A New Machine Learning Model can Classify Lung Cancer Slides at the Pathologist Level

Machine learning has improved dramatically in recent years and shown great promise in the field of medical image analysis. A team of research specialists at Dartmouth's Norris Cotton Cancer Center have utilized machine learning capabilities to assist with the challenging task of grading tumor patterns and subtypes of lung adenocarcinoma, the most common form of the leading cause of cancer-related deaths worldwide.

Currently, lung adenocarcinoma, requires pathologist's visual examination of lobectomy slides to determine the tumor patterns and subtypes. This classification has an important role in prognosis and determination of treatment for lung cancer, however is a difficult and subjective task. Using recent advances in machine learning, the team, led by Saeed Hassanpour, PhD, developed a deep neural network to classify different types of lung adenocarcinoma on histopathology slides, and found that the model performed on par with three practicing pathologists.

"Our study demonstrates that machine learning can achieve high performance on a challenging image classification task and has the potential to be an asset to lung cancer management," says Hassanpour. "Clinical implementation of our system would be able to assist pathologists for accurate classification of lung cancer subtypes, which is critical for prognosis and treatment."

The team's conclusions, "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks" are newly published in Scientific Reports. Recognizing that the approach is potentially applicable to other histopathology image analysis tasks, Hassanpour's team made their code publicly available to promote new research and collaborations in this domain.

In addition to testing the deep learning model in a clinical setting to validate its ability to improve lung cancer classification, the team plans to apply the method to other challenging histopathology image analysis tasks in breast, esophageal, and colorectal cancer. "If validated through clinical trials, our neural network model can potentially be implemented in clinical practice to assist pathologists," says Hassanpour. "Our machine learning method is also fast and can process a slide in less than one minute, so it could help triage patients before examination by physicians and potentially greatly assist pathologists in the visual examination of slides."

Jason W Wei, Laura J Tafe, Yevgeniy A Linnik, Louis J Vaickus, Naofumi Tomita, Saeed Hassanpour.
Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks.
Scientific Reportsvolume 9, Article number: 3358 (2019). doi: 10.1038/s41598-019-40041-7.

Most Popular Now

A New Machine Learning Model can Classif…

Machine learning has improved dramatically in recent years and shown great promise in the field of medical image analysis. A team of research specialists at Dartmouth's Norris Cotton Cancer Center...

Could Blockchain Ensure Integrity of Cli…

UC San Francisco researchers have created a proof-of-concept method for ensuring the integrity of clinical trials data with blockchain. The system creates an immutable audit trail that makes it easy...

3D Child Welfare: How Data, Design and D…

Opinion Article by Rainer Binder, Managing Director, Global Employment and Social Services, Accenture Child welfare remains a pressing challenge for governments around the world, and the statistics are heart-breaking. In the...

Bringing more Human Intelligence to AI, …

The advent of data science, wireless connectivity and sensors, artificial intelligence (AI), and the Internet of Things (IoT) has raised the prospects for digital automation, smart hospital design and the...

Scotland's Digital Health Leaders Recogn…

Scotland's digital health champions have been recognised for their achievements at the Holyrood Connect Digital Health and Care Awards 2019. William Edwards, director of eHealth at NHS Greater Glasgow and...

DMEA 2019: International Exchange on Dig…

9 - 11 April 2019, Berlin, Germany. DMEA (formerly conhIT) is the industry's main event for digital healthcare. In that context, an international exchange of experiences and networking beyond national borders...

Philips to Expand its Radiology Informat…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today announced that it has signed an agreement to acquire the Healthcare Information Systems business of Carestream Health...

Three Winners of 2019 Sandoz Healthcare …

Sandoz, a Novartis division, announced the winners of the 2019 Sandoz Healthcare Access Challenge (HACk). Sandoz HACk invites entrepreneurs and innovators in the field of digital technology to submit ideas...

UK Sales of Xanax and other Prescription…

Sales of prescription psychiatric drugs such as Xanax and diazepam via darknet online drug markets have increased in the UK at an alarming rate, according to new research by the...

Accenture Wins GLOMO Award for Virtual R…

The Accenture (NYSE: ACN) Virtual Experience Solutions (AVEnueS) has won "Best Mobile VR or AR" at the GSMA GLOMO Awards 2019. The award was presented at MWC19 Barcelona.

Study Finds Robots can Detect Breast Can…

Breast cancer is the most common cancer in women, and despite important improvements in therapy, it is still a major cause for cancer-related mortality, accounting for approximately 500,000 annual deaths...