Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Artificial intelligence identifies previously unknown features associated with cancer recurrence

18.12.2019

Artificial intelligence (AI) technology developed by the RIKEN Center for Advanced Intelligence Project (AIP) in Japan has successfully found features in pathology images from human cancer patients, without annotation, that could be understood by human doctors.

Further, the AI identified features relevant to cancer prognosis that were not previously noted by pathologists, leading to a higher accuracy of prostate cancer recurrence compared to pathologist-based diagnosis.


The AIP's RAIDEN AI supercomputer

Credit: RIKEN

Combining the predictions made by the AI with predictions by human pathologists led to an even greater accuracy.

According to Yoichiro Yamamoto, the first author of the study published in Nature Communications, "This technology could contribute to personalized medicine by making highly accurate prediction of cancer recurrence possible by acquiring new knowledge from images. It could also contribute to understanding how AI can be used safely in medicine by helping to resolve the issue of AI being seen as a 'black box.'"

The research group led by Yamamoto and Go Kimura, in collaboration with a number of university hospitals in Japan, adopted an approach called "unsupervised learning." As long as humans teach the AI, it is not possible to acquire knowledge beyond what is currently known.

Rather than being "taught" medical knowledge, the AI was asked to learn using unsupervised deep neural networks, known as autoencoders, without being given any medical knowledge. The researchers developed a method for translating the features found by the AI--only numbers initially--into high-resolution images that can be understood by humans.

To perform this feat the group acquired 13,188 whole-mount pathology slide images of the prostate from Nippon Medical School Hospital (NMSH), The amount of data was enormous, equivalent to approximately 86 billion image patches (sub-images divided for deep neural networks), and the computation was performed on AIP's powerful RAIDEN supercomputer.

The AI learned using pathology images without diagnostic annotation from 11 million image patches. Features found by AI included cancer diagnostic criteria that have been used worldwide, on the Gleason score, but also features involving the stroma--connective tissues supporting an organ--in non-cancer areas that experts were not aware of.

In order to evaluate these AI-found features, the research group verified the performance of recurrence prediction using the remaining cases from NMSH (internal validation). The group found that the features discovered by the AI were more accurate (AUC=0.820) than predictions made based on the human-established cancer criteria developed by pathologists, the Gleason score (AUC=0.744).

Furthermore, combining both AI-found features and the human-established criteria predicted the recurrence more accurately than using either method alone (AUC=0.842). The group confirmed the results using another dataset including 2,276 whole-mount pathology images (10 billion image patches) from St. Marianna University Hospital and Aichi Medical University Hospital (external validation).

"I was very happy," says Yamamoto, "to discover that the AI was able to identify cancer on its own from unannotated pathology images. I was extremely surprised to see that AI found features that can be used to predict recurrence that pathologists had not identified."

He continues, "We have shown that AI can automatically acquire human-understandable knowledge from diagnostic annotation-free histopathology images. This 'newborn' knowledge could be useful for patients by allowing highly-accurate predictions of cancer recurrence. What is very nice is that we found that combining the AI's predictions with those of a pathologist increased the accuracy even further, showing that AI can be used hand-in-hand with doctors to improve medical care. In addition, the AI can be used as a tool to discover characteristics of diseases that have not been noted so far, and since it does not require human knowledge, it could be used in other fields outside medicine."

Media Contact

Jens Wilkinson
jens.wilkinson@riken.jp
81-484-621-225

 @riken_en

http://www.riken.jp/en/  

Jens Wilkinson | EurekAlert!
Further information:
http://dx.doi.org/10.1038/s41467-019-13647-8

Further reports about: AI Artificial Intelligence RIKEN neural networks prostate

More articles from Information Technology:

nachricht Research alliance: TRUMPF and Fraunhofer IPA ramping up artificial intelligence for industrial use
06.08.2020 | Fraunhofer-Institut für Produktionstechnik und Automatisierung IPA

nachricht Novel approach improves graphene-based supercapacitors
03.08.2020 | University of Technology Sydney

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: ScanCut project completed: laser cutting enables more intricate plug connector designs

Scientists at the Fraunhofer Institute for Laser Technology ILT have come up with a striking new addition to contact stamping technologies in the ERDF research project ScanCut. In collaboration with industry partners from North Rhine-Westphalia, the Aachen-based team of researchers developed a hybrid manufacturing process for the laser cutting of thin-walled metal strips. This new process makes it possible to fabricate even the tiniest details of contact parts in an eco-friendly, high-precision and efficient manner.

Plug connectors are tiny and, at first glance, unremarkable – yet modern vehicles would be unable to function without them. Several thousand plug connectors...

Im Focus: New Strategy Against Osteoporosis

An international research team has found a new approach that may be able to reduce bone loss in osteoporosis and maintain bone health.

Osteoporosis is the most common age-related bone disease which affects hundreds of millions of individuals worldwide. It is estimated that one in three women...

Im Focus: AI & single-cell genomics

New software predicts cell fate

Traditional single-cell sequencing methods help to reveal insights about cellular differences and functions - but they do this with static snapshots only...

Im Focus: TU Graz Researchers synthesize nanoparticles tailored for special applications

“Core-shell” clusters pave the way for new efficient nanomaterials that make catalysts, magnetic and laser sensors or measuring devices for detecting electromagnetic radiation more efficient.

Whether in innovative high-tech materials, more powerful computer chips, pharmaceuticals or in the field of renewable energies, nanoparticles – smallest...

Im Focus: Tailored light inspired by nature

An international research team with Prof. Cornelia Denz from the Institute of Applied Physics at the University of Münster develop for the first time light fields using caustics that do not change during propagation. With the new method, the physicists cleverly exploit light structures that can be seen in rainbows or when light is transmitted through drinking glasses.

Modern applications as high resolution microsopy or micro- or nanoscale material processing require customized laser beams that do not change during...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

“Conference on Laser Polishing – LaP 2020”: The final touches for surfaces

23.07.2020 | Event News

Conference radar for cybersecurity

21.07.2020 | Event News

Contact Tracing Apps against COVID-19: German National Academy Leopoldina hosts international virtual panel discussion

07.07.2020 | Event News

 
Latest News

Rare Earth Elements in Norwegian Fjords?

06.08.2020 | Earth Sciences

Anode material for safe batteries with a long cycle life

06.08.2020 | Power and Electrical Engineering

Turning carbon dioxide into liquid fuel

06.08.2020 | Life Sciences

VideoLinks
Science & Research
Overview of more VideoLinks >>>