New AI tool to diagnose breast cancer is nearly 100% accurate
Researchers at Northeastern University, a New England Council member, have developed a new AI tool geared toward detecting breast cancer that they say has achieved an accuracy rate of 99.72%.
This group of researchers is led by bioengineering professor Saeed Amal. Projects such as this one are part of a greater effort by Amal to create a digital basis that doctors can use to diagnose a range of cancers using innovative AI technologies and, according to Amal, “redefine digital pathology.”
“The AI would look at the high-resolution images and would learn from historical data to identify cancer patterns and perform diagnoses,” said Amal. “The AI can’t miss a tumor in the biopsy and won’t be exhausted after diagnosing 10 or 20 people.”
Ideally, the framework of this tool will allow doctors to not only treat patients in a more timely and accurate manner, but also give way to the development of new AI models that can be used to diagnose rare and uncommon cancers that lack substantial patient data, according to Amal.
The New England Council commends Northeastern University for its research and efforts to help strengthen the accuracy and efficiency of breast cancer diagnoses through the architecture of innovative AI technologies.
Read more in Northeastern Global News.