Evaluation of Diffusion Lesion Volume Measurements in Acute Ischemic Stroke Using Encoder-Decoder Convolutional Network
- 1 June 2019
- journal article
- research article
- Published by Wolters Kluwer Health in Stroke
- Vol. 50 (6) , 1444-1451
Abstract
Background and Purpose—: Automatic segmentation of cerebral infarction on diffusion-weighted imaging (DWI) is typically performed based on a fixed apparent diffusion coefficient (ADC) threshold. Fixed ADC threshold methods may not be accurate because ADC values vary over time after stroke onset. Deep learning has the potential to improve the accuracy, provided that a large set of correctly annotated lesion data is used for training. The purpose of this study was to evaluate deep learning–based methods and compare them with commercial software in terms of lesion volume measurements. Methods—: U-net, an encoder-decoder convolutional neural network, was adopted to train segmentation models. Two U-net models were developed: a U-net (DWI+ADC) model, trained on DWI and ADC data, and a U-net (DWI) model, trained on DWI data only. A total of 296 subjects were used for training and 134 for external validation. An expert neurologist manually delineated the stroke lesions on DWI images, which were used as the ground-truth reference. Lesion volume measurements from the U-net methods were compared against the expert’s manual segmentation and Rapid Processing of Perfusion and Diffusion (RAPID; iSchemaView Inc) analysis. Results—: In external validation, U-net (DWI+ADC) showed the highest intraclass correlation coefficient with manual segmentation (intraclass correlation coefficient, 1.0; 95% CI, 0.99–1.00) and sufficiently high correlation with the RAPID results (intraclass correlation coefficient, 0.99; 95% CI, 0.98–0.99). U-net (DWI+ADC) and manual segmentation resulted in the smallest 95% Bland-Altman limits of agreement (−5.31 to 4.93 mL) with a mean difference of −0.19 mL. Conclusions—: The presented deep learning–based method is fully automatic and shows a high correlation of diffusion lesion volume measurements with manual segmentation and commercial software. The method has the potential to be used in patient selection for endovascular reperfusion therapy in the late time window of acute stroke.Keywords
This publication has 17 references indexed in Scilit:
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Global, regional, and national life expectancy, all-cause mortality, and cause-specific mortality for 249 causes of death, 1980–2015: a systematic analysis for the Global Burden of Disease Study 2015The Lancet, 2016
- Thrombectomy within 8 Hours after Symptom Onset in Ischemic StrokeNew England Journal of Medicine, 2015
- A Multicenter, Randomized, Controlled Study to Investigate Extending the Time for Thrombolysis in Emergency Neurological Deficits with Intra-Arterial Therapy (EXTEND-IA)International Journal of Stroke, 2013
- Apparent Diffusion Coefficient Threshold for Delineation of Ischemic CoreInternational Journal of Stroke, 2013
- The Infarct Core is Well Represented by the Acute Diffusion Lesion: Sustained Reversal is InfrequentJournal of Cerebral Blood Flow & Metabolism, 2011
- Signal Evolution and Infarction Risk for Apparent Diffusion Coefficient Lesions in Acute Ischemic Stroke Are Both Time- and Perfusion-DependentStroke, 2011
- Real‐time diffusion‐perfusion mismatch analysis in acute strokeJournal of Magnetic Resonance Imaging, 2010
- Risk Assessment of Symptomatic Intracerebral Hemorrhage After Thrombolysis Using DWI-ASPECTSStroke, 2009
- Large Ischemic Lesions on Diffusion-Weighted Imaging Done Before Intravenous Tissue Plasminogen Activator Thrombolysis Predicts a Poor Outcome in Patients With Acute StrokeStroke, 2008