Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology.
Ontology highlight
ABSTRACT: Purpose
Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs.Experimental design
We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM.Results
Gadolinium-enhanced T1-weighted or hyperintense fluid-attenuated inversion recovery failed to reflect the morphologic complexity underlying tumor in patients with GBM. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in GBM specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0%, and 93.4% accuracy, respectively.Conclusions
Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of GBM.
SUBMITTER: Ye Z
PROVIDER: S-EPMC7572819 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:OBJECTIVE:Multiple sclerosis (MS) lesions are heterogeneous with regard to inflammation, demyelination, axonal injury, and neuronal loss. We previously developed a diffusion basis spectrum imaging (DBSI) technique to better address MS lesion heterogeneity. We hypothesized that the profiles of multiple DBSI metrics can identify lesion-defining patterns. Here we test this hypothesis by combining a deep learning algorithm using deep neural network (DNN) with DBSI and other imaging methods. METHODS:Thirty-eight MS patients were scanned with diffusion-weighted imaging, magnetization transfer imaging, and standard conventional MRI sequences (cMRI). A total of 499 regions of interest were identified on standard MRI and labeled as persistent black holes (PBH), persistent gray holes (PGH), acute black holes (ABH), acute gray holes (AGH), nonblack or gray holes (NBH), and normal appearing white matter (NAWM). DBSI, diffusion tensor imaging (DTI), and magnetization transfer ratio (MTR) were applied to the 43,261 imaging voxels extracted from these ROIs. The optimized DNN with 10 fully connected hidden layers was trained using the imaging metrics of the lesion subtypes and NAWM. RESULTS:Concordance, sensitivity, specificity, and accuracy were determined for the different imaging methods. DBSI-DNN derived lesion classification achieved 93.4% overall concordance with predetermined lesion types, compared with 80.2% for DTI-DNN model, 78.3% for MTR-DNN model, and 74.2% for cMRI-DNN model. DBSI-DNN also produced the highest specificity, sensitivity, and accuracy. CONCLUSIONS:DBSI-DNN improves the classification of different MS lesion subtypes, which could aid clinical decision making. The efficacy and efficiency of DBSI-DNN shows great promise for clinical applications in automatic MS lesion detection and classification.
| S-EPMC7261762 | biostudies-literature
Project description:Chromosome 22q11.2 deletion syndrome (22q11.2DS) is a genetic neurodevelopmental syndrome that has been studied intensively in order to understand relationships between the genetic microdeletion, brain development, cognitive function, and the emergence of psychiatric symptoms. White matter microstructural abnormalities identified using diffusion tensor imaging methods have been reported to affect a variety of neuroanatomical tracts in 22q11.2DS. In the present study, we sought to combine two discovery-based approaches: (1) white matter query language was used to parcellate the brain's white matter into tracts connecting pairs of 34, bilateral cortical regions and (2) the diffusion imaging characteristics of the resulting tracts were analyzed using a machine-learning method called support vector machine in order to optimize the selection of a set of imaging features that maximally discriminated 22q11.2DS and comparison subjects. With this unique approach, we both confirmed previously-recognized 22q11.2DS-related abnormalities in the inferior longitudinal fasciculus (ILF), and identified, for the first time, 22q11.2DS-related anomalies in the middle longitudinal fascicle and the extreme capsule, which may have been overlooked in previous, hypothesis-guided studies. We further observed that, in participants with 22q11.2DS, ILF metrics were significantly associated with positive prodromal symptoms of psychosis.
| S-EPMC5522376 | biostudies-literature
Project description:To determine if apparent diffusion coefficients (ADC) can discriminate between posterior fossa brain tumours on a multicentre basis. A total of 124 paediatric patients with posterior fossa tumours (including 55 Medulloblastomas, 36 Pilocytic Astrocytomas and 26 Ependymomas) were scanned using diffusion weighted imaging across 12 different hospitals using a total of 18 different scanners. Apparent diffusion coefficient maps were produced and histogram data was extracted from tumour regions of interest. Total histograms and histogram metrics (mean, variance, skew, kurtosis and 10th, 20th and 50th quantiles) were used as data input for classifiers with accuracy determined by tenfold cross validation. Mean ADC values from the tumour regions of interest differed between tumour types, (ANOVA P < 0.001). A cut off value for mean ADC between Ependymomas and Medulloblastomas was found to be of 0.984 × 10-3 mm2 s-1 with sensitivity 80.8% and specificity 80.0%. Overall classification for the ADC histogram metrics were 85% using Naïve Bayes and 84% for Random Forest classifiers. The most commonly occurring posterior fossa paediatric brain tumours can be classified using Apparent Diffusion Coefficient histogram values to a high accuracy on a multicentre basis.
| S-EPMC7862387 | biostudies-literature
Project description:As diffusion tensor imaging gains widespread use, many researchers have been motivated to go beyond the tensor model and fit more complex diffusion models, to gain a more complete description of white matter microstructure and associated pathology. Two such models are diffusion kurtosis imaging (DKI) and diffusion basis spectrum imaging (DBSI). It is not clear which DKI parameters are most closely related to DBSI parameters, so in the interest of enabling comparisons between DKI and DBSI studies, we conducted an empirical survey of the interrelation of these models in 12 healthy volunteers using the same diffusion acquisition. We found that mean kurtosis is positively associated with the DBSI fiber ratio and negatively associated with the hindered ratio. This was primarily driven by the radial component of kurtosis. The axial component of kurtosis was strongly and specifically correlated with the restricted ratio. The joint spatial distributions of DBSI and DKI parameters are tissue-dependent and stable across healthy individuals. Our contribution is a better understanding of the biological interpretability of the parameters generated by the two models in healthy individuals.
| S-EPMC5372828 | biostudies-literature
Project description:Background and purposeTraumatic brain injury (TBI) can cause progressive neuropathology that leads to chronic impairments, creating a need for biomarkers to detect and monitor this condition to improve outcomes. This study aimed to analyze the ability of data-driven analysis of diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to develop biomarkers to infer symptom severity and determine whether they outperform conventional T1-weighted imaging.Materials and methodsA machine learning-based model was developed using a dataset of hybrid diffusion imaging of patients with chronic traumatic brain injury. We first extracted the useful features from the hybrid diffusion imaging (HYDI) data and then used supervised learning algorithms to classify the outcome of TBI. We developed three models based on DTI, NODDI, and T1-weighted imaging, and we compared the accuracy results across different models.ResultsCompared with the conventional T1-weighted imaging-based classification with an accuracy of 51.7-56.8%, our machine learning-based models achieved significantly better results with DTI-based models at 58.7-73.0% accuracy and NODDI with an accuracy of 64.0-72.3%.ConclusionThe machine learning-based feature selection and classification algorithm based on hybrid diffusion features significantly outperform conventional T1-weighted imaging. The results suggest that advanced algorithms can be developed for inferring symptoms of chronic brain injury using feature selection and diffusion-weighted imaging.
| S-EPMC10484001 | biostudies-literature
Project description:Human obesity is associated with low-grade chronic systemic inflammation, alterations in brain structure and function, and cognitive impairment. Rodent models of obesity show that high-calorie diets cause brain inflammation (neuroinflammation) in multiple regions, including the hippocampus, and impairments in hippocampal-dependent memory tasks. To determine if similar effects exist in humans with obesity, we applied Diffusion Basis Spectrum Imaging (DBSI) to evaluate neuroinflammation and axonal integrity. We examined diffusion-weighted magnetic resonance imaging (MRI) data in two independent cohorts of obese and non-obese individuals (Cohort 1: 25 obese/21 non-obese; Cohort 2: 18 obese/41 non-obese). We applied Tract-based Spatial Statistics (TBSS) to allow whole-brain white matter (WM) analyses and compare DBSI-derived isotropic and anisotropic diffusion measures between the obese and non-obese groups. In both cohorts, the obese group had significantly greater DBSI-derived restricted fraction (DBSI-RF; an indicator of neuroinflammation-related cellularity), and significantly lower DBSI-derived fiber fraction (DBSI-FF; an indicator of apparent axonal density) in several WM tracts (all corrected p < 0.05). Moreover, using region of interest analyses, average DBSI-RF and DBSI-FF values in the hippocampus were significantly greater and lower, respectively, in obese relative to non-obese individuals (Cohort 1: p = 0.045; Cohort 2: p = 0.008). Hippocampal DBSI-FF and DBSI-RF and amygdalar DBSI-FF metrics related to cognitive performance in Cohort 2. In conclusion, these findings suggest that greater neuroinflammation-related cellularity and lower apparent axonal density are associated with human obesity and cognitive performance. Future studies are warranted to determine a potential role for neuroinflammation in obesity-related cognitive impairment.
| S-EPMC6971102 | biostudies-literature
Project description:Study designProspective cohort study.ObjectiveApply a machine learning clustering algorithm to baseline imaging data to identify clinically relevant cervical spondylotic myelopathy (CSM) patient phenotypes.Summary of background dataA major shortcoming in improving care for CSM patients is the lack of robust quantitative imaging tools to guide surgical decision-making. Advanced diffusion-weighted magnetic resonance imaging (MRI) techniques, such as diffusion basis spectrum imaging (DBSI), may help address this limitation by providing detailed evaluations of white matter injury in CSM.MethodsFifty CSM patients underwent comprehensive clinical assessments and diffusion-weighted MRI, followed by DBSI modeling. DBSI metrics included fractional anisotropy, axial and radial diffusivity, fiber fraction, extra-axonal fraction, restricted fraction, and nonrestricted fraction. Neurofunctional status was assessed by the modified Japanese Orthopedic Association, myelopathic disability index, and disabilities of the arm, shoulder, and hand. Quality-of-life was measured by the 36-Item Short Form Survey physical component summary and mental component summary. The neck disability index was used to measure self-reported neck pain. K-means clustering was applied to baseline DBSI measures to identify 3 clinically relevant CSM disease phenotypes. Baseline demographic, clinical, radiographic, and patient-reported outcome measures were compared among clusters using one-way analysis of variance (ANOVA).ResultsTwenty-three (55%) mild, 9 (21%) moderate, and 10 (24%) severe myelopathy patients were enrolled. Eight patients were excluded due to MRI data of insufficient quality. Of the remaining 42 patients, 3 groups were generated by k-means clustering. When compared with clusters 1 and 2, cluster 3 performed significantly worse on the modified Japanese Orthopedic Association and all patient-reported outcome measures (P<0.001), except the 36-Item Short Form Survey mental component summary (P>0.05). Cluster 3 also possessed the highest proportion of non-Caucasian patients (43%, P=0.04), the worst hand dynamometer measurements (P<0.05), and significantly higher intra-axonal axial diffusivity and extra-axonal fraction values (P<0.001).ConclusionsUsing baseline imaging data, we delineated a clinically meaningful CSM disease phenotype, characterized by worse neurofunctional status, quality-of-life, and pain, and more severe imaging markers of vasogenic edema.Level of evidenceII.
| S-EPMC10042585 | biostudies-literature
Project description:Diffusion tensor imaging (DTI) has emerged as a promising method for noninvasive quantification of myocardial microstructure. However, the origin and behavior of DTI measurements during myocardial normal development and remodeling remain poorly understood. In this work, conventional and bicompartmental DTI in addition to three-dimensional histological correlation were performed in a sheep model of myocardial development from third trimester to postnatal 5 months of age. Comparing the earliest time points in the third trimester with the postnatal 5 month group, the scalar transverse diffusivities preferentially increased in both left ventricle (LV) and right ventricle (RV): secondary eigenvalues D2 increased by 54% (LV) and 36% (RV), whereas tertiary eigenvalues D3 increased by 85% (LV) and 67% (RV). The longitudinal diffusivity D1 changes were small, which led to a decrease in fractional anisotropy by 41% (LV) and 33% (RV) in 5 month versus fetal hearts. Histological analysis suggested that myocardial development is associated with hyperplasia in the early stages of the third trimester followed by myocyte growth in the later stages up to 5 months of age (increased average myocyte width by 198%, myocyte length by 128%, and decreased nucleus density by 70% between preterm and postnatal 5 month hearts.) In a few histological samples (N = 6), correlations were observed between DTI longitudinal diffusivity and myocyte length (r = 0.86, P < 0.05), and transverse diffusivity and myocyte width (r = 0.96, P < 0.01). Linear regression analysis showed that transverse diffusivities are more affected by changes in myocyte size and nucleus density changes than longitudinal diffusivities, which is consistent with predictions of classical models of diffusion in porous media. Furthermore, primary and secondary DTI eigenvectors during development changed significantly. Collectively, the findings demonstrate a role for DTI to monitor and quantify myocardial development, and potentially cardiac disease. Copyright © 2016 John Wiley & Sons, Ltd.
| S-EPMC5160010 | biostudies-literature
Project description:BackgroundAdvanced magnetic resonance imaging (MRI) methods can provide more specific information about various microstructural tissue changes in multiple sclerosis (MS) brain. Quantitative measurement of T1 and T2 relaxation, and diffusion basis spectrum imaging (DBSI) yield metrics related to the pathology of neuroinflammation and neurodegeneration that occurs across the spectrum of MS.ObjectiveTo use relaxation and DBSI MRI metrics to describe measures of neuroinflammation, myelin and axons in different MS subtypes.Methods103 participants (20 clinically isolated syndrome (CIS), 33 relapsing-remitting MS (RRMS), 30 secondary progressive MS and 20 primary progressive MS) underwent quantitative T1, T2, DBSI and conventional 3T MRI. Whole brain, normal-appearing white matter, lesion and corpus callosum MRI metrics were compared across MS subtypes.ResultsA gradation of MRI metric values was seen from CIS to RRMS to progressive MS. RRMS demonstrated large oedema-related differences, while progressive MS had the most extensive abnormalities in myelin and axonal measures.ConclusionRelaxation and DBSI-derived MRI measures show differences between MS subtypes related to the severity and composition of underlying tissue damage. RRMS showed oedema, demyelination and axonal loss compared with CIS. Progressive MS had even more evidence of increased oedema, demyelination and axonal loss compared with CIS and RRMS.
| S-EPMC9665421 | biostudies-literature
Project description:ObjectiveTo evaluate in-vivo neuroinflammation and white matter (WM) microstructural integrity in occupational manganese (Mn) exposure.MethodsWe assessed brain inflammation using Diffusion Basis Spectrum Imaging (DBSI) in 26 Mn-exposed welders, 17 Mn-exposed workers, and 26 non-exposed participants. Cumulative Mn exposure was estimated from work histories and the Unified Parkinson's Disease Rating Scale motor subsection 3 (UPDRS3) scores were completed by a movement specialist. Tract-based Spatial Statistics allowed for whole-brain voxel-wise WM analyses to compare WM DBSI-derived measures between the Mn-exposed and non-exposed groups. Exploratory grey matter region of interest (ROI) analyses examined the presence of similar alterations in the basal ganglia. We used voxelwise general linear modeling and linear regression to evaluate the association between cumulative Mn exposure, WM or basal ganglia DBSI metrics, and UPDRS3 scores, while adjusting for age.ResultsMn-exposed welders had higher DBSI-derived restricted fraction (DBSI-RF), higher DBSI-derived nonrestricted fraction (DBSI-NRF), and lower DBSI-derived fiber fraction (DBSI-FF) in multiple WM tracts (all p < 0.05) in comparison to less-exposed workers and non-exposed participants. Basal ganglia ROI analyses revealed higher average caudate DBSI-NRF and DBSI-derived radial diffusion (DBSI-RD) values in Mn-exposed welders relative to non-exposed participants (p < 0.05). Caudate DBSI-NRF was also associated with greater cumulative Mn exposure and higher UPRDS3 scores.ConclusionsMn-exposed welders demonstrate greater DBSI-derived indicators of neuroinflammation-related cellularity (DBSI-RF), greater extracellular edema (DBSI-NRF), and lower apparent axonal density (DBSI-FF) in multiple WM tracts suggesting a neuroinflammatory component in the pathophysiology of Mn neurotoxicity. Caudate DBSI-NRF was positively associated with both cumulative Mn exposure and clinical parkinsonism, indicating a possible dose-dependent effect on extracellular edema with associated motor effects.
| S-EPMC10524700 | biostudies-literature