You are free to share this article under the Attribution 4.0 International license. A new artificial intelligence system could help pathologists read biopsies more accurately, and lead to better detection and diagnosis of breast cancer, researchers say. Doctors examine images of breast tissue biopsies to diagnose breast cancer. But the differences between cancerous and benign images can be difficult for the human eye to classify. The new algorithm helps interpret them, and does so nearly as accurately or better than an experienced pathologist, depending on the task.
"It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments," said Dr. Joann Elmore, the study's senior author and a professor of medicine at the David Geffen School of Medicine at UCLA. Why would there be a need for such a study? Well, because, according to a 2015 study led by Elmore, pathologists often disagree on the outcome of breast biopsies. Furthermore, research has also found that diagnostic errors occurred in about one out of every six women who had ductal carcinoma in situ (DCIS) and incorrect diagnoses were given in about half of the biopsy cases of breast atypia. These are quite some significant errors.
Sudanese radiologist Dr Hania Fadl speaks with reporters in 2015 at the Khartoum Breast Care Centre (KBCC), which she opened in 2010 and equipped with screening and anesthetic equipment despite financial advisers' warnings to abandon the project. The mammogram is one of medical science's best tools for detecting breast cancer, but when the typically painful test reveals a potential problem, women frequently undergo breast biopsies for a closer look--a practice that's all too often unnecessary, according to a group of artificial intelligence (AI) researchers, and which doctors may be able to significantly reduce thanks to a little insight from computers. Announced today, researchers from Houston Methodist have developed AI software that can interpret mammogram results a full 30 times quicker than doctors and with 99 percent accuracy, according to the team's recent study. Published in the journal Cancer, the study found that the software was able to intuitively translate patient charts into diagnostic information for human review at top speeds, which offers doctors reliable and seriously time-saving support when it comes to assessing patient cancer risk and the need for further tests. To determine the software's effectiveness for assessing breast cancer risk, the team provided its AI with mammogram and pathology reports of 500 breast cancer patients, as well as information on diagnostic features and correlated mammogram findings for breast cancer subtypes.
Breast cancer is the most common cancer in the UK, with one in eight women receiving the terrifying diagnosis in their lifetime. But researchers have now developed artificial intelligence software that can accurately predict breast cancer risk, which would enable doctors to closely monitor those most at risk of developing the potentially life-threatening disease. The AI program reliably interprets mammograms and translates patient data into diagnostic information 30 times faster than a human doctor, with 99 per cent accuracy. It was developed by researchers at Houston Methodist Research Institute in Texas. "This software intelligently reviews millions of records in a short amount of time, enabling us to determine breast cancer risk more efficiently using a patient's mammogram," said Stephen T Wong, chair of the Department of Systems Medicine and Bioengineering at the institute.
US scientists are using artificial intelligence to predict whether breast lesions identified from a biopsy will turn out to cancerous. The machine learning system has been tested on 335 high-risk lesions, and correctly diagnosed 97% as malignant. It reduced the number of unnecessary surgeries by more than 30%, the scientists said. One breast cancer specialist said that the research was "useful". The machine learning system was trained on information about such lesions, the system looks for patterns among a range of data points, such as demographics, family history, biopsies and pathology reports.