Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: a pilot study.
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 correspond...
| Publicado en: | Abdominal Radiology Vol. 45; no. 1; pp. 24 - 36 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Jan2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=141078458&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 141078458 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: Jan2020 vid: 45 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 141078458 10.1007/s00261-019-02306-7 141078458 ppf: 24 ppct: 12 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: a pilot study. aug: au: Yamashita, Rikiya Mittendorf, Amber Zhu, Zhe Fowler, Kathryn J. Santillan, Cynthia S. Sirlin, Claude B. Bashir, Mustafa R. Do, Richard K. G. affil: Department of Radiology, Body Imaging Service, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, 10065, New York, NY, USA sug: ab: 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. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|