Artificial Intelligence boosts breast cancer detection accuracy

AI can spot breast cancer more accurately than doctors

A retrospective study measured the diagnostic value of an artificial intelligence (AI) algorithm to detect breast cancer and found that it outperformed the detection ability of radiologists. Radiologists getting an assist from A.I can detect cancer with a reduced rate of false positive incidents from mammography images.

AI has come a long way from its humble beginnings. Communication, education and transportation are some of the sectors that were influenced positively with advancements in technology.  With the development of AI systems and machine learning, more significant medical applications are emerging.

A team of researchers from Beth Israel Deaconess Medical Center of Harvard Medical School led by Dr. Andrew Beck showed that analysis of data through deep-learning had decreased the error rate in breast cancer diagnosis by 85%. The AI algorithm was trained with 170,230 mammography examinations obtained from five institutions in the United States, the UK, and South Korea.

Pathologist Andrew Beck, explained that the “AI method is based on deep learning, a machine-learning algorithm used for a range of applications including speech recognition and image recognition.” “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.”

From this research, Dr. Beck concluded that “The goal was to build a computational system to assist in the identification of metastatic areas of cancer in lymph nodes,” and the results were astonishing as they successfully diagnosed cancer accurately 92% of the time. “But the truly exciting thing was when we combined the pathologist’s analysis with our automated computational diagnostic method, the result improved to 99.5% accuracy,” said Beck. “Combining these two methods yielded a major reduction in errors.”

In 2019 alone there were an estimated 1,762,450 new cancer cases and some of which were misdiagnosed. Some people receive a cancer diagnosis where there is no disease, while others do not receive a diagnosis at all when cancer is present. All researchers and oncologists agree on the fact that early detection of cancer increases the patient’s chances of survival tremendously, but as it stands now most patients are diagnosed during the final stages of the disease.

In order to diagnose, doctors have access to high quality imaging, and skilled radiologists can spot the telltale signs of abnormal growth. Once identified, the next step is for doctors to ascertain the type of malignancy. The most reliable method to identify how far cancer has come is by taking a biopsy although even at this stage errors have occurred.

Artificial intelligence can undoubtedly improve accuracy in cancer detection and eventually have a sizable impact in detecting cancer early, avoiding more costly and potentially harmful treatments down the line.