Cancer cells distinguished by artificial intelligence-based system

December 10, 2018

Osaka, Japan - In cancer patients, there can be tremendous variation in the types of cancer cells from one patient to another, even within the same disease. Identification of the particular cell types present can be very useful when choosing the treatment that would be most effective, but the methods of doing this are time-consuming and often hampered by human error and the limits of human sight.

In a major advance that could signal a new era in cancer diagnosis and treatment, a team at Osaka University and colleagues have shown how these problems can be overcome through an artificial intelligence-based system that can identify different types of cancer cells simply by scanning microscopic images, achieving higher accuracy than human judgment. This approach could have major benefits in the field of oncology.

The system is based on a convolutional neural network, a form of artificial intelligence modeled on the human visual system. In this study, reported in the journal Cancer Research, this system was applied to distinguish cancer cells from mice and humans, as well as equivalent cells that had also been selected for resistance to radiation.

"We first trained our system on 8,000 images of cells obtained from a phase-contrast microscope," corresponding author Hideshi Ishii says. "We then tested its accuracy on another 2,000 images, to see whether it had learned the features that distinguish mouse cancer cells from human ones, and radioresistant cancer cells from radiosensitive ones."

Upon creating a two-dimensional plot of the findings obtained by the system, the results for each cell type clustered together, while being clearly separated from the other cells. This showed that, after training, the system could correctly identify cells based on the microscopic images of them alone.

"The automation and high accuracy with which this system can identify cells should be very useful for determining exactly which cells are present in a tumor or circulating in the body of cancer patients," lead author Masayasu Toratani says. "For example, knowing whether or not radioresistant cells are present is vital when deciding whether radiotherapy would be effective, and the same approach can then be applied after treatment to see whether it has had the desired effect."

In the future, the team hopes to train the system on more cancer cell types, with the eventual goal of establishing a universal system that can automatically identify and distinguish all such cells.
-end-
The article "A convolution neural network uses microscopic images to differentiate between mouse and human cell lines and their radioresistant clones" was published in Cancer Research, https://doi.org/10.1158/0008-5472.CAN-18-0653.

About Osaka University

Osaka University was founded in 1931 as one of the seven imperial universities of Japan and now has expanded to one of Japan's leading comprehensive universities. The University has now embarked on open research revolution from a position as Japan's most innovative university and among the most innovative institutions in the world according to Reuters 2015 Top 100 Innovative Universities and the Nature Index Innovation 2017. The university's ability to innovate from the stage of fundamental research through the creation of useful technology with economic impact stems from its broad disciplinary spectrum.

Website: https://resou.osaka-u.ac.jp/en/top

Osaka University

Related Cancer Cells Articles from Brightsurf:

Cancer researchers train white blood cells to attacks tumor cells
Scientists at the National Center for Tumor Diseases Dresden (NCT/UCC) and Dresden University Medicine, together with an international team of researchers, were able to demonstrate that certain white blood cells, so-called neutrophil granulocytes, can potentially - after completing a special training program -- be utilized for the treatment of tumors.

New way to target some rapidly dividing cancer cells, leaving healthy cells unharmed
Scientists at Johns Hopkins Medicine and the University of Oxford say they have found a new way to kill some multiplying human breast cancer cells by selectively attacking the core of their cell division machinery.

Breast cancer cells use message-carrying vesicles to send oncogenic stimuli to normal cells
According to a Wistar study, breast cancer cells starved for oxygen send out messages that induce oncogenic changes in surrounding normal epithelial cells.

Breast cancer cells turn killer immune cells into allies
Researchers at Johns Hopkins University School of Medicine have discovered that breast cancer cells can alter the function of immune cells known as Natural killer (NK) cells so that instead of killing the cancer cells, they facilitate their spread to other parts of the body.

Breast cancer cells can reprogram immune cells to assist in metastasis
Johns Hopkins Kimmel Cancer Center investigators report they have uncovered a new mechanism by which invasive breast cancer cells evade the immune system to metastasize, or spread, to other areas of the body.

Engineered immune cells recognize, attack human and mouse solid-tumor cancer cells
CAR-T therapy has been used successfully in patients with blood cancers such as lymphoma and leukemia.

Drug that keeps surface receptors on cancer cells makes them more visible to immune cells
A drug that is already clinically available for the treatment of nausea and psychosis, called prochlorperazine (PCZ), inhibits the internalization of receptors on the surface of tumor cells, thereby increasing the ability of anticancer antibodies to bind to the receptors and mount more effective immune responses.

Engineered bone marrow cells slow growth of prostate and pancreatic cancer cells
In experiments with mice, researchers at the Johns Hopkins Kimmel Cancer Center say they have slowed the growth of transplanted human prostate and pancreatic cancer cells by introducing bone marrow cells with a specific gene deletion to induce a novel immune response.

First phase i clinical trial of CRISPR-edited cells for cancer shows cells safe and durable
Following the first US test of CRISPR gene editing in patients with advanced cancer, researchers report these patients experienced no negative side effects and that the engineered T cells persisted in their bodies -- for months.

Zika virus' key into brain cells ID'd, leveraged to block infection and kill cancer cells
Two different UC San Diego research teams identified the same molecule -- αvβ5 integrin -- as Zika virus' key to brain cell entry.

Read More: Cancer Cells News and Cancer Cells Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.