Researchers at Houston Methodist have developed an artificial intelligence (AI) software that reliably interprets mammograms, assisting doctors with a quick and accurate prediction of breast cancer risk. According to a new study published in Cancer (early online Aug. 29), the computer software intuitively translates patient charts into diagnostic information at 30 times human speed and with 99 percent accuracy.
“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. This has the potential to decrease unnecessary biopsies,” says Stephen T. Wong, Ph.D., P.E., chair of the Department of Systems Medicine and Bioengineering at Houston Methodist Research Institute.
The team led by Wong and Jenny C. Chang, M.D., director of the Houston Methodist Cancer Center used the AI software to evaluate mammograms and pathology reports of 500 breast cancer patients. The software scanned patient charts, collected diagnostic features and correlated mammogram findings with breast cancer subtype. Clinicians used results, like the expression of tumor proteins, to accurately predict each patient’s probability of breast cancer diagnosis.
In the United States, 12.1 million mammograms are performed annually, according to the Centers for Disease Control and Prevention (CDC). Fifty percent yield false positive results, according to the American Cancer Society (ACS), resulting in one in every two healthy women told they have cancer.
Currently, when mammograms fall into the suspicious category, a broad range of 3 to 95 percent cancer risk, patients are recommended for biopsies.
Over 1.6 million breast biopsies are performed annually nationwide, and about 20 percent are unnecessarily performed due to false-positive mammogram results of cancer free breasts, estimates the ACS.
The Houston Methodist team hopes this artificial intelligence software will help physicians better define the percent risk requiring a biopsy, equipping doctors with a tool to decrease unnecessary breast biopsies.
Manual review of 50 charts took two clinicians 50-70 hours. AI reviewed 500 charts in a few hours, saving over 500 physician hours.
“Accurate review of this many charts would be practically impossible without AI,” says Wong.
The Latest on: Breast cancer risk prediction
via Google News
The Latest on: Breast cancer risk prediction
- MRI Radiomic Features: Association with Disease-Free Survival in Patients with Triple-Negative Breast Canceron February 28, 2020 at 2:12 am
Breast cancer is a heterogeneous disease ... Nonetheless, the radiomics score enabled further improvement in DFS prediction, showing that radiomic features do contain additional information that can ...
- Automated volumetric radiomic analysis of breast cancer vascularization improves survival prediction in primary breast canceron February 28, 2020 at 2:12 am
... cancer vascularization improved survival prediction compared to the Nottingham Prognostic Index alone (NPI). The NPI is a well-established and widely used method of predicting survival of primary ...
- Genetics may predict cancer patients at highest risk of ‘chemo brain’ after blood or marrow transplanton February 24, 2020 at 11:25 am
“There is limited data in breast-cancer survivors implicating genes involved in DNA repair and oxidative ... Using machine-learning techniques, the researchers built a risk-prediction model featuring ...
- Higher risk of womb cancer link to specific genetic variantson February 18, 2020 at 1:30 am
There were likely to be more SNPs involved in womb cancer development, they added, saying that hundreds had been implicated in breast cancer, for example ... “The multiplicative effects of these SNPs ...
- Increased risk of uterine cancer linked to 24 gene variantson February 17, 2020 at 4:35 pm
because almost 200 SNPs have been found to increase the risk of breast cancer. On the other hand, these 24 might be useful, incorporated into a single risk index, to forecast a personalized risk ...
- Mammographic Density, Breast Cancer Risk and Risk Predictionon February 8, 2020 at 4:00 pm
BI-RADS = Breast Imaging Reporting and Data System; CI = confidence interval; Ref = reference; RR = relative risk. Visual classification of the mammographic image into four categories based on ...
- Breast cancer: How to predict risk for African Americanson February 2, 2020 at 4:00 pm
Previous breast cancer risk prediction models for African-American women have used information on only a few factors and may have underestimated risk, Palmer says. “The new model appears to ...
- Precancerous milestone discoveries improve clinical risk prediction and cancer preventionon January 30, 2020 at 6:11 am
A team of researchers affiliated with multiple institutions in Massachusetts has discovered some of the precancerous milestones that can lead to breast cancer in women with a BRCA2 gene mutation.
- Shivom Partnership With Genetic Technologies Will Enable Better Cancer Prediction and Prevention Through Mass Genomic Data Analysison January 29, 2020 at 4:00 pm
that is expected to accelerate the prediction of cancer for millions of individuals worldwide. GTG, whose lead product is BREVAGenplus® - a clinically validated risk assessment test for non-hereditary ...
- Nobel Prize Winner Talks About Breast Cancer Researchon October 22, 2019 at 5:48 pm
Dr. William Kaelin talked to WBZ-TV's Paula Ebben about his research on cells and how it will help in the fight against breast cancer.
via Bing News