles Darwin University
Skip to main content
You are viewing this website as a Domestic Student You are viewing this website as an International Student Switch to Domestic International
You are viewing this website as a Domestic Student
You are viewing this website as an International Student
Domestic Student
I am an Australian or New Zealand citizen.
I am an Australian Permanent Resident (including Humanitarian Visa holders).
I am a Domestic Student
International Student
I am not a citizen of Australia or New Zealand.
I am not an Australian permanent resident or Humanitarian Visa holders.
I am an International Student
Still unsure? Contact Student Central.
Close
Search Menu
Search
Search Close
Search Charles Darwin University
Search
Search for
General
Courses
Current Students
Staff
Research Portal
Governance Library
Close
Start of main content
- Home
- Newsroom
- AI diagnoses major cancer with near perfect accuracy
AI diagnoses major cancer with near perfect accuracy
14 March 2025
The model enhances the images in various ways to highlight the most important area and analyse tissue.
One of Australia's most common gynaecological cancers could be detected sooner and more accurately thanks to a specialised Artificial Intelligence (AI) model, new research shows.
Researchers from Daffodil International University in Bangladesh, Charles Darwin University, the University of Calgary and Australian Catholic University developed an AI model which can detect endometrial cancer with 99.26 per cent accuracy.
Endometrial cancer is the most common gynecological cancer in Australia and one of the most diagnosed cancers in Australian women, according to the Cancer Council.
The model, called ECgMPL, examines histopathological images, which are microscopic images of tissue used in disease analysis. The model enhances the quality of the images, identifies the most important areas and analyses the tissue.
The current endometrial accuracy using automated diagnosis is reported to be approximately 78.91 per cent to 80.93 per cent.
Co-author and CDU Lecturer in Information Technology Dr Asif Karim said the model could enhance clinical processes.
“The proposed ECgMLP model outperforms existing methods by achieving 99.26 per cent accuracy, surpassing transfer learning and custom models discussed in the research while being computationally efficient,” Dr Karim said.
“Optimised through ablation studies, self-attention mechanisms, and efficient training, ECgMLP generalises well across multiple histopathology datasets thereby making it a robust and clinically applicable solution for endometrial cancer diagnosis.”
Co-author and CDU adjunct Associate Professor Niusha Shafiabady, who is also an Associate Professor at Australian Catholic University, said the model also had benefits outside of endometrial cancer diagnosis.
“The same methodology can be applied for fast and accurate early detection and diagnosis of other diseases which ultimately leads to better patient outcomes,” Associate Professor Shafiabady said.
“We evaluated the model on several histopathology image datasets. It diagnosed colorectoral cancer with 98.57 per cent accuracy, breast cancer with 98.20 per cent accuracy, and oral cancer with 97.34 per cent accuracy.
“The core AI model developed through this research can be adopted as the brain of a software system to be used to assist the doctors for decision-making in cancer diagnosis.”
ECgMLP: A novel gated MLP model for enhanced endometrial cancer diagnosis was published in the journal Computer Methods and Programs in Biomedicine Update.
Share this page
Related Articles
-
25 March 2025
“But officer, I wasn’t driving!”: Research reveals the problem with self-driving cars and traffic laws
Self-driving vehicles are becoming more commonplace on our roads but the traffic legislation keeping them in check is not up to speed, according to new research led by Charles Darwin University.
Read more about “But officer, I wasn’t driving!”: Research reveals the problem with self-driving cars and traffic laws
-
13 March 2025
Birds of a feather: Unexpected relationships take flight in the face of climate change
The pressures of climate change may be strengthening bonds between unlikely allies in Central Australia’s bird community as species are forced to work together to access life-saving resources, a study has found.
Read more about Birds of a feather: Unexpected relationships take flight in the face of climate change
-
12 March 2025
New breakthrough from CDU researchers could improve detection of potentially fatal sleep disorder
Many Australians could be suffering from undiagnosed Obstructive Sleep Apnoea (OSA), with CDU researchers developing a new technique to screen for the potentially fatal condition.
Read more about New breakthrough from CDU researchers could improve detection of potentially fatal sleep disorder
Back to top
Charles Darwin University acknowledges the traditional custodians across the lands on which we live and work, and we pay our respects to Elders past, present and emerging.
CRICOS Provider No: 00300K RTO Provider No: 0373 TEQSA Provider ID PRV12069
ABN 54 093 513 649 | Privacy | Copyright and Disclaimer | Cookies | Feedback
Shortlist
0
Your Shortlist
Your Shortlist is empty
Find courses and add them to your shortlist by clicking on the
Your Shortlist was sent to your inbox
It may take up to 5 minutes.
Return to Shortlist
Course
Course Code
Add some items to your shortlist
Send Shortlist to...
Email AddressSend
Cookie compliance notice
We use cookies to improve our service. By continuing you agree to our privacy statement. EU/EA members can update your cookie settings here.
Accept