October 21, 2019
Did you know 1 in 8 United States women will develop invasive breast cancer during their lifetime? It is the most common type of cancer for women, according to the Centers for Disease Control and Prevention.
IEEE Fellow Karen Panetta has built an artificial intelligence tool that differentiates breast cancer cells from non-cancerous cells by analyzing biopsy images. If a cancer is present, the AI technology will also determine the grade of cancer.
“We use deep learning strategies based on convolutional neural networks to automatically handle the detection, segmentation and classification tasks for complicated medical images,” explains Panetta. “These strategies can learn and extract deep, high-level features directly from the raw input data and achieve much better classification performance in comparison to traditional approaches.”
Learn more about deep learning for diagnosing cancer
How Artificial Intelligence for Breast Cancer Will Bring Accurate Treatment
Artificial Intelligence for breast cancer detection can be beneficial for understaffed and rural hospitals where human expertise might be limited. An AI algorithm outperformed human experts in nearly every aspect, revealed Panetta.
Panetta believes a quicker and more accurate diagnosis will save time and improve the efficiency of treatment plans for patients.
“This would help not only expedite the treatment plan for the patient, but also help prevent the under-and over-diagnosis, or incorrect diagnosis, that could potentially miss detecting the cancer,” says Panetta. “This could result in the patient going through unnecessary or inappropriate expensive treatments.”
Panetta and her team have also developed an AI detector for skin cancer, and are developing a similar detector for prostate cancer.
New technologies like Panetta’s are leading the future of cancer diagnosis in the health industry. Doctors and health practitioners will continue to rely on the use of artificial intelligence to produce faster, more accurate results in order to save more lives.