Automated Image Quality Evaluation of T -weighted Liver MRI Utilizing Deep Learning Architecture
Overview
Authors
Affiliations
Purpose: To develop and test a deep learning approach named Convolutional Neural Network (CNN) for automated screening of T -weighted (T WI) liver acquisitions for nondiagnostic images, and compare this automated approach to evaluation by two radiologists.
Materials And Methods: We evaluated 522 liver magnetic resonance imaging (MRI) exams performed at 1.5T and 3T at our institution between November 2014 and May 2016 for CNN training and validation. The CNN consisted of an input layer, convolutional layer, fully connected layer, and output layer. 351 T WI were anonymized for training. Each case was annotated with a label of being diagnostic or nondiagnostic for detecting lesions and assessing liver morphology. Another independently collected 171 cases were sequestered for a blind test. These 171 T WI were assessed independently by two radiologists and annotated as being diagnostic or nondiagnostic. These 171 T WI were presented to the CNN algorithm and image quality (IQ) output of the algorithm was compared to that of two radiologists.
Results: There was concordance in IQ label between Reader 1 and CNN in 79% of cases and between Reader 2 and CNN in 73%. The sensitivity and the specificity of the CNN algorithm in identifying nondiagnostic IQ was 67% and 81% with respect to Reader 1 and 47% and 80% with respect to Reader 2. The negative predictive value of the algorithm for identifying nondiagnostic IQ was 94% and 86% (relative to Readers 1 and 2).
Conclusion: We demonstrate a CNN algorithm that yields a high negative predictive value when screening for nondiagnostic T WI of the liver.
Level Of Evidence: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:723-728.
Smart forecasting of artifacts in contrast-enhanced breast MRI before contrast agent administration.
Liebert A, Das B, Kapsner L, Eberle J, Skwierawska D, Folle L Eur Radiol. 2023; 34(7):4752-4763.
PMID: 38099964 PMC: 11213750. DOI: 10.1007/s00330-023-10469-7.
Clinical applications of artificial intelligence in radiology.
Mello-Thoms C, Mello C Br J Radiol. 2023; 96(1150):20221031.
PMID: 37099398 PMC: 10546456. DOI: 10.1259/bjr.20221031.
Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency.
Xu J, Lala S, Gagoski B, Abaci Turk E, Grant P, Golland P Med Image Comput Comput Assist Interv. 2022; 12266:386-395.
PMID: 36383490 PMC: 9652031. DOI: 10.1007/978-3-030-59725-2_37.
A Brief Survey on No-Reference Image Quality Assessment Methods for Magnetic Resonance Images.
Stepien I, Oszust M J Imaging. 2022; 8(6).
PMID: 35735959 PMC: 9224540. DOI: 10.3390/jimaging8060160.
Image Quality Control in Lumbar Spine Radiography Using Enhanced U-Net Neural Networks.
Chen X, Deng Q, Wang Q, Liu X, Chen L, Liu J Front Public Health. 2022; 10:891766.
PMID: 35558524 PMC: 9087032. DOI: 10.3389/fpubh.2022.891766.