Longitudinal diffusion MRI analysis using Segis-Net: A single-step deep-learning framework for simultaneous segmentation and registration.

This work presents a single-step deep-learning framework for longitudinal image analysis, coined Segis-Net. To optimally exploit information available in longitudinal data, this method concurrently learns a multi-class segmentation and nonlinear registration. Segmentation and registration are modeled using a convolutional neural network and optimized simultaneously for their mutual benefit. An objective function that optimizes spatial correspondence for the segmented structures across time-points is proposed. We applied Segis-Net to the analysis of white matter tracts from N=8045 longitudinal brain MRI datasets of 3249 elderly individuals. Segis-Net approach showed a significant increase in registration accuracy, spatio-temporal segmentation consistency, and reproducibility compared with two multistage pipelines. This also led to a significant reduction in the sample-size that would be required to achieve the same statistical power in analyzing tract-specific measures. Thus, we expect that Segis-Net can serve as a new reliable tool to support longitudinal imaging studies to investigate macro- and microstructural brain changes over time.

Advanced imaging for quantification of abnormalities in the salivary glands of patients with primary Sjögren's syndrome.

OBJECTIVES: To assess non-invasive imaging for detection and quantification of gland structure, inflammation and function in patients with primary Sjogren's syndrome (pSS) using PET-CT with 11C-Methionine (11C-MET; radiolabelled amino acid), and 18F-fluorodeoxyglucose (18F-FDG; glucose uptake marker), to assess protein synthesis and inflammation, respectively; multiparametric MRI evaluated salivary gland structural and physiological changes. METHODS: In this imaging/clinical/histology comparative study (GSK study 203818; NCT02899377) patients with pSS and age- and sex-matched healthy volunteers underwent MRI of the salivary glands and 11C-MET PET-CT. Patients also underwent 18F-FDG PET-CT and labial salivary gland biopsies. Clinical and biomarker assessments were performed. Primary endpoints were semi-quantitative parameters of 11C-MET and 18F-FDG uptake in submandibular and parotid salivary glands and quantitative MRI measures of structure and inflammation. Clinical and minor salivary gland histological parameter correlations were explored. RESULTS: Twelve patients with pSS and 13 healthy volunteers were included. Lower 11C-MET uptake in parotid, submandibular and lacrimal glands, lower submandibular gland volume, higher MRI fat fraction, and lower pure diffusion in parotid and submandibular glands were observed in patients vs healthy volunteer, consistent with reduced synthetic function. Disease duration correlated positively with fat fraction and negatively with 11C-MET and 18F-FDG uptake, consistent with impaired function, inflammation and fatty replacement over time. Lacrimal gland 11C-MET uptake positively correlated with tear flow in patients, and parotid gland 18F-FDG uptake positively correlated with salivary gland CD20+ B-cell infiltration. CONCLUSION: Molecular imaging and MRI may be useful tools to non-invasively assess loss of glandular function, increased glandular inflammation and fat accumulation in pSS.

Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging.

Subtle changes in white matter (WM) microstructure have been associated with normal aging and neurodegeneration. To study these associations in more detail, it is highly important that the WM tracts can be accurately and reproducibly characterized from brain diffusion MRI. In addition, to enable analysis of WM tracts in large datasets and in clinical practice it is essential to have methodology that is fast and easy to apply. This work therefore presents a new approach for WM tract segmentation: Neuro4Neuro, that is capable of direct extraction of WM tracts from diffusion tensor images using convolutional neural network (CNN). This 3D end-to-end method is trained to segment 25 WM tracts in aging individuals from a large population-based study (N â€‹= â€‹9752, 1.5T MRI). The proposed method showed good segmentation performance and high reproducibility, i.e., a high spatial agreement (Cohen's kappa, κ=0.72-0.83) and a low scan-rescan error in tract-specific diffusion measures (e.g., fractional anisotropy: ε=1%-5%). The reproducibility of the proposed method was higher than that of a tractography-based segmentation algorithm, while being orders of magnitude faster (0.5s to segment one tract). In addition, we showed that the method successfully generalizes to diffusion scans from an external dementia dataset (N â€‹= â€‹58, 3T MRI). In two proof-of-principle experiments, we associated WM microstructure obtained using the proposed method with age in a normal elderly population, and with disease subtypes in a dementia cohort. In concordance with the literature, results showed a widespread reduction of microstructural organization with aging and substantial group-wise microstructure differences between dementia subtypes. In conclusion, we presented a highly reproducible and fast method for WM tract segmentation that has the potential of being used in large-scale studies and clinical practice.

Hearing loss and microstructural integrity of the brain in a dementia-free older population.

INTRODUCTION: As hearing loss has been identified as an important risk factor for dementia, we aimed to assess the association between hearing loss and microstructural integrity of the brain. METHODS: A total of 1086 dementia-free participants (mean age = 75.2 [standard deviation: 4.9], 61.4% female) of the population-based Atherosclerosis Risk in Communities (ARIC) study underwent hearing assessment (2016-2017) and magnetic resonance imaging of the brain (2011-2013). Microstructural integrity was determined with diffusion tensor imaging. Multivariable linear regression was used to investigate associations between hearing loss and microstructural integrity of different brain regions and white matter (WM) tracts. RESULTS: Hearing loss was associated with lower WM microstructural integrity in the temporal lobe, lower gray matter integrity of the hippocampus, and with lower WM microstructural integrity of the limbic tracts and the uncinate fasciculus. CONCLUSION: Our results demonstrate that hearing loss is indepedently associated with lower microstructural integrity in brain regions that are important for different cognitive processes.

Use of autologous 99mTechnetium-labelled neutrophils to quantify lung neutrophil clearance in COPD.

RATIONALE: There is a need to develop imaging protocols which assess neutrophilic inflammation in the lung. AIM: To quantify whole lung neutrophil accumulation in (1) healthy volunteers (HV) following inhaled lipopolysaccharide (LPS) or saline and (2) patients with COPD using radiolabelled autologous neutrophils and single-photon emission computed tomography/CT (SPECT/CT). METHODS: 20 patients with COPD (Global initiative for chronic obstructive lung disease (GOLD) stages 2-3) and 18 HVs were studied. HVs received inhaled saline (n=6) or LPS (50 µg, n=12) prior to the injection of radiolabelled cells. Neutrophils were isolated using dextran sedimentation and Percoll plasma gradients and labelled with 99mTechnetium (Tc)-hexamethylpropyleneamine oxime. SPECT was performed over the thorax/upper abdomen at 45 min, 2 hours, 4 hours and 6 hours. Circulating biomarkers were measured prechallenge and post challenge. Blood neutrophil clearance in the lung was determined using Patlak-Rutland graphical analysis. RESULTS: There was increased accumulation of 99mTc-neutrophils in the lungs of patients with COPD and LPS-challenged subjects compared with saline-challenged subjects (saline: 0.0006±0.0003 mL/min/mL lung blood distribution volume [mean ±1 SD]; COPD: 0.0022±0.0010 mL/min/mL [p<0.001]; LPS: 0.0025±0.0008 mL/min/mL [p<0.001]). The accumulation of labelled neutrophils in 10 patients with COPD who underwent repeat radiolabelling/imaging 7-10 days later was highly reproducible (0.0022±0.0010 mL/min/mL vs 0.0023±0.0009 mL/min/mL). Baseline interleukin (IL)-6 levels in patients with COPD were elevated compared with HVs (1.5±1.06 pg/mL [mean ±1 SD] vs 0.4±0.24 pg/mL). LPS challenge increased the circulating IL-6 levels (7.5±2.72 pg/mL) 9 hours post challenge. CONCLUSIONS: This study shows the ability to quantify 'whole lung' neutrophil accumulation in HVs following LPS inhalation and in subjects with COPD using autologous radiolabelled neutrophils and SPECT/CT imaging. Moreover, the reproducibility observed supports the feasibility of using this approach to determine the efficacy of therapeutic agents aimed at altering neutrophil migration to the lungs.

Disconnection due to white matter hyperintensities is associated with lower cognitive scores.

Previous studies have linked global burden of age-related white matter hyperintensities (WMHs) to cognitive impairment. We aimed to determine how WMHs in individual white matter connections relate to measures of cognitive function relative to measures of connectivity which do not take WMHs into account. Brain connectivity and WMH-related disconnectivity were derived from 3714 participants of the population-based Rotterdam Study. Connectivity was represented by the structural connectome, which was defined using diffusion tensor data, whereas the disconnectome represented disconnectivity due to WMH. The relationship between (dis)connectivity and cognitive measures was estimated using linear regression. We found that lower disconnectivity and higher connectivity corresponded to better cognitive function. There were many more significant associations with cognitive function in the disconnectome than in the connectome. Most connectome associations attenuated when disconnection was included in the model. WMH-related disconnectivity was especially related to worse executive functioning. Better cognitive speed corresponded to higher connectivity in specific connections independent of WMH presence. We conclude that WMH-related disconnectivity explains more variation in cognitive function than does connectivity. Efficient wiring in specific connections is important to information processing speed independent of WMH presence.

Multiparametric computer-aided differential diagnosis of Alzheimer's disease and frontotemporal dementia using structural and advanced MRI.

OBJECTIVES: To investigate the added diagnostic value of arterial spin labelling (ASL) and diffusion tensor imaging (DTI) to structural MRI for computer-aided classification of Alzheimer's disease (AD), frontotemporal dementia (FTD), and controls. METHODS: This retrospective study used MRI data from 24 early-onset AD and 33 early-onset FTD patients and 34 controls (CN). Classification was based on voxel-wise feature maps derived from structural MRI, ASL, and DTI. Support vector machines (SVMs) were trained to classify AD versus CN (AD-CN), FTD-CN, AD-FTD, and AD-FTD-CN (multi-class). Classification performance was assessed by the area under the receiver-operating-characteristic curve (AUC) and accuracy. Using SVM significance maps, we analysed contributions of brain regions. RESULTS: Combining ASL and DTI with structural MRI resulted in higher classification performance for differential diagnosis of AD and FTD (AUC = 84%; p = 0.05) than using structural MRI by itself (AUC = 72%). The performance of ASL and DTI themselves did not improve over structural MRI. The classifications were driven by different brain regions for ASL and DTI than for structural MRI, suggesting complementary information. CONCLUSIONS: ASL and DTI are promising additions to structural MRI for classification of early-onset AD, early-onset FTD, and controls, and may improve the computer-aided differential diagnosis on a single-subject level. KEY POINTS: • Multiparametric MRI is promising for computer-aided diagnosis of early-onset AD and FTD. • Diagnosis is driven by different brain regions when using different MRI methods. • Combining structural MRI, ASL, and DTI may improve differential diagnosis of dementia.

The effect of hippocampal function, volume and connectivity on posterior cingulate cortex functioning during episodic memory fMRI in mild cognitive impairment.

OBJECTIVES: Diminished function of the posterior cingulate cortex (PCC) is a typical finding in early Alzheimer's disease (AD). It is hypothesized that in early stage AD, PCC functioning relates to or reflects hippocampal dysfunction or atrophy. The aim of this study was to examine the relationship between hippocampus function, volume and structural connectivity, and PCC activation during an episodic memory task-related fMRI study in mild cognitive impairment (MCI). METHOD: MCI patients (n = 27) underwent episodic memory task-related fMRI, 3D-T1w MRI, 2D T2-FLAIR MRI and diffusion tensor imaging. Stepwise linear regression analysis was performed to examine the relationship between PCC activation and hippocampal activation, hippocampal volume and diffusion measures within the cingulum along the hippocampus. RESULTS: We found a significant relationship between PCC and hippocampus activation during successful episodic memory encoding and correct recognition in MCI patients. We found no relationship between the PCC and structural hippocampal predictors. CONCLUSIONS: Our results indicate a relationship between PCC and hippocampus activation during episodic memory engagement in MCI. This may suggest that during episodic memory, functional network deterioration is the most important predictor of PCC functioning in MCI. KEY POINTS: • PCC functioning during episodic memory relates to hippocampal functioning in MCI. • PCC functioning during episodic memory does not relate to hippocampal structure in MCI. • Functional network changes are an important predictor of PCC functioning in MCI.

White Matter Microstructure Improves Stroke Risk Prediction in the General Population.

BACKGROUND AND PURPOSE: The presence of subclinical vascular brain disease, including white matter lesions and lacunar infarcts, substantially increases the risk of clinical stroke. White matter microstructural integrity is considered an earlier, potentially better, marker of the total burden of vascular brain disease. Its association with risk of stroke, a focal event, remains unknown. METHODS: From the population-based Rotterdam Study, 4259 stroke-free participants (mean age: 63.6 years, 55.6% women) underwent brain magnetic resonance imaging, including diffusion magnetic resonance imaging, between 2006 and 2011. All participants were followed up for incident stroke until 2013. Cox proportional hazards models were used to associate markers of the microstructure of normal-appearing white matter with risk of stroke, adjusting for age, sex, white matter lesion volume, lacunar infarcts, and additionally for cardiovascular risk factors. Finally, we assessed the predictive value of white matter microstructural integrity for stroke beyond the Framingham Stroke Risk Profile. RESULTS: During 18 476 person-years of follow-up, 58 people experienced a stroke. Both lower fractional anisotropy and higher MD increased risk of stroke, independent of age, sex, cardiovascular risk factors, white matter lesion volume, and lacunar infarcts (hazard ratio per SD increase in: fractional anisotropy: 0.75 [95% confidence interval, 0.57-0.98] and MD: 1.50 [95% confidence interval, 1.08-2.09]). MD improved stroke prediction beyond the Framingham Stroke Risk Profile (continuous net reclassification improvement: 0.52 [95% confidence interval, 0.24-0.81]). CONCLUSIONS: Future stroke is predicted not only by prevalent vascular lesions but also by subtle alterations in the microstructure of normal-appearing white matter. Inclusion of this effect in risk prediction models produces a significant advantage in stroke prediction compared with the existing Framingham Stroke Risk Profile.

White Matter Degeneration with Aging: Longitudinal Diffusion MR Imaging Analysis.

PURPOSE: To determine longitudinally the rate of change in diffusion-tensor imaging (DTI) parameters of white matter microstructure with aging and to investigate whether cardiovascular risk factors influence this longitudinal change. MATERIALS AND METHODS: This prospective population-based cohort study was approved by a dedicated ethics committee overseen by the national government, and all participants gave written informed consent. Community-dwelling participants without dementia were examined by using a research-dedicated 1.5-T magnetic resonance (MR) imager on two separate visits that were, on average, 2.0 years apart. Among 810 persons who were eligible for imaging at baseline, longitudinal imaging data were available for 501 persons (mean age, 69.9 years; age range, 64.1-91.1 years). Changes in normal-appearing white matter DTI characteristics in the tract centers were analyzed globally to investigate diffuse patterns of change and then locally by using voxelwise multilinear regression. The influence of cardiovascular risk factors was assessed by treating them as additional determinants in both analyses. RESULTS: Over the 2.0-year follow-up interval, global fractional anisotropy (FA) decreased by 0.0042 (P < .001), while mean diffusivity (MD) increased by 8.1 × 10(-6) mm(2)/sec (P < .001). Voxelwise analysis of the brain white matter skeleton showed an average decrease of 0.0082 (Pmean = .002) in FA in 57% of skeleton voxels. The sensorimotor pathway, however, showed an increase of 0.0078 (Pmean = .009) in FA. MD increased by 10.8 × 10(-6)mm(2)/sec (Pmean < .001) on average in 79% of white matter skeleton voxels. Additionally, white matter degeneration was more pronounced in older persons. Cardiovascular risk factors were generally not associated with longitudinal changes in white matter microstructure. CONCLUSION: Longitudinal diffusion analysis indicates widespread microstructural deterioration of the normal-appearing white matter in normal aging, with relative sparing of sensorimotor fibers.

Tract-specific white matter degeneration in aging: the Rotterdam Study.

BACKGROUND: Loss of brain white matter microstructure is presumed to be an early sign of neurodegenerative disease. Yet, little is known on microstructural changes of various white matter tracts with normal aging. METHODS: In 4532 nondemented elderly persons, we studied age-related changes in tract-specific diffusion characteristics for 25 tracts using probabilistic tractography. We studied how diffusion differs across tracts with aging, whether this depends on macrostructural white matter changes, and whether cardiovascular risk factors affect microstructure. RESULTS: With increasing age, loss of microstructural organization occurred in association, commissural and limbic tracts. White matter lesions and atrophy each partially explained this loss. We observed worse microstructure with severe hypertension, current smoking and diabetes mellitus, independent from age and macrostructural white matter changes. CONCLUSIONS: Microstructure of white matter tracts changes with age, and may mark neurodegeneration more sensitively than white matter lesion load and atrophy. Cardiovascular factors relate to loss in microstructural organization.

Global and focal white matter integrity in breast cancer survivors 20 years after adjuvant chemotherapy.

OBJECTIVES: To date, only four small studies have investigated the effects of adjuvant chemotherapy for breast cancer on the microstructure of cerebral white matter with magnetic resonance imaging (MRI). These studies, which were conducted shortly up to 10 years post-treatment, showed that chemotherapy is associated with focal loss of microstructural white matter integrity. We investigated the long-term effect of chemotherapy on white matter microstructural integrity by comparing the brains of chemotherapy-exposed breast cancer survivors to those of a population-based sample of women without a history of cancer. EXPERIMENTAL DESIGN: Diffusion tensor imaging (DTI) MRI (1.5 T) was performed in 187 CMF (cyclophosphamide, methotrexate, and 5-flourouracil) chemotherapy-exposed breast cancer survivors, mean age 64.2 (sd = 6.5) years, who had been diagnosed with cancer on average 21.2 (sd = 4.4) years before, and 374 age-matched cancer-free reference subjects from a population-based cohort study. Outcome measures were whole-brain microstructural integrity as measured by fractional anisotropy and mean/axial/radial diffusivity and focal white matter integrity, which was analyzed with tract-based spatial statistics. All analyses were adjusted for age, cardiovascular risk factors, education, and symptoms of depression. PRINCIPAL OBSERVATIONS: No significant group differences were observed in white matter integrity. However, within the breast cancer survivors, time since treatment was inversely associated with lower global and focal white matter integrity. CONCLUSIONS: This cross-sectional study suggests that among chemotherapy-exposed breast cancer survivors white matter microstructural integrity deteriorates with accumulating time since treatment. This warrants further investigation.

Cerebral small vessel disease affects white matter microstructure in mild cognitive impairment.

Microstructural white matter deterioration is a frequent finding in mild cognitive impairment (MCI), potentially underlying default mode network (DMN) dysfunctioning. Thus far, microstructural damage in MCI has been attributed to Alzheimer's disease pathophysiology. A cerebrovascular role, in particular the role of cerebral small vessel disease (CSVD), received less interest. Here, we used diffusion tensor imaging (DTI) to examine the role of CSVD in microstructural deterioration within the normal appearing white matter (NAWM) in MCI. MCI patients were subdivided into those with (n = 20) and without (n = 31) macrostructural CSVD evidence on MRI. Using TBSS we performed microstructural integrity comparisons within the whole brain NAWM. Secondly, we segmented white matter tracts interconnecting DMN brain regions by means of automated tractography segmentation. We used NAWM DTI measures from these tracts as dependent variables in a stepwise-linear regression analysis, with structural and demographical predictors. Our results indicated microstructural deterioration within the anterior corpus callosum, internal and external capsule and periventricular white matter in MCI patients with CSVD, while in MCI patients without CSVD, deterioration was restricted to the right perforant path, a tract along the hippocampus. Within the full cohort of MCI patients, microstructure within the NAWM of the DMN fiber tracts was affected by the presence of CSVD. Within the cingulum along the hippocampal cortex we found a relationship between microstructural integrity and ipsilateral hippocampal volume and the extent of white matter hyperintensity. In conclusion, we found evidence of CSVD-related microstructural damage in fiber tracts subserving the DMN in MCI.

Expectation maximisation pseudo labels.

In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high-quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi-class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo-labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.

Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021.

Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.

Changes in normal-appearing white matter precede development of white matter lesions.

BACKGROUND AND PURPOSE: It is unknown whether white matter lesions (WML) develop abruptly in previously normal brain areas, or whether tissue changes are already present before WML become apparent on MRI. We therefore investigated whether development of WML is preceded by quantifiable changes in normal-appearing white matter (NAWM). METHODS: In 689 participants from the general population (mean age 67 years), we performed 2 MRI scans (including diffusion tensor imaging and Fluid Attenuation Inversion Recovery [FLAIR] sequences) 3.5 years apart using the same 1.5-T scanner. Using automated tissue segmentation, we identified NAWM at baseline. We assessed which NAWM regions converted into WML during follow-up and differentiated new WML into regions of WML growth and de novo WML. Fractional anisotropy, mean diffusivity, and FLAIR intensity of regions converting to WML and regions of persistent NAWM were compared using 3 approaches: a whole-brain analysis, a regionally matched approach, and a voxel-wise approach. RESULTS: All 3 approaches showed that low fractional anisotropy, high mean diffusivity, and relatively high FLAIR intensity at baseline were associated with WML development during follow-up. Compared with persistent NAWM regions, NAWM regions converting to WML had significantly lower fractional anisotropy (0.337 vs 0.387; P<0.001), higher mean diffusivity (0.910 × 10(-3) mm(2)/s vs 0.729 × 10(-3) mm(2)/s; P<0.001), and relatively higher normalized FLAIR intensity (1.233 vs -0.340; P<0.001). This applied to both NAWM developing into growing and de novo WML. CONCLUSIONS: White matter changes in NAWM are present and can be quantified on diffusion tensor imaging and FLAIR before WML develop. This suggests that WML develop gradually, and that visually appreciable WML are only the tip of the iceberg of white matter pathology.

Improving alignment in Tract-based spatial statistics: evaluation and optimization of image registration.

Anatomical alignment in neuroimaging studies is of such importance that considerable effort is put into improving the registration used to establish spatial correspondence. Tract-based spatial statistics (TBSS) is a popular method for comparing diffusion characteristics across subjects. TBSS establishes spatial correspondence using a combination of nonlinear registration and a "skeleton projection" that may break topological consistency of the transformed brain images. We therefore investigated feasibility of replacing the two-stage registration-projection procedure in TBSS with a single, regularized, high-dimensional registration. To optimize registration parameters and to evaluate registration performance in diffusion MRI, we designed an evaluation framework that uses native space probabilistic tractography for 23 white matter tracts, and quantifies tract similarity across subjects in standard space. We optimized parameters for two registration algorithms on two diffusion datasets of different quality. We investigated reproducibility of the evaluation framework, and of the optimized registration algorithms. Next, we compared registration performance of the regularized registration methods and TBSS. Finally, feasibility and effect of incorporating the improved registration in TBSS were evaluated in an example study. The evaluation framework was highly reproducible for both algorithms (R(2) 0.993; 0.931). The optimal registration parameters depended on the quality of the dataset in a graded and predictable manner. At optimal parameters, both algorithms outperformed the registration of TBSS, showing feasibility of adopting such approaches in TBSS. This was further confirmed in the example experiment.

A meta-analysis of structural MRI studies of the brain in systemic lupus erythematosus (SLE).

A comprehensive search of published literature in brain volumetry was conducted in three autoimmune diseases - systemic lupus erythematosus (SLE), rheumatoid arthritis (RA), and ulcerative colitis (UC) - with the intention of performing a meta-analysis of published data. Due to the lack of data in RA and UC, the reported meta-analysis was limited to SLE. The MEDLINE database was searched for studies from 1988 to March 2022. A total of 175 papers met the initial inclusion criteria, and 16 were included in a random-effects meta-analysis. The reduction in the number of papers included in the final analysis is primarily due to the lack of overlap in measured and reported brain regions. A significantly lower volume was seen in patients with SLE in the hippocampus, corpus callosum, and total gray matter volume measurements as compared to age- and sex-matched controls. There were not enough studies to perform a meta-analysis for RA and UC; instead, we include a summary of published volumetric studies. The meta-analyses revealed structural brain abnormalities in patients with SLE, suggesting that lower global brain volumes are associated with disease status. This volumetric difference was seen in both the hippocampus and corpus callosum and total gray matter volume measurements. These results indicate both gray and white matter involvements in SLE and suggest there may be both localized and global reductions in brain volume.

MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations With Limited Labels.

Semi-supervised learning (SSL) is a promising machine learning paradigm to address the ubiquitous issue of label scarcity in medical imaging. The state-of-the-art SSL methods in image classification utilise consistency regularisation to learn unlabelled predictions which are invariant to input level perturbations. However, image level perturbations violate the cluster assumption in the setting of segmentation. Moreover, existing image level perturbations are hand-crafted which could be sub-optimal. In this paper, we propose MisMatch, a semi-supervised segmentation framework based on the consistency between paired predictions which are derived from two differently learnt morphological feature perturbations. MisMatch consists of an encoder and two decoders. One decoder learns positive attention for foreground on unlabelled data thereby generating dilated features of foreground. The other decoder learns negative attention for foreground on the same unlabelled data thereby generating eroded features of foreground. We normalise the paired predictions of the decoders, along the batch dimension. A consistency regularisation is then applied between the normalised paired predictions of the decoders. We evaluate MisMatch on four different tasks. Firstly, we develop a 2D U-net based MisMatch framework and perform extensive cross-validation on a CT-based pulmonary vessel segmentation task and show that MisMatch statistically outperforms state-of-the-art semi-supervised methods. Secondly, we show that 2D MisMatch outperforms state-of-the-art methods on an MRI-based brain tumour segmentation task. We then further confirm that 3D V-net based MisMatch outperforms its 3D counterpart based on consistency regularisation with input level perturbations, on two different tasks including, left atrium segmentation from 3D CT images and whole brain tumour segmentation from 3D MRI images. Lastly, we find that the performance improvement of MisMatch over the baseline might originate from its better calibration. This also implies that our proposed AI system makes safer decisions than the previous methods.

Statistical analysis of minimum cost path based structural brain connectivity.

Diffusion MRI can be used to study the structural connectivity within the brain. Brain connectivity is often represented by a binary network whose topology can be studied using graph theory. We present a framework for the construction of weighted structural brain networks, containing information about connectivity, which can be effectively analyzed using statistical methods. Network nodes are defined by segmentation of subcortical structures and by cortical parcellation. Connectivity is established using a minimum cost path (mcp) method with an anisotropic local cost function based directly on diffusion weighted images. We refer to this framework as Statistical Analysis of Minimum cost path based Structural Connectivity (SAMSCo) and the weighted structural connectivity networks as mcp-networks. In a proof of principle study we investigated the information contained in mcp-networks by predicting subject age based on the mcp-networks of a group of 974 middle-aged and elderly subjects. Using SAMSCo, age was predicted with an average error of 3.7 years. This was significantly better than predictions based on fractional anisotropy or mean diffusivity averaged over the whole white matter or over the corpus callosum, which showed average prediction errors of at least 4.8 years. Additionally, we classified subjects, based on the mcp-networks, into groups with low and high white matter lesion load, while correcting for age, sex and white matter atrophy. The SAMSCo classification outperformed the classification based on the diffusion measures with a classification accuracy of 76.0% versus 63.2%. We also performed a classification in groups with mild and severe atrophy, correcting for age, sex and white matter lesion load. In this case, mcp-networks and diffusion measures yielded similar classification accuracies of 68.3% and 67.8% respectively. The SAMSCo prediction and classification experiments indicate that the mcp-networks contain information regarding age, white matter lesion load and white matter atrophy, and that in case of age and white matter lesion load the mcp-network based models outperformed the predictions based on diffusion measures.