Effectiveness of Deep Learning Algorithms to Determine Laterality in Radiographs.
Develop a highly accurate deep learning model to reliably classify radiographs by laterality. Digital Imaging and Communications in Medicine (DICOM) data for nine body parts was extracted retrospectively. Laterality was determined directly if encoded properly or inferred using other elements. Curati...
| Published in: | Journal of Digital Imaging Vol. 32; no. 4; pp. 656 - 665 |
|---|---|
| Main Authors: | , |
| Format: | diagnostic images research tables/charts Journal Article |
| Published: |
Springer Nature
Aug2019
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=137642033&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 137642033 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: 137642033 137642033 137642033 10.1007/s10278-019-00226-y 137642033 ppf: 656 ppct: 9 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Effectiveness of Deep Learning Algorithms to Determine Laterality in Radiographs. aug: au: Filice, Ross W. Frantz, Shelby K. affil: MedStar Georgetown University Hospital, 3800 Reservoir Road, NW CG201, 20007, Washington, DC, USA sug: subj: Digital Imaging Deep Learning Algorithms Radiography Patient Safety Human Retrospective Design ROC Curve Sensitivity and Specificity Image Processing, Computer Assisted Radiographic Image Interpretation, Computer-Assisted ab: Develop a highly accurate deep learning model to reliably classify radiographs by laterality. Digital Imaging and Communications in Medicine (DICOM) data for nine body parts was extracted retrospectively. Laterality was determined directly if encoded properly or inferred using other elements. Curation confirmed categorization and identified inaccurate labels due to human error. Augmentation enriched training data to semi-equilibrate classes. Classification and object detection models were developed on a dedicated workstation and tested on novel images. Receiver operating characteristic (ROC) curves, sensitivity, specificity, and accuracy were calculated. Study-level accuracy was determined and both were compared to human performance. An ensemble model was tested for the rigorous use-case of automatically classifying exams retrospectively. The final classification model identified novel images with an ROC area under the curve (AUC) of 0.999, improving on previous work and comparable to human performance. A similar ROC curve was observed for per-study analysis with AUC of 0.999. The object detection model classified images with accuracy of 99% or greater at both image and study level. Confidence scores allow adjustment of sensitivity and specificity as needed; the ensemble model designed for the highly specific use-case of automatically classifying exams was comparable and arguably better than human performance demonstrating 99% accuracy with 1% of exams unchanged and no incorrect classification. Deep learning models can classify radiographs by laterality with high accuracy and may be applied in a variety of settings that could improve patient safety and radiologist satisfaction. Rigorous use-cases requiring high specificity are achievable. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|