Brain age prediction using interpretable multi-feature-based convolutional neural network in mild traumatic brain injury.

BACKGROUND: Convolutional neural network (CNN) can capture the structural features changes of brain aging based on MRI, thus predict brain age in healthy individuals accurately. However, most studies use single feature to predict brain age in healthy individuals, ignoring adding information from multiple sources and the changes in brain aging patterns after mild traumatic brain injury (mTBI) were still unclear. METHODS: Here, we leveraged the structural data from a large, heterogeneous dataset (N = 1464) to implement an interpretable 3D combined CNN model for brain-age prediction. In addition, we also built an atlas-based occlusion analysis scheme with a fine-grained human Brainnetome Atlas to reveal the age-sstratified contributed brain regions for brain-age prediction in healthy controls (HCs) and mTBI patients. The correlations between brain predicted age gaps (brain-PAG) following mTBI and individual's cognitive impairment, as well as the level of plasma neurofilament light were also examined. RESULTS: Our model utilized multiple 3D features derived from T1w data as inputs, and reduced the mean absolute error (MAE) of age prediction to 3.08 years and improved Pearson's r to 0.97 on 154 HCs. The strong generalizability of our model was also validated across different centers. Regions contributing the most significantly to brain age prediction were the caudate and thalamus for HCs and patients with mTBI, and the contributive regions were mostly located in the subcortical areas throughout the adult lifespan. The left hemisphere was confirmed to contribute more in brain age prediction throughout the adult lifespan. Our research showed that brain-PAG in mTBI patients was significantly higher than that in HCs in both acute and chronic phases. The increased brain-PAG in mTBI patients was also highly correlated with cognitive impairment and a higher level of plasma neurofilament light, a marker of neurodegeneration. The higher brain-PAG and its correlation with severe cognitive impairment showed a longitudinal and persistent nature in patients with follow-up examinations. CONCLUSION: We proposed an interpretable deep learning framework on a relatively large dataset to accurately predict brain age in both healthy individuals and mTBI patients. The interpretable analysis revealed that the caudate and thalamus became the most contributive role across the adult lifespan in both HCs and patients with mTBI. The left hemisphere contributed significantly to brain age prediction may enlighten us to be concerned about the lateralization of brain abnormality in neurological diseases in the future. The proposed interpretable deep learning framework might also provide hope for testing the performance of related drugs and treatments in the future.

Magnetic Resonance Imaging Measures to Track Atrophy Progression in Progressive Supranuclear Palsy in Clinical Trials.

BACKGROUND: Several magnetic resonance imaging (MRI) measures have been suggested as progression biomarkers in progressive supranuclear palsy (PSP), and some PSP staging systems have been recently proposed. OBJECTIVE: Comparing structural MRI measures and staging systems in tracking atrophy progression in PSP and estimating the sample size to use them as endpoints in clinical trials. METHODS: Progressive supranuclear palsy-Richardson's syndrome (PSP-RS) patients with one-year-follow-up longitudinal brain MRI were selected from the placebo arms of international trials (NCT03068468, NCT01110720, NCT01049399) and the DescribePSP cohort. The discovery cohort included patients from the NCT03068468 trial; the validation cohort included patients from other sources. Multisite age-matched healthy controls (HC) were included for comparison. Several MRI measures were compared: automated atlas-based volumetry (44 regions), automated planimetric measures of brainstem regions, and four previously described staging systems, applied to volumetric data. RESULTS: Of 508 participants, 226 PSP patients including discovery (n = 121) and validation (n = 105) cohorts, and 251 HC were included. In PSP patients, the annualized percentage change of brainstem and midbrain volume, and a combined index including midbrain, frontal lobe, and third ventricle volume change, were the progression biomarkers with the highest effect size in both cohorts (discovery: >1.6; validation cohort: >1.3). These measures required the lowest sample sizes (n < 100) to detect 30% atrophy progression, compared with other volumetric/planimetric measures and staging systems. CONCLUSIONS: This evidence may inform the selection of imaging endpoints to assess the treatment efficacy in reducing brain atrophy rate in PSP clinical trials, with automated atlas-based volumetry requiring smaller sample size than staging systems and planimetry to observe significant treatment effects. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Enhancing the Contouring Efficiency for Head and Neck Cancer Radiotherapy Using Atlas-based Auto-segmentation and Scripting.

BACKGROUND/AIM: Intensity-modulated radiation therapy can deliver a highly conformal dose to a target while minimizing the dose to the organs at risk (OARs). Delineating the contours of OARs is time-consuming, and various automatic contouring software programs have been employed to reduce the delineation time. However, some software operations are manual, and further reduction in time is possible. This study aimed to automate running atlas-based auto-segmentation (ABAS) and software operations using a scripting function, thereby reducing work time. MATERIALS AND METHODS: Dice coefficient and Hausdorff distance were used to determine geometric accuracy. The manual delineation, automatic delineation, and modification times were measured. While modifying the contours, the degree of subjective correction was rated on a four-point scale. RESULTS: The model exhibited generally good geometric accuracy. However, some OARs, such as the chiasm, optic nerve, retina, lens, and brain require improvement. The average contour delineation time was reduced from 57 to 29 min (p<0.05). The subjective revision degree results indicated that all OARs required minor modifications; only the submandibular gland, thyroid, and esophagus were rated as modified from scratch. CONCLUSION: The ABAS model and scripted automation in head and neck cancer reduced the work time and software operations. The time can be further reduced by improving contour accuracy.

Microstructural changes of the white matter in systemic lupus erythematosus patients without neuropsychiatric symptoms: a multi-shell diffusion imaging study.

BACKGROUND: Diffusion kurtosis imaging (DKI) and neurite orientation dispersion and density imaging (NODDI) provide more comprehensive and informative perspective on microstructural alterations of cerebral white matter (WM) than single-shell diffusion tensor imaging (DTI), especially in the detection of crossing fiber. However, studies on systemic lupus erythematosus patients without neuropsychiatric symptoms (non-NPSLE patients) using multi-shell diffusion imaging remain scarce. METHODS: Totally 49 non-NPSLE patients and 41 age-, sex-, and education-matched healthy controls underwent multi-shell diffusion magnetic resonance imaging. Totally 10 diffusion metrics based on DKI (fractional anisotropy, mean diffusivity, axial diffusivity, radial diffusivity, mean kurtosis, axial kurtosis and radial kurtosis) and NODDI (neurite density index, orientation dispersion index and volume fraction of the isotropic diffusion compartment) were evaluated. Tract-based spatial statistics (TBSS) and atlas-based region-of-interest (ROI) analyses were performed to determine group differences in brain WM microstructure. The associations of multi-shell diffusion metrics with clinical indicators were determined for further investigation. RESULTS: TBSS analysis revealed reduced FA, AD and RK and increased ODI in the WM of non-NPSLE patients (P < 0.05, family-wise error corrected), and ODI showed the best discriminative ability. Atlas-based ROI analysis found increased ODI values in anterior thalamic radiation (ATR), inferior frontal-occipital fasciculus (IFOF), forceps major (F_major), forceps minor (F_minor) and uncinate fasciculus (UF) in non-NPSLE patients, and the right ATR showed the best discriminative ability. ODI in the F_major was positively correlated to C3. CONCLUSION: This study suggested that DKI and NODDI metrics can complementarily detect WM abnormalities in non-NPSLE patients and revealed ODI as a more sensitive and specific biomarker than DKI, guiding further understanding of the pathophysiological mechanism of normal-appearing WM injury in SLE.

Comparison of commercial atlas-based automatic segmentation software for prostate radiotherapy treatment planning.

This study aims to assess the accuracy of automatic atlas-based contours for various key anatomical structures in prostate radiotherapy treatment planning. The evaluated structures include the bladder, rectum, prostate, seminal vesicles, femoral heads and penile bulb. CT images from 20 patients who underwent intensity-modulated radiotherapy were randomly chosen to create an atlas library. Atlas contours of the seven anatomical structures were generated using four software packages: ABAS, Eclipse, MIM, and RayStation. These contours were then compared to manual delineations performed by oncologists, which served as the ground truth. Evaluation metrics such as dice similarity coefficient (DSC), mean distance to agreement (MDA), and volume ratio (VR) were calculated to assess the accuracy of the contours. Additionally, the time taken by each software to generate the atlas contour was recorded. The mean DSC values for the bladder exhibited strong agreement (>0.8) with manual delineations for all software except for Eclipse and RayStation. Similarly, the femoral heads showed significant similarity between the atlas contours and ground truth across all software, with mean DSC values exceeding 0.9 and MDA values close to zero. On the other hand, the penile bulb displayed only moderate agreement with the ground truth, with mean DSC values ranging from 0.5 to 0.7 for all software. A similar trend was observed in the prostate atlas contours, except for MIM, which achieved a mean DSC of over 0.8. For the rectum, both ABAS and MIM atlases demonstrated strong agreement with the ground truth, resulting in mean DSC values of more than 0.8. Overall, MIM and ABAS outperformed Eclipse and RayStation in both DSC and MDA. These results indicate that the atlas-based segmentation employed in this study produces acceptable contours for the anatomical structures of interest in prostate radiotherapy treatment planning.

Brodmann Areas, V1 Atlas and Cognitive Impairment: Assessing Cortical Thickness for Cognitive Impairment Diagnostics.

Background and Objectives: Magnetic resonance imaging is vital for diagnosing cognitive decline. Brodmann areas (BA), distinct regions of the cerebral cortex categorized by cytoarchitectural variances, provide insights into cognitive function. This study aims to compare cortical thickness measurements across brain areas identified by BA mapping. We assessed these measurements among patients with and without cognitive impairment, and across groups categorized by cognitive performance levels using the Montreal Cognitive Assessment (MoCA) test. Materials and Methods: In this cross-sectional study, we included 64 patients who were divided in two ways: in two groups with (CI) or without (NCI) impaired cognitive function and in three groups with normal (NC), moderate (MPG) and low (LPG) cognitive performance according to MoCA scores. Scans with a 3T MRI scanner were carried out, and cortical thickness data was acquired using Freesurfer 7.2.0 software. Results: By analyzing differences between the NCI and CI groups cortical thickness of BA3a in left hemisphere (U = 241.000, p = 0.016), BA4a in right hemisphere (U = 269.000, p = 0.048) and BA28 in left hemisphere (U = 584.000, p = 0.005) showed significant differences. In the LPG, MPG and NC cortical thickness in BA3a in left hemisphere (H (2) = 6.268, p = 0.044), in V2 in right hemisphere (H (2) = 6.339, p = 0.042), in BA28 in left hemisphere (H (2) = 23.195, p < 0.001) and in BA28 in right hemisphere (H (2) = 10.015, p = 0.007) showed significant differences. Conclusions: Our study found that cortical thickness in specific Brodmann Areas-BA3a and BA28 in the left hemisphere, and BA4a in the right-differ significantly between NCI and CI groups. Significant differences were also observed in BA3a (left), V2 (right), and BA28 (both hemispheres) across LPG, MPG, NC groups. Despite a small sample size, these findings suggest cortical thickness measurements can serve as effective biomarkers for cognitive impairment diagnosis, warranting further validation with a larger cohort.

Deep learning and atlas-based models to streamline the segmentation workflow of total marrow and lymphoid irradiation.

PURPOSE: To improve the workflow of total marrow and lymphoid irradiation (TMLI) by enhancing the delineation of organs at risk (OARs) and clinical target volume (CTV) using deep learning (DL) and atlas-based (AB) segmentation models. MATERIALS AND METHODS: Ninety-five TMLI plans optimized in our institute were analyzed. Two commercial DL software were tested for segmenting 18 OARs. An AB model for lymph node CTV (CTV_LN) delineation was built using 20 TMLI patients. The AB model was evaluated on 20 independent patients, and a semiautomatic approach was tested by correcting the automatic contours. The generated OARs and CTV_LN contours were compared to manual contours in terms of topological agreement, dose statistics, and time workload. A clinical decision tree was developed to define a specific contouring strategy for each OAR. RESULTS: The two DL models achieved a median [interquartile range] dice similarity coefficient (DSC) of 0.84 [0.71;0.93] and 0.85 [0.70;0.93] across the OARs. The absolute median Dmean difference between manual and the two DL models was 2.0 [0.7;6.6]% and 2.4 [0.9;7.1]%. The AB model achieved a median DSC of 0.70 [0.66;0.74] for CTV_LN delineation, increasing to 0.94 [0.94;0.95] after manual revision, with minimal Dmean differences. Since September 2022, our institution has implemented DL and AB models for all TMLI patients, reducing from 5 to 2 h the time required to complete the entire segmentation process. CONCLUSION: DL models can streamline the TMLI contouring process of OARs. Manual revision is still necessary for lymph node delineation using AB models.

A collection of 157 individual neuromelanin-sensitive images accompanied by non-linear neuromelanin-sensitive atlas and a probabilistic locus coeruleus atlas.

The current dataset aims to support and enhance the research reliability of neuromelanin regions in the brainstem, such as locus coeruleus (LC), by offering raw neuromelanin-sensitive images. The dataset includes raw neuromelanin-sensitive images from 157 healthy individuals (8-64 years old). In addition, leveraging individual neuromelanin-sensitive images, a non-linear neuromelanin-sensitive atlas, generated through an iterative warping process, is included to tackle the common challenge of a limited field of view in neuromelanin-sensitive images. Finally, the dataset encompasses a probabilistic LC atlas generated through a majority voting approach with pre-existing multiple atlas-based segmentations. This process entails warping pre-existing atlases onto individual spaces and identifying voxels with a majority consensus of over 50 % across the atlases. This LC probabilistic atlas can minimize uncertainty variance associated with choosing a specific single atlas.

Advanced Hyperpolarized 13C Metabolic Imaging Protocol for Patients with Gliomas: A Comprehensive Multimodal MRI Approach.

This study aimed to implement a multimodal 1H/HP-13C imaging protocol to augment the serial monitoring of patients with glioma, while simultaneously pursuing methods for improving the robustness of HP-13C metabolic data. A total of 100 1H/HP [1-13C]-pyruvate MR examinations (104 HP-13C datasets) were acquired from 42 patients according to the comprehensive multimodal glioma imaging protocol. Serial data coverage, accuracy of frequency reference, and acquisition delay were evaluated using a mixed-effects model to account for multiple exams per patient. Serial atlas-based HP-13C MRI demonstrated consistency in volumetric coverage measured by inter-exam dice coefficients (0.977 ± 0.008, mean ± SD; four patients/11 exams). The atlas-derived prescription provided significantly improved data quality compared to manually prescribed acquisitions (n = 26/78; p = 0.04). The water-based method for referencing [1-13C]-pyruvate center frequency significantly reduced off-resonance excitation relative to the coil-embedded [13C]-urea phantom (4.1 ± 3.7 Hz vs. 9.9 ± 10.7 Hz; p = 0.0007). Significantly improved capture of tracer inflow was achieved with the 2-s versus 5-s HP-13C MRI acquisition delay (p = 0.007). This study demonstrated the implementation of a comprehensive multimodal 1H/HP-13C MR protocol emphasizing the monitoring of steady-state/dynamic metabolism in patients with glioma.

Clinical evaluation of deep learning and atlas-based auto-segmentation for organs at risk delineation.

Manual delineation of organs at risk and clinical target volumes is essential in radiotherapy planning. Atlas-based auto-segmentation (ABAS) algorithms have become available and been shown to provide accurate contouring for various anatomical sites. Recently, deep learning auto-segmentation (DL-AS) algorithms have emerged as the state-of-the-art in medical image segmentation. This study aimed to evaluate the effect of auto-segmentation on the clinical workflow for contouring different anatomical sites of cancer, such as head and neck (H&N), breast, abdominal region, and prostate. Patients with H&N, breast, abdominal, and prostate cancer (n = 30 each) were enrolled in the study. Twenty-seven different organs at four sites were evaluated. RayStation was used to apply the ABAS. Siemens AI-Rad Companion Organs RT was used to apply the DL-AS. Evaluations were performed with similarity indices using geometric methods, time-evaluation, and qualitative scoring visual evaluations by radiation oncologists. The DL-AS algorithm was more accurate than ABAS algorithm on geometric indices for half of the structures. The qualitative scoring results of the two algorithms were significantly different, and DL-AS was more accurate on many contours. DL-AS had 41%, 29%, 86%, and 15% shorter edit times in the HnN, breast, abdomen, and prostate groups, respectively, than ABAS. There were no correlations between the geometric indices and visual assessments. The time required to edit the contours was considerably shorter for DL-AS than for ABAS. Auto-segmentation with deep learning could be the first step for clinical workflow optimization in radiotherapy.

White matter microstructure alterations in idiopathic restless legs syndrome: a study combining crossing fiber-based and tensor-based approaches.

Introduction: Restless legs syndrome (RLS) is a common sensorimotor disorder characterized by an irrepressible urge to move the legs and frequently accompanied by unpleasant sensations in the legs. The pathophysiological mechanisms underlying RLS remain unclear, and RLS is hypothesized to be associated with alterations in white matter tracts. Methods: Diffusion MRI is a unique noninvasive method widely used to study white matter tracts in the human brain. Thus, diffusion-weighted images were acquired from 18 idiopathic RLS patients and 31 age- and sex-matched healthy controls (HCs). Whole brain tract-based spatial statistics (TBSS) and atlas-based analyzes combining crossing fiber-based metrics and tensor-based metrics were performed to investigate the white matter patterns in individuals with RLS. Results: TBSS analysis revealed significantly higher fractional anisotropy (FA) and partial volume fraction of primary (F1) fiber populations in multiple tracts associated with the sensorimotor network in patients with RLS than in HCs. In the atlas based analysis, the bilateral anterior thalamus radiation, bilateral corticospinal tract, bilateral inferior fronto-occipital fasciculus, left hippocampal cingulum, left inferior longitudinal fasciculus, and left uncinate fasciculus showed significantl increased F1, but only the left hippocampal cingulum showed significantly higher FA. Discussion: The results demonstrated that F1 identified extensive alterations in white matter tracts compared with FA and confirmed the hypothesis that crossing fiber-based metrics are more sensitive than tensor-based metrics in detecting white matter abnormalities in RLS. The present findings provide evidence that the increased F1 metric observed in sensorimotor tracts may be a critical neural substrate of RLS, enhancing our understanding of the underlying pathological changes.

A review of PET attenuation correction methods for PET-MR.

Despite being thirteen years since the installation of the first PET-MR system, the scanners constitute a very small proportion of the total hybrid PET systems installed. This is in stark contrast to the rapid expansion of the PET-CT scanner, which quickly established its importance in patient diagnosis within a similar timeframe. One of the main hurdles is the development of an accurate, reproducible and easy-to-use method for attenuation correction. Quantitative discrepancies in PET images between the manufacturer-provided MR methods and the more established CT- or transmission-based attenuation correction methods have led the scientific community in a continuous effort to develop a robust and accurate alternative. These can be divided into four broad categories: (i) MR-based, (ii) emission-based, (iii) atlas-based and the (iv) machine learning-based attenuation correction, which is rapidly gaining momentum. The first is based on segmenting the MR images in various tissues and allocating a predefined attenuation coefficient for each tissue. Emission-based attenuation correction methods aim in utilising the PET emission data by simultaneously reconstructing the radioactivity distribution and the attenuation image. Atlas-based attenuation correction methods aim to predict a CT or transmission image given an MR image of a new patient, by using databases containing CT or transmission images from the general population. Finally, in machine learning methods, a model that could predict the required image given the acquired MR or non-attenuation-corrected PET image is developed by exploiting the underlying features of the images. Deep learning methods are the dominant approach in this category. Compared to the more traditional machine learning, which uses structured data for building a model, deep learning makes direct use of the acquired images to identify underlying features. This up-to-date review goes through the literature of attenuation correction approaches in PET-MR after categorising them. The various approaches in each category are described and discussed. After exploring each category separately, a general overview is given of the current status and potential future approaches along with a comparison of the four outlined categories.

Structural and microstructural neuroimaging signature of C9orf72-associated ALS: A multiparametric MRI study.

BACKGROUND: ALS patients with hexanucleotide expansion in C9orf72 are characterized by a specific clinical phenotype, including more aggressive disease course and cognitive decline. Computerized multiparametric MRI with gray matter volumetry and diffusion tensor imaging (DTI) to analyze white matter structural connectivity is a potential in vivo biomarker. OBJECTIVE: The objective of this study was to develop a multiparametric MRI signature in a large cohort of ALS patients with C9orf72 mutations. The aim was to investigate how morphological features of C9orf72-associated ALS differ in structural MRI and DTI compared to healthy controls and ALS patients without C9orf72 mutations. METHODS: Atlas-based volumetry (ABV) and whole brain-based DTI-based analyses were performed in a cohort of n = 51 ALS patients with C9orf72 mutations and compared with both n = 51 matched healthy controls and n = 51 C9orf72 negative ALS patients, respectively. Subsequently, Spearman correlation analysis of C9orf72 ALS patients' data with clinical parameters (age of onset, sex, ALS-FRS-R, progression rate, survival) as well as ECAS and p-NfH in CSF was performed. RESULTS: The whole brain voxel-by-voxel comparison of fractional anisotropy (FA) maps between C9orf72 ALS patients and controls showed significant bilateral alterations in axonal structures of the white matter at group level, primarily along the corticospinal tracts and in fibers projecting to the frontal lobes. For the frontal lobes, these alterations were also significant between C9orf72 positive and C9orf72 negative ALS patients. In ABV, patients with C9orf72 mutations showed lower volumes of the frontal, temporal, and parietal lobe, with the lowest values in the gray matter of the superior frontal and the precentral gyrus, but also in hippocampi and amygdala. Compared to C9orf72 negative ALS, the differences were shown to be significant for cerebral gray matter (p = 0.04), especially in the frontal (p = 0.01) and parietal lobe (p = 0.01), and in the thalamus (p = 0.004). A correlation analysis between ECAS and averaged regional FA values revealed significant correlations between cognitive performance in ECAS and frontal association fibers. Lower FA values in the frontal lobes were associated with worse performance in all cognitive domains measured (language, verbal fluency, executive functions, memory and spatial perception). In addition, there were significant negative correlations between age of onset and atlas-based volumetry results for gray matter. CONCLUSIONS: This study demonstrates a distinct pattern of DTI alterations of the white matter and ubiquitous volume reductions of the gray matter early in the disease course of C9orf72-associated ALS. Alterations were closely linked to a more aggressive cognitive phenotype. These results are in line with an expected pTDP43 propagation pattern of cortical affection and thus strengthen the hypothesis that an underlying developmental disorder is present in ALS with C9orf72 expansions. Thus, multiparametric MRI could contribute to the assessment of the disease as an in vivo biomarker even in the early phase of the disease.

ADHD diagnosis using structural brain MRI and personal characteristic data with machine learning framework.

An essential yet challenging task is an automatic diagnosis of attention-deficit/hyperactivity disorder (ADHD) without manual intervention. The present study emphasises utilizing structural MRI and personal characteristic (PC) data for developing an automated diagnostic system for ADHD classification. Here, an age-balanced dataset of 316 ADHD and 316 Typically Developing Children (TDC) was prepared from the publicly available dataset. We extracted volumetric features from gray matter (GM) volumes from brain regions defined by Automated Anatomical Labelling (AAL3) atlas and cortical thickness-based (CT) features using the Destrieux atlas. A set of salient features were selected independently using minimum redundancy and maximum relevance (mRMR) and ensemble feature selection (EFS) methods. Decision models were trained using five well-known classifiers: K-nearest neighbours, logistic regression, linear Support Vector Machine (SVM), radial-based SVM (RBSVM), and Random Forest. The performance of the proposed system was evaluated using accuracy, recall, and specificity with ten runs of a ten-fold cross-validation scheme. We run seven experiments by considering different combinations of features. The maximum classification accuracy of 75% was obtained with CT and PC features with RBSVM and SVM with the EFS. An increase in GM volume in fifteen brain regions and loss of cortical thickness in twenty-seven brain regions were observed.

Evaluation of different algorithms for automatic segmentation of head-and-neck lymph nodes on CT images.

PURPOSE: To investigate the performance of 4 atlas-based (multi-ABAS) and 2 deep learning (DL) solutions for head-and-neck (HN) elective nodes (CTVn) automatic segmentation (AS) on CT images. MATERIAL AND METHODS: Bilateral CTVn levels of 69 HN cancer patients were delineated on contrast-enhanced planning CT. Ten and 49 patients were used for atlas library and for training a mono-centric DL model, respectively. The remaining 20 patients were used for testing. Additionally, three commercial multi-ABAS methods and one commercial multi-centric DL solution were investigated. Quantitative evaluation was assessed using volumetric Dice Similarity Coefficient (DSC) and 95-percentile Hausdorff distance (HD95%). Blind evaluation was performed for 3 solutions by 4 physicians. One recorded the time needed for manual corrections. A dosimetric study was finally conducted using automated planning. RESULTS: Overall DL solutions had better DSC and HD95% results than multi-ABAS methods. No statistically significant difference was found between the 2 DL solutions. However, the contours provided by multi-centric DL solution were preferred by all physicians and were also faster to correct (1.1 min vs 4.17 min, on average). Manual corrections for multi-ABAS contours took on average 6.52 min Overall, decreased contour accuracy was observed from CTVn2 to CTVn3 and to CTVn4. Using the AS contours in treatment planning resulted in underdosage of the elective target volume. CONCLUSION: Among all methods, the multi-centric DL method showed the highest delineation accuracy and was better rated by experts. Manual corrections remain necessary to avoid elective target underdosage. Finally, AS contours help reducing the workload of manual delineation task.

Automatic Segmentation of Parkinson Disease Therapeutic Targets Using Nonlinear Registration and Clinical MR Imaging: Comparison of Methodology, Presence of Disease, and Quality Control.

INTRODUCTION: Accurate and precise delineation of the globus pallidus pars interna (GPi) and subthalamic nucleus (STN) is critical for the clinical treatment and research of Parkinson's disease (PD). Automated segmentation is a developing technology which addresses limitations of visualizing deep nuclei on MR imaging and standardizing their definition in research applications. We sought to compare manual segmentation with three workflows for template-to-patient nonlinear registration providing atlas-based automatic segmentation of deep nuclei. METHODS: Bilateral GPi, STN, and red nucleus (RN) were segmented for 20 PD and 20 healthy control (HC) subjects using 3T MRIs acquired for clinical purposes. The automated workflows used were an option available in clinical practice and two common research protocols. Quality control (QC) was performed on registered templates via visual inspection of readily discernible brain structures. Manual segmentation using T1, proton density, and T2 sequences was used as "ground truth" data for comparison. Dice similarity coefficient (DSC) was used to assess agreement between segmented nuclei. Further analysis was done to compare the influences of disease state and QC classifications on DSC. RESULTS: Automated segmentation workflows (CIT-S, CRV-AB, and DIST-S) had the highest DSC for the RN and lowest for the STN. Manual segmentations outperformed automated segmentation for all workflows and nuclei; however, for 3/9 workflows (CIT-S STN, CRV-AB STN, and CRV-AB GPi) the differences were not statically significant. HC and PD only showed significant differences in 1/9 comparisons (DIST-S GPi). QC classification only demonstrated significantly higher DSC in 2/9 comparisons (CRV-AB RN and GPi). CONCLUSION: Manual segmentations generally performed better than automated segmentations. Disease state does not appear to have a significant effect on the quality of automated segmentations via nonlinear template-to-patient registration. Notably, visual inspection of template registration is a poor indicator of the accuracy of deep nuclei segmentation. As automatic segmentation methods continue to evolve, efficient and reliable QC methods will be necessary to support safe and effective integration into clinical workflows.

Socio-cognitive, expertise-based and appearance-based accounts of the other-'race' effect in face perception: A label-based systematic review of neuroimaging results.

Two competing theories explain the other-'race' effect (ORE) either by greater perceptual expertise to same-'race' (SR) faces or by social categorization of other-'race' (OR) faces at the expense of individuation. To assess expertise and categorization contributions to the ORE, a promising-yet overlooked-approach is comparing activations for different other-'races'. We present a label-based systematic review of neuroimaging studies reporting increased activity in response to OR faces (African, Caucasian, or Asian) when compared with the SR of participants. Hypothetically, while common activations would reflect general aspects of OR perception, 'race'-preferential ones would represent effects of 'race'-specific visual appearance. We find that several studies report activation of occipito-temporal and midcingulate areas in response to faces across different other-'races', presumably due to high demand on the visual system and category processing. Another area reported in response to all OR faces, the caudate nucleus, suggests the involvement of socio-affective processes and behavioural regulation. Overall, our results support hybrid models-both expertise and social categorization contribute to the ORE, but they provide little evidence for reduced motivation to process OR faces. Additionally, we identify areas preferentially responding to specific OR faces, reflecting effects of visual appearance.

Diffusion tensor imaging in patients with chronic migraine: an analysis with atlas-based analysis and tract-based spatial statistics / 中华神经医学杂志

Objective:To study the structural damage of cerebral white matter in patients with chronic migraine (CM) using magnetic resonance diffusion tensor imaging (DTI), and analyze its correlation with clinical data.Methods:Sixty CM patients, enrolled from Outpatient of Departments of Neurosurgery and Neurology, Affiliated Hospital of Chengdu University of Traditional Chinese Medicine from September 2020 to December 2022, were chosen; and from October 2020 to June 2022, 60 healthy controls matched with age and gender were recruited socially. All subjects accepted whole brain DTI. DTI data were automatically processed by PANDA and FSL softwares, differences of whole brain DTI data between CM patients and healthy controls were compared by atlas-based analysis (ABA) and tract-based spatial statistics (TBSS), and correlations of clinical features with ABA results were analyzed by Pearson correlation in CM patients.Results:In ABA, compared with the healthy control group, the CM group had significantly decreased FA values in the bilateral cerebral peduncles, left inferior cerebellar peduncles, right superior cerebellar peduncles, bilateral medial thalamic tracts, bilateral tapetum (the inner sagittal layer of the corpus callosum), bilateral hook bundles, and right posterior limb of the internal capsule ( P<0.05); compared with the healthy control group, the CM group had significantly increased mean diffusivity (MD) in the right cingulate gyrus and posterior part of the internal lenticular nucleus, statistically decreased axial diffusivity (AD) in the bilateral cerebral peduncles, bilateral medial thalamic tracts, and right cingulate gyrus ( P<0.05); compared with the healthy control group, the CM group had significantly increased radial diffusivity (RD) in the left tapetum, left inferior cerebellar peduncles, and cerebral peduncles ( P<0.05). In TBSS, no differences in FA, MD, RD and AD in the white matter fiber skeleton were noted between the 2 groups ( P>0.05). In CM patients, visual analogue scale (VAS) scores were negatively correlated with FA in the left subiculum, left medial colliculus and right cerebral peduncle, AD in the right cerebral peduncle, and RD in the left tapetum ( P<0.05); disease duration was negatively correlated with FA in the left subiculum peduncle and positively correlated with RD in the left subiculum peduncle ( P<0.05). Conclusions:Notwithstanding the structural damage of cerebral white matter in CM patients, the white matter fiber skeleton remains unaltered from normal subjects, without pathological damage of the fiber skeleton. Structural changes in the brainstem, cerebellum and corpus callosum are associated with VAS scores and disease duration, and may be important factors for CM pathogenesis.

Atlas-Based Segmentation in Extraction of Knee Joint Bone Structures from CT and MR.

The main goal of the approach proposed in this study, which is dedicated to the extraction of bone structures of the knee joint (femoral head, tibia, and patella), was to show a fully automated method of extracting these structures based on atlas segmentation. In order to realize the above-mentioned goal, an algorithm employed automated image-matching as the first step, followed by the normalization of clinical images and the determination of the 11-element dataset to which all scans in the series were allocated. This allowed for a delineation of the average feature vector for the teaching group in the next step, which automated and streamlined known fuzzy segmentation methods (fuzzy c-means (FCM), fuzzy connectedness (FC)). These averaged features were then transmitted to the FCM and FC methods, which were implemented for the testing group and correspondingly for each scan. In this approach, two features are important: the centroids (which become starting points for the fuzzy methods) and the surface area of the extracted bone structure (protects against over-segmentation). This proposed approach was implemented in MATLAB and tested in 61 clinical CT studies of the lower limb on the transverse plane and in 107 T1-weighted MRI studies of the knee joint on the sagittal plane. The atlas-based segmentation combined with the fuzzy methods achieved a Dice index of 85.52-89.48% for the bone structures of the knee joint.

Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system.

BACKGROUND AND PURPOSE: To investigate the performance of head-and-neck (HN) organs-at-risk (OAR) automatic segmentation (AS) using four atlas-based (ABAS) and two deep learning (DL) solutions. MATERIAL AND METHODS: All patients underwent iodine contrast-enhanced planning CT. Fourteen OAR were manually delineated. DL.1 and DL.2 solutions were trained with 63 mono-centric patients and > 1000 multi-centric patients, respectively. Ten and 15 patients with varied anatomies were selected for the atlas library and for testing, respectively. The evaluation was based on geometric indices (DICE coefficient and 95th percentile-Hausdorff Distance (HD95%)), time needed for manual corrections and clinical dosimetric endpoints obtained using automated treatment planning. RESULTS: Both DICE and HD95% results indicated that DL algorithms generally performed better compared with ABAS algorithms for automatic segmentation of HN OAR. However, the hybrid-ABAS (ABAS.3) algorithm sometimes provided the highest agreement to the reference contours compared with the 2 DL. Compared with DL.2 and ABAS.3, DL.1 contours were the fastest to correct. For the 3 solutions, the differences in dose distributions obtained using AS contours and AS + manually corrected contours were not statistically significant. High dose differences could be observed when OAR contours were at short distances to the targets. However, this was not always interrelated. CONCLUSION: DL methods generally showed higher delineation accuracy compared with ABAS methods for AS segmentation of HN OAR. Most ABAS contours had high conformity to the reference but were more time consuming than DL algorithms, especially when considering the computing time and the time spent on manual corrections.