A team of researchers from the Hong Kong University of Science and Technology (HKUST) in China developed an AI-based microscopic imaging system.

The system, named Computational High-throughput Autofluorescence Microscopy by Pattern Illumination (CHAMP), aims to transform the precision of tumour tissue assessment during cancer surgeries.

CHAMP is designed to offer a direct, rapid, and high-quality visualisation of cancer cells, potentially reducing the need for repeat surgeries.

It can detect cancer cells within just three minutes, achieving an accuracy rate exceeding 90%. This performance is on par with the one-week turnaround of conventional tests.

Using ultraviolet (UV) light, the system can excite tissue samples at a specific wavelength, creating a greyscale image.

Subsequently, a deep learning algorithm developed by the HKUST team transforms this image into a histological view, allowing for immediate interpretation by medical professionals.

The CHAMP technology does not require any tissue processing and is a versatile platform applicable to various organ types.

The research has so far led to the filing of six US provisional invention patents.

Additionally, the research team is exploring the technology's use for liver, colorectal, kidney, skin, and prostate cancer on a smaller scale.

With the support of the Research, Academic and Industry Sectors One-plus (RAISe+) scheme, HKUST is gearing up for a large-scale multi-centre clinical trial across five hospitals.

The trial will include Queen Mary Hospital and Prince of Wales Hospital in Hong Kong, along with Peking University Shenzhen Hospital, the People’s Hospital of Guangxi Zhuang Autonomous Region, and Anyang Tumor Hospital on the Chinese Mainland.

In addition, HKUST School of Engineering department of chemical and biological engineering associate professor Terence Wong established the medtech start-up PhoMedics Limited.

PhoMedics focuses on commercialising the CHAMP system, which is currently intended for lung and breast cancer applications.