AI for image analysis is predicted to be the top digital health technology for 2019 based on a survey of healthcare professionals, according to Forbes.

University of Arizona in Tuscon researchers, led by Diego Martin, MD, PhD, chair of the university’s medical imaging department, have developed an MRI technique aimed to replace blood tests and invasive biopsies for measuring nonalcoholic fatty liver disease, according to a report by the Arizona Daily Star.

Russian researchers and radiologists have developed AI software that can distinguish and subsequently mark lung cancers on a CT scan within 20 seconds. 

“In this study, for patients with stage-IV disease, we have a treatment paradigm that can result in long-term survival while maintaining overall quality of life,” said senior author of the study, Dwight E. Heron, MD.

Researchers used a convolutional neural network (CNN) to classify acute and non-acute findings in pediatric elbow x-rays, according to new research published in Radiology: Artificial Intelligence. The team’s recurrent neural network was able to interpret an entire series of images together, mimicking the decision-making process of a human radiologist.

A group of researchers from the Republic of Korea found the 2018 Liver Imaging and Reporting Data System (LI-RADS) could accurately differentiate hepatocellular carcinoma (HCC) from other malignancy in patients with liver cirrhosis, according to a study published Jan. 29 in Radiology.

Current conversion ratios may be underestimating the long-term cardiotoxicity of common chemotherapy agents like mitoxantrone and overestimating the cardiovascular risk of anthracyclines like daunorubicin, researchers reported in JAMA Oncology Jan. 31.

Companies developing machine-learning solutions for medical imaging have received more than $1.2 billion in capital investments since 2014, according to a report by Signify Research.