| 1. |
- Ali, Muhaddisa Barat, 1986, et al.
(författare)
-
A novel federated deep learning scheme for glioma and its subtype classification
- 2023
-
Ingår i: Frontiers in Neuroscience. - 1662-4548 .- 1662-453X. ; 17
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Deep learning (DL) has shown promising results in molecular-based classification of glioma subtypes from MR images. DL requires a large number of training data for achieving good generalization performance. Since brain tumor datasets are usually small in size, combination of such datasets from different hospitals are needed. Data privacy issue from hospitals often poses a constraint on such a practice. Federated learning (FL) has gained much attention lately as it trains a central DL model without requiring data sharing from different hospitals. Method: We propose a novel 3D FL scheme for glioma and its molecular subtype classification. In the scheme, a slice-based DL classifier, EtFedDyn, is exploited which is an extension of FedDyn, with the key differences on using focal loss cost function to tackle severe class imbalances in the datasets, and on multi-stream network to exploit MRIs in different modalities. By combining EtFedDyn with domain mapping as the pre-processing and 3D scan-based post-processing, the proposed scheme makes 3D brain scan-based classification on datasets from different dataset owners. To examine whether the FL scheme could replace the central learning (CL) one, we then compare the classification performance between the proposed FL and the corresponding CL schemes. Furthermore, detailed empirical-based analysis were also conducted to exam the effect of using domain mapping, 3D scan-based post-processing, different cost functions and different FL schemes. Results: Experiments were done on two case studies: classification of glioma subtypes (IDH mutation and wild-type on TCGA and US datasets in case A) and glioma grades (high/low grade glioma HGG and LGG on MICCAI dataset in case B). The proposed FL scheme has obtained good performance on the test sets (85.46%, 75.56%) for IDH subtypes and (89.28%, 90.72%) for glioma LGG/HGG all averaged on five runs. Comparing with the corresponding CL scheme, the drop in test accuracy from the proposed FL scheme is small (−1.17%, −0.83%), indicating its good potential to replace the CL scheme. Furthermore, the empirically tests have shown that an increased classification test accuracy by applying: domain mapping (0.4%, 1.85%) in case A; focal loss function (1.66%, 3.25%) in case A and (1.19%, 1.85%) in case B; 3D post-processing (2.11%, 2.23%) in case A and (1.81%, 2.39%) in case B and EtFedDyn over FedAvg classifier (1.05%, 1.55%) in case A and (1.23%, 1.81%) in case B with fast convergence, which all contributed to the improvement of overall performance in the proposed FL scheme. Conclusion: The proposed FL scheme is shown to be effective in predicting glioma and its subtypes by using MR images from test sets, with great potential of replacing the conventional CL approaches for training deep networks. This could help hospitals to maintain their data privacy, while using a federated trained classifier with nearly similar performance as that from a centrally trained one. Further detailed experiments have shown that different parts in the proposed 3D FL scheme, such as domain mapping (make datasets more uniform) and post-processing (scan-based classification), are essential.
|
|
| 2. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Enlarged Training Dataset by Pairwise GANs for Molecular-Based Brain Tumor Classification
- 2020
-
Ingår i: IEEE Access. - 2169-3536 .- 2169-3536. ; 8:1, s. 22560-22570
-
Tidskriftsartikel (refereegranskat)abstract
- This paper addresses issues of brain tumor subtype classification using Magnetic Resonance Images (MRIs) from different scanner modalities like T1 weighted, T1 weighted with contrast-enhanced, T2 weighted and FLAIR images. Currently most available glioma datasets are relatively moderate in size, and often accompanied with incomplete MRIs in different modalities. To tackle the commonly encountered problems of insufficiently large brain tumor datasets and incomplete modality of image for deep learning, we propose to add augmented brain MR images to enlarge the training dataset by employing a pairwise Generative Adversarial Network (GAN) model. The pairwise GAN is able to generate synthetic MRIs across different modalities. To achieve the patient-level diagnostic result, we propose a post-processing strategy to combine the slice-level glioma subtype classification results by majority voting. A two-stage course-to-fine training strategy is proposed to learn the glioma feature using GAN-augmented MRIs followed by real MRIs. To evaluate the effectiveness of the proposed scheme, experiments have been conducted on a brain tumor dataset for classifying glioma molecular subtypes: isocitrate dehydrogenase 1 (IDH1) mutation and IDH1 wild-type. Our results on the dataset have shown good performance (with test accuracy 88.82%). Comparisons with several state-of-the-art methods are also included.
|
|
| 3. |
- Memedi, Mevludin, et al.
(författare)
-
Validity and responsiveness of at-home touch-screen assessments in advanced Parkinson's disease
- 2015
-
Ingår i: IEEE journal of biomedical and health informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 2168-2194 .- 2168-2208. ; 19:6, s. 1829-1834
-
Tidskriftsartikel (refereegranskat)abstract
- The aim of this study was to investigate if a telemetry test battery can be used to measure effects of Parkinson’s disease (PD) treatment intervention and disease progression in patients with fluctuations. Sixty-five patients diagnosed with advanced PD were recruited in an open longitudinal 36-month study; 35 treated with levodopa-carbidopa intestinal gel (LCIG) and 30 were candidates for switching from oral PD treatment to LCIG. They utilized a test battery, consisting of self-assessments of symptoms and fine motor tests (tapping and spiral drawings), four times per day in their homes during week-long test periods. The repeated measurements were summarized into an overall test score (OTS) to represent the global condition of the patient during a test period. Clinical assessments included ratings on Unified PD Rating Scale (UPDRS) and 39-item PD Questionnaire (PDQ-39) scales. In LCIG-naïve patients, mean OTS compared to baseline was significantly improved from the first test period on LCIG treatment until month 24. In LCIG-non-naïve patients, there were no significant changes in mean OTS until month 36. The OTS correlated adequately with total UPDRS (rho = 0.59) and total PDQ-39 (0.59). Responsiveness measured as effect size was 0.696 and 0.536 for OTS and UPDRS respectively. The trends of the test scores were similar to the trends of clinical rating scores but dropout rate was high. Correlations between OTS and clinical rating scales were adequate indicating that the test battery contains important elements of the information of well-established scales. The responsiveness and reproducibility were better for OTS than for total UPDRS.
|
|
| 4. |
- Ge, Chenjie, 1991, et al.
(författare)
-
3D Multi-Scale Convolutional Networks for Glioma Grading Using MR Images
- 2018
-
Ingår i: Proceedings - International Conference on Image Processing, ICIP. - 1522-4880. - 9781479970612 ; , s. 141-145
-
Konferensbidrag (refereegranskat)abstract
- This paper addresses issues of grading brain tumor, glioma, from Magnetic Resonance Images (MRIs). Although feature pyramid is shown to be useful to extract multi-scale features for object recognition, it is rarely explored in MRI images for glioma classification/grading. For glioma grading, existing deep learning methods often use convolutional neural networks (CNNs) to extract single-scale features without considering that the scales of brain tumor features vary depending on structure/shape, size, tissue smoothness, and locations. In this paper, we propose to incorporate the multi-scale feature learning into a deep convolutional network architecture, which extracts multi-scale semantic as well as fine features for glioma tumor grading. The main contributions of the paper are: (a) propose a novel 3D multi-scale convolutional network architecture for the dedicated task of glioma grading; (b) propose a novel feature fusion scheme that further refines multi-scale features generated from multi-scale convolutional layers; (c) propose a saliency-aware strategy to enhance tumor regions of MRIs. Experiments were conducted on an open dataset for classifying high/low grade gliomas. Performance on the test set using the proposed scheme has shown good results (with accuracy of 89.47%).
|
|
| 5. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Multiscale Deep Convolutional Networks for Characterization and Detection of Alzheimer's Disease using MR Images
- 2019
-
Ingår i: Proceedings - International Conference on Image Processing, ICIP. - 1522-4880. ; 2019-September, s. 789-793
-
Konferensbidrag (refereegranskat)abstract
- This paper addresses the issues of Alzheimer's disease (AD) characterization and detection from Magnetic Resonance Images (MRIs). Many existing AD detection methods use single-scale feature learning from brain scans. In this paper, we propose a multiscale deep learning architecture for learning AD features. The main contributions of the paper include: (a) propose a novel 3D multiscale CNN architecture for the dedicated task of AD detection; (b) propose a feature fusion and enhancement strategy for multiscale features; (c) empirical study on the impact of several settings, including two dataset partitioning approaches, and the use of multiscale and feature enhancement. Experiments were conducted on an open ADNI dataset (1198 brain scans from 337 subjects), test results have shown the effectiveness of the proposed method with test accuracy of 93.53%, 87.24% (best, average) on subject separated dataset, and 99.44%, 98.80% (best, average) on random brain scan-partitioned dataset. Comparison with eight existing methods has provided further support to the proposed method.
|
|
| 6. |
- Wang, Wenjuan, et al.
(författare)
-
Developing and externally validating a machine learning risk prediction model for 30-day mortality after stroke using national stroke registers in the UK and Sweden.
- 2023
-
Ingår i: BMJ Open. - : BMJ Publishing Group Ltd. - 2044-6055. ; 13:11
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVES: We aimed to develop and externally validate a generalisable risk prediction model for 30-day stroke mortality suitable for supporting quality improvement analytics in stroke care using large nationwide stroke registers in the UK and Sweden.DESIGN: Registry-based cohort study.SETTING: Stroke registries including the Sentinel Stroke National Audit Programme (SSNAP) in England, Wales and Northern Ireland (2013-2019) and the national Swedish stroke register (Riksstroke 2015-2020).PARTICIPANTS AND METHODS: Data from SSNAP were used for developing and temporally validating the model, and data from Riksstroke were used for external validation. Models were developed with the variables available in both registries using logistic regression (LR), LR with elastic net and interaction terms and eXtreme Gradient Boosting (XGBoost). Performances were evaluated with discrimination, calibration and decision curves.OUTCOME MEASURES: The primary outcome was all-cause 30-day in-hospital mortality after stroke.RESULTS: In total, 488 497 patients who had a stroke with 12.4% 30-day in-hospital mortality were used for developing and temporally validating the model in the UK. A total of 128 360 patients who had a stroke with 10.8% 30-day in-hospital mortality and 13.1% all mortality were used for external validation in Sweden. In the SSNAP temporal validation set, the final XGBoost model achieved the highest area under the receiver operating characteristic curve (AUC) (0.852 (95% CI 0.848 to 0.855)) and was well calibrated. The performances on the external validation in Riksstroke were as good and achieved AUC at 0.861 (95% CI 0.858 to 0.865) for in-hospital mortality. For Riksstroke, the models slightly overestimated the risk for in-hospital mortality, while they were better calibrated at the risk for all mortality.CONCLUSION: The risk prediction model was accurate and externally validated using high quality registry data. This is potentially suitable to be deployed as part of quality improvement analytics in stroke care to enable the fair comparison of stroke mortality outcomes across hospitals and health systems across countries.
|
|
| 7. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Multi-Stream Multi-Scale Deep Convolutional Networks for Alzheimer's Disease Detection using MR Images
- 2019
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 350, s. 60-69
-
Tidskriftsartikel (refereegranskat)abstract
- This paper addresses the issue of Alzheimer's disease (AD) detection from Magnetic Resonance Images (MRIs). Existing AD detection methods rely on global feature learning from the whole brain scans, while depending on the tissue types, AD related features in dierent tissue regions, e.g. grey matter (GM), white matter (WM), and cerebrospinal uid (CSF), show different characteristics. In this paper, we propose a deep learning method for multi-scale feature learning based on segmented tissue areas. A novel deep 3D multi-scale convolutional network scheme is proposed to generate multi-resolution features for AD detection. The proposed scheme employs several parallel 3D multi-scale convolutional networks, each applying to individual tissue regions (GM, WM and CSF) followed by feature fusions. The proposed fusion is applied in two separate levels: the rst level fusion is applied on different scales within the same tissue region, and the second level is on dierent tissue regions. To further reduce the dimensions of features and mitigate overtting, a feature boosting and dimension reduction method, XGBoost, is utilized before the classication. The proposed deep learning scheme has been tested on a moderate open dataset of ADNI (1198 scans from 337 subjects), with excellent test performance on randomly partitioned datasets (best 99.67%, average 98.29%), and good test performance on subject-separated partitioned datasets (best 94.74%, average 89.51%). Comparisons with state-of-the-art methods are also included.
|
|
| 8. |
- Westin, Jerker, et al.
(författare)
-
A new computer method for assessing drawing impairment in Parkinson's disease
- 2010
-
Ingår i: Journal of Neuroscience Methods. - Amsterdam : Elsevier. - 0165-0270 .- 1872-678X. ; 190:1, s. 143-148
-
Tidskriftsartikel (refereegranskat)abstract
- A test battery, consisting of self-assessments and motor tests (tapping and spiral drawing tasks) was used on 9482 test occasions by 62 patients with advanced Parkinson's disease (PD) in a telemedicine setting. On each test occasion, three Archimedes spirals were traced. A new computer method, using wavelet transforms and principal component analysis processed the spiral drawings to generate a spiral score. In a web interface, two PD specialists rated drawing impairment in spiral drawings from three random test occasions per patient, using a modification of the Bain & Findley 10-category scale. A standardised manual rating was defined as the mean of the two raters’ assessments. Bland-Altman analysis was used to evaluate agreement between the spiral score and the standardised manual rating. Another selection of spiral drawings was used to estimate the Spearman rank correlations between the raters (r = 0.87), and between the mean rating and the spiral score (r = 0.89). The 95% confidence interval for the method's prediction errors was ±1.5 scale units, which was similar to the differences between the human raters. In conclusion, the method could assess PD-related drawing impairments well comparable to trained raters.
|
|
| 9. |
- de Dios, Eddie, et al.
(författare)
-
Introduction to Deep Learning in Clinical Neuroscience
- 2022
-
Ingår i: Acta Neurochirurgica, Supplement. - Cham : Springer International Publishing. - 2197-8395 .- 0065-1419. ; , s. 79-89
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- The use of deep learning (DL) is rapidly increasing in clinical neuroscience. The term denotes models with multiple sequential layers of learning algorithms, architecturally similar to neural networks of the brain. We provide examples of DL in analyzing MRI data and discuss potential applications and methodological caveats. Important aspects are data pre-processing, volumetric segmentation, and specific task-performing DL methods, such as CNNs and AEs. Additionally, GAN-expansion and domain mapping are useful DL techniques for generating artificial data and combining several smaller datasets. We present results of DL-based segmentation and accuracy in predicting glioma subtypes based on MRI features. Dice scores range from 0.77 to 0.89. In mixed glioma cohorts, IDH mutation can be predicted with a sensitivity of 0.98 and specificity of 0.97. Results in test cohorts have shown improvements of 5–7% in accuracy, following GAN-expansion of data and domain mapping of smaller datasets. The provided DL examples are promising, although not yet in clinical practice. DL has demonstrated usefulness in data augmentation and for overcoming data variability. DL methods should be further studied, developed, and validated for broader clinical use. Ultimately, DL models can serve as effective decision support systems, and are especially well-suited for time-consuming, detail-focused, and data-ample tasks.
|
|
| 10. |
- Javeed, Ashir, 1989-, et al.
(författare)
-
Decision Support System for Predicting Mortality in Cardiac Patients Based on Machine Learning
- 2023
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 13:8
-
Tidskriftsartikel (refereegranskat)abstract
- Researchers have proposed several automated diagnostic systems based on machine learning and data mining techniques to predict heart failure. However, researchers have not paid close attention to predicting cardiac patient mortality. We developed a clinical decision support system for predicting mortality in cardiac patients to address this problem. The dataset collected for the experimental purposes of the proposed model consisted of 55 features with a total of 368 samples. We found that the classes in the dataset were highly imbalanced. To avoid the problem of bias in the machine learning model, we used the synthetic minority oversampling technique (SMOTE). After balancing the classes in the dataset, the newly proposed system employed a (Formula presented.) statistical model to rank the features from the dataset. The highest-ranked features were fed into an optimized random forest (RF) model for classification. The hyperparameters of the RF classifier were optimized using a grid search algorithm. The performance of the newly proposed model ((Formula presented.) _RF) was validated using several evaluation measures, including accuracy, sensitivity, specificity, F1 score, and a receiver operating characteristic (ROC) curve. With only 10 features from the dataset, the proposed model (Formula presented.) _RF achieved the highest accuracy of 94.59%. The proposed model (Formula presented.) _RF improved the performance of the standard RF model by 5.5%. Moreover, the proposed model (Formula presented.) _RF was compared with other state-of-the-art machine learning models. The experimental results show that the newly proposed decision support system outperforms the other machine learning systems using the same feature selection module ((Formula presented.)).
|
|
