Researchers determine quantitative ultrasound could be superior to conventional ultrasound for predicting fat acculturation in the liver.
Quantitative ultrasound could be more effective in predicting the grade of fat accumulation in patients with non-alcoholic fatty liver disease (NAFLD) than conventional ultrasound. In a study conducted at the University of California at San Diego, published in the American Journal of Roentgenology, researchers explored whether investigational quantitative ultrasound (QUS) parameters were more effective than conventional ultrasound (CUS) and MRI-estimated proton density fat fraction (PDFF) for predicting fat accumulation in the liver (hepatic steatosis) in non-alcoholic adults. For the study, 61 adults with confirmed NAFLD underwent QUS, CUS, and MRI examinations within 100 days of liver biopsy. Based on analysis, CUS had 51.7 percent grading accuracy. Raw and cross-validated steatosis grading accuracies were 61.7 percent and 55.0 percent, respectively, for attenuated co-efficient, 68.3 percent and 68.3 percent for backscatter co-efficient. For MRI-estimated PDFF, it was 76.7 percent and 71.3 percent. Interobserver agreements were 53.3 percent for CUS, 90 percent for attenuation coefficient, and 71.7 percent for backscatter coefficient.
The Reading Room: Racial and Ethnic Minorities, Cancer Screenings, and COVID-19
November 3rd 2020In this podcast episode, Dr. Shalom Kalnicki, from Montefiore and Albert Einstein College of Medicine, discusses the disparities minority patients face with cancer screenings and what can be done to increase access during the pandemic.
What New Research Reveals About ChatGPT and Ultrasound Detection of Thyroid Nodules
March 13th 2024In a comparison of image-to-text large language models (LLMs), ChatGPT 4.0 offered a 95 percent sensitivity rate and an 83 percent AUC that were comparable to that of two senior radiologists and one junior radiologist interacting with LLM to differentiate between malignant and benign thyroid nodules on ultrasound.
ECR Study Finds Mixed Results with AI on Breast Ultrasound
March 6th 2024While adjunctive use of AI led to significantly higher specificity and accuracy rates in detecting cancer on breast ultrasound exams in comparison to unassisted reading by breast radiologists, researchers noted that 12 of 13 BI-RADS 3 lesions upgraded by AI were ultimately benign, according to research presented at the European Congress of Radiology.