Publications by authors named "Efstratios Syrmas"
Article Synopsis
- The study assessed how well pre-trained deep learning models can grade hepatic steatosis (HS) in patients with Non-Alcoholic Fatty Liver Disease (NAFLD) using ultrasound images of the liver and kidney.
- A total of 112 NAFLD patients underwent ultrasound examinations, and various deep learning models (like InceptionV3 and DenseNet201) were trained and tested on cropped images that were either augmented or not.
- The models showed high accuracy in HS grading, particularly DenseNet201 with augmented data, which may serve as a useful tool for diagnosing and grading NAFLD alongside radiologist assessments.
