Deep learning enhances breast cancer risk assessment
May 7, 2019 -- By analyzing subtle imaging patterns on screening mammograms that may portend future cancer, a deep-learning algorithm can beat current breast cancer risk-assessment methods that only assess traditional risk factors such as breast density and family history, according to research published online May 7 in Radiology. Read More
Radiology is leading by example when it comes to AI
May 1, 2019 -- The radiology community's proactive response to the adoption of artificial intelligence (AI) offers an important lesson to other clinical specialties in how they should prepare for the new era of AI, according to an editorial published online April 25 in the Yearbook of Medical Informatics. Read More
Practical Considerations of AI: Part 3 -- More AI issues
April 29, 2019 -- Will artificial intelligence (AI) provide better patient care? Almost certainly. Improve radiologist productivity? Without a doubt. But key aspects of AI need to be sorted out, according to part 3 of our series on practical considerations of AI by the PACSman, Michael J. Cannavo. Read More
DeepPET network smooths out PET image quality
April 25, 2019 -- Researchers from Memorial Sloan Kettering Cancer Center in New York City have developed a deep-learning network called DeepPET to generate high-quality PET images more than 100 times faster than currently possible, according to a study published in the May issue of Medical Image Analysis. Read More
Can radiomics detect pancreatic ductal adenocarcinoma?
April 25, 2019 -- Radiomics and a machine-learning algorithm can differentiate pancreatic ductal adenocarcinoma from a normal pancreas on CT studies, potentially enabling earlier diagnosis of this highly lethal cancer, according to research published online April 23 in the American Journal of Roentgenology. Read More
AI predicts lung cancer survival from CT scan data
April 22, 2019 -- Harvard researchers have developed an artificial intelligence (AI) algorithm capable of analyzing routine CT scans to predict how well lung cancer patients will respond to treatment, as well as their likelihood of survival, according to an article published online April 22 in Clinical Cancer Research. Read More