Deep Learning for Detection of Complete Anterior Cruciate Ligament Tear.
Deep learning for MRI detection of sports injuries poses unique challenges. To address these difficulties, this study examines the feasibility and incremental benefit of several customized network architectures in evaluation of complete anterior cruciate ligament (ACL) tears. Two hundred sixty patie...
| Publicado en: | Journal of Digital Imaging Vol. 32; no. 6; pp. 980 - 987 |
|---|---|
| Autores principales: | , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
Springer Nature
Dec2019
|
| 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=139568172&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 139568172 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Dec2019 vid: 32 iid: 6 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 139568172 139568172 139568172 10.1007/s10278-019-00193-4 139568172 ppf: 980 ppct: 7 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Deep Learning for Detection of Complete Anterior Cruciate Ligament Tear. aug: au: Chang, Peter D. Wong, Tony T. Rasiej, Michael J. affil: Center for Artificial Intelligence in Diagnostic Medicine, University of California Irvine Medical Center, 101 The City Drive South, Building 55, Suite 201, 92868, Orange, CA, USA sug: subj: Anterior Cruciate Ligament Injuries Diagnosis Magnetic Resonance Imaging Methods Image Processing, Computer Assisted Methods Deep Learning Methods Human Adolescence Adult Record Review Neural Networks (Computer) Algorithms Sensitivity and Specificity Predictive Value of Tests Adolescent: 13-18 years Adult: 19-44 years ab: Deep learning for MRI detection of sports injuries poses unique challenges. To address these difficulties, this study examines the feasibility and incremental benefit of several customized network architectures in evaluation of complete anterior cruciate ligament (ACL) tears. Two hundred sixty patients, ages 18–40, were identified in a retrospective review of knee MRIs obtained from September 2013 to March 2016. Half of the cases demonstrated a complete ACL tear (624 slices), the other half a normal ACL (3520 slices). Two hundred cases were used for training and validation, and the remaining 60 cases as an independent test set. For each exam with an ACL tear, coronal proton density non-fat suppressed sequence was manually annotated to delineate: (1) a bounding-box around the cruciate ligaments; (2) slices containing the tear. Multiple convolutional neural network (CNN) architectures were implemented including variations in input field-of-view and dimensionality. For single-slice CNN architectures, validation accuracy of a dynamic patch-based sampling algorithm (0.765) outperformed both cropped slice (0.720) and full slice (0.680) strategies. Using the dynamic patch-based sampling algorithm as a baseline, a five-slice CNN input (0.915) outperformed both three-slice (0.865) and single-slice (0.765) inputs. The final highest performing five-slice dynamic patch-based sampling algorithm resulted in independent test set AUC, sensitivity, specificity, PPV, and NPV of 0.971, 0.967, 1.00, 0.938, and 1.00. A customized 3D deep learning architecture based on dynamic patch-based sampling demonstrates high performance in detection of complete ACL tears with over 96% test set accuracy. A cropped field-of-view and 3D inputs are critical for high algorithm performance. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|