Dataset Information

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging.

ABSTRACT:

Importance

Predicting infarct size and location is important for decision-making and prognosis in patients with acute stroke.

Objectives

To determine whether a deep learning model can predict final infarct lesions using magnetic resonance images (MRIs) acquired at initial presentation (baseline) and to compare the model with current clinical prediction methods.

Design, setting, and participants

In this multicenter prognostic study, a specific type of neural network for image segmentation (U-net) was trained, validated, and tested using patients from the Imaging Collaterals in Acute Stroke (iCAS) study from April 14, 2014, to April 15, 2018, and the Diffusion Weighted Imaging Evaluation for Understanding Stroke Evolution Study-2 (DEFUSE-2) study from July 14, 2008, to September 17, 2011 (reported in October 2012). Patients underwent baseline perfusion-weighted and diffusion-weighted imaging and MRI at 3 to 7 days after baseline. Patients were grouped into unknown, minimal, partial, and major reperfusion status based on 24-hour imaging results. Baseline images acquired at presentation were inputs, and the final true infarct lesion at 3 to 7 days was considered the ground truth for the model. The model calculated the probability of infarction for every voxel, which can be thresholded to produce a prediction. Data were analyzed from July 1, 2018, to March 7, 2019.

Main outcomes and measures

Area under the curve, Dice score coefficient (DSC) (a metric from 0-1 indicating the extent of overlap between the prediction and the ground truth; a DSC of ?0.5 represents significant overlap), and volume error. Current clinical methods were compared with model performance in subgroups of patients with minimal or major reperfusion.

Results

Among the 182 patients included in the model (97 women [53.3%]; mean [SD] age, 65?[16] years), the deep learning model achieved a median area under the curve of 0.92 (interquartile range [IQR], 0.87-0.96), DSC of 0.53 (IQR, 0.31-0.68), and volume error of 9 (IQR, -14 to 29) mL. In subgroups with minimal (DSC, 0.58 [IQR, 0.31-0.67] vs 0.55 [IQR, 0.40-0.65]; P?=?.37) or major (DSC, 0.48 [IQR, 0.29-0.65] vs 0.45 [IQR, 0.15-0.54]; P?=?.002) reperfusion for which comparison with existing clinical methods was possible, the deep learning model had comparable or better performance.

Conclusions and relevance

The deep learning model appears to have successfully predicted infarct lesions from baseline imaging without reperfusion information and achieved comparable performance to existing clinical methods. Predicting the subacute infarct lesion may help clinicians prepare for decompression treatment and aid in patient selection for neuroprotective clinical trials.

SUBMITTER: Yu Y

PROVIDER: S-EPMC7068232 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging.

Yu Yannan Y Xie Yuan Y Thamm Thoralf T Gong Enhao E Ouyang Jiahong J Huang Charles C Christensen Soren S Marks Michael P MP Lansberg Maarten G MG Albers Gregory W GW Zaharchuk Greg G

JAMA network open 20200302 3

<h4>Importance</h4>Predicting infarct size and location is important for decision-making and prognosis in patients with acute stroke.<h4>Objectives</h4>To determine whether a deep learning model can predict final infarct lesions using magnetic resonance images (MRIs) acquired at initial presentation (baseline) and to compare the model with current clinical prediction methods.<h4>Design, setting, and participants</h4>In this multicenter prognostic study, a specific type of neural network for imag ...[more]

PMID: 32163165

Similar Datasets

Project description:BackgroundMultiple linear stapler firings during double stapling technique (DST) after laparoscopic low anterior resection (LAR) are associated with an increased risk of anastomotic leakage (AL). However, it is difficult to predict preoperatively the need for multiple linear stapler cartridges during DST anastomosis.AimTo develop a deep learning model to predict multiple firings during DST anastomosis based on pelvic magnetic resonance imaging (MRI).MethodsWe collected 9476 MR images from 328 mid-low rectal cancer patients undergoing LAR with DST anastomosis, which were randomly divided into a training set (n = 260) and testing set (n = 68). Binary logistic regression was adopted to create a clinical model using six factors. The sequence of fast spin-echo T2-weighted MRI of the entire pelvis was segmented and analyzed. Pure-image and clinical-image integrated deep learning models were constructed using the mask region-based convolutional neural network segmentation tool and three-dimensional convolutional networks. Sensitivity, specificity, accuracy, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC) was calculated for each model.ResultsThe prevalence of ≥ 3 linear stapler cartridges was 17.7% (58/328). The prevalence of AL was statistically significantly higher in patients with ≥ 3 cartridges compared to those with ≤ 2 cartridges (25.0% vs 11.8%, P = 0.018). Preoperative carcinoembryonic antigen level > 5 ng/mL (OR = 2.11, 95%CI 1.08-4.12, P = 0.028) and tumor size ≥ 5 cm (OR = 3.57, 95%CI 1.61-7.89, P = 0.002) were recognized as independent risk factors for use of ≥ 3 linear stapler cartridges. Diagnostic performance was better with the integrated model (accuracy = 94.1%, PPV = 87.5%, and AUC = 0.88) compared with the clinical model (accuracy = 86.7%, PPV = 38.9%, and AUC = 0.72) and the image model (accuracy = 91.2%, PPV = 83.3%, and AUC = 0.81).ConclusionMRI-based deep learning model can predict the use of ≥ 3 linear stapler cartridges during DST anastomosis in laparoscopic LAR surgery. This model might help determine the best anastomosis strategy by avoiding DST when there is a high probability of the need for ≥ 3 linear stapler cartridges.

Project description:BackgroundThe purpose of this study was to develop a deep learning-based system with a cascade feature pyramid network for the detection and classification of breast lesions in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).MethodsThis retrospective study enrolled 191 consecutive patients with pathological confirmed breast lesions who underwent preoperative magnetic resonance imaging (MRI) at the Second Affiliated Hospital of Xi'an Jiaotong University. Patients were randomly divided into a training set comprising 153 patients with 126 malignant and 27 benign lesions and a validation set containing 38 patients with 31 malignant and 7 benign lesions under 5-fold cross-validation. Two radiologists annotated the location and classification of all lesions. After augmentation with pseudo-color image fusion, MRI images were fed into the developed cascade feature pyramid network system, feature pyramid network, and faster region-based convolutional neural network (CNN) for breast lesion detection and classification, respectively. The performance on large (>2 cm) and small (≤2 cm) breast lesions was further evaluated. Average precision (AP), mean AP, F1-score, sensitivity, and false positives were used to evaluate different systems. Cohen's kappa scores were calculated to assess agreement between different systems, and Student's t-test and the Holm-Bonferroni method were used to compare multiple groups.ResultsThe cascade feature pyramid network system outperformed the other systems with a mean AP and highest sensitivity of 0.826±0.051 and 0.970±0.014 (at 0.375 false positives), respectively. The F1-score of the cascade feature pyramid network in real detection was also superior to that of the other systems at both the slice and patient levels. The mean AP values of the cascade feature pyramid network reached 0.779±0.152 and 0.790±0.080 in detecting large and small lesions, respectively. Especially for small lesions, the cascade feature pyramid network achieved the best performance in detecting benign and malignant breast lesions at both the slice and patient levels.ConclusionsThe deep learning-based system with the developed cascade feature pyramid network has the potential to detect and classify breast lesions on DCE-MRI, especially small lesions.

Dataset Information

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging.

Importance

Objectives

Design, setting, and participants

Main outcomes and measures

Results

Conclusions and relevance

Publications

Use of Deep Learning to Predict Final Ischemic Stroke Lesions From Initial Magnetic Resonance Imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets