Ensemble of Deep Convolutional Neural Networks for Prognosis of Ischemic Stroke

Choi, Youngwon; Kwon, Yongchan; Lee, Hanbyul; Kim, Beom Joon; Paik, Myunghee Cho; Won, Joong Ho

doi:10.1007/978-3-319-55524-9_22

Cited by 39 publications

(44 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multiscale U-net architecture trained with the negative Dice score achieved the best performance among the nine combinations considered. The implementation details such as pre-processing, data augmentation, and regularization are similar to ( 30 ), which ranked the 1st place in ISLES 2016. There are two major improvements from our approach to the 2016 challenge.…”

Section: A1 Isles 2016mentioning

confidence: 99%

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

et al. 2018

Self Cite

View full text Add to dashboard Cite

Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).

show abstract

Section: A1 Isles 2016mentioning

confidence: 99%

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is also worth pointing out that while deep learning has won several predictive modeling challenges, these have mostly involved image segmentation (Choi et al, 2016, Kamnitsas et al, 2017a, Hongwei Li et al, 2018. The success of DNNs has been less clear in other neuroimaging challenges.…”

Section: Potential Reasons Why Dnns Did Not Outperform Kernel Regressmentioning

confidence: 99%

“…Deep neural networks can perform well in certain scenarios and tasks, where large quantities of data are unavailable, e.g., winning multiple MICCAI predictive modeling challenges involving image segmentation (Choi et al, 2016, Kamnitsas et al, 2017a, Hongwei Li et al, 2018. Yet, the conventional wisdom is that DNNs perform especially well when applied to well-powered samples, for instance, the 14 million images in ImageNet (Russakovsky et al, 2015) and Google 1 Billion Word Corpus (Chelba et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Networks and Kernel Regression Achieve Comparable Accuracies for Functional Connectivity Prediction of Behavior and Demographics

Kong

Holmes

et al. 2018

Preprint

116

View full text Add to dashboard Cite

There is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies.

show abstract

“…At the 2017 edition of the ISLES challenge ( 21 ) we presented a robust network on perfusion image data to predict an average lesion outcome and ranked second overall for the binary segmentation output. Many of the top-ranked methods exploited a U-Net architecture, such as the challenge winner ( 22 ) who used a 3D U-Net within an ensemble along with other networks and focused on its hyperparameter optimization. In our 2D network instead, we added further skip connections within the encoding path to enhance sensitivity in particular for the difficult smaller lesions in comparison to a standard U-Net ( 23 ).…”

Section: Image Analysismentioning

confidence: 99%

Learning to Predict Ischemic Stroke Growth on Acute CT Perfusion Data by Interpolating Low-Dimensional Shape Representations

et al. 2018

View full text Add to dashboard Cite

Cerebrovascular diseases, in particular ischemic stroke, are one of the leading global causes of death in developed countries. Perfusion CT and/or MRI are ideal imaging modalities for characterizing affected ischemic tissue in the hyper-acute phase. If infarct growth over time could be predicted accurately from functional acute imaging protocols together with advanced machine-learning based image analysis, the expected benefits of treatment options could be better weighted against potential risks. The quality of the outcome prediction by convolutional neural networks (CNNs) is so far limited, which indicates that even highly complex deep learning algorithms are not fully capable of directly learning physiological principles of tissue salvation through weak supervision due to a lack of data (e.g., follow-up segmentation). In this work, we address these current shortcomings by explicitly taking into account clinical expert knowledge in the form of segmentations of the core and its surrounding penumbra in acute CT perfusion images (CTP), that are trained to be represented in a low-dimensional non-linear shape space. Employing a multi-scale CNN (U-Net) together with a convolutional auto-encoder, we predict lesion tissue probabilities for new patients. The predictions are physiologically constrained to a shape embedding that encodes a continuous progression between the core and penumbra extents. The comparison to a simple interpolation in the original voxel space and an unconstrained CNN shows that the use of such a shape space can be advantageous to predict time-dependent growth of stroke lesions on acute perfusion data, yielding a Dice score overlap of 0.46 for predictions from expert segmentations of core and penumbra. Our interpolation method models monotone infarct growth robustly on a linear time scale to automatically predict clinically plausible tissue outcomes that may serve as a basis for more clinical measures such as the expected lesion volume increase and can support the decision making on treatment options and triage.

show abstract

Ensemble of Deep Convolutional Neural Networks for Prognosis of Ischemic Stroke

Cited by 39 publications

References 8 publications

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI

Deep Neural Networks and Kernel Regression Achieve Comparable Accuracies for Functional Connectivity Prediction of Behavior and Demographics

Learning to Predict Ischemic Stroke Growth on Acute CT Perfusion Data by Interpolating Low-Dimensional Shape Representations

Contact Info

Product

Resources

About