Posted in | News | Medical Robotics

Latest Artificial Intelligence Analyses Identify Breast Cancer with 99.5% Precision

For the past century, disease diagnosis has been carried out by pathologists in the same way - manual review of images using a microscope. A new study is likely to change this age old approach.

Image Credit: BlueSkyImage |

A team of researchers from Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) have created artificial intelligence (AI) techniques focused on manipulating computers to interpret pathology images. They also hope to build AI-powered systems that will be capable of making pathologic diagnoses much better. Their research will soon help doctors to diagnose cancer and other diseases in an accurate manner using the computers.

Our AI method is based on deep learning, a machine-learning algorithm used for a range of applications including speech recognition and image recognition. 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.

Andrew Beck, MD, PhD, Director of Bioinformatics at the Cancer Research Institute, Beth Israel Deaconess Medical Center (BIDMC)

Recently, the Beck lab’s method was tested in a competition conducted as a part of the annual meeting of the International Symposium of Biomedical Imaging (ISBI). The test comprised analyzing lymph node images to make a decision whether or not any of the nodes 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, were placed first in two different categories. They had won against international academic research institutions and private companies. The team published a technical article illustrating their method in the repository, which is an open access archive of e-prints in physics, quantitative biology, computer science, mathematics, 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. 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.

Andrew Beck, MD, PhD, Director of Bioinformatics at the Cancer Research Institute, Beth Israel Deaconess Medical Center (BIDMC)

Khosla further added that in an objective assessment, the competing researchers were asked to establish if lymph node cells contained cancer or not from the slides provided. The automated diagnostic technique used by the research team proved to be precise about 92% of the time.

“This nearly matched the success rate of a human pathologist, whose results were 96% 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 successfully manipulated the computer to differentiate between normal regions and cancerous tumor regions according to a deep multilayer convolutional system.

In our approach, we started with hundreds of training slides for which a pathologist has labeled regions of cancer and regions of normal cells. We then extracted millions of these small training examples and used deep learning to build a computational model to classify them.

Dayong Wang, PhD

Subsequently, the team identified the exact training samples for which the computer had the tendency to make errors and re-manipulated the computer using bigger numbers of the more complex training samples. In this manner, the performance of the computer began to get better and better.

“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."

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.

Jeroen van der Laak, PhD, Radboud University Medical Center

Recently, Beck and Khosla created a start-up company (PathAI) with the aim of creating and applying AI technology in the field of pathology.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Azthena logo powered by Azthena AI

Your AI Assistant finding answers from trusted AZoM content

Azthena logo with the word Azthena

Your AI Powered Scientific Assistant

Hi, I'm Azthena, you can trust me to find commercial scientific answers from

A few things you need to know before we start. Please read and accept to continue.

  • Use of “Azthena” is subject to the terms and conditions of use as set out by OpenAI.
  • Content provided on any AZoNetwork sites are subject to the site Terms & Conditions and Privacy Policy.
  • Large Language Models can make mistakes. Consider checking important information.

Great. Ask your question.

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.