Rise of AI brings hope for earlier cancer diagnosis
Impactful AI transform healthcare by detecting and diagnosing cancer faster than ever beforeEuropost
Whether you admit it or not, humankind is currently witnessing the extraordinary growth of artificial intelligence (AI) right before its eyes. While it has been introduced across countless industries, it has also begun to transform the clinical domains, with researchers across the globe trusting more and more its potential to tackle healthcare’s ever-growing complexity, rate of change, and burden of disease.
But what this technology has particularly struck was a chord with cancer research surrounding early detection, diagnostics and medical decision-making - a long-standing concern for the cancer community.
Most recently, for instance, in a research published earlier this month in Nature Medicine scientists at New York University re-trained an off-the-shelf Google deep learning algorithm to distinguish between two of the most common types of lung cancers. As a result NYU’s neural network learned how to do something no pathologist has ever done: identify the genetic mutations teeming inside each tumor from just a simple picture.
“I thought the real novelty would be not just to show the AI is as good as humans, but to have it provide insights a human expert would not be able to,” Aristotelis Tsirigos, a pathologist at the NYU School of Medicine and a lead author on the new study, commented.
To achieve that, Tsirigos’ team started with Google’s Inception v3—an open-source algorithm that Google trained to identify 1000 different classes of objects. To teach the algorithm to distinguish between images of cancerous and healthy tissue, Tsirigos’ team showed Google’s Inception v3 (an open-source algorithm for object identification) hundreds of thousands of images taken from The Cancer Genome Atlas. Once the 'Inception' figured out how to pick out cancerous cells with 99 percent accuracy, the next step was teaching it to tell two kinds of lung cancers apart -adenocarcinoma from squamous cell carcinoma, which represent the most prevalent forms of the disease that kills more than 150,000 people a year. While they appear very similar under the microscope, the two cancer types are treated very differently and seeing the difference is literally question of life and death for patients. Still, 'Inception' managed to differentiate them with up to 97% accuracy.
This is, however only one of the many examples how the cumulative effect of AI presents new ways of seeing, understanding, and taking action in the world of medicine earlier than ever before with its ability to hear the ‘sound of silence’ of missing data, create new and deeper understanding of diseases and diagnosis and overcoming conceptual and procedural barriers entrenched in traditional approach, among many others.
"Whether AI becomes as ingrained in the health care system as a surgeon scrubbing down before operating will depend on the extent to which the key participants in the health care system—patients, providers, payers, and regulators—are willing to embrace these technologies," an article published in Managed Healthcare Executive on the topic said.