Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time. Issue 124 (March 2020)

• Record Type: Journal Article
• Authors: Cunha, Guilherme Moura; Hasenstab, Kyle A.; Higaki, Atsushi; Wang, Kang; Delgado, Timo; Brunsing, Ryan L.; Schlein, Alexandra; Schwartzman, Armin; Hsiao, Albert; Sirlin, Claude B; Fowler, Katie J.
• Is Part Of: European journal of radiology. Issue 124(2020)
• Publication Date: 2020-03
• Subjects: Gd-EOB-DTPA Gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid -- CNN Convolutional Neural Network -- HBP Hepatobiliary Phase -- LI-RADS Liver Imaging Reporting and Data System -- AUC Area Under the ROC Curve; Liver -- Magnetic resonance imaging -- Gd-EOB-DTPA; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2020.108837
• Languages: English
• ISSNs: 0720-048X

Abstract

Graphical abstract: Highlights: 20-minute HBP delay is often inefficient as adequate liver enhancement may occur earlier. Automated assessment of HBP adequacy may improve workflow efficiency. In this study, 48 % of patients achieved adequate HBP earlier than 20 min. Abstract: Purpose: To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations. Methods: We retrospectively identified EOB-enhanced MRI-HBP series from examinations performed 2011–2018 (internal and external datasets). Our algorithm, comprising a liver segmentation and classification CNN, produces an adequacy score. Two abdominal radiologists independently classified series as adequate or suboptimal. The consensus determination of HBP adequacy was used as ground truth for CNN model training and validation. Reader agreement was evaluated with Cohen's kappa. Performance of the algorithm was assessed by receiver operating characteristics (ROC) analysis and computation of the area under the ROC curve (AUC). Potential examination duration reduction was evaluated descriptively. Results: 1408 HBP series from 484 patients were included. Reader kappa agreement was 0.67 (internal dataset) and 0.80 (external dataset). AUCs were 0.97 (0.96-0.99) for internal and 0.95 (0.92–96) for external and were not significantly different from each other (p = 0.24). 48 % (50/105) examinations could have been shorter by applying the algorithm. Conclusion: A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.