Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: A pilot study Journal Article
| Authors: | Yamashita, R.; Mittendorf, A.; Zhu, Z.; Fowler, K. J.; Santillan, C. S.; Sirlin, C. B.; Bashir, M. R.; Do, R. K. G. |
| Article Title: | Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: A pilot study |
| Abstract: | Purpose: To develop a deep convolutional neural network (CNN) model to categorize multiphase CT and MRI liver observations using the liver imaging reporting and data system (LI-RADS) (version 2014). Methods: A pre-existing dataset comprising 314 hepatic observations (163 CT, 151 MRI) with corresponding diameters and LI-RADS categories (LR-1–5) assigned in consensus by two LI-RADS steering committee members was used to develop two CNNs: pre-trained network with an input of triple-phase images (training with transfer learning) and custom-made network with an input of quadruple-phase images (training from scratch). The dataset was randomly split into training, validation, and internal test sets (70:15:15 split). The overall accuracy and area under receiver operating characteristic curve (AUROC) were assessed for categorizing LR-1/2, LR-3, LR-4, and LR-5. External validation was performed for the model with the better performance on the internal test set using two external datasets (EXT-CT and EXT-MR: 68 and 44 observations, respectively). Results: The transfer learning model outperformed the custom-made model: overall accuracy of 60.4% and AUROCs of 0.85, 0.90, 0.63, 0.82 for LR-1/2, LR-3, LR-4, LR-5, respectively. On EXT-CT, the model had an overall accuracy of 41.2% and AUROCs of 0.70, 0.66, 0.60, 0.76 for LR-1/2, LR-3, LR-4, LR-5, respectively. On EXT-MR, the model had an overall accuracy of 47.7% and AUROCs of 0.88, 0.74, 0.69, 0.79 for LR-1/2, LR-3, LR-4, LR-5, respectively. Conclusion: Our study shows the feasibility of CNN for assigning LI-RADS categories from a relatively small dataset but highlights the challenges of model development and validation. © 2019, Springer Science+Business Media, LLC, part of Springer Nature. |
| Keywords: | major clinical study; hepatocellular carcinoma; disease classification; liver cell carcinoma; nuclear magnetic resonance imaging; magnetic resonance imaging; diagnostic accuracy; computer assisted tomography; image processing; diagnostic test accuracy study; human; priority journal; article; x-ray computed tomography; deep learning; convolutional neural network; transfer of learning; imaging algorithm |
| Journal Title: | Abdominal Radiology |
| Volume: | 45 |
| Issue: | 1 |
| ISSN: | 2366-004X |
| Publisher: | Springer |
| Date Published: | 2020-01-01 |
| Start Page: | 24 |
| End Page: | 35 |
| Language: | English |
| DOI: | 10.1007/s00261-019-02306-7 |
| PUBMED: | 31696269 |
| PROVIDER: | scopus |
| PMCID: | PMC6946904 |
| DOI/URL: | |
| Notes: | Article -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work