Over the years, machine learning has improved dramatically and has shown great improvement in image analysis. The research specialists at Dartmouth’s Norris Cotton Cancer Center have developed a new machine learning model to classify different types of lung cancer in under a minute. Machine Learning is a subset of AI and is a type of algorithm that trains itself to predict outcomes.
The researchers have utilized machine learning to assist different tumor patterns and subtypes of lung adenocarcinoma, the leading cause of cancer-related deaths. Lung adenocarcinoma requires visual examination of lobectomy slides to determine the pattern and subtypes of lung cancer. Lobectomy is a type of lung cancer surgery where one lobe of the lung is removed. This classification plays a pivotal role in determination of treatment of lung cancer.
“Our study demonstrates that machine learning can achieve high performance on a challenging image classification task and has the potential to be an asset to lung cancer management,” said Saeed Hassanpour, who led the study. “Clinical implementation of our system would be able to assist pathologists for accurate classification of lung cancer subtypes, which is critical for prognosis and treatment,” he said in a statement.
With recent advances in machine learning, they developed a deep neural network to classify different types of lung adenocarcinoma on histopathology slides. Their developed novel machine learning model classified different types of lung cancer and found that it performed on par with three practicing pathologists. In addition, the team also plans to apply the method to various challenging histopathology image analysis tasks in breast, colorectal and esophageal cancer.
The information shared in this blog is for educational purposes only and is not a substitute for medical advice.
Share your thoughts on the story in the comments section below.