It can be difficult to pick out cancerous cells from healthy ones, even under a microscope. One way to differentiate them is by measuring the level of acidity, or pH level, inside the cells.
Tapping on this distinguishing characteristic, a research team from the National University of Singapore (NUS), led by Professor Lim Chwee Teck, Director of the NUS Institute for Health Innovation & Technology (iHealthtech), developed a novel low-cost technique that uses artificial intelligence (AI), a pH-sensitive dye and a standard microscope with a digital camera to determine whether a single cell is healthy or cancerous by analysing its pH level. This approach produces results with an accuracy of more than 95 per cent.
“The ability to analyse single cells is one of the holy grails of health innovation for precision medicine or personalised therapy. Our proof-of-concept study demonstrates the potential of our technique to be used as a fast, inexpensive and accurate tool for cancer diagnosis,” said Lim, who is also the inaugural NUSS Chair Professor at the NUS Department of Biomedical Engineering.
Their method utilises bromothymol blue—a pH-sensitive dye that changes colour according to the level of acidity of a solution—by applying it to living cells. The cells are then illuminated and captured by a digital camera fitted to a standard microscope. As cancer cells have an altered pH, they react differently to the dye, resulting in a unique combination or ‘fingerprint’ of red, green and blue signals.
AI can define cancer and type
But the team didn’t just stop there. By developing an AI-based algorithm, they were able to quantitatively map unique acidic fingerprints, which can not only distinguish between cancerous and healthy cells but also accurately pinpoint different cell types.
This novel high-throughput method allows for thousands of cells from various cancerous tissues to be imaged simultaneously and single-cell features to be extracted and analysed.
Compared with current methods of cancer cell imaging that require several hours, the process developed by the team can be completed in less than 35 minutes each time.
“Unlike other cell analysis techniques, our approach uses simple, inexpensive equipment, and does not require lengthy preparation and sophisticated devices. Using AI, we are able to screen cells faster and accurately. Furthermore, we can monitor and analyse living cells without causing any toxicity to the cells or the need to kill them. This would allow for further downstream analysis that may require live cells," explained Lim.
The simple and low-cost technique accurately monitors and analyses living cells without causing toxicity to the cells.
Opening the door for faster detection
The research team is planning to develop a real-time version of this technique, which will allow the cells to be promptly separated for further downstream molecular analysis, such as genetic sequencing, to check for drug-treatable mutations.
“We are also exploring the possibility of performing real-time analysis on circulating cancer cells suspended in blood,” said Lim. “One potential application for this would be in liquid biopsy where tumour cells that escaped from a primary tumour can be isolated in a minimally-invasive fashion from bodily fluids such as blood.”
The team is looking forward to advancing their concept so that it can be used to accurately determine different stages of malignancies in cancer cells.
Adapted by Drima Chakraborty and Chua Li Min from: NUS News