A comparison of automated segmentation and manual tracing in estimating hippocampal volume in ischemic stroke and healthy control participants

Automated hippocampal segmentation algorithms evaluated in stroke patients

Deep learning segmentation algorithms can produce reproducible results in a matter of seconds. However, their application to more complex datasets is uncertain and may fail in the presence of severe structural abnormalities-such as those commonly seen in stroke patients. In this investigation, six recent, deep learning-based hippocampal segmentation algorithms were tested on 641 stroke patients of a multicentric, open-source dataset ATLAS 2.0. The comparisons of the volumes showed that the methods are not interchangeable with concordance correlation coefficients from 0.266 to 0.816. While the segmentation algorithms demonstrated an overall good performance (volumetric similarity [VS] 0.816 to 0.972, DICE score 0.786 to 0.921, and Hausdorff distance [HD] 2.69 to 6.34), no single out-performing algorithm was identified: FastSurfer performed best in VS, QuickNat in DICE and average HD, and Hippodeep in HD. Segmentation performance was significantly lower for ipsilesional segmentation, with a decrease in performance as a function of lesion size due to the pathology-based domain shift. Only QuickNat showed a more robust performance in volumetric similarity. Even though there are many pre-trained segmentation methods, it is important to be aware of the possible decrease in performance for the segmentation results on the lesion side due to the pathology-based domain shift. The segmentation algorithm should be selected based on the research question and the evaluation parameter needed. More research is needed to improve current hippocampal segmentation methods.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Nomograms of human hippocampal volume shifted by polygenic scores

Nomograms are important clinical tools applied widely in both developing and aging populations. They are generally constructed as normative models identifying cases as outliers to a distribution of healthy controls. Currently used normative models do not account for genetic heterogeneity. Hippocampal volume (HV) is a key endophenotype for many brain disorders. Here, we examine the impact of genetic adjustment on HV nomograms and the translational ability to detect dementia patients. Using imaging data from 35,686 healthy subjects aged 44-82 from the UK Biobank (UKB), we built HV nomograms using Gaussian process regression (GPR), which - compared to a previous method - extended the application age by 20 years, including dementia critical age ranges. Using HV polygenic scores (HV-PGS), we built genetically adjusted nomograms from participants stratified into the top and bottom 30% of HV-PGS. This shifted the nomograms in the expected directions by ~100 mm3 (2.3% of the average HV), which equates to 3 years of normal aging for a person aged ~65. Clinical impact of genetically adjusted nomograms was investigated by comparing 818 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database diagnosed as either cognitively normal (CN), having mild cognitive impairment (MCI) or Alzheimer's disease (AD) patients. While no significant change in the survival analysis was found for MCI-to-AD conversion, an average of 68% relative decrease was found in intra-diagnostic-group variance, highlighting the importance of genetic adjustment in untangling phenotypic heterogeneity.

Grey and white matter atrophy one year after stroke aphasia

Dynamic whole-brain changes occur following stroke, and not just in association with recovery. We tested the hypothesis that the presence of a specific behavioural deficit after stroke would be associated with structural decline (atrophy) in the brain regions supporting the affected function, by examining language deficits post-stroke. We quantified whole-brain structural volume changes longitudinally (3–12 months) in stroke participants with (N = 32) and without aphasia (N = 59) as assessed by the Token Test at 3 months post-stroke, compared with a healthy control group (N = 29). While no significant difference in language decline rates (change in Token Test scores from 3 to 12 months) was observed between groups and some participants in the aphasic group improved their scores, stroke participants with aphasia symptoms at 3 months showed significant atrophy (>2%, P = 0.0001) of the left inferior frontal gyrus not observed in either healthy control or non-aphasic groups over the 3–12 months period. We found significant group differences in the inferior frontal gyrus volume, accounting for age, sex, stroke severity at baseline, education and total intracranial volume (Bonferroni-corrected P = 0.0003). In a subset of participants (aphasic N = 14, non-aphasic N = 36, and healthy control N = 25) with available diffusion-weighted imaging data, we found significant atrophy in the corpus callosum and the left superior longitudinal fasciculus in the aphasic compared with the healthy control group. Language deficits at 3 months post-stroke are associated with accelerated structural decline specific to the left inferior frontal gyrus, highlighting that known functional brain reorganization underlying behavioural improvement may occur in parallel with atrophy of brain regions supporting the language function.

Testing a convolutional neural network-based hippocampal segmentation method in a stroke population

As stroke mortality rates decrease, there has been a surge of effort to study poststroke dementia (PSD) to improve long-term quality of life for stroke survivors. Hippocampal volume may be an important neuroimaging biomarker in poststroke dementia, as it has been associated with many other forms of dementia. However, studying hippocampal volume using MRI requires hippocampal segmentation. Advances in automated segmentation methods have allowed for studying the hippocampus on a large scale, which is important for robust results in the heterogeneous stroke population. However, most of these automated methods use a single atlas-based approach and may fail in the presence of severe structural abnormalities common in stroke. Hippodeep, a new convolutional neural network-based hippocampal segmentation method, does not rely solely on a single atlas-based approach and thus may be better suited for stroke populations. Here, we compared quality control and the accuracy of segmentations generated by Hippodeep and two well-accepted hippocampal segmentation methods on stroke MRIs (FreeSurfer 6.0 whole hippocampus and FreeSurfer 6.0 sum of hippocampal subfields). Quality control was performed using a stringent protocol for visual inspection of the segmentations, and accuracy was measured as volumetric correlation with manual segmentations. Hippodeep performed significantly better than both FreeSurfer methods in terms of quality control. All three automated segmentation methods had good correlation with manual segmentations and no one method was significantly more correlated than the others. Overall, this study suggests that both Hippodeep and FreeSurfer may be useful for hippocampal segmentation in stroke rehabilitation research, but Hippodeep may be more robust to stroke lesion anatomy.

The ENIGMA Stroke Recovery Working Group: Big data neuroimaging to study brain-behavior relationships after stroke

The goal of the Enhancing Neuroimaging Genetics through Meta-Analysis (ENIGMA) Stroke Recovery working group is to understand brain and behavior relationships using well-powered meta- and mega-analytic approaches. ENIGMA Stroke Recovery has data from over 2,100 stroke patients collected across 39 research studies and 10 countries around the world, comprising the largest multisite retrospective stroke data collaboration to date. This article outlines the efforts taken by the ENIGMA Stroke Recovery working group to develop neuroinformatics protocols and methods to manage multisite stroke brain magnetic resonance imaging, behavioral and demographics data. Specifically, the processes for scalable data intake and preprocessing, multisite data harmonization, and large-scale stroke lesion analysis are described, and challenges unique to this type of big data collaboration in stroke research are discussed. Finally, future directions and limitations, as well as recommendations for improved data harmonization through prospective data collection and data management, are provided.

Norms for Automatic Estimation of Hippocampal Atrophy and a Step Forward for Applicability to the Italian Population

INTRODUCTION

Hippocampal volume is one of the main biomarkers of Alzheimer's Dementia (AD). Over the years, advanced tools that performed automatic segmentation of Magnetic Resonance Imaging (MRI) T13D scans have been developed, such as FreeSurfer (FS) and ACM-Adaboost (AA). Hippocampal volume is considered abnormal when it is below the 5th percentile of the normative population. The aim of this study was to set norms, established from the Alzheimer's Disease Neuroimaging Initiative (ADNI) population, for hippocampal volume measured with FS v.6.0 and AA tools in the neuGRID platform (www.neugrid2.eu) and demonstrate their applicability for the Italian population.

METHODS

Norms were set from a large group of 545 healthy controls belonging to ADNI. For each pipeline, subjects with segmentation errors were discarded, resulting in 532 valid segmentations for FS and 421 for AA (age range 56-90 years). The comparability of ADNI and the Italian Brain Normative Archive (IBNA), representative of the Italian general population, was assessed testing clinical variables, neuropsychological scores and normalized hippocampal volumes. Finally, percentiles were validated using the Italian Alzheimer's disease Repository Without Borders (ARWiBo) as external independent data set to evaluate FS and AA generalizability.

RESULTS

Hippocampal percentiles were checked with the chi-square goodness of fit test. P-values were not significant, showing that FS and AA algorithm distributions fitted the data well. Clinical, neuropsychological and volumetric features were similar in ADNI and IBNA (p > 0.01). Hippocampal volumes measured with both FS and AA were associated with age (p < 0.001). The 5th percentile thresholds, indicating left/right hippocampal atrophy were respectively: (i) below 3,223/3,456 mm3 at 56 years and 2,506/2,415 mm3 at 90 years for FS; (ii) below 4,583/4,873 mm3 at 56 years and 3,831/3,870 mm3 at 90 years for AA. The average volumes computed on 100 cognitively intact healthy controls (CN) selected from ARWiBo were close to the 50th percentiles, while those for 100 AD patients were close to the abnormal percentiles.

DISCUSSION

Norms generated from ADNI through the automatic FS and AA segmentation tools may be used as normative references for Italian patients with suspected AD.

Hippocampal subfield volumes are associated with verbal memory after first-ever ischemic stroke

INTRODUCTION

Hippocampal subfield volumes are more closely associated with cognitive impairment than whole hippocampal volume in many diseases. Both memory and whole hippocampal volume decline after stroke. Understanding the subfields' temporal evolution could reveal valuable information about post-stroke memory.

METHODS

We sampled 120 participants (38 control, 82 stroke), with cognitive testing and 3T-MRI available at 3 months and 3 years, from the Cognition and Neocortical Volume after Stroke (CANVAS) study. Verbal memory was assessed using the Hopkins Verbal Learning Test-Revised. Subfields were delineated using FreeSurfer. We used partial Pearson's correlation to assess the associations between subfield volumes and verbal memory scores, adjusting for years of education, sex, and stroke side.

RESULTS

The left cornu ammonis areas 2/3 and hippocampal tail volumes were significantly associated with verbal memory 3-month post-stroke. At 3 years, the associations became stronger and involved more subfields.

DISCUSSION

Hippocampal subfield volumes may be a useful biomarker for post-stroke cognitive impairment.

Longer Duration of Hypertension and MRI Microvascular Brain Alterations Are Associated with Lower Hippocampal Volumes in Older Individuals with Hypertension

BACKGROUND

Hippocampal atrophy is associated with cognitive decline. Determining the clinical features associated with hippocampal volume (HV)/atrophy may help in tailoring preventive strategies.

OBJECTIVE

This study was aimed to investigate the association between HV (at visit 2) and vascular status (both at visit 1 and visit 2) in a cohort of individuals aged 60+ with hypertension and without overt cognitive impairment at visit 1 (visit 1 and visit 2 were separated by approximately 8 years).

METHODS

Hippocampal volume was estimated in brain MRIs as HV both clinically with the Scheltens' Medial Temporal Atrophy score, and automatically with the Free Surfer Software application. A detailed medical history, somatometric measurements, cognitive tests, leukoaraiosis severity (Fazekas score), vascular parameters including pulse wave velocity, central blood pressure, and carotid artery plaques, as well as several biochemical parameters were also measured.

RESULTS

113 hypertensive patients, 47% male, aged 75.1±5.6 years, participated in both visit 1 and visit 2 of the ADELAHYDE study. Age (β= -0.30) and hypertension duration (β= -0.20) at visit 1 were independently associated with smaller HV at visit 2 (p < 0.05 for all). In addition to these variables, low body mass index (β= 0.18), high MRI Fazekas score (β= -0.20), and low Gröber-Buschke total recall (β= 0.27) were associated with smaller HV at visit 2 (p < 0.05 for all).

CONCLUSION

In a cohort of older individuals without cognitive impairment at baseline, we described several factors associated with lower HV, of which hypertension duration can potentially be modified.

Characterizing the subtype of anhedonia in major depressive disorder: A symptom-specific multimodal MRI study

Anhedonia is a core symptom of major depressive disorder (MDD). Two subtypes of anhedonia: anticipatory anhedonia and consummatory anhedonia has been recognized in MDD patients. However, our knowledge regarding the distinction of anticipatory anhedonia and consummatory anhedonia in MDD remains limited. This study aimed to characterize the anticipatory anhedonia and consummatory anhedonia in first-episode, drug-naïve MDD patients. Resting-state functional MRI and T1-structural MRI were acquired for 38 MDD patients and 65 matched healthy controls (HCs). The ALFF and cortical surface indexes were compared between MDD and HCs. Then the correlations between the ALFF and cortical surface indexes alternations and the scores of anticipatory and consummatory pleasure measured by Temporal Experience of Pleasure Scale were evaluated. The elevated ALFF of left dorsal anterior cingulate cortex (dACC) and the reduced cortical thickness (CT) of left rostral ACC and lateral orbitofrontal cortex (lOFC) were respectively correlated with anticipatory anhedonia and consummatory anhedonia in MDD patients. These findings suggested the dissociated pathophysiological basis and imaging characteristics of anticipatory anhedonia and consummatory anhedonia. The ALFF and CT values of ACC and lOFC might serve as the imaging biomarker of the subtypes of anhedonia in early onset of MDD.

Machine Learning for Diagnosis of AD and Prediction of MCI Progression From Brain MRI Using Brain Anatomical Analysis Using Diffeomorphic Deformation

Background: With the growing momentum for the adoption of machine learning (ML) in medical field, it is likely that reliance on ML for imaging will become routine over the next few years. We have developed a software named BAAD, which uses ML algorithms for the diagnosis of Alzheimer's disease (AD) and prediction of mild cognitive impairment (MCI) progression. Methods: We constructed an algorithm by combining a support vector machine (SVM) to classify and a voxel-based morphometry (VBM) to reduce concerned variables. We grouped progressive MCI and AD as an AD spectrum and trained SVM according to this classification. We randomly selected half from the total 1,314 subjects of AD neuroimaging Initiative (ADNI) from North America for SVM training, and the remaining half were used for validation to fine-tune the model hyperparameters. We created two types of SVMs, one based solely on the brain structure (SVMst), and the other based on both the brain structure and Mini-Mental State Examination score (SVMcog). We compared the model performance with two expert neuroradiologists, and further evaluated it in test datasets involving 519, 592, 69, and 128 subjects from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL), Japanese ADNI, the Minimal Interval Resonance Imaging in AD (MIDIAD) and the Open Access Series of Imaging Studies (OASIS), respectively. Results: BAAD's SVMs outperformed radiologists for AD diagnosis in a structural magnetic resonance imaging review. The accuracy of the two radiologists was 57.5 and 70.0%, respectively, whereas, that of the SVMst was 90.5%. The diagnostic accuracy of the SVMst and SVMcog in the test datasets ranged from 88.0 to 97.1% and 92.5 to 100%, respectively. The prediction accuracy for MCI progression was 83.0% in SVMst and 85.0% in SVMcog. In the AD spectrum classified by SVMst, 87.1% of the subjects were Aβ positive according to an AV-45 positron emission tomography. Similarly, among MCI patients classified for the AD spectrum, 89.5% of the subjects progressed to AD. Conclusion: Our ML has shown high performance in AD diagnosis and prediction of MCI progression. It outperformed expert radiologists, and is expected to provide support in clinical practice.

Gray matter volume of rostral anterior cingulate cortex predicts rapid antidepressant response to ketamine

Ketamine was recently approved for treatment resistant depression. However, despite its therapeutic potential, about 50% of patients do not show improvement under this therapy. In this prospective two-site study, we investigated baseline brain structural predictors for rapid symptom improvement after a single subanesthetic ketamine infusion. Furthermore, given the preclinical evidence and findings from a pilot study in a clinical population that ketamine induces rapid neuroplasticity, we performed an exploratory investigation of macroscopic changes 24 h post-treatment. T1-weighted MRI brain images from 33 depressed patients were acquired before and 24 h after a single ketamine infusion and analyzed using voxel-based morphometry (VBM). Additionally, we performed a region of interest (ROI)-based analysis of structures that have previously been shown to play a role in the antidepressant effects of ketamine: bilateral hippocampus, nucleus accumbens, anterior cingulate cortex, and thalamus. A whole-brain regression analysis showed that greater baseline volume of the bilateral rostral anterior cingulate cortex (rACC) significantly predicts rapid symptom reduction. The right ACC showed the same association in the ROI analysis, while the other regions yielded no significant results. Exploratory follow-up analyses revealed no volumetric changes 24 h after treatment. This is the first study reporting an association between pretreatment gray matter volume of the bilateral rACC and the rapid antidepressant effects of ketamine. Results are in line with previous investigations, which highlighted the potential of the rACC as a biomarker for response prediction to different antidepressant treatments. Ketamine-induced volumetric changes may be seen at later time points.

FreeSurfer ‐based segmentation of hippocampal subfields: A review of methods and applications, with a novel quality control procedure for ENIGMA studies and other collaborative efforts

Structural hippocampal abnormalities are common in many neurological and psychiatric disorders, and variation in hippocampal measures is related to cognitive performance and other complex phenotypes such as stress sensitivity. Hippocampal subregions are increasingly studied, as automated algorithms have become available for mapping and volume quantification. In the context of the Enhancing Neuro Imaging Genetics through Meta Analysis Consortium, several Disease Working Groups are using the FreeSurfer software to analyze hippocampal subregion (subfield) volumes in patients with neurological and psychiatric conditions along with data from matched controls. In this overview, we explain the algorithm's principles, summarize measurement reliability studies, and demonstrate two additional aspects (subfield autocorrelation and volume/reliability correlation) with illustrative data. We then explain the rationale for a standardized hippocampal subfield segmentation quality control (QC) procedure for improved pipeline harmonization. To guide researchers to make optimal use of the algorithm, we discuss how global size and age effects can be modeled, how QC steps can be incorporated and how subfields may be aggregated into composite volumes. This discussion is based on a synopsis of 162 published neuroimaging studies (01/2013–12/2019) that applied the FreeSurfer hippocampal subfield segmentation in a broad range of domains including cognition and healthy aging, brain development and neurodegeneration, affective disorders, psychosis, stress regulation, neurotoxicity, epilepsy, inflammatory disease, childhood adversity and posttraumatic stress disorder, and candidate and whole genome (epi‐)genetics. Finally, we highlight points where FreeSurfer‐based hippocampal subfield studies may be optimized.

Cortical Thickness Estimation in Individuals With Cerebral Small Vessel Disease, Focal Atrophy, and Chronic Stroke Lesions

BACKGROUND

Regional changes to cortical thickness in individuals with neurodegenerative and cerebrovascular diseases (CVD) can be estimated using specialized neuroimaging software. However, the presence of cerebral small vessel disease, focal atrophy, and cortico-subcortical stroke lesions, pose significant challenges that increase the likelihood of misclassification errors and segmentation failures.

PURPOSE

The main goal of this study was to examine a correction procedure developed for enhancing FreeSurfer's (FS's) cortical thickness estimation tool, particularly when applied to the most challenging MRI obtained from participants with chronic stroke and CVD, with varying degrees of neurovascular lesions and brain atrophy.

METHODS

In 155 CVD participants enrolled in the Ontario Neurodegenerative Disease Research Initiative (ONDRI), FS outputs were compared between a fully automated, unmodified procedure and a corrected procedure that accounted for potential sources of error due to atrophy and neurovascular lesions. Quality control (QC) measures were obtained from both procedures. Association between cortical thickness and global cognitive status as assessed by the Montreal Cognitive Assessment (MoCA) score was also investigated from both procedures.

RESULTS

Corrected procedures increased "Acceptable" QC ratings from 18 to 76% for the cortical ribbon and from 38 to 92% for tissue segmentation. Corrected procedures reduced "Fail" ratings from 11 to 0% for the cortical ribbon and 62 to 8% for tissue segmentation. FS-based segmentation of T1-weighted white matter hypointensities were significantly greater in the corrected procedure (5.8 mL vs. 15.9 mL, p < 0.001). The unmodified procedure yielded no significant associations with global cognitive status, whereas the corrected procedure yielded positive associations between MoCA total score and clusters of cortical thickness in the left superior parietal (p = 0.018) and left insula (p = 0.04) regions. Further analyses with the corrected cortical thickness results and MoCA subscores showed a positive association between left superior parietal cortical thickness and Attention (p < 0.001).

CONCLUSION

These findings suggest that correction procedures which account for brain atrophy and neurovascular lesions can significantly improve FS's segmentation results and reduce failure rates, thus maximizing power by preventing the loss of our important study participants. Future work will examine relationships between cortical thickness, cerebral small vessel disease, and cognitive dysfunction due to neurodegenerative disease in the ONDRI study.

Dose-dependent volume loss in subcortical deep grey matter structures after cranial radiotherapy

•

Subcortical grey matter is susceptible to dose-dependent volume loss after RT.

•

Hippocampal age increases 1 year after radiotherapy, by a median of 11 years.

•

We may need to reconsider current sparing strategies in RT for brain tumours.

•

Future studies should examine the impact of deep GM volume loss on cognition.

Background and purpose

The relation between radiotherapy (RT) dose to the brain and morphological changes in healthy tissue has seen recent increased interest. There already is evidence for changes in the cerebral cortex and white matter, as well as selected subcortical grey matter (GM) structures. We studied this relation in all deep GM structures, to help understand the aetiology of post-RT neurocognitive symptoms.

Materials and methods

We selected 31 patients treated with RT for grade II-IV glioma. Pre-RT and 1 year post-RT 3D T1-weighted MRIs were automatically segmented, and the changes in volume of the following structures were assessed: amygdala, nucleus accumbens, caudate nucleus, hippocampus, globus pallidus, putamen, and thalamus. The volumetric changes were related to the mean RT dose received by each structure. Hippocampal volumes were entered into a population-based nomogram to estimate hippocampal age.

Results

A significant relation between RT dose and volume loss was seen in all examined structures, except the caudate nucleus. The volume loss rates ranged from 0.16 to 1.37%/Gy, corresponding to 4.9–41.2% per 30 Gy. Hippocampal age, as derived from the nomogram, was seen to increase by a median of 11 years.

Conclusion

Almost all subcortical GM structures are susceptible to radiation-induced volume loss, with higher volume loss being observed with increasing dose. Volume loss of these structures is associated with neurological deterioration, including cognitive decline, in neurodegenerative diseases. To support a causal relationship between radiation-induced deep GM loss and neurocognitive functioning in glioma patients, future studies are needed that directly correlate volumetrics to clinical outcomes.

Dynamic Regional Brain Atrophy Rates in the First Year After Ischemic Stroke

BACKGROUND AND PURPOSE

Brain atrophy can be regarded as an end-organ effect of cumulative cardiovascular risk factors. Accelerated brain atrophy is described following ischemic stroke, but it is not known whether atrophy rates vary over the poststroke period. Examining rates of brain atrophy allows the identification of potential therapeutic windows for interventions to prevent poststroke brain atrophy.

METHODS

We charted total and regional brain volume and cortical thickness trajectories, comparing atrophy rates over 2 time periods in the first year after ischemic stroke: within 3 months (early period) and between 3 and 12 months (later period). Patients with first-ever or recurrent ischemic stroke were recruited from 3 Melbourne hospitals at 1 of 2 poststroke time points: within 6 weeks (baseline) or 3 months. Whole-brain 3T magnetic resonance imaging was performed at 3 time points: baseline, 3 months, and 12 months. Eighty-six stroke participants completed testing at baseline; 125 at 3 months (76 baseline follow-up plus 49 delayed recruitment); and 113 participants at 12 months. Their data were compared with 40 healthy control participants with identical testing. We examined 5 brain measures: hippocampal volume, thalamic volume, total brain and hemispheric brain volume, and cortical thickness. We tested whether brain atrophy rates differed between time points and groups. A linear mixed-effect model was used to compare brain structural changes, including age, sex, years of education, a composite cerebrovascular risk factor score, and total intracranial volume as covariates.

RESULTS

Atrophy rates were greater in stroke than control participants. Ipsilesional hemispheric, hippocampal, and thalamic atrophy rates were 2 to 4 times greater in the early versus later period.

CONCLUSIONS

Regional atrophy rates vary over the first year after stroke. Rapid brain volume loss in the first 3 months after stroke may represent a potential window for intervention. Registration: URL: https://www.clinicaltrials.gov. Unique identifier: NCT02205424.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

Borderline Personality Traits Are Not Correlated With Brain Structure in Two Large Samples

BACKGROUND

Borderline personality disorder is associated with severe psychiatric presentations and has been linked to variability in brain structure. Dimensional models of borderline personality traits (BPTs) have become influential; however, associations between BPTs and brain structure remain poorly understood.

METHODS

We tested whether BPTs are associated with regional cortical thickness, cortical surface area, and subcortical volumes (n = 152 brain structure metrics) in data from the Duke Neurogenetics Study (n = 1299) and Human Connectome Project (n = 1099). Positive control analyses tested whether BPTs are associated with related behaviors (e.g., suicidal thoughts and behaviors, psychiatric diagnoses) and experiences (e.g., adverse childhood experiences).

RESULTS

While BPTs were robustly associated with all positive control measures, they were not significantly associated with any brain structure metrics in the Duke Neurogenetics Study or Human Connectome Project, or in a meta-analysis of both samples. The strongest findings from the meta-analysis showed a positive association between BPTs and volumes of the left ventral diencephalon and thalamus (p values < .005 uncorrected, p values > .1 false discovery rate-corrected). Contrasting high and low BPT decile groups (n = 552) revealed no false discovery rate-significant associations with brain structure.

CONCLUSIONS

We find replicable evidence that BPTs are not associated with brain structure despite being correlated with independent behavioral measures. Prior reports linking brain morphology to borderline personality disorder may be driven by factors other than traits (e.g., severe presentations, comorbid conditions, severe childhood adversity, or medication) or reflect false positives. The etiology or consequences of BPTs may not be attributable to brain structure measured via magnetic resonance imaging. Future studies of BPTs will require much larger sample sizes to detect these very small effects.

Assessment of longitudinal hippocampal atrophy in the first year after ischemic stroke using automatic segmentation techniques

•

First-year hippocampal atrophy in stroke is more accelerated ipsi-lesionally.

•

Volume estimation is not impacted by hemisphere side, study group, or scan timepoint.

•

Segmentation method-hippocampal size interaction determines volume estimation.

•

FreeSurfer/Subfields and fsl/FIRST segmentations agreed best with manual tracing.

We assessed first-year hippocampal atrophy in stroke patients and healthy controls using manual and automated segmentations: AdaBoost, FIRST (fsl/v5.0.8), FreeSurfer/v5.3 and v6.0, and Subfields (in FreeSurfer/v6.0). We estimated hippocampal volumes in 39 healthy controls and 124 stroke participants at three months, and 38 controls and 113 stroke participants at one year. We used intra-class correlation, concordance, and reduced major axis regression to assess agreement between automated and ‘Manual’ estimations. A linear mixed-effect model was used to characterize hippocampal atrophy.

Overall, hippocampal volumes were reduced by 3.9% in first-ever stroke and 9.2% in recurrent stroke at three months post-stroke, with comparable ipsi-and contra-lesional reductions in first-ever stroke. Mean atrophy rates between time points were 0.5% for controls and 1.0% for stroke patients (0.6% contra-lesionally, 1.4% ipsi-lesionally). Atrophy rates in left and right-hemisphere strokes were comparable. All methods revealed significant volume change in first-ever and ipsi-lesional stroke (p < 0.001).

Hippocampal volume estimation was not impacted by hemisphere, study group, or scan time point, but rather, by the interaction between the automated segmentation method and hippocampal size. Compared to Manual, Subfields and FIRST recorded the lowest bias. FreeSurfer/v5.3 overestimated volumes the most for large hippocampi, while FIRST was the most accurate in estimating small volumes. AdaBoost performance was average.

Our findings suggest that first-year ipsi-lesional hippocampal atrophy rate especially in first-ever stroke, is greater than atrophy rates in healthy controls and contra-lesional stroke. Subfields and FIRST can complementarily be effective in characterizing the hippocampal atrophy in healthy and stroke cohorts.

The hippocampal-to-ventricle ratio (HVR): Presentation of a manual segmentation protocol and preliminary evidence

Disentangling age-related changes from developmental variations in hippocampal volume has proven challenging. This article presents a manual segmentation protocol for the hippocampal-to-ventricle ratio (HVR), a measure combining the assessment of hippocampal volume with surrounding ventricular volume. By providing in a single measure both a standard volumetric assessment of the hippocampus and an approximation of volume loss, based on ventricular enlargement, we believe the HVR provides a superior cross-sectional estimation of hippocampal structural integrity. In a first attempt to validate this measure, we contrasted the HVR and standard hippocampal volume in their associations with age and memory performance in two independent cohorts of healthy aging individuals. The first cohort consisted in 50 cognitively normal subjects (mean age: 66.8 years, SD: 4.96, range: 60-75 years), while the second cohort included 88 cognitively normal subjects (mean age: 65.06 years, SD: 6.42, range: 55-80 years). We showed that the manual segmentation protocol for the HVR can be implemented with high reliability. In both cohorts, the HVR showed stronger negative associations with age than standard hippocampal volume. Correlations with memory performance were also numerically superior with the HVR than standard hippocampal volume, across the two cohorts. These findings support an added benefit of using the HVR over standard hippocampal volume when examining relationships with age or memory function in aging individuals. Although further validation is required, we propose that the computation of the HVR is a promising method to improve the evaluation of hippocampal integrity from cross-sectional MR images.