Etiology of liver disease and CT technique did not affect staging accuracy.
A deep learning system can accurately stage liver fibrosis using CT images, according to a study published in the journal Radiology.
Researchers from Korea sought to develop and validate a deep learning system (DLS) for staging liver fibrosis by using CT images in the liver.
The researchers created the DLS for CT-based staging of liver fibrosis using a development data set that included portal venous phase CT images in 7,461 patients with pathologically confirmed liver fibrosis. The diagnostic performance of the DLS was evaluated in separate test data sets for 891 patients. They evaluated the influence of patient characteristics and CT techniques on the staging accuracy of the DLS.
A subset of 421 patients were evaluated for the diagnostic performance of the DLS compared with that of the radiologist’s assessment, aminotransferase-to-platelet ratio index (APRI), and fibrosis-4 index by using the area under the receiver operating characteristic curve (AUROC) and Obuchowski index.
The results showed that the DLS had a staging accuracy of 79.4 percent (707 of 891). The AUROC was:
• 0.96 for diagnosing significant fibrosis (F2–4)
• 0.97 for diagnosing advanced fibrosis (F3–4)
• 0.95 for diagnosing cirrhosis (F4)
At multivariable analysis, only pathologic fibrosis stage significantly affected the staging accuracy of the DLS, whereas etiology of liver disease and CT technique did not. The DLS (Obuchowski index, 0.94) outperformed the radiologist’s interpretation, APRI, and fibrosis-4 index (Obuchowski index range, 0.71–0.81; P Ë .001) for staging liver fibrosis.
The researchers concluded that the deep learning system allows for accurate staging of liver fibrosis by using CT images.
Could Virtual Non-Contrast Images from Photon-Counting CT Reduce Radiation Dosing with CCTA?
March 28th 2024Emerging research on coronary artery calcium scoring for the assessment of coronary artery disease (CAD) suggests the use of virtual non-contrast images from photon-counting CT may lead to a nearly 20 percent reduction in radiation dosing.
The Reading Room Podcast: Emerging Trends in the Radiology Workforce
February 11th 2022Richard Duszak, MD, and Mina Makary, MD, discuss a number of issues, ranging from demographic trends and NPRPs to physician burnout and medical student recruitment, that figure to impact the radiology workforce now and in the near future.
FDA Clears CT-Based AI Tools for PE Detection and Stroke Severity Assessment
March 26th 2024The artificial intelligence (AI) modalities CINA-iPE and CINA-ASPECTS may facilitate improved detection of incidental pulmonary embolism and stroke evaluation, respectively, based on computed tomography (CT) scans.
FDA Clears Remote Scanning Support Platform for MRI, CT and PET/CT
March 25th 2024The multimodality system nCommand Lite reportedly facilitates real-time remote imaging guidance on scanning parameters and procedure assessments to licensed technologists for a variety of imaging modalities including CT and MRI.
Female Representation in Radiology: Where Things Stand
March 25th 2024Women comprise nearly 80 percent of breast imaging departments and 45 percent of pediatric radiology departments at academic institutions, but burnout, the COVID-19 pandemic and discrimination have impeded further progress in radiology, according to a recently published literature review.