Cancer is classified in two ways. One is the type of tissue in which the cancer originates (histotype), and the other is the primary site, or the location in the body where the cancer first formed. Researchers at Texas Tech University have now developed a deep learning model that classifies cancer cells by type. Deep learning networks analyze images to classify cell types accurately and efficiently.
The survey results are APL machine learning In an article titled “Label-free identification of different cancer cells using deep learning-based image analysis.”
“Cancer cells are highly heterogeneous, and recent studies suggest that specific subpopulations of cells, rather than the whole population, are responsible for cancer metastasis,” says the author, an associate professor at Texas Tech University. Professor Wei Li, Ph.D. “Identifying cancer cell subpopulations is an important step in determining disease severity.”
“Cancer diagnosis is a critical area of cancer recovery and survival, requiring many costly procedures to deliver correct treatment,” the researchers wrote. “Machine learning (ML) approaches are useful for diagnostic prediction from circulating tumor cells in liquid biopsies or primary tumors in solid biopsies. Patients can be treated safely and correctly.This paper explores the use of deep convolutional neural networks to predict specific cancer cell lines as a tool for label-free identification.”
“The problem with these complex and time-consuming techniques is that they require resources and effort that can be devoted to researching different areas of cancer prevention and recovery,” said author Texas Tech. Dr. Karl Gardner, research assistant at the university, said.
“Our classification procedure does not consist of additional chemicals or biological solutions when taking pictures of cells,” Gardner said. “This is a ‘label-free’ method of identifying potential metastases. ”
The team’s neural networks are also easy to use, efficient, and automated. After feeding the images, the tool converts the data into probabilities. A result of less than 0.5 classifies the cancer as one cell type, while a number greater than 0.5 designates another cell type.
The tool was trained to optimize prediction accuracy using a series of images of two cancer cell lines. He reached an accuracy of over 94% across the datasets used in the study.
The authors aim to extend and generalize the model to include both single cells and clusters.
