Aunt Minnie (3/14, Ridley) reports that research presented last month at the SPIE Medical Imaging 2018 conference in Houston demonstrated that an artificial intelligence algorithm may enable breast imagers to sharply reduce radiation dose from digital breast tomosynthesis (DBT) exams – perhaps by as much as 80 percent. A multi-institutional team led by Junchi Liu from the Illinois Institute of Technology in Chicago “developed a deep learning-based image processing technique that can convert lower-dose DBT images to virtual images that approximate higher-dose exams,” according to Aunt Minnie. In testing on images acquired on cadaver phantoms, the method yielded high-quality images at as little as 79 percent of the dose of standard DBT studies, according to the article.
MedPage Today (3/12, Bankhead) reports on a guideline issued by the American Society for Radiation Oncology (ASTRO) stating that “most women with breast cancer should receive accelerated whole-breast irradiation (WBI) as the standard of care.” The guideline adds that “accelerated, or hypofractionated, WBI is the preferred form of radiotherapy for breast cancer, regardless of a patient’s age, tumor stage, or whether the patient has received chemotherapy.”
The Radiology Business Journal (3/9, Walter) reported that “researchers used machine learning techniques to confirm that radiomic imaging features of breast tumors extracted from digital mammography are associated with breast cancer subtypes, according to a new study published in Academic Radiology.” The researchers “had the best results classifying subtypes by using a combination of mediolateral oblique view and craniocaudal view images.”
ABC News (3/7, Byun) reports on its website that research suggests “a higher percentage of Asian, Black and Hispanic women are diagnosed with breast cancer by age 50 than white women,” which means “the widely accepted current guideline” for when women should start getting mammograms may “not be early enough for some ethnic groups.”
Modern Healthcare (3/7, Johnson, Subscription Publication) reports that David Chang, the co-author of a study, said that “if people were to follow the USPSTF guidelines and do not screen patients until age 50, then minority patients would be harmed.” Modern Healthcare adds, “The scientific findings that make up the basis for task force guidelines, as well as for recommendations issued by leading medical and advocacy organizations...are mostly derived from research conducted on largely white populations.”
HealthDay (3/7, Preidt) reports that for the study, researchers “analyzed US National Cancer Institute data on women aged 40 to 75 who were diagnosed with breast cancer between 1973 and 2010.” The researchers found that “percentages of patients diagnosed before age 50 were: 31 percent for blacks, 35 percent for Hispanics, 33 percent for Asians, and 24 percent for whites.” The data indicated that “advanced cancers were diagnosed in 47 percent of black patients, 43 percent of Hispanic patients, 37 percent of white patients and 36 percent of Asian patients.” Also covering the story are the Radiology Business Journal (3/7, Walter), Aunt Minnie (3/7, Yee), and HealthImaging (3/7, Rohman).
Aunt Minnie (3/7) reports that a new study published in Health Affairs found that the quality of breast cancer care among female Medicare beneficiaries in the US territories is lower than for those in the continental US. Researchers from the US National Cancer Institute compared female Medicare beneficiaries who were residents of US territories and had surgical treatment for breast cancer between 2008 and 2014 with those in the continental US, and “evaluated their receipt of care such as diagnostic needle biopsy and adjuvant radiation therapy following breast-conserving surgery.” The study found that “residents of the territories were less likely to receive recommended care, with 24% lower odds of receiving diagnostic needle biopsy and 34% lower odds of receiving adjuvant radiation therapy.”