AI achieves near-human accuracy in diagnosing cancer
Mon 20 Jun 2016
New research suggests that computer models could help doctors achieve greater accuracy in the diagnosis of cancer and other diseases.
A research team from Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) have developed an artificial intelligence (AI) system which is able to train computers to analyse pathologic image data [PDF]. The scientists hope that the programme could one day aid in diagnosing disease.
‘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 Andrew Beck, director of bioinformatics at the Cancer Research Institute at BIDMC and associate professor at HMS.
He added: ‘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.’
Post-doctoral fellow Dayong Wang explained that the team’s approach began with hundreds of training slides identified as containing regions of cancer and regions of normal cells. They then extracted millions of the training examples and used deep learning to build a computational model to classify them.
In a recent competition hosted at the International Symposium of Biomedical Imaging (ISBI) the AI system was put to work on a collection of images of lymph nodes to deduce whether or not breast cancer was present. Beck’s lab placed first in two separate categories above private companies and other research institutions from around the world.
‘Identifying the presence or absence of metastatic cancer in a patient’s lymph nodes is a routine and critically important task for pathologists,’ said Beck. ‘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 the evaluation, the AI diagnosed cancerous lymph nodes with 92% accuracy, compared to a human pathologist success rate of 96%. The researchers were particularly excited to see that combining the pathologist’s analysis with the AI saw the results improve to 99.5% accuracy.