Human and computer analyses together identify cancer with 99.5% accuracy
Pathologists have been largely diagnosing disease the same way for the past 100 years, by manually reviewing images under a microscope. But new work suggests that computers can help doctors improve accuracy and significantly change the way cancer and other diseases are diagnosed.
A research team from Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) recently developed artificial intelligence (AI) methods aimed at training computers to interpret pathology images, with the long-term goal of building AI-powered systems to make pathologic diagnoses more accurate.
“Our AI method is based on deep learning, a machine-learning algorithm used for a range of applications including speech recognition and image recognition,” explained pathologist Andrew Beck, MD, PhD, Director of Bioinformatics at the Cancer Research Institute at Beth Israel Deaconess Medical Center (BIDMC) and an Associate Professor at Harvard Medical School. “This approach teaches machines to interpret the complex patterns and structure observed in real-life data by building multi-layer artificial neural networks, in a process which is thought to show similarities with the learning process that occurs in layers of neurons in the brain’s neocortex, the region where thinking occurs.”
The Beck lab’s approach was recently put to the test in a competition held at the annual meeting of the International Symposium of Biomedical Imaging (ISBI), which involved examining images of lymph nodes to decide whether or not they contained breast cancer. The research team of Beck and his lab’s post-doctoral fellows Dayong Wang, PhD and Humayun Irshad, PhD, and student Rishab Gargya, together with Aditya Khosla of the MIT Computer Science and Artificial Intelligence Laboratory, placed first in two separate categories, competing against private companies and academic research institutions from around the world. The research team today posted a technical report describing their approach to the arXiv.org repository, an open access archive of e-prints in physics, mathematics, computer science, quantitative biology, quantitative finance and statistics.
“Identifying the presence or absence of metastatic cancer in a patient’s lymph nodes is a routine and critically important task for pathologists,” Beck explained. “Peering into the microscope to sift through millions of normal cells to identify just a few malignant cells can prove extremely laborious using conventional methods. We thought this was a task that the computer could be quite good at – and that proved to be the case.”
In an objective evaluation in which researchers were given slides of lymph node cells and asked to determine whether or not they contained cancer, the team’s automated diagnostic method proved accurate approximately 92 percent of the time, explained Khosla, adding, “This nearly matched the success rate of a human pathologist, whose results were 96 percent accurate.”
“But the truly exciting thing was when we combined the pathologist’s analysis with our automated computational diagnostic method, the result improved to 99.5 percent accuracy,” said Beck. “Combining these two methods yielded a major reduction in errors.”
The team trained the computer to distinguish between cancerous tumor regions and normal regions based on a deep multilayer convolutional network.
“In our approach, we started with hundreds of training slides for which a pathologist has labeled regions of cancer and regions of normal cells,” said Wang. “We then extracted millions of these small training examples and used deep learning to build a computational model to classify them.” The team then identified the specific training examples for which the computer is prone to making mistakes and re-trained the computer using greater numbers of the more difficult training examples. In this way, the computer’s performance continued to improve.
“There have been many reasons to think that digitizing images and using machine learning could help pathologists be faster, more accurate and make more accurate diagnoses for patients,” Beck added. “This has been a big mission in the field of pathology for more than 30 years. But it’s been only recently that improved scanning, storage, processing and algorithms have made it possible to pursue this mission effectively. Our results in the ISBI competition show that what the computer is doing is genuinely intelligent and that the combination of human and computer interpretations will result in more precise and more clinically valuable diagnoses to guide treatment decisions.”
Jeroen van der Laak, PhD, who leads a digital pathology research group at Radboud University Medical Center in the Netherlands and was an organizer for the competition, said, “When we started this challenge, we expected some interesting results. The fact that computers had almost comparable performance to humans is way beyond what I had anticipated. It is a clear indication that artificial intelligence is going to shape the way we deal with histopathological images in the years to come.”
Beck and Khosla recently formed a start-up company (PathAI) with the mission of developing and applying AI technology for pathology.
The Latest on: Artificial intelligence disease diagnosis
via Google News
The Latest on: Artificial intelligence disease diagnosis
- Artificial intelligence in the fight against river blindnesson August 14, 2019 at 6:31 am
They now want to develop a method in which artificial intelligence ... causing symptoms of vision impairment and skin inflammation. In order to eradicate the disease for good, treatment must ...
- Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learningon August 14, 2019 at 2:20 am
Artificial intelligence (AI ... AI extracted structural features such as laboratory tests, diagnosis, prescription and ICD 10 codes. AI picked up the past history, current diseases and prescriptions ...
- Healthcare Artificial Intelligence Market – Industry Growth Analysis & Forecast By 2025on August 13, 2019 at 5:17 am
U.S. artificial intelligence market dominated the North America region with more than 90% revenue share in 2018. Considerable revenue share is attributed to high adoption of innovative healthcare ...
- Artificial intelligence helps banana growers protect the world's most favorite fruiton August 12, 2019 at 10:49 am
Using artificial intelligence, scientists created an easy-to-use tool ... To build it, researchers uploaded 20,000 images that depicted various visible banana disease and pest symptoms. With this ...
- Artificial intelligence helps banana growers protect the world's favorite fruiton August 12, 2019 at 9:15 am
Artificial intelligence-powered tools ... researchers uploaded 20,000 images that depicted various visible banana disease and pest symptoms. With this information, the app scans photos of parts ...
- Artificial intelligence scores another victory in diagnosing breast canceron August 9, 2019 at 4:00 pm
(Elmore Lab/UCLA Photo) Human doctors once again fell short of artificial intelligence in a test to accurately diagnose ... Sometimes doctors do not even agree with their previous diagnosis when they ...
- Could artificial intelligence prevent sepsis in hospital patients? Sentara thinks so.on August 9, 2019 at 10:54 am
Sentara Healthcare is now deploying artificial intelligence to use that data ... And that can sometimes lead to delays in diagnosis, which have been shown over and over again to severely impact ...
- NHS artificial intelligence boost to tackle cancer and dementiaon August 7, 2019 at 8:44 pm
A new £250m investment in "robot" technology to treat cancer, dementia and heart disease in the NHS ... is to make the NHS a world leader in artificial intelligence - digital computers or ...
- NHS looks to artificial intelligence to improve healthcareon August 7, 2019 at 4:01 pm
The National Health Service will become a world leader in using artificial intelligence to improve healthcare ... health report based on their DNA so that diseases can be detected even before people ...
- Artificial Intelligence Models Identify Alzheimer’s Cognitive Declineon August 5, 2019 at 6:41 am
August 05, 2019 - A team from the Massachusetts Institute of Technology (MIT) has developed artificial intelligence tools to determine ... candidates who are in the early stages of the disease before ...
via Bing News