AI tool needs more diverse skin types in datasets
November 29, 2019 -- A dermatology algorithm powered by artificial intelligence (AI) that can identify a range of skin conditions doesn't work effectively on black skin, according to researchers in Uganda and Sweden. The study highlights the potential risks of AI-based healthcare and the need to ensure diversity in datasets used to train algorithms.  Discuss
SERAM president gazes into radiology's future
November 28, 2019 -- The radiologist as an "information manager" will coexist with the radiologist as a "carer of the patient" during the era of artificial intelligence. That's the prediction of Dr. Pablo Valdés Solís, president of the Spanish Society of Medical Radiology (SERAM), who is concerned about possible turf wars and continued economic problems.  Discuss
10 factors to consider when selecting AI vendors
November 27, 2019 -- More than 150 independent software companies are developing artificial intelligence (AI) solutions for medical imaging, so sorting through the options is a challenge. Market analyst Sanjay M. Parekh, PhD, lists 10 factors radiologists should consider -- and questions they should ask -- before partnering with vendors.  Discuss
Antoch spells out how radiology can thrive beyond 2020
November 20, 2019 -- Radiologists can only ensure their future success if they work together, learn more about artificial intelligence (AI) and radiomics, and obtain reliable data to validate, standardize, and certify potential AI applications. That's the view of Prof. Gerald Antoch, president of the German Röntgen Society.  Discuss
Medical students, radiologists may view AI differently
November 15, 2019 -- Radiologists are less afraid of artificial intelligence (AI) than medical students, who may avoid choosing radiology due to their pessimistic view of the technology's effects, according to the findings of a Swiss survey published online on 9 November in the European Journal of Radiology.  Discuss
Deep learning advances in 3D quantification of body composition
November 11, 2019 -- Accurate fully automatic segmentation of subcutaneous fat, visceral fat, and psoas muscle from abdominal CT is feasible without human input. That's the main finding of new artificial intelligence research conducted at the Utrecht University Medical Center in the Netherlands.  Discuss
Germany leads in new survey of burnout in radiology
November 6, 2019 -- Burnout has reached "crisis levels" in Germany among radiographers and imaging directors, according to a new survey of job satisfaction in four developed countries. In fact, 97% of respondents from Germany reported either "moderate" or "high" burnout levels -- a much higher rate than in other nations.  Discuss
Utrecht showcases flagship AI infrastructure
October 18, 2019 -- An artificial intelligence (AI) infrastructure developed at the Utrecht University Medical Center has enabled easier deployment of AI algorithms and enhanced workflow in daily routine practice, according to a presentation at the European Society of Medical Imaging Informatics annual meeting in Valencia, Spain.  Discuss
JFR: French AI initiative to play major role in algorithm validation
October 11, 2019 -- The French national radiology congress (JFR) kicked off officially on Friday with a strengthened focus on artificial intelligence (AI) and machine learning. The discussion included an update on an ambitious project to create a national ecosystem in France for AI algorithm development.  Discuss
European societies join in ethical AI statement
October 1, 2019 -- The European Society of Radiology and the European Society of Medical Imaging Informatics have collaborated with five other radiology and imaging informatics organizations to produce a new statement calling for codes of ethics and practice governing the use of artificial intelligence (AI).  Discuss