In what’s expected to soon be commonplace, artificial intelligence is being harnessed to pick up signs of cancer more accurately than the trained human eye. This latest AI model has a near 100% success rate and serves as a clear sign of things to come.
An international team of scientists including those from Australia’s Charles Darwin University (CDU) has developed a novel AI model known as ECgMPL, which can assess microscopic images of cells and tissue to identify endometrial cancer – one of the most common forms of reproductive tumors – with an impressive 99.26% accuracy. And the researchers say it can be adapted to identify a broad range of disease, including colorectal and oral cancer.
“The proposed ECgMLP model outperforms existing methods by achieving 99.26 percent accuracy, surpassing transfer learning and custom models discussed in the research while being computationally efficient,” said the study’s co-author Dr. Asif Karim, from CDU. “Optimized through ablation studies, self-attention mechanisms, and efficient training, ECgMLP generalizes well across multiple histopathology datasets thereby making it a robust and clinically applicable solution for endometrial cancer diagnosis.”
What that science-speak means is that the well-trained model is able to look at these microscopic scans – histopathology images – and enhance image quality in order to identify early stages of cancer, homing in on certain areas of the scans to pinpoint problematic growth that may not be easily detected by the naked eye. Right now, current human-led diagnostic methods are around 78.91% to 80.93% accurate. Endometrial cancer is treatable and, if found in time, has a good five-year outcome for patients. However, once it spreads outside the uterus, it becomes difficult to effectively treat – which makes timely diagnosis critical in saving lives.
Karim et al/Computer Methods and Programs in Biomedicine Update
Currently, more than 600,000 Americans have battled the disease. And while this cancer may not personally impact half of the population, the scientists confirm that ECgMLP analysis has much broader application than what it has been trained on.
“The same methodology can be applied for fast and accurate early detection and diagnosis of other diseases which ultimately leads to better patient outcomes,” said co-author Niusha Shafiabady, an associate professor at ACU. “We evaluated the model on several histopathology image datasets. It diagnosed colorectoral cancer with 98.57% per cent accuracy, breast cancer with 98.20% accuracy, and oral cancer with 97.34% accuracy.”
Of course, it’s not a tool designed to replace medical professionals but to be used in collaboration with cancer specialists to accurately spot the disease and then monitor how successful treatment has been. What’s more, this kind of model is a much more rapid, accessible and affordable way to diagnose cancers.
“The core AI model developed through this research can be adopted as the brain of a software system to be used to assist the doctors for decision-making in cancer diagnosis,” added Shafiabady.
“The early and accurate detection of endometrial cancer is crucial for effective treatment and management,” the researchers noted. “Classifying endometrial cancer using histopathological images was achieved with superior performance, better accuracy and processing time, using deep learning algorithms.”
The study was published in the journal Computer Methods and Programs in Biomedicine Update.
Source: Charles Darwin University