Tetris-like program could speed breast cancer detection

September 6, 2018 by Crispin Savage, University of Adelaide
Three-dimensional culture of human breast cancer cells, with DNA stained blue and a protein in the cell surface membrane stained green. Image created in 2014 by Tom Misteli, Ph.D., and Karen Meaburn, Ph.D. at the NIH IRP.

Researchers from the University of Adelaide's Australian Institute for Machine Learning (AIML) are developing a fully automated medical image analysis program to detect breast tumours. The program uses a unique style to focus on the affected area.

In conjunction with an MRI scan, this autonomous program – using − employs the traversal movement and style of a retro video game to examine the breast area.

University of Adelaide Ph.D. candidate Gabriel Maicas Suso and Associate Professor Gustavo Carneiro from AIML developed the program.

"Just as vintage 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. The square changes to red in colour if a lesion is detected," says Mr Maicas.Suso.

"Our research shows that this unique approach is 1.78 times faster in finding a lesion than existing methods of detecting breast cancer, and the results are just as accurate," he says.

The researchers created this program by applying deep reinforcement learning methods, a form of artificial intelligence (AI) that enables computers and machines to learn how to do complex tasks without being programmed by humans. As a result, the program can independently analyse breast tissue.

Credit: University of Adelaide

They were able to train the computer program with a relatively small amount of data, which is a critical challenge in medical imaging.

"By incorporating machine learning into medical imaging analysis, we have developed a program that intuitively locates quickly and accurately," says Associate Professor Carneiro.

"More research is needed before the program could be used clinically. 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.

"Artificial intelligence has an important role to play in the imaging medical field, the potential to use AI in this field is boundless," he says.

Explore further: SPIE journal announces public access to largest multi-lesion medical imaging dataset

Related Stories

SPIE journal announces public access to largest multi-lesion medical imaging dataset

July 20, 2018
A paper published today in the Journal of Medical Imaging - "DeepLesion: Automated mining of large-scale lesion annotations and universal lesion detection with deep learning,—announced the open availability of the largest ...

Machine learning identifies breast lesions likely to become cancer

October 17, 2017
A machine learning tool can help identify which high-risk breast lesions are likely to become cancerous, according to a new study appearing online in the journal Radiology. Researchers said the technology has the potential ...

Mathematical methods for diagnosing breast cancer

May 16, 2018
A team of researchers at Kaunas University of Technology, Lithuania, is developing mathematical methods to diagnose breast cancer. Applying deep learning, the researchers are aiming to teach a computer to recognise malignant ...

Diagnostics of genetic cardiac diseases using stem cell-derived cardiomyocytes

June 20, 2018
A new study by Professors Martti Juhola and Katriina Aalto-Setälä of the University of Tampere in Finland demonstrates that with the use of artificial intelligence and machine learning, it is possible not only to accurately ...

Recommended for you

Metal chemotherapy drugs boost the impact of immunotherapy in cancer

December 18, 2018
Due to their powerful tumour-killing effect, metal-based chemotherapies are frequently used in cancer treatment. However, it was hitherto assumed that they damaged the immune system, because of their cytotoxic (cell-damaging) ...

10-year follow-up after negative colonoscopies linked to lower colorectal cancer risk

December 17, 2018
Ten years after a negative colonoscopy, Kaiser Permanente members had 46 percent lower risk of being diagnosed with and were 88 percent less likely to die from colorectal cancer compared with those who did not undergo colorectal ...

Survivors of childhood Hodgkin lymphoma face high long-term risk of solid cancers

December 17, 2018
New research refines existing evidence that survivors of childhood Hodgkin lymphoma face an elevated risk of developing various types of solid tumors many years later. In addition, certain subgroups of patients have an especially ...

Immunotherapy combo not approved for advanced kidney cancer patients on the NHS

December 14, 2018
People with a certain type of advanced kidney cancer will not be able to have a combination of two immunotherapy drugs on the NHS in England.

New drug seeks receptors in sarcoma cells, attacks tumors in animal trials

December 13, 2018
A new compound that targets a receptor within sarcoma cancer cells shrank tumors and hampered their ability to spread in mice and pigs, a study from researchers at the University of Illinois reports.

Surgery unnecessary for many prostate cancer patients

December 13, 2018
Otherwise healthy men with advanced prostate cancer may benefit greatly from surgery, but many with this diagnosis have no need for it. These conclusions were reached by researchers after following a large group of Scandinavian ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.