| 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. |
- Latini, Francesco, M.D. 1982-
(författare)
-
Significance of white matter anatomy in interpreting features and behaviour of low-grade gliomas and implications for surgical treatment
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Diffuse gliomas are extremely heterogeneous tumours characterized by slow growth but extensive infiltration. Their kinetic features reflect the complex interaction over time with the surrounding brain, influencing treatment planning and outcome. Indeed, resection of diffuse gliomas present a surgical challenge due to their invasiveness and the preferential location in eloquent regions. White matter bundles are the main eloquent limit to surgical resection, but this anatomical-functional information cannot be predicted preoperatively on the individual level. The incomplete description of the human brain connectome, the complex application of pathological/lesion model to the brain connectomic organization, and the underestimated role of white matter anatomy in radiological classification systems are among the major limitations for the comprehension of the glioma/white matter interaction. The overall aim of this thesis was to explore a new approach and new techniques to study the glioma/white matter interaction. A combination of white matter dissection and diffusion tensor tractography (DTT) was used to describe the connectomic organization of two major temporo-occipital connections, the inferior and the middle longitudinal fasciculus. This information was applied to patients with diffuse gliomas, demonstrating how white matter analysis was important to decode patient specific cognitive and language impairment. A new classification system for diffuse gliomas, the Brain-Grid, was created, merging local radiological anatomy with a DTT atlas for infiltration analysis. This standardized radiological tool provided information on subcortical extension (tumour invasiveness), speed, and preferential direction of glioma progression. Applied to a larger cohort of patients, differences were detected between diffuse gliomas subtypes. Tumour invasiveness and the preferential location, type, and extent of white matter involvement differed, impacting overall survival. Regional differences in white matter infiltration were detected among five major white matter bundles, and possible favourable morphological and diffusion features were investigated with transmission electron microscopy and DTT. Fibre diameter, myelin thickness, and the organization of the white matter fibres were different in regions with high infiltration frequency, providing a possible link to the preferential location of diffuse gliomas. Finally, the white matter connectivity, tumour-induced neuroplasticity, clinical and demographic information, preoperative assessment (neuropsychological and language evaluation) were compared with intraoperative findings during awake surgery. Neuropsychological impairment was associated with more invasive tumours and a higher risk of the intraoperative finding of eloquent tumour. The pattern of early cortical neuroplasticity seemed exhausted at the time of diagnosis, with age as a factor predicting the neuroplasticity potential. The combined use of these new techniques revealed new insights into the glioma/white matter interaction. The results provided in this thesis, describe a new way to structure the multidisciplinary perioperative management of these patients. This new information may improve the functional outcome at the individual level, resulting in prolonged survival for adults with diffuse gliomas.
|
|
| 4. |
- Borrelli, Pablo, et al.
(författare)
-
Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival
- 2021
-
Ingår i: Clinical Physiology and Functional Imaging. - : Wiley. - 1475-0961 .- 1475-097X. ; 41:1, s. 62-67
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. Methods A group of 399 patients with biopsy-proven PCa who had undergone(18)F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated. Results The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117;p = .045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111;p = .63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival. Conclusion This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.
|
|
| 5. |
- Grynne, A., et al.
(författare)
-
Women's experience of the health information process involving a digital information tool before commencing radiation therapy for breast cancer : a deductive interview study
- 2023
-
Ingår i: BMC Health Services Research. - : BioMed Central (BMC). - 1472-6963. ; 23:1
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Individuals undergoing radiation therapy for breast cancer frequently request information before, throughout and after the treatment as a means to reduce distress. Nevertheless, the provision of information to meet individuals needs from their level of health literacy is often overlooked. Thus, individuals information needs are often unmet, leading to reports of discontent. Internet and digital information technology has significantly augmented the available information and changed the way in which persons accesses and comprehends information. As health information is no longer explicitly obtained from healthcare professionals, it is essential to examine the sequences of the health information process in general, and in relation to health literacy. This paper reports on qualitative interviews, targeting women diagnosed with breast cancer who were given access to a health information technology tool, Digi-Do, before commencing radiation therapy, during, and after treatment. METHODS: A qualitative research design, inspired by the integrated health literacy model, was chosen to enable critical reflection by the participating women. Semi-structured interviews were conducted with 15 women with access to a digital information tool, named Digi-Do, in addition to receiving standard information (oral and written) before commencing radiation therapy, during, and after treatment. A deductive thematic analysis process was conducted. RESULTS: The results demonstrate how knowledge, competence, and motivation influence women's experience of the health information process. Three main themes were found: Meeting interactive and personal needs by engaging with health information; Critical recognition of sources of information; and Capability to communicate comprehended health information. The findings reflect the women's experience of the four competencies: to access, understand, appraise, and apply, essential elements of the health information process. CONCLUSIONS: We can conclude that there is a need for tailored digital information tools, such as the Digi-Do, to enable iterative access and use of reliable health information before, during and after the radiation therapy process. The Digi-Do can be seen as a valuable complement to the interpersonal communication with health care professionals, facilitating a better understanding, and enabling iterative access and use of reliable health information before, during and after the radiotherapy treatment. This enhances a sense of preparedness before treatment starts.
|
|
| 6. |
- Alevronta, Eleftheria, et al.
(författare)
-
Dose-response relationships of intestinal organs and excessive mucus discharge after gynaecological radiotherapy
- 2021
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203 .- 1932-6203. ; 16:4 April
-
Tidskriftsartikel (refereegranskat)abstract
- Background The study aims to determine possible dose-volume response relationships between the rectum, sigmoid colon and small intestine and the ‘excessive mucus discharge’ syndrome after pelvic radiotherapy for gynaecological cancer. Methods and materials From a larger cohort, 98 gynaecological cancer survivors were included in this study. These survivors, who were followed for 2 to 14 years, received external beam radiation therapy but not brachytherapy and not did not have stoma. Thirteen of the 98 developed excessive mucus discharge syndrome. Three self-assessed symptoms were weighted together to produce a score interpreted as ‘excessive mucus discharge’ syndrome based on the factor loadings from factor analysis. The dose-volume histograms (DVHs) for rectum, sigmoid colon, small intestine for each survivor were exported from the treatment planning systems. The dose-volume response relationships for excessive mucus discharge and each organ at risk were estimated by fitting the data to the Probit, RS, LKB and gEUD models. Results The small intestine was found to have steep dose-response curves, having estimated dose-response parameters: γ : 1.28, 1.23, 1.32, D : 61.6, 63.1, 60.2 for Probit, RS and LKB respectively. The sigmoid colon (AUC: 0.68) and the small intestine (AUC: 0.65) had the highest AUC values. For the small intestine, the DVHs for survivors with and without excessive mucus discharge were well separated for low to intermediate doses; this was not true for the sigmoid colon. Based on all results, we interpret the results for the small intestine to reflect a relevant link. Conclusion An association was found between the mean dose to the small intestine and the occurrence of ‘excessive mucus discharge’. When trying to reduce and even eliminate the incidence of ‘excessive mucus discharge’, it would be useful and important to separately delineate the small intestine and implement the dose-response estimations reported in the study.
|
|
| 7. |
- Makvandi, Kianoush, et al.
(författare)
-
Multiparametric magnetic resonance imaging allows non-invasive functional and structural evaluation of diabetic kidney disease
- 2022
-
Ingår i: Clinical Kidney Journal. - : Oxford University Press (OUP). - 2048-8505 .- 2048-8513. ; 15:7, s. 1387-1402
-
Tidskriftsartikel (refereegranskat)abstract
- Background We sought to develop a novel non-contrast multiparametric MRI (mpMRI) protocol employing several complementary techniques in a single scan session for a comprehensive functional and structural evaluation of diabetic kidney disease (DKD). Methods In the cross-sectional part of this prospective observational study, 38 subjects ages 18-79 years with type 2 diabetes and DKD [estimated glomerular filtration rate (eGFR) 15-60 mL/min/1.73 m(2)] and 20 age- and gender-matched healthy volunteers (HVs) underwent mpMRI. Repeat mpMRI was performed on 23 DKD subjects and 10 HVs. By measured GFR (mGFR), 2 DKD subjects had GFR stage G2, 16 stage G3 and 20 stage G4/G5. A wide range of MRI biomarkers associated with kidney haemodynamics, oxygenation and macro/microstructure were evaluated. Their optimal sensitivity, specificity and repeatability to differentiate diabetic versus healthy kidneys and categorize various stages of disease as well as their correlation with mGFR/albuminuria was assessed. Results Several MRI biomarkers differentiated diabetic from healthy kidneys and distinct GFR stages (G3 versus G4/G5); mean arterial flow (MAF) was the strongest predictor (sensitivity 0.94 and 1.0, specificity 1.00 and 0.69; P = .04 and .004, respectively). Parameters significantly correlating with mGFR were specific measures of kidney haemodynamics, oxygenation, microstructure and macrostructure, with MAF being the strongest univariate predictor (r = 0.92; P < .0001). Conclusions A comprehensive and repeatable non-contrast mpMRI protocol was developed that, as a single, non-invasive tool, allows functional and structural assessment of DKD, which has the potential to provide valuable insights into underlying pathophysiology, disease progression and analysis of efficacy/mode of action of therapeutic interventions in DKD.
|
|
| 8. |
- Law, Lucy, 1987-
(författare)
-
Subclinical cardiovascular disease and health related quality of life in patients with radiographic axial spondyloarthritis
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Background: Radiographic axial spondyloarthritis (r-axSpA) is a chronic inflammatory rheumatic disease predominantly affecting the axial skeleton. The global prevalence of r-axSpA is between 0.1-1.4%. The disease is associated with extra-musculoskeletal manifestations (EMMs) such as anterior uveitis (AU), as well as increased risk of cardiovascular disease (CVD)-related comorbidities such as atherosclerosis that significantly contribute to mortality and the burden of disease in patients with r-axSpA. The increased CVD risk is not fully explained by traditional CVD risk factors, and little is known about the difference in CVD risk profiles between the sexes. Moreover, the association of disease related variables and subclinical signs of CVD by ultrasound remain to be comprehensively investigated in a well-characterized and sex stratified patient cohort. Additionally, studies investigating factors related to health-related quality of life (HRQoL) in patients with r-axSpA acknowledge that r-axSpA patients have a lower HRQoL than the general population. However, constancy in study methods and comparison to general population controls, especially stratified by sex, are limited. Objectives: The global aim of this thesis was to explore novel methods relating to the evaluation, detection, and monitoring of factors contributing to the burden of CVD in patients with r-axSpA, and to increase knowledge about HRQoL. More specifically, to study the impact of r-axSpA on HRQoL (Paper 1) and identify novel ultrasound markers of subclinical CVD (Papers 2-4) in patients with r-axSpA, overall, stratified by sex, and compared to controls. Materials and methods: Paper 1: The Short Form-36 (SF-36) questionnaire was used to assess HRQoL in patients with r-axSpA from Western Sweden (n=210, females 42.4%). Each patient was compared to 5 age- and sex-matched persons from the SF-36 Swedish normative population database (n=1055). Papers 2-4: Ultrasound was used to (i) assess bilateral common carotid arterial (CCA) stiffness by calculation of b-stiffness index and circumferential 2D strain (Paper 2); (ii) measure mean bilateral carotid intima media thickness (cIMT) and investigate its relationship with biomarkers of inflammation (Paper 3); and (iii) assess the mean thickness of the epicardial adipose tissue (EAT) deposit and its associations with traditional CVD related risk factors (Paper 4). Papers 2-4 used a well characterized patient group from Northern Sweden (‘Backbone cohort’, n=155, female 31.0%). The control group for paper 2 included 46 age- and sex- matched persons from the local population, with no traditional CVD risk factors. The control group for papers 3 and 4, was derived from the Umeå region Swedish CArdioPulmonary bioImaging Study (SCAPIS) recall study (n= 400, females 51.0%). All results were presented stratified by sex. Uni- and multi-variate regression analysis methods were used to evaluate associations with disease and demographic variables. All studies were of cross-sectional design.Results: Paper 1: Patients exhibited significantly lower HRQoL compared to controls (P<0.001). Upon stratification by sex, both sexes scored significantly lower physical compared to the mental HRQoL scores. Multivariable logistic regression analysis found that patients with a longer disease duration, worse physical function (assessed by the Bath Ankylosing Spondylitis Functional Index (BASFI), high disease activity (measured by the Ankylosing Spondylitis Disease Activity Score (ASDAS)), or who lived alone had significantly lower physical HRQoL. Lower mental HRQoL was associated with fatigue, high ASDAS and living alone. Some differences in sex were also found. Paper 2: Patients had higher mean bilateral CCA b-stiffness index, and lower 2D CCA circumferential strain, compared to controls. Multivariate linear regression analysis found that several disease related parameters, in addition to age, were related to 2D circumferential strain (R2 0.33), whereas only age was related to b-stiffness index (R2 0.19). Paper 3: Linear regression analysis, with various adjustment models, showed that patients had increased cIMT compared to controls. White blood cell (WBC)- and monocyte- count were the only inflammatory biomarkers associated with cIMT. This association was only seen in male patients and remained after adjustments. Paper 4: Mean EAT was thicker in r-axSpA patients overall and stratified by sex compared to controls. No difference in mean EAT was found between the sexes. There were borderline significant associations between EAT thickness and cholesterol levels in male patients.Conclusion: Patients with r-axSpA have decreased HRQoL and increased subclinical indicators of CVD compared to controls. By modifying factors, such as ASDAS-CRP and fatigue, HRQoL may be improved in patients with r-axSpA. Additionally, ultrasound methods are non-invasive, and easily obtainable, offering additional insights into the factors that influence the risk of CVD in r-axSpA patients. Although further studies are required to validate novel ultrasound methods, these techniques represent a powerful approach to non-invasively to detect, monitor, and help manage CVD related comorbidities.
|
|
| 9. |
- Olivo, G., et al.
(författare)
-
Immediate effects of a single session of physical exercise on cognition and cerebral blood flow: A randomized controlled study of older adults
- 2021
-
Ingår i: Neuroimage. - : Elsevier BV. - 1053-8119 .- 1095-9572. ; 225
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Regular physical activity is beneficial for cognitive performance in older age. A single bout of aerobic physical exercise can transiently improve cognitive performance. Researchers have advanced improvements in cerebral circulation as a mediator of long-term effects of aerobic physical exercise on cognition, but the immediate effects of exercise on cognition and cerebral perfusion are not well characterized and the effects in older adults are largely unknown. Methods: Forty-nine older adults were randomized to a 30-min aerobic exercise at moderate intensity or relaxation. Groups were matched on age and cardiovascular fitness (VO2 max). Average Grey Matter Blood Flow (GMBF), measured by a pulsed arterial-spin labeling (pASL) magnetic resonance imaging (MRI) acquisition, and working memory performance, measured by figurative n-back tasks with increasing loads were assessed before and 7 min after exercising/resting. Results: Accuracy on the n-back task increased from before to after exercising/resting regardless of the type of activity. GMBF decreased after exercise, relative to the control (resting) group. In the exercise group, higher n-back performance after exercise was associated with lower GMBF in the right hippocampus, left medial frontal cortex and right orbitofrontal cortex, and higher cardiovascular fitness was associated with lower GMBF. Conclusion: The decrease of GMBF reported in younger adults shortly after exercise also occurs in older adults and relates to cardiovascular fitness, potentially supporting the link between cardiovascular fitness and cerebrovascular reactivity in older age.
|
|
| 10. |
- 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.
|
|
