;
Asian model fists her palm against the cancer.

SINGAPORE: AI has become Singaporean women’s new ally against breast cancer. The process of screening for breast cancer through mammogram images may be revolutionised thanks to a technology developed by FathomX, a Singapore-based medical technology start-up.

As reported by The Edge Singapore, currently, detecting signs of breast cancer in mammogram images is not very easy. These images display the breast in shades of grey and white against a black background, with dense tissues appearing as white areas.

The challenge lies in distinguishing between benign and malignant abnormalities, a task made even more difficult in dense breasts, which are common among Asian women.

According to the US National Cancer Institute, there’s a 20% chance that mammograms may miss breast cancers present at the time of screening.

This, coupled with the weeks-long wait for results, contributes to unnecessary anxiety and deters many women from undergoing screening.

According to the National Population Health Survey 2022, only 37.6% of women aged 50 to 69 in Singapore had undergone mammography in the past two years.

Recognising the urgent need for improvement, FathomX developed FxMammo, an AI-powered radiological computer-assisted detection software.

See also  Singapore central bank pledges $100M to boost AI and quantum technologies in finance

This innovative tool analyses mammogram images, quickly identifying suspicious cases and assisting radiologists in making accurate diagnoses.

It functions as an assistant, highlighting potential lesions and providing a malignancy probability score, significantly reducing both false positives and false negatives.

According to Mr Stephen Lim, CEO of FathomX, There is no cure yet for breast cancer. So, early discovery will help improve the survival rate and reduce the medical costs associated with the necessary treatment.

Singapore’s screening rate is below the World Health Organization’s recommended level, and among the bottlenecks are the long waiting time [for mammogram results and the shortage of] radiologists.”

Professor Mikael Hartman and Professor Feng Meng Ling, founders of FathomX, spearheaded the development of FxMammo.

Professor Hartman said, Mammograms are inherently difficult to read [by relying on the naked eye]. Today, mammogram images are digital and we have readily available AI tools, computing power for AI, and datasets to train AI.

See also  Jasper secures S$9M investment for AI digitalisation for maritime operations

So, it makes sense to use AI to detect breast cancer from mammogram images better.”

Their solution emerged as a frontrunner in The Dream Challenge, an initiative the United States Whitehouse organised to promote AI technologies in healthcare.

Recognising its potential, FathomX spun off from the National University of Singapore with the support of NUS Enterprise.

FathomX collaborates with top universities and hospitals across Asia to validate the software’s accuracy and effectiveness. 

The company collaborates with leading universities and hospitals across Asia-Pacific, including Japan, Taiwan, China, Hong Kong, Thailand, Malaysia, Australia, and Singapore, to assess FxMammo’s precision and efficacy.

Hospitals such as Tokyo Medical & Dental University, National Cancer Centre Hospital East in Japan, and Chulalongkorn Hospital in Thailand use FxMammo on patients.

In Singapore, radiologists from NUH’s Department of Diagnostic Imaging are conducting a study on FxMammo, but it has not yet been integrated into patient services.

According to the company, the AI-powered tool can slash diagnosis times to minutes and reduce false positives by over 20% and false negatives by more than 38%.

See also  2 in 5 IT experts advocate AI adoption for cybersecurity

FathomX designed FxMammo to integrate seamlessly into existing healthcare systems and encourage widespread adoption.

Mr Lim, CEO of FathomX, emphasises the importance of scalability and ease of integration, particularly in Asia, where dense breasts are more prevalent.

He also said, “AWS’s compute service, Amazon EC2, provided us with the horsepower to train our AI model.

Also, as healthcare AI applications evolve, the demand for more advanced algorithms and larger datasets grows, which is why we need scalable computing infrastructure.”

Looking ahead, FathomX aims to expand its suite of AI-powered tools to enhance breast cancer screening further.

By working with organisations like Enterprise Singapore, AWS Activate and the National Health Innovation Centre’s Innovation, the start-up is poised to scale its solutions globally, making high-quality breast cancer screening accessible to more women while reducing healthcare costs. /TISG

Read also: Local research team bring new hope for paralyzed people with spinal cord injuries to stand again

Featured image by Depositphotos