| 1. |
- 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.
|
|
| 2. |
- 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.
|
|
| 3. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Cross-Modality Augmentation of Brain Mr Images Using a Novel Pairwise Generative Adversarial Network for Enhanced Glioma Classification
- 2019
-
Ingår i: Proceedings - International Conference on Image Processing, ICIP. - 1522-4880.
-
Konferensbidrag (refereegranskat)abstract
- © 2019 IEEE. Brain Magnetic Resonance Images (MRIs) are commonly used for tumor diagnosis. Machine learning for brain tumor characterization often uses MRIs from many modalities (e.g., T1-MRI, Enhanced-T1-MRI, T2-MRI and FLAIR). This paper tackles two issues that may impact brain tumor characterization performance from deep learning: insufficiently large training dataset, and incomplete collection of MRIs from different modalities. We propose a novel pairwise generative adversarial network (GAN) architecture for generating synthetic brain MRIs in missing modalities by using existing MRIs in other modalities. By improving the training dataset, we aim to mitigate the overfitting and improve the deep learning performance. Main contributions of the paper include: (a) propose a pairwise generative adversarial network (GAN) for brain image augmentation via cross-modality image generation; (b) propose a training strategy to enhance the glioma classification performance, where GAN-augmented images are used for pre-training, followed by refined-training using real brain MRIs; (c) demonstrate the proposed method through tests and comparisons of glioma classifiers that are trained from mixing real and GAN synthetic data, as well as from real data only. Experiments were conducted on an open TCGA dataset, containing 167 subjects for classifying IDH genotypes (mutation or wild-type). Test results from two experimental settings have both provided supports to the proposed method, where glioma classification performance has consistently improved by using mixed real and augmented data (test accuracy 81.03%, with 2.57% improvement).
|
|
| 4. |
- Culverhouse, R. C., et al.
(författare)
-
Collaborative meta-analysis finds no evidence of a strong interaction between stress and 5-HTTLPR genotype contributing to the development of depression
- 2018
-
Ingår i: Molecular Psychiatry. - : Springer Science and Business Media LLC. - 1359-4184 .- 1476-5578. ; 23:1, s. 133-142
-
Tidskriftsartikel (refereegranskat)abstract
- The hypothesis that the S allele of the 5-HTTLPR serotonin transporter promoter region is associated with increased risk of depression, but only in individuals exposed to stressful situations, has generated much interest, research and controversy since first proposed in 2003. Multiple meta-analyses combining results from heterogeneous analyses have not settled the issue. To determine the magnitude of the interaction and the conditions under which it might be observed, we performed new analyses on 31 data sets containing 38 802 European ancestry subjects genotyped for 5-HTTLPR and assessed for depression and childhood maltreatment or other stressful life events, and meta-analysed the results. Analyses targeted two stressors (narrow, broad) and two depression outcomes (current, lifetime). All groups that published on this topic prior to the initiation of our study and met the assessment and sample size criteria were invited to participate. Additional groups, identified by consortium members or self-identified in response to our protocol (published prior to the start of analysis) with qualifying unpublished data, were also invited to participate. A uniform data analysis script implementing the protocol was executed by each of the consortium members. Our findings do not support the interaction hypothesis. We found no subgroups or variable definitions for which an interaction between stress and 5-HTTLPR genotype was statistically significant. In contrast, our findings for the main effects of life stressors (strong risk factor) and 5-HTTLPR genotype (no impact on risk) are strikingly consistent across our contributing studies, the original study reporting the interaction and subsequent meta-analyses. Our conclusion is that if an interaction exists in which the S allele of 5-HTTLPR increases risk of depression only in stressed individuals, then it is not broadly generalisable, but must be of modest effect size and only observable in limited situations.
|
|
| 5. |
- 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.)).
|
|
| 6. |
- Augustian, Midhumol, et al.
(författare)
-
EEG Analysis from Motor Imagery to Control a Forestry Crane
- 2018
-
Ingår i: Intelligent Human Systems Integration (IHSI 2018). - Cham : Springer. - 9783319738871 - 9783319738888 ; , s. 281-286
-
Konferensbidrag (refereegranskat)abstract
- Brain-computer interface (BCI) systems can provide people with ability to communicate and control real world systems using neural activities. Therefore, it makes sense to develop an assistive framework for command and control of a future robotic system which can assist the human robot collaboration. In this paper, we have employed electroencephalographic (EEG) signals recorded by electrodes placed over the scalp. The human-hand movement based motor imagery mentalization is used to collect brain signals over the motor cortex area. The collected µ-wave (8–13 Hz) EEG signals were analyzed with event-related desynchronization/synchronization (ERD/ERS) quantification to extract a threshold between hand grip and release movement and this information can be used to control forestry crane grasping and release functionality. The experiment was performed with four healthy persons to demonstrate the proof-of concept BCI system. From this study, it is demonstrated that the proposed method has potential to assist the manual operation of crane operators performing advanced task with heavy cognitive work load.
|
|
| 7. |
- Staron, Miroslaw, 1977, et al.
(författare)
-
Robust machine learning in critical care - Software engineering and medical perspectives
- 2021
-
Ingår i: Proceedings - 2021 IEEE/ACM 1st Workshop on AI Engineering - Software Engineering for AI, WAIN 2021. - : Institute of Electrical and Electronics Engineers Inc.. ; , s. 62-69
-
Konferensbidrag (refereegranskat)abstract
- Using machine learning in clinical practice poses hard requirements on explainability, reliability, replicability and robustness of these systems. Therefore, developing reliable software for monitoring critically ill patients requires close collaboration between physicians and software engineers. However, these two different disciplines need to find own research perspectives in order to contribute to both the medical and the software engineering domain. In this paper, we address the problem of how to establish a collaboration where software engineering and medicine meets to design robust machine learning systems to be used in patient care. We describe how we designed software systems for monitoring patients under carotid endarterectomy, in particular focusing on the process of knowledge building in the research team. Our results show what to consider when setting up such a collaboration, how it develops over time and what kind of systems can be constructed based on it. We conclude that the main challenge is to find a good research team, where different competences are committed to a common goal.
|
|
| 8. |
- Gryska, Emilia, 1992, et al.
(författare)
-
Deep learning for automatic brain tumour segmentation on MRI: evaluation of recommended reporting criteria via a reproduction and replication study.
- 2022
-
Ingår i: BMJ open. - : BMJ. - 2044-6055. ; 12:7
-
Tidskriftsartikel (refereegranskat)abstract
- To determine the reproducibility and replicability of studies that develop and validate segmentation methods for brain tumours on MRI and that follow established reproducibility criteria; and to evaluate whether the reporting guidelines are sufficient.Two eligible validation studies of distinct deep learning (DL) methods were identified. We implemented the methods using published information and retraced the reported validation steps. We evaluated to what extent the description of the methods enabled reproduction of the results. We further attempted to replicate reported findings on a clinical set of images acquired at our institute consisting of high-grade and low-grade glioma (HGG, LGG), and meningioma (MNG) cases.We successfully reproduced one of the two tumour segmentation methods. Insufficient description of the preprocessing pipeline and our inability to replicate the pipeline resulted in failure to reproduce the second method. The replication of the first method showed promising results in terms of Dice similarity coefficient (DSC) and sensitivity (Sen) on HGG cases (DSC=0.77, Sen=0.88) and LGG cases (DSC=0.73, Sen=0.83), however, poorer performance was observed for MNG cases (DSC=0.61, Sen=0.71). Preprocessing errors were identified that contributed to low quantitative scores in some cases.Established reproducibility criteria do not sufficiently emphasise description of the preprocessing pipeline. Discrepancies in preprocessing as a result of insufficient reporting are likely to influence segmentation outcomes and hinder clinical utilisation. A detailed description of the whole processing chain, including preprocessing, is thus necessary to obtain stronger evidence of the generalisability of DL-based brain tumour segmentation methods and to facilitate translation of the methods into clinical practice.
|
|
| 9. |
- 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%).
|
|
| 10. |
- Slijper, Angelique, et al.
(författare)
-
Computer game-based upper extremity training in the home environment in stroke persons : a single subject design
- 2014
-
Ingår i: Journal of NeuroEngineering and Rehabilitation. - : Biomed Central. - 1743-0003. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: The objective of the present study was to assess whether computer game-based training in the home setting in the late phase after stroke could improve upper extremity motor function.METHODS: Twelve subjects with prior stroke were recruited; 11 completed the study.DESIGN: The study had a single subject design; there was a baseline test (A1), a during intervention test (B) once a week, a post-test (A2) measured directly after the treatment phase, plus a follow-up (C) 16-18 weeks after the treatment phase. Information on motor function (Fugl-Meyer), grip force (GrippitR) and arm function in activity (ARAT, ABILHAND) was gathered at A1, A2 and C. During B, only Fugl-Meyer and ARAT were measured. The intervention comprised five weeks of game-based computer training in the home environment. All games were designed to be controlled by either the affected arm alone or by both arms. Conventional formulae were used to calculate the mean, median and standard deviations. Wilcoxon's signed rank test was used for tests of dependent samples. Continuous data were analyzed by methods for repeated measures and ordinal data were analyzed by methods for ordered multinomial data using cumulative logistic models. A p-value of < 0.05 was considered statistically significant.RESULTS: Six females and five males, participated in the study with an average age of 58 years (range 26-66). FMA-UE A-D (motor function), ARAT, the maximal grip force and the mean grip force on the affected side show significant improvements at post-test and follow-up compared to baseline. No significant correlation was found between the amount of game time and changes in the outcomes investigated in this study.CONCLUSION: The results indicate that computer game-based training could be a promising approach to improve upper extremity function in the late phase after stroke, since in this study, changes were achieved in motor function and activity capacity.
|
|
