Analytics in Action News

Deep Learning Technique Could Improve Cancer Diagnostics

A new two-step technique to train deep learning algorithms could enhance researchers’ understanding of cancer diagnostics and biology.

Deep learning technique could improve cancer diagnostics

Source: Thinkstock

By Jessica Kent

- A team from the Lawrence J. Ellison Institute for Transformative Medicine of USC have developed a technique to train a deep learning algorithm for improved cancer diagnostics.

In a study published in Scientific Reports, researchers describe using novel tissue fingerprints of tumors paired with correct diagnoses to facilitate deep learning in the classification of breast cancer.

Developing artificial intelligence algorithms for cancer diagnostics is a challenging task, the team noted. These tools need clinically annotated data from tens of thousands of patients to analyze before they can recognize meaningful relationships in the data with consistency. In cancer pathology, an ideal size dataset is nearly impossible to collect. Researchers typically only have access to hundreds or low thousands of pathology slides annotated with correct diagnoses.