Quantum mechanics

Engineering

Effective diffusion coefficient

Biochemistry

Computer science

Thrombolysis

Receiver operating characteristic

Radiology

Biomarker

Mechanical engineering

Physics

Stroke (engine)

Imaging biomarker

Myocardial infarction

Internal medicine

Artificial intelligence

Area under the curve

Perfusion scanning

Medicine

Chemistry

Deep learning

Nuclear medicine

Tissue plasminogen activator

Cutoff

Convolutional neural network

Magnetic resonance imaging

Perfusion

Stroke

Background and Purpose— Treatment options for patients with acute ischemic stroke depend on the volume of salvageable tissue. This volume assessment is currently based on fixed thresholds and single imagine modalities, limiting accuracy. We wish to develop and validate a predictive model capable of automatically identifying and combining acute imaging features to accurately predict final lesion volume. Methods— Using acute magnetic resonance imaging, we developed and trained a deep convolutional neural network (CNN deep ) to predict final imaging outcome. A total of 222 patients were included, of which 187 were treated with rtPA (recombinant tissue-type plasminogen activator). The performance of CNN deep was compared with a shallow CNN based on the perfusion-weighted imaging biomarker Tmax (CNN Tmax ), a shallow CNN based on a combination of 9 different biomarkers (CNN shallow ), a generalized linear model, and thresholding of the diffusion-weighted imaging biomarker apparent diffusion coefficient (ADC) at 600×10 −6 mm 2 /s (ADC thres ). To assess whether CNN deep is capable of differentiating outcomes of ±intravenous rtPA, patients not receiving intravenous rtPA were included to train CNN deep, −rtpa to access a treatment effect. The networks’ performances were evaluated using visual inspection, area under the receiver operating characteristic curve (AUC), and contrast. Results— CNN deep yields significantly better performance in predicting final outcome (AUC=0.88±0.12) than generalized linear model (AUC=0.78±0.12; P =0.005), CNN Tmax (AUC=0.72±0.14; P &lt;0.003), and ADC thres (AUC=0.66±0.13; P &lt;0.0001) and a substantially better performance than CNN shallow (AUC=0.85±0.11; P =0.063). Measured by contrast, CNN deep improves the predictions significantly, showing superiority to all other methods ( P ≤0.003). CNN deep also seems to be able to differentiate outcomes based on treatment strategy with the volume of final infarct being significantly different ( P =0.048). Conclusions— The considerable prediction improvement accuracy over current state of the art increases the potential for automated decision support in providing recommendations for personalized treatment plans.

Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning