\n \n \n “. concat(self. i18n. t(‘search. voice. recognition_retry’), “\n
A new technique that combines imaging data with synthetic intelligence (AI) can diagnose osteoporosis from hip X-rays, according to a study published in Radiology: Artificial Intelligence. The researchers said the technique could help speed up patients’ treatment before fractures occur.
OAK BROOK, Ill. , May 25, 2022 /PRNewswire-PRWeb/ — A new technique that combines imaging data with synthetic intelligence (AI) can diagnose osteoporosis from hip X-rays, according to a study published May 25 in the journal Radiology: Artificial Intelligence. The researchers said the technique could help speed up patients’ treatment before fractures occur.
People with osteoporosis, a skeletal disease that thins and weakens bones, are more likely to suffer fractures related to bone fragility, resulting in poor quality of life and higher mortality. According to statistics from the International Osteoporosis Foundation, one in 3 international women during the age of 50 and one in five men will suffer osteoporotic fractures throughout their lives.
Early detection of osteoporosis through X-ray bienergetic absorptiometry (DXA) to assess bone mineral density is a vital tool for immediate remedy that can decrease the threat of fractures. However, the low availability of scanners and the relatively high load have limited their use for screening and post-remedy tracking.
On the contrary, popular radiography is widely available and is used for various clinical indications in daily practice. Despite those attributes, it has been relatively underutilized in controlling osteoporosis because diagnosing osteoporosis using only X-rays is difficult, even for an experienced physician. radiologist.
“For patients with hip pain, radiologists only compare the effects of symbols that can cause pain, such as fractures, osteonecrosis and osteoarthritis,” said exam author Hee-Dong Chae, M. D. , of the Department of Radiology at Seoul National University Hospital in Seoul, Korea. “Although X-ray symbols involve more data about the physical condition of the patient’s bones and muscles, this data is overlooked or considered less important. “
Dr. Chae and his colleagues have developed a style that can diagnose osteoporosis from hip X-rays. The approach combines radiomics, a series of symbol processing and research strategies to download symbol data, with deep learning, a complex type of AI. Deep learning can be trained to locate patterns in symbols related to the disease.
The researchers developed the deep radiomic style on nearly 5,000 hip X-rays of 4308 patients received over more than 10 years. They developed the styles with a variety of deep, clinical, and textured features, and then tested them externally on 444 hip X-rays. of some other installation.
The deep radiomics style with deep, clinical and textured features was able to diagnose osteoporosis on hip x-rays with amazing diagnostic functionality than texture styles or deep features alone, allowing for an opportunistic diagnosis of osteoporosis.
“Our study shows that opportunistic screening for osteoporosis in those X-ray photographs is advantageous, and our style can serve as a classification tool that recommends DXA in patients with a strong suspicion of osteoporosis,” Dr. Chae said.
The researchers plan a larger one that combines clinical data from the Korean National Health Insurance Service’s knowledge base with imaging knowledge from Seoul University Hospital.
###
“Technique based on deep radiomics for the diagnosis of hip x-rays of osteoporosis”. Sangwook Kim, B. S. , Bo Ram Kim, M. D. , Jimin Lee, Ph. D. , Sung-Joon Ye, Ph. D. , Dong Hyun Kim, M. D. , Sung Hwan Hong, M. D. , Ph. D. collaborated with Dr. Chae. . , Ja-Young Choi, M. D. , Ph. D. , and Hye Jin Yoo, M. D. , Ph. D.
Radiology: Artificial Intelligence is edited by Charles E. Kahn Jr. , M. D. , M. S. , Perelman School of Medicine at the University of Pennsylvania, and is owned and through the Radiological Society of North America, Inc. (https://pubs. rsnaArrayorg /daily/ai)
The RSNA is an arrangement of radiologists, radiation oncologists, medical physicists, and similar scientists who sell excellence in patient care and education, studies, and technological innovation. The company is headquartered in Oak Brook, Illinois. (RSNA. org)
For more data on musculoskeletal imaging, RadiologyInfo. org.
Media Contact
Linda Brooks, American Society of Radiology (NISR), 630-590-7762, lbrooks@rsna. org
SOURCE Radiological Society of North America (NISR)