High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.
The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and Jul...
| Publicado en: | Journal of Digital Imaging Vol. 30; no. 1; pp. 95 - 102 |
|---|---|
| Autores principales: | , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
Springer Nature
Feb2017
|
| 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=120947494&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 120947494 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Feb2017 vid: 30 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 120947494 120947494 143989613 120947494 10.1007/s10278-016-9914-9 120947494 ppf: 95 ppct: 7 formats: fmt: @attributes: type: P tig: atl: High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks. aug: au: Rajkomar, Alvin Lingam, Sneha Taylor, Andrew Blum, Michael Mongan, John affil: Center for Digital Health Innovation , University of California, San Francisco , San Francisco USA sug: subj: Radiography, Thoracic Classification Image Processing, Computer Assisted Neural Networks (Computer) Utilization Software Human Female Male Confidence Intervals Retrospective Design Academic Medical Centers California California Female Male ab: The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73-100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|