Scientists from the California Institute of Technology and the University of Washington School of Medicine used artificial intelligence algorithms to predict lung cancer metastasis from biopsy images. Results of scientific studies published In Journal of Pathology (JP).
118 people with lung cancer participated in the study. All volunteers underwent biopsy; This is a research method in which intravital tissue (biopsy) is removed from the body for diagnostic purposes. Tumor tissue samples were then examined under a microscope that also takes photographs at the cellular level.
After capturing and selecting the images, the scientists used them to train an artificial intelligence (AI) program called a deep learning network. They also provided the system with data on whether participants developed brain metastases within five years of being diagnosed with lung cancer. AI was then provided with 40 additional biopsy images to predict possible lung cancer metastasis.
Tests showed that the AI model could predict this probability with 87% accuracy. Four expert pathologists examining the same images were able to make only 57% accurate predictions.
The authors of the study said that they could improve the predictive capabilities of the artificial intelligence program in the future. The research team will also begin studying the complex properties of tumor cells and their environment, changes that the AI program can focus on for diagnosis.
Previously was named A reliable way to reduce the risk of dangerous lung diseases.
What are you thinking?
Source: Gazeta
Barbara Dickson is a seasoned writer for “Social Bites”. She keeps readers informed on the latest news and trends, providing in-depth coverage and analysis on a variety of topics.