Abstract WP79: The Value of Pre-Training for Deep Learning Acute Stroke Triaging Models

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Yannan Yu ◽  
Yuan Xie ◽  
Enhao Gong ◽  
Thoralf thamm ◽  
Jiahong Ouyang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ground Truth ◽  
Residue Function ◽  
Fine Tuning ◽  
Wilcoxon Test ◽  
Lesion Volume ◽  
Learning Models ◽  
Wide Range ◽  
Training Strategies ◽  
Ischemic Core

Objective: We investigated if deep learning models are able to define the penumbra and ischemic core by comparing models from two training strategies (with and without pre-training) and clinical thresholding criteria (MRI parameter time-to-peak of the residue function [Tmax] and apparent diffusion coefficient [ADC]). Methods: We selected patients from two multicenter stroke trials, with baseline perfusion-weighted imaging (PWI) and diffusion-weighted imaging (DWI) and 3-7 day T2-FLAIR. Based on reperfusion rate calculated from baseline and 24 hr PWI, patients were grouped into unknown (no 24 hr PWI scan), minimal (≤20%), partial (20%-80%), and major (≥80%) reperfusion. Attention-gated U-net structure was selected for training, with eight image channels from baseline PWI/DWI as inputs and the infarct lesion manually segmented on T2-FLAIR as ground truth. Two training strategies were used: (1) training two models separately in minimal and major reperfusion patients; (2) pre-training a model using patients with partial and unknown reperfusion, then fine-tuning two models using minimal and major reperfusion patients, respectively. Prediction was evaluated by Dice score coefficient (DSC), and lesion volume error at an optimal threshold. In minimal and major reperfusion patients, the deep learning models and Tmax and ADC thresholding were compared using paired sample Wilcoxon test. Results: 182 patients were included (85 males, age 65±16 yrs, baseline NIHSS 15 IQR 10-19), with a breakdown of minimal/major/partial/unknown reperfusion status of 32/65/43/42 patients, respectively. The pre-training approach performed the best among all approaches (Table 1, Figure 1). Conclusion: Deep learning models to predict penumbra and ischemic core are best trained using general pre-training on a wide range of stroke cases followed by fine-tuning on the extreme cases. This method outperforms conventional DWI-PWI mismatch inspired thresholding approaches.

Abstract P319: Can Deep Learning Find the Ischemic Core on CT? Transfer Learning From Pre-Trained MRI-Based Networks

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Yannan Yu ◽  
Soren Christensen ◽  
Yuan Xie ◽  
Enhao Gong ◽  
Maarten G Lansberg ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ground Truth ◽  
Learning Model ◽  
Fine Tuning ◽  
Learning Models ◽  
Starting Point ◽  
Stroke Lesion ◽  
Ischemic Core ◽  
Deep Learning Model

Objective: Ischemic core prediction from CT perfusion (CTP) remains inaccurate compared with gold standard diffusion-weighted imaging (DWI). We evaluated if a deep learning model to predict the DWI lesion from MR perfusion (MRP) could facilitate ischemic core prediction on CTP. Method: Using the multi-center CRISP cohort of acute ischemic stroke patient with CTP before thrombectomy, we included patients with major reperfusion (TICI score≥2b), adequate image quality, and follow-up MRI at 3-7 days. Perfusion parameters including Tmax, mean transient time, cerebral blood flow (CBF), and cerebral blood volume were reconstructed by RAPID software. Core lab experts outlined the stroke lesion on the follow-up MRI. A previously trained MRI model in a separate group of patients was used as a starting point, which used MRP parameters as input and RAPID ischemic core on DWI as ground truth. We fine-tuned this model, using CTP parameters as input, and follow-up MRI as ground truth. Another model was also trained from scratch with only CTP data. 5-fold cross validation was used. Performance of the models was compared with ischemic core (rCBF≤30%) from RAPID software to identify the presence of a large infarct (volume>70 or >100ml). Results: 94 patients in the CRISP trial met the inclusion criteria (mean age 67±15 years, 52% male, median baseline NIHSS 18, median 90-day mRS 2). Without fine-tuning, the MRI model had an agreement of 73% in infarct >70ml, and 69% in >100ml; the MRI model fine-tuned on CT improved the agreement to 77% and 73%; The CT model trained from scratch had agreements of 73% and 71%; All of the deep learning models outperformed the rCBF segmentation from RAPID, which had agreements of 51% and 64%. See Table and figure. Conclusions: It is feasible to apply MRP-based deep learning model to CT. Fine-tuning with CTP data further improves the predictions. All deep learning models predict the stroke lesion after major recanalization better than thresholding approaches based on rCBF.

scholarly journals Training Strategies for Radiology Deep Learning Models in Data-Limited Scenarios

2021 ◽  
Author(s):  
Sema Candemir ◽  
Xuan V. Nguyen ◽  
Les R. Folio ◽  
Luciano M. Prevedello
Keyword(s):  
Deep Learning ◽  
Learning Models ◽  
Training Strategies

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Covid-19 detection via deep neural network and occlusion sensitivity maps

2021 ◽  
Author(s):  
Noor Ahmad ◽  
Muhammad Aminu ◽  
Mohd Halim Mohd Noor
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Color Images ◽  
Fine Tuning ◽  
Training Dataset ◽  
Learning Approaches ◽  
Learning Models ◽  
Sensitivity Maps

Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue, we propose a deep learning architecture called CovidNet which requires a relatively smaller number of parameters. CovidNet accepts grayscale images as inputs and is suitable for training with limited training dataset. Experimental results show that CovidNet outperforms other state-of-the-art deep learning models for Covid-19 detection.

A comparative study of fine-tuning deep learning models for plant disease identification

2019 ◽  
Vol 161 ◽  
pp. 272-279 ◽  
Author(s):  
Edna Chebet Too ◽  
Li Yujian ◽  
Sam Njuki ◽  
Liu Yingchun
Keyword(s):  
Deep Learning ◽  
Comparative Study ◽  
Plant Disease ◽  
Fine Tuning ◽  
Learning Models ◽  
Disease Identification

scholarly journals Covid-19 detection via deep neural network and occlusion sensitivity maps

2021 ◽  
Author(s):  
Noor Ahmad ◽  
Muhammad Aminu ◽  
Mohd Halim Mohd Noor
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Color Images ◽  
Fine Tuning ◽  
Training Dataset ◽  
Learning Approaches ◽  
Learning Models ◽  
Sensitivity Maps

Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue, we propose a deep learning architecture called CovidNet which requires a relatively smaller number of parameters. CovidNet accepts grayscale images as inputs and is suitable for training with limited training dataset. Experimental results show that CovidNet outperforms other state-of-the-art deep learning models for Covid-19 detection.

scholarly journals Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2025
Author(s):  
Jasjit S. Suri ◽  
Sushant Agarwal ◽  
Pranav Elavarthi ◽  
Rajesh Pathak ◽  
Vedmanvitha Ketireddy ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Ground Truth ◽  
Chest Ct ◽  
Learning Models ◽  
Lung Segmentation ◽  
Variability Analysis ◽  
Experience Levels ◽  
Training Stage ◽  
Variability Study

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

scholarly journals Deep learning-based fully automated Z-axis coverage range definition from scout scans to eliminate overscanning in chest CT imaging

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Yazdan Salimi ◽  
Isaac Shiri ◽  
Azadeh Akhavanallaf ◽  
Zahra Mansouri ◽  
Abdollah Saberi Manesh ◽  
...  
Keyword(s):  
Deep Learning ◽  
Radiation Dose ◽  
Absorbed Dose ◽  
Test Group ◽  
Ground Truth ◽  
Chest Ct ◽  
Fine Tuning ◽  
Reduce Radiation Dose ◽  
Automatic Methods ◽  
Range Selection

Abstract Background Despite the prevalence of chest CT in the clinic, concerns about unoptimized protocols delivering high radiation doses to patients still remain. This study aimed to assess the additional radiation dose associated with overscanning in chest CT and to develop an automated deep learning-assisted scan range selection technique to reduce radiation dose to patients. Results A significant overscanning range (31 ± 24) mm was observed in clinical setting for over 95% of the cases. The average Dice coefficient for lung segmentation was 0.96 and 0.97 for anterior–posterior (AP) and lateral projections, respectively. By considering the exact lung coverage as the ground truth, and AP and lateral projections as input, The DL-based approach resulted in errors of 0.08 ± 1.46 and − 1.5 ± 4.1 mm in superior and inferior directions, respectively. In contrast, the error on external scout views was − 0.7 ± 4.08 and 0.01 ± 14.97 mm for superior and inferior directions, respectively.The ED reduction achieved by automated scan range selection was 21% in the test group. The evaluation of a large multi-centric chest CT dataset revealed unnecessary ED of more than 2 mSv per scan and 67% increase in the thyroid absorbed dose. Conclusion The proposed DL-based solution outperformed previous automatic methods with acceptable accuracy, even in complicated and challenging cases. The generizability of the model was demonstrated by fine-tuning the model on AP scout views and achieving acceptable results. The method can reduce the unoptimized dose to patients by exclunding unnecessary organs from field of view.

scholarly journals Metrics for Automatic Evaluation of Text from NLP Models for Text to Scene Generation

2021 ◽  
Vol 5 (4) ◽  
pp. 20-25
Author(s):  
S. Yashaswini ◽  
S. S. Shylaja
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Cost Function ◽  
Performance Metrics ◽  
Evaluation Criteria ◽  
Ground Truth ◽  
Automatic Evaluation ◽  
Mean Square ◽  
Learning Models ◽  
Classification Tasks

Performance metrics give us an indication of which model is better for which task. Researchers attempt to apply machine learning and deep learning models to measure the performance of models through cost function or evaluation criteria like Mean square error (MSE) for regression, accuracy, and f1-score for classification tasks Whereas in NLP performance measurement is a complex due variation of ground truth and results obta.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

Sign in / Sign up

Export Citation Format

Share Document