The detection of illness is essential for its treatment. The interpretation of medical images plays an increasingly dominant role in diagnoses, and the help sometimes comes from the engineering sciences.
Prof Heng Pheng-Ann, a biomedical engineer, and his team in the Department of Computer Science and Engineering of The Chinese University of Hong Kong (CUHK) have developed an artificial intelligence (AI) platform for analysing medical images, enabling quick and accurate identification of the source of illness and hence timely and appropriate treatment.
“It mimics how our brains receive visual stimuli from the eyes to construct meaningful output. The AI platform will analyse and interpret the data collected, following the instructions of the clinicians or the platform engineers.” Professor Heng explains how the system works.
Achieving accuracies of 91% and 99% respectively on the detection of lung and breast cancer, the platform now acts as a tireless and reliable assistant to doctors. Traditionally, the screening of pulmonary nodules, a sign of early lung cancer, on a medical image by a radiologist takes about five minutes; now it can be done in merely 30 seconds. The same goes for breast cancer cells, whose detection by AI in five to 10 minutes emulates that by the naked eye which takes a quarter to half an hour.
What’s more, the AI platform is capable of deep learning. To train it up to identify false positives that bear resemblance to the cancerous nodules, Professor Heng’s team exposed the platform to the suspected samples, while annotating and locating the exact nodules for the system to learn from real examples.
Running since 2013, the AI system has analysed over 5,000 samples from patients of different nationalities.
Positive feedback from the medical sector has prompted a wider application of the platform and more collaborations to come. The research team is now joining hands with Sun Yat-sen University Cancer Center on AI-assisted delineation of the targeted area for radiotherapy for nasopharyngeal cancer. The technology is also commercialised under ImSight Medical Technology, a startup founded and headed by Professor Heng devoted to developing medical image analysis software, and receives ample funds from government and the commercial sector. In February this year, ImSight even came to forge a partnership with CUHK’s Shenzhen Research Institute for research and development.
“Big data is transforming medicine. We’re in the new era seeing how the medical diagnoses are optimised by data-driven insights. Together with the healthcare professionals, we’re producing the best outcomes for patients.” Professor Heng says.