Manual, semi-automated, and automated delineation of chronic brain lesions: a comparison of methods

Post-stroke urinary incontinence is associated with behavior control deficits and overactive bladder

BACKGROUND

Although urinary incontinence in stroke survivors can substantially impact the patient's quality of life, the underlying neuropsychological mechanisms and its neural basis have not been adequately investigated. Therefore, we investigated this topic via neuropsychological assessment and neuroimaging in a cross-sectional study.

METHODS

We recruited 71 individuals with cerebrovascular disease. The relationship between urinary incontinence and neuropsychological indices was investigated using simple linear regression analysis or Mann-Whitney U test, along with other explanatory variables, e.g., severity of overactive bladder. Variables with a p-value of <0.1 in the simple regression analysis were entered in the final multiple linear regression model to control for potential confounding factors. To carry out an in-depth examination of the neuroanatomical substrate for urinary incontinence, voxel-based lesion-behavior mapping was performed using MRIcron software.

RESULTS

Behavioral control deficits and severity of overactive bladder were closely related to severity of urinary incontinence. The voxel-based lesion-behavior mapping suggests a potential role for ventromedial prefrontal cortex lesioning in the severity of urinary incontinence, although this association is not statistically significant.

CONCLUSIONS

Post-stroke urinary incontinence is closely related to two factors: neurogenic overactive bladder, a physiological disinhibition of micturition reflex, and cognitive dysfunction, characterized by behavior control deficits.

Stroke classification and treatment support system artificial intelligence for usefulness of stroke diagnosis

Background and aims

It is important to diagnose cerebral infarction at an early stage and select an appropriate treatment method. The number of stroke-trained physicians is unevenly distributed; thus, a shortage of specialists is a major problem in some regions. In this retrospective design study, we tested whether an artificial intelligence (AI) we built using computer-aided detection/diagnosis may help medical physicians to classify stroke for the appropriate treatment.

Methods

To build the Stroke Classification and Treatment Support System AI, the clinical data of 231 hospitalized patients with ischemic stroke from January 2016 to December 2017 were used for training the AI. To verify the diagnostic accuracy, 151 patients who were admitted for stroke between January 2018 and December 2018 were also enrolled.

Results

By utilizing multimodal data, such as DWI and ADC map images, as well as patient examination data, we were able to construct an AI that can explain the analysis results with a small amount of training data. Furthermore, the AI was able to classify with high accuracy (Cohort 1, evaluation data 88.7%; Cohort 2, validation data 86.1%).

Conclusion

In recent years, the treatment options for cerebral infarction have increased in number and complexity, making it even more important to provide appropriate treatment according to the initial diagnosis. This system could be used for initial treatment to automatically diagnose and classify strokes in hospitals where stroke-trained physicians are not available and improve the prognosis of cerebral infarction.

Mapping spoken language and cognitive deficits in post-stroke aphasia

Aphasia is an acquired disorder caused by damage, most commonly due to stroke, to brain regions involved in speech and language. While language impairment is the defining symptom of aphasia, the co-occurrence of non-language cognitive deficits and their importance in predicting rehabilitation and recovery outcomes is well documented. However, people with aphasia (PWA) are rarely tested on higher-order cognitive functions, making it difficult for studies to associate these functions with a consistent lesion correlate. Broca's area is a particular brain region of interest that has long been implicated in speech and language production. Contrary to classic models of speech and language, cumulative evidence shows that Broca's area and surrounding regions in the left inferior frontal cortex (LIFC) are involved in, but not specific to, speech production. In this study we aimed to explore the brain-behaviour relationships between tests of cognitive skill and language abilities in thirty-six adults with long-term speech production deficits caused by post-stroke aphasia. Our findings suggest that non-linguistic cognitive functions, namely executive functions and verbal working memory, explain more of the behavioural variance in PWA than classical language models imply. Additionally, lesions to the LIFC, including Broca's area, were associated with non-linguistic executive (dys)function, suggesting that lesions to this area are associated with non-language-specific higher-order cognitive deficits in aphasia. Whether executive (dys)function - and its neural correlate in Broca's area - contributes directly to PWA's language production deficits or simply co-occurs with it, adding to communication difficulties, remains unclear. These findings support contemporary models of speech production that place language processing within the context of domain-general perception, action and conceptual knowledge. An understanding of the covariance between language and non-language deficits and their underlying neural correlates will inform better targeted aphasia treatment and outcomes.

Gamma knife capsulotomy for intractable OCD: Neuroimage analysis of lesion size, location, and clinical response

Obsessive-compulsive disorder (OCD) affects 2-3% of the population. One-third of patients are poorly responsive to conventional therapies, and for a subgroup, gamma knife capsulotomy (GKC) is an option. We examined lesion characteristics in patients previously treated with GKC through well-established programs in Providence, RI (Butler Hospital/Rhode Island Hospital/Alpert Medical School of Brown University) and São Paulo, Brazil (University of São Paolo). Lesions were traced on T1 images from 26 patients who had received GKC targeting the ventral half of the anterior limb of the internal capsule (ALIC), and the masks were transformed into MNI space. Voxel-wise lesion-symptom mapping was performed to assess the influence of lesion location on Y-BOCS ratings. General linear models were built to compare the relationship between lesion size/location along different axes of the ALIC and above or below-average change in Y-BOCS ratings. Sixty-nine percent of this sample were full responders (≥35% improvement in OCD). Lesion occurrence anywhere within the targeted region was associated with clinical improvement, but modeling results demonstrated that lesions occurring posteriorly (closer to the anterior commissure) and dorsally (closer to the mid-ALIC) were associated with the greatest Y-BOCS reduction. No association was found between Y-BOCS reduction and overall lesion volume. GKC remains an effective treatment for refractory OCD. Our data suggest that continuing to target the bottom half of the ALIC in the coronal plane is likely to provide the dorsal-ventral height required to achieve optimal outcomes, as it will cover the white matter pathways relevant to change. Further analysis of individual variability will be essential for improving targeting and clinical outcomes, and potentially further reducing the lesion size necessary for beneficial outcomes.

The elusive metric of lesion load

One of the widely used metrics in lesion-symptom mapping is lesion load that codes the amount of damage to a given brain region of interest. Lesion load aims to reduce the complex 3D lesion information into a feature that can reflect both site of damage, defined by the location of the region of interest, and size of damage within that region of interest. Basically, the process of estimation of lesion load converts a voxel-based lesion map into a region-based lesion map, with regions defined as atlas-based or data-driven spatial patterns. Here, after examining current definitions of lesion load, four methodological issues are discussed: (1) lesion load is agnostic to the location of damage within the region of interest, and it disregards damage outside the region of interest, (2) lesion load estimates are prone to errors introduced by the uncertainty in lesion delineation, spatial warping of the lesion/region, and binarization of the lesion/region, (3) lesion load calculation depends on brain parcellation selection, and (4) lesion load does not necessarily reflect a white matter disconnection. Overall, lesion load, when calculated in a robust way, can serve as a clinically-useful feature for explaining and predicting post-stroke outcome and recovery.

The Unresolved Methodological Challenge of Detecting Neuroplastic Changes in Astronauts

After completing a spaceflight, astronauts display a salient upward shift in the position of the brain within the skull, accompanied by a redistribution of cerebrospinal fluid. Magnetic resonance imaging studies have also reported local changes in brain volume following a spaceflight, which have been cautiously interpreted as a neuroplastic response to spaceflight. Here, we provide evidence that the grey matter volume changes seen in astronauts following spaceflight are contaminated by preprocessing errors exacerbated by the upwards shift of the brain within the skull. While it is expected that an astronaut's brain undergoes some neuroplastic adaptations during spaceflight, our findings suggest that the brain volume changes detected using standard processing pipelines for neuroimaging analyses could be contaminated by errors in identifying different tissue types (i.e., tissue segmentation). These errors may undermine the interpretation of such analyses as direct evidence of neuroplastic adaptation, and novel or alternate preprocessing or experimental paradigms are needed in order to resolve this important issue in space health research.

The multi-level classification network (MCN) with modified residual U-Net for ischemic stroke lesions segmentation from ATLAS

Ischemic and hemorrhagic strokes are two major types of internal brain injury. 3D brain MRI is suggested by neurologists to examine the brain. Manual examination of brain MRI is very sensitive and time-consuming task. However, automatic diagnosis can assist doctors in this regard. Anatomical Tracings of Lesions After Stroke (ATLAS) is publicly available dataset for research experiments. One of the major issues in medical imaging is class imbalance. Similarly, pixel representation of stroke lesion is less than 1% in ATLAS. Second major challenge in this dataset is inter-class similarity. A multi-level classification network (MCN) is proposed for segmentation of ischemic stroke lesions. MCN consists of three cascaded discrete networks. The first network designed to reduce the slice level class imbalance, where a classifier model is trained to extract the slices of stroke lesions from a whole brain MRI volume. The interclass similarity cause to produce false positives in segmented output. Therefore, all extracted stroke slices were divided into overlapping patches (64 × 64) and carried to the second network. The task associated with second network is to classify the patches comprises of stroke lesion. The third network is a 2D modified residual U-Net that segments out the stroke lesions from the patches extracted by the second network. MCN achieved 0.754 mean dice score on test dataset which is higher than the other state-of-the-art methods on the same dataset.

Application of Machine Learning Techniques for Characterization of Ischemic Stroke with MRI Images: A Review

Magnetic resonance imaging (MRI) is a standard tool for the diagnosis of stroke, but its manual interpretation by experts is arduous and time-consuming. Thus, there is a need for computer-aided-diagnosis (CAD) models for the automatic segmentation and classification of stroke on brain MRI. The heterogeneity of stroke pathogenesis, morphology, image acquisition modalities, sequences, and intralesional tissue signal intensity, as well as lesion-to-normal tissue contrast, pose significant challenges to the development of such systems. Machine learning (ML) is increasingly being used in predictive neuroimaging diagnosis and prognostication. This paper reviews image processing and machine learning techniques that have been applied to detect ischemic stroke on brain MRI, including details on image acquisition, pre-processing, techniques to segment, extraction of features, and classification into stroke types. The main objective of this work is to find the state-of-art machine learning techniques used to predict the ischemic stroke and their application in clinical set-up. The article selection is performed according to PRISMA guideline. The state-of-the-art on automated MRI stroke diagnosis, with a focus on machine learning, is discussed, along with its advantages and limitations. We found that the various machine learning models discussed in this article are able to detect the infarcts with an acceptable accuracy of 70–90%. However, no one has highlighted the time complexity to predict the stroke in the model developed, which is an important factor. The work concludes with proposals for future recommendations for building efficient and robust deep learning (DL) models for quantitative brain MRI analysis. In recent work, with the application of DL approaches, using large datasets to train the models has improved the detection accuracy and reduced computational complexity. We suggest that the design of a decision support system based on artificial intelligence (AI) and clinical data presenting symptoms is essential to support clinicians to accelerate diagnosis and timeous therapy in the emergency management of stroke.

Improving interobserver agreement and performance of deep learning models for segmenting acute ischemic stroke by combining DWI with optimized ADC thresholds

OBJECTIVES

To examine the role of ADC threshold on agreement across observers and deep learning models (DLMs) plus segmentation performance of DLMs for acute ischemic stroke (AIS).

METHODS

Twelve DLMs, which were trained on DWI-ADC-ADC combination from 76 patients with AIS using 6 different ADC thresholds with ground truth manually contoured by 2 observers, were tested by additional 67 patients in the same hospital and another 78 patients in another hospital. Agreement between observers and DLMs were evaluated by Bland-Altman plot and intraclass correlation coefficient (ICC). The similarity between ground truth (GT) defined by observers and between automatic segmentation performed by DLMs was evaluated by Dice similarity coefficient (DSC). Group comparison was performed using the Mann-Whitney U test. The relationship between the DSC and ADC threshold as well as AIS lesion size was evaluated by linear regression analysis. A p < .05 was considered statistically significant.

RESULTS

Excellent interobserver agreement and intraobserver repeatability in the manual segmentation (all ICC > 0.98, p < .001) were achieved. The 95% limit of agreement was reduced from 11.23 cm² for GT on DWI to 0.59 cm² for prediction at an ADC threshold of 0.6 × 10^-3 mm²/s combined with DWI. The segmentation performance of DLMs was improved with an overall DSC from 0.738 ± 0.214 on DWI to 0.971 ± 0.021 on an ADC threshold of 0.6 × 10^-3 mm²/s combined with DWI.

CONCLUSIONS

Combining an ADC threshold of 0.6 × 10^-3 mm²/s with DWI reduces interobserver and inter-DLM difference and achieves best segmentation performance of AIS lesions using DLMs.

KEY POINTS

• Higher Dice similarity coefficient (DSC) in predicting acute ischemic stroke lesions was achieved by ADC thresholds combined with DWI than by DWI alone (all p < .05). • DSC had a negative association with the ADC threshold in most sizes, both hospitals, and both observers (most p < .05) and a positive association with the stroke size in all ADC thresholds, both hospitals, and both observers (all p < .001). • An ADC threshold of 0.6 × 10^-3 mm²/s eliminated the difference of DSC at any stroke size between observers or between hospitals (p = .07 to > .99).

Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.

Emerging role of artificial intelligence in stroke imaging

Introduction: The recognition and therapy of patients with stroke is becoming progressively intricate as additional treatment choices become accessible and new associations between disease characteristics and treatment response are incessantly uncovered. Therefore, clinicians must regularly learn new skill, stay up to date with the literature and integrate advances into daily practice. The application of artificial intelligence (AI) to assist clinical decision making could diminish inter-rater variation in routine clinical practice and accelerate the mining of vital data that could expand recognition of patients with stroke, forecast of treatment responses and patient outcomes.Areas covered: In this review, the authors provide an up-to-date review of AI in stroke, analyzing the latest papers on this subject. These have been divided in two main groups: stroke diagnosis and outcome prediction.Expert opinion: The highest value of AI is its capability to merge, select and condense a large amount of clinical and imaging features of a single patient and to associate these with fitted models that have gone through robust assessment and optimization with large cohorts of data to support clinical decision making.

Ischemic infarct detection, localization, and segmentation in noncontrast CT human brain scans: review of automated methods

Noncontrast Computed Tomography (NCCT) of the brain has been the first-line diagnosis for emergency evaluation of acute stroke, so a rapid and automated detection, localization, and/or segmentation of ischemic lesions is of great importance. We provide the state-of-the-art review of methods for automated detection, localization, and/or segmentation of ischemic lesions on NCCT in human brain scans along with their comparison, evaluation, and classification. Twenty-two methods are (1) reviewed and evaluated; (2) grouped into image processing and analysis-based methods (11 methods), brain atlas-based methods (two methods), intensity template-based methods (1 method), Stroke Imaging Marker-based methods (two methods), and Artificial Intelligence-based methods (six methods); and (3) properties of these groups of methods are characterized. A new method classification scheme is proposed as a 2 × 2 matrix with local versus global processing and analysis, and density versus spatial sampling. Future studies are necessary to develop more efficient methods directed toward deep learning methods as well as combining the global methods with a high sampling both in space and density for the merged radiologic and neurologic data.

Artificial intelligence for decision support in acute stroke - current roles and potential

The identification and treatment of patients with stroke is becoming increasingly complex as more treatment options become available and new relationships between disease features and treatment response are continually discovered. Consequently, clinicians must constantly learn new skills (such as clinical evaluations or image interpretation), stay up to date with the literature and incorporate advances into everyday practice. The use of artificial intelligence (AI) to support clinical decision making could reduce inter-rater variation in routine clinical practice and facilitate the extraction of vital information that could improve identification of patients with stroke, prediction of treatment responses and patient outcomes. Such support systems would be ideal for centres that deal with few patients with stroke or for regional hubs, and could assist informed discussions with the patients and their families. Moreover, the use of AI for image processing and interpretation in stroke could provide any clinician with an imaging assessment equivalent to that of an expert. However, any AI-based decision support system should allow for expert clinician interaction to enable identification of errors (for example, in automated image processing). In this Review, we discuss the increasing importance of imaging in stroke management before exploring the potential and pitfalls of AI-assisted treatment decision support in acute stroke.

Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction

Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-weighted data using data of patients with head and neck tumors; 18 patients with head and neck tumors underwent multiparametric magnetic resonance imaging, including T2w, T1w, T2*, perfusion (k_trans), and apparent diffusion coefficient (ADC) measurements. Owing to strong geometrical distortions in diffusion-weighted echo planar imaging in the head and neck region, ADC data were additionally distortion corrected. To investigate the influence of geometrical correction, first 14 CNNs were trained on data with geometrically corrected ADC and another 14 CNNs were trained using data without the correction on different samples of 13 patients for training and 4 patients for validation each. The different sets were each trained from scratch using randomly initialized weights, but the training data distributions were pairwise equal for corrected and uncorrected data. Segmentation performance was evaluated on the remaining 1 test-patient for each of the 14 sets. The CNN segmentation performance scored an average Dice coefficient of 0.40 ± 0.18 for data including distortion-corrected ADC and 0.37 ± 0.21 for uncorrected data. Paired t test revealed that the performance was not significantly different (P = .313). Thus, geometrical distortion on diffusion-weighted imaging data in patients with head and neck tumor does not significantly impair CNN segmentation performance in use.

Accuracy and practical aspects of semi- and fully automatic segmentation methods for resected brain areas

Purpose

Precise segmentation of brain lesions is essential for neurological research. Specifically, resection volume estimates can aid in the assessment of residual postoperative tissue, e.g. following surgery for glioma. Furthermore, behavioral lesion-symptom mapping in epilepsy relies on accurate delineation of surgical lesions. We sought to determine whether semi- and fully automatic segmentation methods can be applied to resected brain areas and which approach provides the most accurate and cost-efficient results.

Methods

We compared a semi-automatic (ITK-SNAP) with a fully automatic (lesion_GNB) method for segmentation of resected brain areas in terms of accuracy with manual segmentation serving as reference. Additionally, we evaluated processing times of all three methods. We used T1w, MRI-data of epilepsy patients (n = 27; 11 m; mean age 39 years, range 16–69) who underwent temporal lobe resections (17 left).

Results

The semi-automatic approach yielded superior accuracy (p < 0.001) with a median Dice similarity coefficient (mDSC) of 0.78 and a median average Hausdorff distance (maHD) of 0.44 compared with the fully automatic approach (mDSC 0.58, maHD 1.32). There was no significant difference between the median percent volume difference of the two approaches (p > 0.05). Manual segmentation required more human input (30.41 min/subject) and therefore inferring significantly higher costs than semi- (3.27 min/subject) or fully automatic approaches (labor and cost approaching zero).

Conclusion

Semi-automatic segmentation offers the most accurate results in resected brain areas with a moderate amount of human input, thus representing a viable alternative compared with manual segmentation, especially for studies with large patient cohorts.

Automatic post-stroke lesion segmentation on MR images using 3D residual convolutional neural network

In this paper, we demonstrate the feasibility and performance of deep residual neural networks for volumetric segmentation of irreversibly damaged brain tissue lesions on T1-weighted MRI scans for chronic stroke patients. A total of 239 T1-weighted MRI scans of chronic ischemic stroke patients from a public dataset were retrospectively analyzed by 3D deep convolutional segmentation models with residual learning, using a novel zoom-in&out strategy. Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance (HD) of the identified lesions were measured by using manual tracing of lesions as the reference standard. Bootstrapping was employed for all metrics to estimate 95% confidence intervals. The models were assessed on a test set of 31 scans. The average DSC was 0.64 (0.51-0.76) with a median of 0.78. ASSD and HD were 3.6 mm (1.7-6.2 mm) and 20.4 mm (10.0-33.3 mm), respectively. The latest deep learning architecture and techniques were applied with 3D segmentation on MRI scans and demonstrated effectiveness for volumetric segmentation of chronic ischemic stroke lesions.

Investigating the effect of changing parameters when building prediction models for post-stroke aphasia

Neuroimaging has radically improved our understanding of how speech and language abilities map to the brain in normal and impaired participants, including the diverse, graded variations observed in post-stroke aphasia. A handful of studies have begun to explore the reverse inference: creating brain-to-behaviour prediction models. In this study, we explored the effect of three critical parameters on model performance: (1) brain partitions as predictive features, (2) combination of multimodal neuroimaging and (3) type of machine learning algorithms. We explored the influence of these factors while predicting four principal dimensions of language and cognition variation in post-stroke aphasia. Across all four behavioural dimensions, we consistently found that prediction models derived from diffusion-weighted data did not improve performance over models using structural measures extracted from T1 scans. Our results provide a set of principles to guide future work aiming to predict outcomes in neurological patients from brain imaging data.

A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images

Automatic identification of brain lesions from magnetic resonance imaging (MRI) scans of stroke survivors would be a useful aid in patient diagnosis and treatment planning. It would also greatly facilitate the study of brain-behavior relationships by eliminating the laborious step of having a human expert manually segment the lesion on each brain scan. We propose a multi-modal multi-path convolutional neural network system for automating stroke lesion segmentation. Our system has nine end-to-end UNets that take as input 2-dimensional (2D) slices and examines all three planes with three different normalizations. Outputs from these nine total paths are concatenated into a 3D volume that is then passed to a 3D convolutional neural network to output a final lesion mask. We trained and tested our method on datasets from three sources: Medical College of Wisconsin (MCW), Kessler Foundation (KF), and the publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset. To promote wide applicability, lesions were included from both subacute (1 to 5 weeks) and chronic ( >  3 months) phases post stroke, and were of both hemorrhagic and ischemic etiology. Cross-study validation results (with independent training and validation datasets) were obtained to compare with previous methods based on naive Bayes, random forests, and three recently published convolutional neural networks. Model performance was quantified in terms of the Dice coefficient, a measure of spatial overlap between the model-identified lesion and the human expert-identified lesion, where 0 is no overlap and 1 is complete overlap. Training on the KF and MCW images and testing on the ATLAS images yielded a mean Dice coefficient of 0.54. This was reliably better than the next best previous model, UNet, at 0.47. Reversing the train and test datasets yields a mean Dice of 0.47 on KF and MCW images, whereas the next best UNet reaches 0.45. With all three datasets combined, the current system compared to previous methods also attained a reliably higher cross-validation accuracy. It also achieved high Dice values for many smaller lesions that existing methods have difficulty identifying. Overall, our system is a clear improvement over previous methods for automating stroke lesion segmentation, bringing us an important step closer to the inter-rater accuracy level of human experts.

Automated Detection of Brain Stroke in MRI with Hybrid Fuzzy C-Means Clustering and Random Forest Classifier

Neuroimaging investigation is an essential parameter to detect infarct lesion in stroke patients. Precise detection of brain lesions is an important task related to impaired behavior. In this paper, we aimed to develop an automatic method to segment and classify infarct lesion in diffusion-weighted imaging (DWI) of brain MRI. The method includes hybrid fuzzy [Formula: see text]-means (HFCM) clustering in which the structure of [Formula: see text]-means clustering is modified with rough sets and fuzzy sets to improve the segmentation performance with self-adjusted intensity thresholds. Quantitative evaluation was carried out on 128 MRI slices of brain image collected from ischemic stroke patients at the Department of Radiology, IMS and SUM Hospital, Bhubaneswar. The informative statistical features have been extracted using gray-level co-occurrence matrix (GLCM) and used to classify the types of stroke infarct according to the Oxfordshire Community Stroke Project (OCSP) classification. The parameters such as accuracy, Dice similarity index (DSI) and Jaccard index (JI) were utilized to evaluate the effectiveness of the proposed method in detecting the stroke lesions. The segmentation method achieved the average accuracy, DSI and JI of 96.8%, 95.8% and 92.2%, respectively, in support vector machine (SVM) classifier. The obtained results are higher in terms of random forest (RF) classification. With a high Dice coefficient of 0.958 and other evaluated parameters, the proposed method outperforms earlier published results.

Whole volume brain extraction for multi-centre, multi-disease FLAIR MRI datasets

Automatic segmentation of the brain from magnetic resonance images (MRI) is a fundamental step in many neuroimaging processing frameworks. There are mature technologies for this task for T1- and T2-weighted MRI; however, a widely-accepted brain extraction method for Fluid-Attenuated Inversion Recovery (FLAIR) MRI has yet to be established. FLAIR MRI are becoming increasingly important for the analysis of neurodegenerative diseases and tools developed for this sequence would have clinical value. To maximize translation opportunities and for large scale research studies, algorithms for brain extraction in FLAIR MRI should generalize to multi-centre (MC) data. To this end, this work proposes a fully automated, whole volume brain extraction methodology for MC FLAIR MRI datasets. The framework is built using a novel standardization framework which reduces acquisition artifacts, standardizes the intensities of tissues and normalizes the spatial coordinates of brain tissue across MC datasets. Using the standardized datasets, an intuitive set of features based on intensity, spatial location and gradients are extracted and classified using a random forest (RF) classifier to segment the brain tissue class. A series of experiments were conducted to optimize classifier parameters, and to determine segmentation accuracy for standardized and unstandardized (original) data, as a function of scanner vendor, feature type and disease type. The models are trained, tested and validated on 156 image volumes (∼8000 image slices) from two multi-centre, multi-disease datasets, acquired with varying imaging parameters from 30 centres and three scanner vendors. The image datasets, denoted as CAIN and ADNI for vascular and dementia disease, respectively, represent a diverse collection of MC data to test the generalization capabilities of the proposed design. Results demonstrate the importance of standardization for segmentation of MC data, as models trained on standardized data yielded a drastic improvement in brain extraction accuracy compared to the original, unstandardized data (CAIN: DSC = 91% and ADNI: DSC = 86% vs. CAIN: 78% and ADNI: 65%). It was also found that models created from one scanner vendor based on unstandardized data yielded poor segmentation results in data acquired from other scanner vendors, which was improved through standardization. These results demonstrate that to create consistency in segmentations from multi-institutional datasets it is paramount that MC variability be mitigated to improve stability and to ensure generalization of machine learning algorithms for MRI.

Neural correlates of differential finger gesture imitation deficits in left hemisphere stroke

Behavioural studies in apraxic patients revealed dissociations between the processing of meaningful (MF) and meaningless (ML) gestures. Consequently, the existence of two differential neural mechanisms for the imitation of either gesture type has been postulated. While the indirect (semantic) route exclusively enables the imitation of MF gestures, the direct route can be used for the imitation of any gesture type, irrespective of meaning, and thus especially for ML gestures. Concerning neural correlates, it is debated which of the visuo-motor streams (i.e., the ventral steam, the ventro-dorsal stream, or the dorso-dorsal stream) supports the postulated indirect and direct imitation routes. To probe the hypotheses that regions of the dorso-dorsal stream are involved differentially in the imitation of ML gestures and that regions of the ventro-dorsal stream are involved differentially in the imitation of MF gestures, we analysed behavioural (imitation of MF and ML finger gestures) and lesion data of 293 patients with a left hemisphere (LH) stroke. Confirming previous work, the current sample of LH stroke patients imitated MF finger gestures better than ML finger gestures. The analysis using voxel-based lesion symptom mapping (VLSM) revealed that LH damage to dorso-dorsal stream areas was associated with an impaired imitation of ML finger gestures, whereas damage to ventro-dorsal regions was associated with a deficient imitation of MF finger gestures. Accordingly, the analyses of the imitation of visually uniform and thus highly comparable MF and ML finger gestures support the dual-route model for gesture imitation at the behavioural and lesion level in a substantial patient sample. Furthermore, the data show that the direct route for ML finger gesture imitation depends on the dorso-dorsal visuo-motor stream while the indirect route for MF finger gesture imitation is related to regions of the ventro-dorsal visuo-motor stream.

Deficient allo-centric visuospatial processing contributes to apraxic deficits in sub-acute right hemisphere stroke

While visuospatial deficits are well-characterized cognitive sequelae of right hemisphere (RH) stroke, apraxic deficits in RH stroke remain poorly understood. Likewise, very little is known about the association between apraxic and visuospatial deficits in RH stroke or about the putative common or differential pathophysiology underlying these deficits. Therefore, we examined the behavioural and lesion patterns of apraxic deficits (pantomime of object use and bucco-facial imitation) and visuospatial deficits (line bisection and letter cancellation tasks) in 50 sub-acute RH stroke patients. Using principal component analysis (PCA), we characterized the relationship between the two deficits. We hypothesized that any interaction of these neuropsychological measures may be influenced by the demands of ego-centric/space-based and/or allo-centric/object-based processing. Contralesional visuospatial deficits were common in our clinically representative patient sample, affecting more than half of RH stroke patients. Furthermore, about one-third of all patients demonstrated apraxic deficits. PCA revealed that pantomiming and the imitation of bucco-facial gestures loaded clearly on a first component (PCA1), while letter cancellation loaded heavily on a second component (PCA2). For line bisection, overall mean deviation loaded on PCA1, while the difference between the mean deviations in contra- versus ipsilesional space loaded on PCA2. These results suggest that PCA1 represents allo-centric/object-based processing and PCA2 ego-centric/space-based processing. This interpretation was corroborated by the statistical lesion analyses with the component scores. Data suggest that disturbed allo-centric/object-based processing contributes to apraxic pantomime and imitation deficits in (sub-acute) RH stroke.

Automated approach for detection of ischemic stroke using Delaunay Triangulation in brain MRI images

It is difficult to develop an accurate algorithm to detect the stroke lesions using magnetic resonance imaging (MRI) images due to variation in different lesion sizes, variation in morphological structure, and similarity in intensity of lesion with normal brain in three types of stroke, namely partial anterior circulation syndrome (PACS), lacunar syndrome (LACS) and total anterior circulation stroke (TACS). In this paper, we have integrated the advantages of Delaunay triangulation (DT) and fractional order Darwinian particle swarm optimization (FODPSO), called DT-FODPSO technique for automatic segmentation of the structure of the stroke lesion. The approach was validated on 192 MRI images obtained from different stroke subjects. Statistical and morphological features were extracted and classified according to the Oxfordshire community stroke project (OCSP) using support vector machine (SVM) and random forest (RF) classifiers. The method effectively detected the stroke lesions and achieved promising results with an average sensitivity of 0.93, accuracy of 0.95, JI of 0.89 and Dice similarity index of 0.93 using RF classifier. These promising results indicates the DT based optimized approach is efficient in detecting ischemic stroke and it can aid the neuro-radiologists to validate their routine screening.

Case-control comparison brain lesion segmentation for early infarct detection

Computed Tomography (CT) images are widely used for the identification of abnormal brain tissues following infarct and hemorrhage of a stroke. The treatment of this medical condition mainly depends on doctors' experience. While manual lesion delineation by medical doctors is currently considered as the standard approach, it is time-consuming and dependent on each doctor's expertise and experience. In this study, a case-control comparison brain lesion segmentation (CCBLS) method is proposed to segment the region pertaining to brain injury by comparing the voxel intensity of CT images between control subjects and stroke patients. The method is able to segment the brain lesion from the stacked CT images automatically without prior knowledge of the location or the presence of the lesion. The aim is to reduce medical doctors' burden and assist them in making an accurate diagnosis. A case study with 300 sets of CT images from control subjects and stroke patients is conducted. Comparing with other existing methods, the outcome ascertains the effectiveness of the proposed method in detecting brain infarct of stroke patients.

Mapping the intersection of language and reading: the neural bases of the primary systems hypothesis

The primary systems framework has been used to relate behavioural performance across many different language activities to the status of core underpinning domain-general cognitive systems. This study provided the first quantitative investigation of this account at both behavioural and neural levels in a group of patients with chronic post-stroke aphasia. Principal components analysis was used to distil orthogonal measures of phonological and semantic processing, which were then related to reading performance and the underlying lesion distributions using voxel-based correlational methodology. Concrete word reading involved both a ventral semantic pathway, and inferior and anterior aspects of the dorsal phonological pathway. Abstract word reading overlapped with the ventral semantic pathway but also drew more extensively on the superior and posterior aspects of the dorsal phonological pathway. Nonword reading was related to phonological processing along the dorsal pathway and was also supported by a more superior set of regions previously associated with speech motor output. The use of continuous measures of behavioural performance and neural integrity allowed us to elucidate for the first time both the lesion and behavioural correlates for the semantic and phonological components of the primary systems hypothesis and to extend these by identifying the importance of an additional dorsal speech motor output system. These results provide a target for future neuroanatomically constrained computational models of reading.

SEGMENTATION AND CLASSIFICATION OF ISCHEMIC STROKE USING OPTIMIZED FEATURES IN BRAIN MRI

Detection of ischemic stroke using brain magnetic resonance imaging (MRI) images is vital and a challenging task in clinical practice. We propose a novel method based on optimization technique to identify stroke lesion in diffusion-weighted imaging (DWI) MRI sequences of the brain. The algorithm was tested in a specific slice having large area of stroke region from a series of 292 real-time images obtained from different stroke affected subjects from IMS and SUM Hospital. The proposed method consists of pre-processing, segmentation, extraction of important features and classification of stroke type. The particle swarm optimization (PSO) and Darwinian particle swarm optimization (DPSO) algorithms were applied in segmenting the stroke lesions. The important features were extracted with the gray-level co-occurrence matrix (GLCM) algorithm and in decision making process, the feature set is classified into three types of stroke according to The Oxfordshire Community Stroke Project (OCSP) classification using support vector machine (SVM) classifier. The lesion area was segmented effectively with DPSO process with classification weighted accuracy of 90.23%, which is higher than PSO method having weighted accuracy of 85.19%. Similarly, the values of different measured parameters were high in DPSO technique, the computational time was also higher in DPSO method for segmenting the stroke lesions. These results confirm that the DPSO-based approach with SVM classifier is an effective way to identify the decision making process of ischemic stroke lesion in MRI images of the brain.

Unification of behavioural, computational and neural accounts of word production errors in post-stroke aphasia

Neuropsychological assessment, brain imaging and computational modelling have augmented our understanding of the multifaceted functional deficits in people with language disorders after stroke. Despite the volume of research using each technique, no studies have attempted to assimilate all three approaches in order to generate a unified behavioural-computational-neural model of post-stroke aphasia. The present study included data from 53 participants with chronic post-stroke aphasia and merged: aphasiological profiles based on a detailed neuropsychological assessment battery which was analysed with principal component and correlational analyses; measures of the impairment taken from Dell's computational model of word production; and the neural correlates of both behavioural and computational accounts analysed by voxel-based correlational methodology. As a result, all three strands coincide with the separation of semantic and phonological stages of aphasic naming, revealing the prominence of these dimensions for the explanation of aphasic performance. Over and above three previously described principal components (phonological ability, semantic ability, executive-demand), we observed auditory working memory as a novel factor. While the phonological Dell parameter was uniquely related to phonological errors/factor, the semantic parameter was less clear-cut, being related to both semantic errors and omissions, and loading heavily with semantic ability and auditory working memory factors. The close relationship between the semantic Dell parameter and omission errors recurred in their high lesion-correlate overlap in the anterior middle temporal gyrus. In addition, the simultaneous overlap of the lesion correlate of omission errors with more dorsal temporal regions, associated with the phonological parameter, highlights the multiple drivers that underpin this error type. The novel auditory working memory factor was located along left superior/middle temporal gyrus and ventral inferior parietal lobe. The present study fused computational, behavioural and neural data to gain comprehensive insights into the nature of the multifaceted presentations in aphasia. Our unified account contributes enhanced knowledge on dimensions explaining chronic post-stroke aphasia, the variety of factors affecting inter-individual variability, the neural basis of performance, and potential clinical implications.

Predicting the pattern and severity of chronic post-stroke language deficits from functionally-partitioned structural lesions

There is an ever-increasing wealth of knowledge arising from basic cognitive and clinical neuroscience on how speech and language capabilities are organised in the brain. It is, therefore, timely to use this accumulated knowledge and expertise to address critical research challenges, including the ability to predict the pattern and level of language deficits found in aphasic patients (a third of all stroke cases). Previous studies have mainly focused on discriminating between broad aphasia dichotomies from purely anatomically-defined lesion information. In the current study, we developed and assessed a novel approach in which core language areas were mapped using principal component analysis in combination with correlational lesion mapping and the resultant ‘functionally-partitioned’ lesion maps were used to predict a battery of 21 individual test scores as well as aphasia subtype for 70 patients with chronic post-stroke aphasia. Specifically, we used lesion information to predict behavioural scores in regression models (cross-validated using 5-folds). The winning model was identified through the adjusted R² (model fit to data) and performance in predicting holdout folds (generalisation to new cases). We also used logistic regression to predict fluent/non-fluent status and aphasia subtype. Functionally-partitioned models generally outperformed other models at predicting individual tests, fluency status and aphasia subtype.

•

Predict the pattern and level of language deficits found in chronic aphasic patients

•

Use principal component analysis to identify functional lesion maps

•

Functionally-partitioned lesion maps used as predictor variables instead of lesion volume

•

Functionally-partitioned lesion model plus age produced the best regression model

•

Model can successfully predict fluent/non-fluent types and aphasia classification

Noun and verb processing in aphasia: Behavioural profiles and neural correlates

The behavioural and neural processes underpinning different word classes, particularly nouns and verbs, have been a long-standing area of interest in psycholinguistic, neuropsychology and aphasiology research. This topic has theoretical implications concerning the organisation of the language system, as well as clinical consequences related to the management of patients with language deficits. Research findings, however, have diverged widely, which might, in part, reflect methodological differences, particularly related to controlling the psycholinguistic variations between nouns and verbs. The first aim of this study, therefore, was to develop a set of neuropsychological tests that assessed single-word production and comprehension with a matched set of nouns and verbs. Secondly, the behavioural profiles and neural correlates of noun and verb processing were explored, based on these novel tests, in a relatively large cohort of 48 patients with chronic post-stroke aphasia. A data-driven approach, principal component analysis (PCA), was also used to determine how noun and verb production and comprehension were related to the patients' underlying fundamental language domains. The results revealed no performance differences between noun and verb production and comprehension once matched on multiple psycholinguistic features including, most critically, imageability. Interestingly, the noun-verb differences found in previous studies were replicated in this study once un-matched materials were used. Lesion-symptom mapping revealed overlapping neural correlates of noun and verb processing along left temporal and parietal regions. These findings support the view that the neural representation of noun and verb processing at single-word level are jointly-supported by distributed cortical regions. The PCA generated five fundamental language and cognitive components of aphasia: phonological production, phonological recognition, semantics, fluency, and executive function. Consistent with the behavioural analyses and lesion-symptom mapping results, both noun and verb processing loaded on common underlying language domains: phonological production and semantics. The neural correlates of these five principal components aligned with existing models of language and the regions implicated by other techniques such as functional neuroimaging and neuro-stimulation.

Triangulation of language-cognitive impairments, naming errors and their neural bases post-stroke

In order to gain a better understanding of aphasia one must consider the complex combinations of language impairments along with the pattern of paraphasias. Despite the fact that both deficits and paraphasias feature in diagnostic criteria, most research has focused only on the lesion correlates of language deficits, with minimal attention on the pattern of patients' paraphasias. In this study, we used a data-driven approach (principal component analysis - PCA) to fuse patient impairments and their pattern of errors into one unified model of chronic post-stroke aphasia. This model was subsequently mapped onto the patients' lesion profiles to generate the triangulation of language-cognitive impairments, naming errors and their neural correlates. Specifically, we established the pattern of co-occurrence between fifteen error types, which avoids focussing on a subset of errors or the use of experimenter-derived methods to combine across error types. We obtained five principal components underlying the patients' errors: omission errors; semantically-related responses; phonologically-related responses; dysfluent responses; and a combination of circumlocutions with mixed errors. In the second step, we aligned these paraphasia-related principal components with the patients' performance on a detailed language and cognitive assessment battery, utilising an additional PCA. This omnibus PCA revealed seven unique fused impairment-paraphasia factors: output phonology; semantics; phonological working memory; speech quanta; executive-cognitive skill; phonological (input) discrimination; and the production of circumlocution errors. In doing so we were able to resolve the complex relationships between error types and impairments. Some are relatively straightforward: circumlocution errors formed their own independent factor; there was a one-to-one mapping for phonological errors with expressive phonological abilities and for dysfluent errors with speech fluency. In contrast, omission-type errors loaded across both semantic and phonological working memory factors, whilst semantically-related errors had the most complex relationship by loading across four factors (phonological ability, speech quanta, executive-cognitive skills and circumlocution-type errors). Three components had unique lesion correlates: phonological working memory with the primary auditory region; semantics with the anterior temporal region; and fluency with the pre-central gyrus, converging with existing literature. In conclusion, the data-driven approach allowed derivation of the triangulation of deficits, error types and lesion correlates in post-stroke aphasia.

•

Using principal component analysis to identify structure in naming errors.

•

Determining the relationship between language impairments and naming errors.

•

Identifying neural correlates of behavioural deficits in performance and errors.

•

Seven independent factors identified to describe performance and error pattern.

•

Phonological working memory, semantic skill and speech quanta had lesion correlates.

Linking left hemispheric tissue preservation to fMRI language task activation in chronic stroke patients

The preservation of near-typical function in distributed brain networks is associated with less severe deficits in chronic stroke patients. However, it remains unclear how task-evoked responses in networks that support complex cognitive functions such as semantic processing relate to the post-stroke brain anatomy. Here, we used recently developed methods for the analysis of multimodal MRI data to investigate the relationship between regional tissue concentration and functional MRI activation evoked during auditory semantic decisions in a sample of 43 chronic left hemispheric stroke patients and 43 age, handedness, and sex-matched controls. Our analyses revealed that closer-to-normal levels of tissue concentration in left temporo-parietal cortex and the underlying white matter correlated with the level of task-evoked activation in distributed regions associated with the semantic network. This association was not attributable to the effects of left hemispheric lesion or brain volumes, and similar results were obtained when using explicit lesion data. Left temporo-parietal tissue concentration and the associated task-evoked activations predicted patient performance on the in-scanner task, and also predicted patient performance on out-of-scanner naming and verbal fluency tasks. Exploratory analyses using the average HCP-842 tractography dataset revealed the presence of fronto-temporal, fronto-parietal, and temporo-parietal semantic network connections in the locations where tissue concentration was found to correlate with task-evoked activation in the semantic network. In summary, our results link the preservation of left posterior temporo-parietal structures with the preservation of task-evoked semantic network function in chronic left hemispheric stroke patients. Speculatively, this relationship may reflect the status of posterior temporo-parietal areas as cortical and white matter convergence zones that support coordinated processing in the distributed semantic network. Damage to these regions may contribute to atypical task-evoked responses during semantic processing in chronic stroke patients.

A hitchhiker's guide to lesion-behaviour mapping

Lesion-behaviour mapping is an influential and popular approach to anatomically localise cognitive brain functions in the human brain. Multiple considerations, ranging from patient selection, assessment of lesion location and patient behaviour, spatial normalisation, statistical testing, to the anatomical interpretation of obtained results, are necessary to optimize a lesion-behaviour mapping study and arrive at meaningful conclusions. Here, we provide a hitchhiker's guide, giving practical guidelines and references for each step of the typical lesion-behaviour mapping study pipeline.

Strength of Temporal White Matter Pathways Predicts Semantic Learning

Learning the associations between words and meanings is a fundamental human ability. Although the language network is cortically well defined, the role of the white matter pathways supporting novel word-to-meaning mappings remains unclear. Here, by using contextual and cross-situational word learning, we tested whether learning the meaning of a new word is related to the integrity of the language-related white matter pathways in 40 adults (18 women). The arcuate, uncinate, inferior-fronto-occipital and inferior-longitudinal fasciculi were virtually dissected using manual and automatic deterministic fiber tracking. Critically, the automatic method allowed assessing the white matter microstructure along the tract. Results demonstrate that the microstructural properties of the left inferior-longitudinal fasciculus predict contextual learning, whereas the left uncinate was associated with cross-situational learning. In addition, we identified regions of special importance within these pathways: the posterior middle temporal gyrus, thought to serve as a lexical interface and specifically related to contextual learning; the anterior temporal lobe, known to be an amodal hub for semantic processing and related to cross-situational learning; and the white matter near the hippocampus, a structure fundamental for the initial stages of new-word learning and, remarkably, related to both types of word learning. No significant associations were found for the inferior-fronto-occipital fasciculus or the arcuate. While previous results suggest that learning new phonological word forms is mediated by the arcuate fasciculus, these findings show that the temporal pathways are the crucial neural substrate supporting one of the most striking human abilities: our capacity to identify correct associations between words and meanings under referential indeterminacy.SIGNIFICANCE STATEMENT The language-processing network is cortically (i.e., gray matter) well defined. However, the role of the white matter pathways that support novel word learning within this network remains unclear. In this work, we dissected language-related (arcuate, uncinate, inferior-fronto-occipital, and inferior-longitudinal) fasciculi using manual and automatic tracking. We found the left inferior-longitudinal fasciculus to be predictive of word-learning success in two word-to-meaning tasks: contextual and cross-situational learning paradigms. The left uncinate was predictive of cross-situational word learning. No significant correlations were found for the arcuate or the inferior-fronto-occipital fasciculus. While previous results showed that learning new phonological word forms is supported by the arcuate fasciculus, these findings demonstrate that learning new word-to-meaning associations is mainly dependent on temporal white matter pathways.

Deep into the Brain: Artificial Intelligence in Stroke Imaging

Artificial intelligence (AI), a computer system aiming to mimic human intelligence, is gaining increasing interest and is being incorporated into many fields, including medicine. Stroke medicine is one such area of application of AI, for improving the accuracy of diagnosis and the quality of patient care. For stroke management, adequate analysis of stroke imaging is crucial. Recently, AI techniques have been applied to decipher the data from stroke imaging and have demonstrated some promising results. In the very near future, such AI techniques may play a pivotal role in determining the therapeutic methods and predicting the prognosis for stroke patients in an individualized manner. In this review, we offer a glimpse at the use of AI in stroke imaging, specifically focusing on its technical principles, clinical application, and future perspectives.

Neuropsychology and cognitive neuroscience in the fMRI era: A recapitulation of localizationist and connectionist views

OBJECTIVE

We highlight the past 25 years of cognitive neuroscience and neuropsychology, focusing on the impact to the field of the introduction in 1992 of functional MRI (fMRI).

METHOD

We reviewed the past 25 years of literature in cognitive neuroscience and neuropsychology, focusing on the relation and interplay of fMRI studies and studies utilizing the "lesion method" in human participants with focal brain damage.

RESULTS

Our review highlights the state of localist/connectionist research debates in cognitive neuroscience and neuropsychology circa 1992, and details how the introduction of fMRI into the field at that time catalyzed a new wave of efforts to map complex human behavior to specific brain regions. This, in turn, eventually evolved into many studies that focused on networks and connections between brain areas, culminating in recent years with large-scale investigations such as the Human Connectome Project.

CONCLUSIONS

We argue that throughout the past 25 years, neuropsychology-and more precisely, the "lesion method" in humans-has continued to play a critical role in arbitrating conclusions and theories derived from inferred patterns of local brain activity or wide-spread connectivity from functional imaging approaches. We conclude by highlighting the future for neuropsychology in the context of an increasingly complex methodological armamentarium. (PsycINFO Database Record

Semantic memory deficits are associated with pica in individuals with acquired brain injury

Although pica is one of the most prominent signs in individuals with severe cognitive impairment, the mechanisms and neural basis for pica have not been well elucidated. To address this issue, patients with acquired brain injury who showed pica and hyperorality were investigated. Eleven patients with pica, i.e., individuals who eat non-food items, and eight patients with hyperorality but who never eat non-food items were recruited. The cognitive and behavioral assessments and neural substrates of the two groups were compared. For basic cognitive and behavioral functions, two kinds of mental state examination-the mini-mental state examination and the new clinical scale for rating of mental states of the elderly-were administered. For pica-related behavioral features, frontal release signs, semantic memory deficits, and changes in eating behaviors were compared. Compared with the hyperorality group, the pica group had more severe semantic memory deficits and fewer frontal release signs, whereas there was no significant difference in changes in eating behaviors. Individuals in the pica group always had a lesion in the posterior part of the middle temporal gyrus. These findings suggest that semantic memory deficits following temporal lobe damage are associated with pica.

Computer-assisted delineation of cerebral infarct from diffusion-weighted MRI using Gaussian mixture model

PURPOSE

Diffusion-weighted imaging (DWI) is a widely used medical imaging modality for diagnosis and monitoring of cerebral stroke. The identification of exact location of stroke lesion helps in perceiving its characteristics, an essential part of diagnosis and treatment planning. This task is challenging due to the typical shape of the stroke lesion. This paper proposes an efficient method for computer-aided delineation of stroke lesions from DWI images.

METHOD

Proposed methodology comprises of three steps. At the initial step, image contrast has been improved by applying fuzzy intensifier leading to the better visual quality of the stroke lesion. In the following step, a two-class (stroke lesion area vs. non-stroke lesion area) segmentation technique based on Gaussian mixture model has been designed for the localization of stroke lesion. To eliminate the artifacts which would appear during segmentation process, a binary morphological post-processing through area operator has been defined for exact delineation of the lesion area.

RESULT

The performance of the proposed methodology has been compared with the manually delineated images (ground truth) obtained from different experts, individually. Quantitative evaluation with respect to various performance measures (such as dice coefficient, Jaccard score, and correlation coefficient) shows the efficient performance of the proposed technique.

The canonical semantic network supports residual language function in chronic post-stroke aphasia

Current theories of language recovery after stroke are limited by a reliance on small studies. Here, we aimed to test predictions of current theory and resolve inconsistencies regarding right hemispheric contributions to long-term recovery. We first defined the canonical semantic network in 43 healthy controls. Then, in a group of 43 patients with chronic post-stroke aphasia, we tested whether activity in this network predicted performance on measures of semantic comprehension, naming, and fluency while controlling for lesion volume effects. Canonical network activation accounted for 22%-33% of the variance in language test scores. Whole-brain analyses corroborated these findings, and revealed a core set of regions showing positive relationships to all language measures. We next evaluated the relationship between activation magnitudes in left and right hemispheric portions of the network, and characterized how right hemispheric activation related to the extent of left hemispheric damage. Activation magnitudes in each hemispheric network were strongly correlated, but four right frontal regions showed heightened activity in patients with large lesions. Activity in two of these regions (inferior frontal gyrus pars opercularis and supplementary motor area) was associated with better language abilities in patients with larger lesions, but poorer language abilities in patients with smaller lesions. Our results indicate that bilateral language networks support language processing after stroke, and that right hemispheric activations related to extensive left hemispheric damage occur outside of the canonical semantic network and differentially relate to behavior depending on the extent of left hemispheric damage. Hum Brain Mapp 38:1636-1658, 2017. © 2016 Wiley Periodicals, Inc.

Using principal component analysis to capture individual differences within a unified neuropsychological model of chronic post-stroke aphasia: Revealing the unique neural correlates of speech fluency, phonology and semantics

Individual differences in the performance profiles of neuropsychologically-impaired patients are pervasive yet there is still no resolution on the best way to model and account for the variation in their behavioural impairments and the associated neural correlates. To date, researchers have generally taken one of three different approaches: a single-case study methodology in which each case is considered separately; a case-series design in which all individual patients from a small coherent group are examined and directly compared; or, group studies, in which a sample of cases are investigated as one group with the assumption that they are drawn from a homogenous category and that performance differences are of no interest. In recent research, we have developed a complementary alternative through the use of principal component analysis (PCA) of individual data from large patient cohorts. This data-driven approach not only generates a single unified model for the group as a whole (expressed in terms of the emergent principal components) but is also able to capture the individual differences between patients (in terms of their relative positions along the principal behavioural axes). We demonstrate the use of this approach by considering speech fluency, phonology and semantics in aphasia diagnosis and classification, as well as their unique neural correlates. PCA of the behavioural data from 31 patients with chronic post-stroke aphasia resulted in four statistically-independent behavioural components reflecting phonological, semantic, executive-cognitive and fluency abilities. Even after accounting for lesion volume, entering the four behavioural components simultaneously into a voxel-based correlational methodology (VBCM) analysis revealed that speech fluency (speech quanta) was uniquely correlated with left motor cortex and underlying white matter (including the anterior section of the arcuate fasciculus and the frontal aslant tract), phonological skills with regions in the superior temporal gyrus and pars opercularis, and semantics with the anterior temporal stem.

Microstructural properties of premotor pathways predict visuomotor performance in chronic stroke

Microstructural properties of the corticospinal tract (CST) descending from the motor cortex predict strength and motor skill in the chronic phase after stroke. Much less is known about the relation between brain microstructure and visuomotor processing after stroke. In this study, individual's poststroke and age-matched controls performed a unimanual force task separately with each hand at three levels of visual gain. We collected diffusion MRI data and used probabilistic tractography algorithms to identify the primary and premotor CSTs. Fractional anisotropy (FA) within each tract was used to predict changes in force variability across different levels of visual gain. Our observations revealed that individuals poststroke reduced force variability with an increase in visual gain, performed the force task with greater variability as compared with controls across all gain levels, and had lower FA in the primary motor and premotor CSTs. Our results also demonstrated that the CST descending from the premotor cortex, rather than the primary motor cortex, best predicted force variability. Together, these findings demonstrate that the microstructural properties of the premotor CST predict visual gain-related changes in force variability in individuals poststroke. Hum Brain Mapp 37:2039-2054, 2016. © 2016 Wiley Periodicals, Inc.

Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans

BACKGROUND

Manual lesion delineation by an expert is the standard for lesion identification in MRI scans, but it is time-consuming and can introduce subjective bias. Alternative methods often require multi-modal MRI data, user interaction, scans from a control population, and/or arbitrary statistical thresholding.

NEW METHOD

We present an approach for automatically identifying stroke lesions in individual T1-weighted MRI scans using naïve Bayes classification. Probabilistic tissue segmentation and image algebra were used to create feature maps encoding information about missing and abnormal tissue. Leave-one-case-out training and cross-validation was used to obtain out-of-sample predictions for each of 30 cases with left hemisphere stroke lesions.

RESULTS

Our method correctly predicted lesion locations for 30/30 un-trained cases. Post-processing with smoothing (8mm FWHM) and cluster-extent thresholding (100 voxels) was found to improve performance.

COMPARISON WITH EXISTING METHOD

Quantitative evaluations of post-processed out-of-sample predictions on 30 cases revealed high spatial overlap (mean Dice similarity coefficient=0.66) and volume agreement (mean percent volume difference=28.91; Pearson's r=0.97) with manual lesion delineations.

CONCLUSIONS

Our automated approach agrees with manual tracing. It provides an alternative to automated methods that require multi-modal MRI data, additional control scans, or user interaction to achieve optimal performance. Our fully trained classifier has applications in neuroimaging and clinical contexts.

Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis

The gold standard for identifying stroke lesions is manual tracing, a method that is known to be observer dependent and time consuming, thus impractical for big data studies. We propose LINDA (Lesion Identification with Neighborhood Data Analysis), an automated segmentation algorithm capable of learning the relationship between existing manual segmentations and a single T1-weighted MRI. A dataset of 60 left hemispheric chronic stroke patients is used to build the method and test it with k-fold and leave-one-out procedures. With respect to manual tracings, predicted lesion maps showed a mean dice overlap of 0.696 ± 0.16, Hausdorff distance of 17.9 ± 9.8 mm, and average displacement of 2.54 ± 1.38 mm. The manual and predicted lesion volumes correlated at r = 0.961. An additional dataset of 45 patients was utilized to test LINDA with independent data, achieving high accuracy rates and confirming its cross-institutional applicability. To investigate the cost of moving from manual tracings to automated segmentation, we performed comparative lesion-to-symptom mapping (LSM) on five behavioral scores. Predicted and manual lesions produced similar neuro-cognitive maps, albeit with some discussed discrepancies. Of note, region-wise LSM was more robust to the prediction error than voxel-wise LSM. Our results show that, while several limitations exist, our current results compete with or exceed the state-of-the-art, producing consistent predictions, very low failure rates, and transferable knowledge between labs. This work also establishes a new viewpoint on evaluating automated methods not only with segmentation accuracy but also with brain-behavior relationships. LINDA is made available online with trained models from over 100 patients.

Lesion-symptom mapping in the study of spoken language understanding

Lesion-symptom mapping studies aim to make inferences about the functional neuroanatomy of spoken language understanding by investigating relationships between damage to different brain regions and the various speech perception and comprehension deficits that result. Voxel-based lesion-symptom mapping (VLSM), voxel-based morphometry (VBM), and studies focused on specific cortical regions of interest or fiber pathways have all yielded insights regarding the localization of different components of spoken language processing. Major challenges include the fact that brain damage rarely impacts just a single brain region or just a single processing component, and that neuroplasticity and recovery can complicate the interpretation of lesion-deficit correlations. Future studies involving large patient cohorts derived from multi-center projects, and multivariate approaches to quantifying patterns of brain damage and patterns of linguistic deficits, will continue to yield new insights into the neural basis of spoken language understanding.