Ankle Fracture Detection Utilizing a Convolutional Neural Network Ensemble Implemented with a Small Sample, De Novo Training, and Multiview Incorporation.
To determine whether we could train convolutional neural network (CNN) models de novo with a small dataset, a total of 596 normal and abnormal ankle cases were collected and processed. Single- and multiview models were created to determine the effect of multiple views. Data augmentation was performe...
| Publicado en: | Journal of Digital Imaging Vol. 32; no. 4; pp. 672 - 678 |
|---|---|
| Autores principales: | , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Springer Nature
Aug2019
|
| 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=137642028&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 137642028 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Aug2019 vid: 32 iid: 4 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 137642028 137642028 137642028 10.1007/s10278-018-0167-7 137642028 ppf: 672 ppct: 6 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Ankle Fracture Detection Utilizing a Convolutional Neural Network Ensemble Implemented with a Small Sample, De Novo Training, and Multiview Incorporation. aug: au: Kitamura, Gene Chung, Chul Y. Moore II, Barry E. affil: Department of Radiology, University of Pittsburgh Medical Center (UPMC), 200 Lothrop St., 15213, Pittsburgh, PA, USA sug: subj: Ankle Fractures Radiography Neural Networks (Computer) Methods Radiographic Image Interpretation, Computer-Assisted Methods Deep Learning Human Models, Anatomic Data Management Programming Languages Conceptual Framework ab: To determine whether we could train convolutional neural network (CNN) models de novo with a small dataset, a total of 596 normal and abnormal ankle cases were collected and processed. Single- and multiview models were created to determine the effect of multiple views. Data augmentation was performed during training. The Inception V3, Resnet, and Xception convolutional neural networks were constructed utilizing the Python programming language with Tensorflow as the framework. Training was performed using single radiographic views. Measured output metrics were accuracy, positive predictive value (PPV), negative predictive value (NPV), sensitivity, and specificity. Model outputs were evaluated using both one and three radiographic views. Ensembles were created from a combination of CNNs after training. A voting method was implemented to consolidate the output from the three views and model ensemble. For single radiographic views, the ensemble of all 5 models produced the best accuracy at 76%. When all three views for a single case were utilized, the ensemble of all models resulted in the best output metrics with an accuracy of 81%. Despite our small dataset size, by utilizing an ensemble of models and 3 views for each case, we achieved an accuracy of 81%, which was in line with the accuracy of other models using a much higher number of cases with pre-trained models and models which implemented manual feature extraction. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|