Cancer cells that commence metastasis, or the spread of the illness from its originating location, vary from cancer cells that remain in the original tumour.

Differentiating metastasis-initiating cell types can help doctors identify the severity of malignancy and plan a treatment plan.

Texas Tech University researchers developed a deep learning model to categorise cancer cells by kind in APL Machine Learning, published by AIP Publishing.

The instrument takes only a basic microscope and a little amount of computational power to provide results that are comparable to or better than more advanced and complex procedures.

"Cancer cells are highly heterogeneous, and recent studies suggest that specific cell subpopulations, rather than the whole, are responsible for cancer metastasis," said author Wei Li. "Identifying subpopulations of cancer cells is a critical step to determine the severity of the disease."

Current methods to categorise cancer cells involve advanced instruments, time-consuming biological techniques, or chemical labels.

"The problem with these complicated and lengthier techniques is that they require resources and effort that could be spent exploring different areas of cancer prevention and recovery," said author Karl Gardner.

Some studies use magnetic nanoparticles to track cancer cells, but attaching these labels could affect the downstream analysis of the cells and the integrity of the measurements.

"Our classification procedure does not consist of additional chemicals or biological solutions when taking pictures of the cells," said Gardner. "It is a 'label-free' identification method of metastatic potential."

The team's neural network is also simple to use, efficient, and automated. After feeding it an image, the tool converts the data to a probability. A result lower than 0.5 categories cancer as one cell type, while a number higher than 0.5 designates another.