LSTM Network for Prediction of Hemorrhagic Transformation in Acute Stroke

Yu, Yannan; Parsi, Bhargav; Speier, William; Arnold, Corey; Lou, Min; Scalzo, Fabien

doi:10.1007/978-3-030-32251-9_20

Cited by 12 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies failed to fully utilize the MRI images, resulting in low prediction accuracy [ 21 , 22 , 32 ]. Besides, although deep learning has become a powerful tool for classification tasks in recent years, its training process often requires a large amount of data, which is often difficult to meet [ 23 , 24 ]. In addition, the poor interpretability of deep learning limits its wide application in clinical practice.…”

Section: Discussionmentioning

confidence: 99%

“…They first extracted the deep features of each slice using inception V3, then fused the features of all slices of each sequence, and finally spliced the features of all sequences with clinical features to realize HT prediction. Yu et al [ 24 ], used long short-term memory (LSTM) for feature extraction and fusion of local patches in a perfusion-weighted imaging (PWI) sequence, and combined them with the corresponding features of DWI images to predict HT. Although the DL method has been proved to have great application potential in segmentation, classification, and other fields, they often need a large amount of data for model training.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction Model of Hemorrhage Transformation in Patient with Acute Ischemic Stroke Based on Multiparametric MRI Radiomics and Machine Learning

Meng

Wang

et al. 2022

Brain Sciences

View full text Add to dashboard Cite

Intravenous thrombolysis is the most commonly used drug therapy for patients with acute ischemic stroke, which is often accompanied by complications of intracerebral hemorrhage transformation (HT). This study proposed to build a reliable model for pretreatment prediction of HT. Specifically, 5400 radiomics features were extracted from 20 regions of interest (ROIs) of multiparametric MRI images of 71 patients. Furthermore, a minimal set of all-relevant features were selected by LASSO from all ROIs and used to build a radiomics model through the random forest (RF). To explore the significance of normal ROIs, we built a model only based on abnormal ROIs. In addition, a model combining clinical factors and radiomics features was further built. Finally, the models were tested on an independent validation cohort. The radiomics model with 14 All-ROIs features achieved pretreatment prediction of HT (AUC = 0.871, accuracy = 0.848), which significantly outperformed the model with only 14 Abnormal-ROIs features (AUC = 0.831, accuracy = 0.818). Besides, combining clinical factors with radiomics features further benefited the prediction performance (AUC = 0.911, accuracy = 0.894). So, we think that the combined model can greatly assist doctors in diagnosis. Furthermore, we find that even if there were no lesions in the normal ROIs, they also provide characteristic information for the prediction of HT.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction Model of Hemorrhage Transformation in Patient with Acute Ischemic Stroke Based on Multiparametric MRI Radiomics and Machine Learning

Meng

Wang

et al. 2022

Brain Sciences

View full text Add to dashboard Cite

show abstract

“…Specifically, by incorporating ICD-10 codes [46] and other potential risk factors patterns from EHRs, Chantamit [45] confirmed that the LSTM algorithm is the most suitable for predictive analysis of any cerebrovascular disease or stroke. In another study, a methodology based on the LSTM model for predicting HDM (hemorrhagic transformation) in ischemic stroke was proposed by Yu et al [47]. The LSTM network structure was designed using a combination of DWI (diffusion weighted images) and PWI (perfusion-weighted magnetic response images).…”

Section: Stroke Prediction Using Machine Learning and Deep Learningmentioning

confidence: 99%

“…This LSTM consists of a structure that explicitly transfers past information to the next state, and by learning long-term dependencies, the cell state serves to convey past information to the next step [41], [42][43][44]. Deep Learning's LSTM has overcome the structural shortcomings of the existing RNN and can solve the problem of having a vanishing gradient when error values are propagated to the neural network layer [41,42,45,47]. LSTM consists of a cell state, an input gate, a forget gate, and an output gate, and vector output values at each gate are generated via the sigmoid layer and the tanh layer (see Figure 5).…”

Section: Experiments and Analysis Based On Deep Learningmentioning

confidence: 99%

AI-Based Stroke Disease Prediction System Using Real-Time Electromyography Signals

Park

Kwon

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Stroke is a leading cause of disabilities in adults and the elderly which can result in numerous social or economic difficulties. If left untreated, stroke can lead to death. In most cases, patients with stroke have been observed to have abnormal bio-signals (i.e., ECG). Therefore, if individuals are monitored and have their bio-signals measured and accurately assessed in real-time, they can receive appropriate treatment quickly. However, most diagnosis and prediction systems for stroke are image analysis tools such as CT or MRI, which are expensive and difficult to use for real-time diagnosis. In this paper, we developed a stroke prediction system that detects stroke using real-time bio-signals with artificial intelligence (AI). Both machine learning (Random Forest) and deep learning (Long Short-Term Memory) algorithms were used in our system. EMG (Electromyography) bio-signals were collected in real time from thighs and calves, after which the important features were extracted, and prediction models were developed based on everyday activities. Prediction accuracies of 90.38% for Random Forest and of 98.958% for LSTM were obtained for our proposed system. This system can be considered an alternative, low-cost, real-time diagnosis system that can obtain accurate stroke prediction and can potentially be used for other diseases such as heart disease.

show abstract

“…Fast and precise stroke lesion detection and segmentation is an extreme important process with regards to stroke diagnosis, treatment, and prognosis. Except from the manual segmentation approach, machine learning based segmentation methods are the most promising ones when considering efficiency and accuracy, and convolutional neural network based models are the first of its kind [25] [32][29] [30] [33] [17]. However, these neural network models do not really align with the brain anatomical structures thus lack of explanatory characteristics of the model outcomes.…”

Section: Introductionmentioning

confidence: 99%

Stroke Lesion Segmentation with Visual Cortex Anatomy Alike Neural Nets

Li¹

2021

Preprint

View full text Add to dashboard Cite

Cerebrovascular accident, or commonly known as stroke, is an acute disease with extreme impact on patients and healthcare systems and is the second largest cause of death worldwide. Fast and precise stroke lesion detection and location is an extreme important process with regards to stroke diagnosis, treatment, and prognosis. Except from the manual segmentation approach, machine learning based segmentation methods are the most promising ones when considering efficiency and accuracy, and convolutional neural network based models are the first of its kind. However, most of these neural network models do not really align with the brain anatomical structures. Intuitively, this work presents a more brain alike model which mimics the anatomical structure of the human visual cortex. Through the preliminary experiments on the stroke lesion segmentation task, the proposed model is found to be able to perform equally well or better to the de-facto standard U-Net. Part of the implementation will be made available at https://github.com/DarkoBomer/VCA-Net.

show abstract

LSTM Network for Prediction of Hemorrhagic Transformation in Acute Stroke

Cited by 12 publications

References 12 publications

Prediction Model of Hemorrhage Transformation in Patient with Acute Ischemic Stroke Based on Multiparametric MRI Radiomics and Machine Learning

Prediction Model of Hemorrhage Transformation in Patient with Acute Ischemic Stroke Based on Multiparametric MRI Radiomics and Machine Learning

AI-Based Stroke Disease Prediction System Using Real-Time Electromyography Signals

Stroke Lesion Segmentation with Visual Cortex Anatomy Alike Neural Nets

Contact Info

Product

Resources

About