The creators of a fully automated medical image analysis program to detect breast tumors was inspired by the classic video game Tetris. It is also almost twice as fast at finding lesions as existing techniques and just as accurate.
“Just as vintage video game Tetris manipulated geometric shapes to fit a space, this program uses a green square to navigate and search over the breast image to locate lesions,” said co-creator Gabriel Maicas Suso, a PhD candidate, from the University of Adelaide’s Australian Institute for Machine Learning. “The square changes to red in color if a lesion is detected.”
Suso and co-creator Gustavo Carneiro, an associate professor at the University of Adelaide’s Australian Institute for Machine Learning, designed the model to employ traversal movement to examine the breast for lesions.
Using a relatively small amount of data, the researchers created the program by applying deep reinforcement learning, which enabled the model to locate lesions quickly, accurately and independently. The program focuses on the affected area and is used with MRI.
“More research is needed before the program could be used clinically,” Carneiro said. “Our ultimate aim is for this detection method to be used by radiologists to complement, support and assist their important work in making a precise and quick prognosis.”
As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.