Search

Background Cerebral small vessel disease (cSVD) is a late consequence of cerebral microvascular dysfunction (MVD). MVD is hard to measure in the brain due to its limited accessibility. Extracerebral MVD (eMVD) measures can give insights in the etiology of cerebral MVD, as MVD may be a systemic process. We aim to investigate whether a compound score consisting of several eMVD measures is associated with structural cSVD MRI markers. Methods Cross-sectional data of the population-based Maastricht Study was used (n = 1872, mean age 59 ± 8 years, 49% women). Measures of eMVD included flicker light-induced retinal arteriolar and venular dilation response (retina), albuminuria and glomerular filtration rate (kidney), heat-induced skin hyperemia (skin), and plasma biomarkers of endothelial dysfunction (sICAM-1, sVCAM-1, sE-selectin, and von Willebrand factor). These measures were standardized into z scores and summarized into a compound score. Linear and logistic regression analyses were used to investigate the associations between the compound score and white matter hyperintensity (WMH) volume, and the presence of lacunes and microbleeds, as measured by brain MRI. Results The eMVD compound score was associated with WMH volume independent of age, sex, and cardiovascular risk factors (St β 0.057 [95% CI 0.010–0.081], p value 0.01), but not with the presence of lacunes (OR 1.011 [95% CI 0.803–1.273], p value 0.92) or microbleeds (OR 1.055 [95% CI 0.896–1.242], p value 0.52). Conclusion A compound score of eMVD is associated with WMH volume. Further research is needed to expand the knowledge about the role of systemic MVD in the pathophysiology of cSVD.

BackgroundIndividuals with depression often experience widespread and persistent cognitive deficits, which might be due to brain atrophy and cerebral small vessel disease (CSVD). We therefore studied the associations between depression, markers of brain atrophy and CSVD, and cognitive functioning.MethodsWe used cross-sectional data from the population-based Maastricht study (n = 4734; mean age 59.1 ± 8.6 years, 50.2% women), which focuses on type 2 diabetes. A current episode of major depressive disorder (MDD, n = 151) was assessed by the Mini-International Neuropsychiatric Interview. Volumes of cerebral spinal fluid, white matter, gray matter and white matter hyperintensities, presence of lacunar infarcts and cerebral microbleeds, and total CSVD burden were assessed by 3 T magnetic resonance imaging. Multiple linear and logistic regression analyses tested the associations between MDD, brain markers and cognitive functioning in memory, information processing speed, and executive functioning & attention, and presence of cognitive impairment. Structural equation modeling was used to test mediation.ResultsIn fully adjusted models, MDD was associated with lower scores in information processing speed [mean difference = −0.18(−0.28;−0.08)], executive functioning & attention [mean difference = −0.13(−0.25;−0.02)], and with higher odds of cognitive impairment [odds ratio (OR) = 1.60(1.06;2.40)]. MDD was associated with CSVD in participants without type 2 diabetes [OR = 1.65(1.06;2.56)], but CSVD or other markers of brain atrophy or CSVD did not mediate the association with cognitive functioning.ConclusionsMDD is associated with more impaired information processing speed and executive functioning & attention, and overall cognitive impairment. Furthermore, MDD was associated with CSVD in participants without type 2 diabetes, but this association did not explain an impaired cognitive profile.

Background and ObjectivesObservational research has shown that a substantial proportion of all dementia cases worldwide are attributable to modifiable risk factors. Dementia risk scores might be useful to identify high-risk individuals and monitor treatment adherence. The objective of this study was to investigate whether a dementia risk score, the Lifestyle for Brain Health (LIBRA) index, is associated with MRI markers and cognitive functioning/impairment in the general population.MethodsCross-sectional data were used from the observational population-based cohort of The Maastricht Study. The weighted compound score of LIBRA (including 12 dementia risk and protective factors, e.g., hypertension, physical inactivity) was calculated, with higher scores indicating higher dementia risk. Standardized volumes of white matter, gray matter, and CSF (as proxy for general brain atrophy), white matter hyperintensities, and presence of cerebral small vessel disease were derived from 3T MRI. Cognitive functioning was tested in 3 domains: memory, information processing speed, and executive function and attention. Values ≤1.5 SDs below the average were defined as cognitive impairment. Multiple regression analyses and structural equation modeling were used, adjusted for age, sex, education, intracranial volume, and type 2 diabetes.ResultsParticipants (n = 4,164; mean age 59 years; 49.7% men) with higher LIBRA scores (mean 1.19, range −2.7 to 9.2), denoting higher dementia risk, had higher volumes of white matter hyperintensities (β = 0.051,p= 0.002) and lower scores on information processing speed (β = −0.067,p= 0.001) and executive function and attention (β = −0.065,p= 0.004). Only in men, associations between LIBRA score and volumes of gray matter (β = −0.093,p< 0.001) and CSF (β = 0.104,p< 0.001) and memory (β = −0.054,p= 0.026) were found. White matter hyperintensities and CSF volume partly mediated the association between LIBRA score and cognition.DiscussionHigher health- and lifestyle-based dementia risk is associated with markers of general brain atrophy, cerebrovascular pathology, and worse cognition, suggesting that LIBRA meaningfully summarizes individual lifestyle-related brain health. Improving LIBRA factors on an individual level might improve population brain health. Sex differences in lifestyle-related pathology and cognition need to be further explored.Classification of EvidenceThis study provides Class II evidence that higher LIBRA scores are significantly associated with lower scores in some cognitive domains and a higher risk of cognitive impairment.

Background Cerebral small vessel disease (CSVD) and neurodegeneration may be involved in the development and persistence of late-life depressive symptoms, but longitudinal evidence is scarce. We investigated the longitudinal associations of markers of CSVD and brain atrophy with incident depressive symptoms and the course of depressive symptoms, above and below 60 years of age. Methods White matter hyperintensity volumes (WMH), presence of lacunar infarcts and cerebral microbleeds, and white matter, grey matter, and cerebral spinal fluid volumes were assessed at baseline by 3T MRI in The Maastricht Study (mean age 59.5±8.5 years, 49.6% women, n=4,347; 16,535 person-years of follow-up). Clinically relevant depressive symptoms (9-item Patient Health Questionnaire≥10) were assessed at baseline and annually over seven years. We used Cox regression and multinomial logistic regression analyses adjusted for demographic, cardiovascular, and lifestyle risk factors. Results Above 60 years of age, larger WMH volumes were associated with an increased risk for incident depressive symptoms (HR[95%CI]:1.24[1.04;1.48] per SD) and a persistent course of depressive symptoms (OR:1.44[1.04;2.00] per SD). Total CSVD burden was associated with persistent depressive symptoms irrespective of age (adjusted OR:1.58[1.03;2.43]), while no associations were found for general markers of brain atrophy. Limitationss Our findings need replication in other large-scale population-based studies. Conclusions Our findings may suggest a temporal association of larger WMH volume with the incidence and persistence of late-life depression in the general population and may provide a potential target for the prevention of chronic late-life depression.

PURPOSE: Permanent breast seed implant (PBSI) using 103Pd is emerging as an effective adjuvant radiation technique for early-stage breast cancer. However, clinical dose evaluations follow the water-based TG-43 approach with its considerable approximations. Towards clinical adoption of advanced TG-186 model-based dose evaluations, this study presents a comprehensive investigation for PBSI considering both target and normal tissue doses. METHODS: Dose calculations are performed with the free open-source Monte Carlo (MC) code, egs_brachy, using 2 types of virtual patient models: TG43sim (simulated TG-43 conditions: all water with no interseed attenuation) and MCref (heterogeneous tissue modelling from patient CT, interseed attenuation, seeds at implant angle) for 35 patients. Sensitivity of dose metrics to seed orientation and the threshold for glandular/adipose tissue segmentation are assessed. RESULTS: In the target volume, D90 is 14.1% lower with MCref than with TG43sim, on average. Conversely, normal tissue doses are generally higher with MCref than with TG43sim, e.g., by 22% for skin D1cm2, 82% for ribs Dmax, and 71% for heart D1cm3. Discrepancies between MCref and TG43sim doses vary over the patient cohort, as well as with the tissue and metric considered. Doses are sensitive to the glandular/adipose tissue segmentation threshold with differences of a few percent in target D90. Skin doses are sensitive to seed orientation. CONCLUSIONS: TG-43 dose evaluations generally underestimate doses to critical normal organs/tissues while overestimating target doses. There is considerable variation in MCref and TG43sim on a patient-by-patient basis, suggesting that clinical adoption of patient-specific MC dose calculations is motivated. The MCref framework presented herein provides a consistent modelling approach for clinical implementation of advanced TG-186 dose calculations., Comment: 25 pages, 5 figures, 1 table

To evaluate the performance of novel spiral MRSI and tissue segmentation pipeline of the brain, to investigate neurometabolic changes in normal-appearing white matter (NAWM) and white matter lesions (WML) of stable relapsing remitting multiple sclerosis (RRMS) compared to healthy controls (HCs).Spiral 3D MRSI using LASER-GOIA-W [16,4] was undertaken on 16 RRMS patients and 9 HCs, to acquire MRSI data from a large volume of interest (VOI) 320 cmCompared to HCs, RRMS demonstrated a statistically significant reduction in all mean brain tissues and increase in CSF volume. Within VOI, WM decreased (-10%) and CSF increased (41%) in RRMS compared to HCs (p 0.001). MRSI revealed that total creatine (tCr) ratios of N-acetylaspartate and glutamate+glutamine in WML were significantly lower than NAWM-MS (-9%, -8%) and HCs (-14%, -10%), respectively. Myo-inositol/tCr in WML was significantly higher than NAWM-MS (14%) and HCs (10%). SVM of MRSI yielded accuracy, sensitivity and specificity of 86%, 95%, and 70%, respectively for HCs vs WML, which were higher than HC vs NAWM and WML vs NAWM models.This study demonstrates the benefit of MRSI in evaluating MS neurometabolic changes in NAWM. SVM of MRSI data in the MS brain may be suited for clinical monitoring and progression of MS patients. Longitudinal MRSI studies are warranted.

Body composition entails the measurement of muscle and fat mass in the body and has been shown to impact clinical outcomes in various aspects of human health. As a result, the need is growing for reliable and efficient noninvasive tools to measure body composition. Traditional methods of estimating body composition, anthropomorphic measurements, dual-energy X-ray absorptiometry, and bioelectrical impedance, are limited in their application. Cross-sectional imaging remains the reference standard for body composition analysis and is accomplished through segmentation of computed tomography and magnetic resonance imaging studies. However, manual segmentation of images by an expert reader is labor intensive and time consuming, limiting its implementation in large-scale studies and in routine clinical practice. In this review, novel methods to automate the process of body composition measurement are discussed including the application of artificial intelligence and deep learning to tissue segmentation.

Accurate segmentation of brain tissues, such as gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF), in magnetic resonance imaging (MRI) images, is helpful for the diagnosis of neurological disorders, such as schizophrenia, Alzheimer's disease, and dementia. Studies on MRI-based brain segmentation have received significant attention in recent years based on the non-invasive imaging and good soft-tissue contrast provided by MRI. A number of studies have used conventional machine learning strategies, as well as convolutional neural network approaches. In this paper, we propose a patch-wise M-net architecture for the automatic segmentation of brain MRI images. In the proposed brain segmentation method, slices from a brain MRI scan are divided into non-overlapping patches, which are then fed into an M-net model with corresponding ground-truth patches to train the network, which is composed of two encoder-decoder processes. Dilated convolutional kernels with different sizes are used in the encoder and decoder modules to derive abundant semantic features from brain MRI scans. The proposed patch-wise M-net overcomes the drawbacks of conventional methods and provides greater retention of fine details. The proposed M-net model was trained and tested on the open-access series of imaging studies dataset. The performance was measured quantitatively using the Dice similarity coefficient. Experimental results demonstrate that the proposed method achieves average segmentation accuracies of 94.81% for CSF, 95.44% for GM, and 96.33% for WM, meaning it outperforms state-of-the-art methods.

Objective Brain atrophy has the potential to become a biomarker for severity of radiation-induced side-effects. Particularly brain tumour patients can show great MRI signal changes over time caused by e.g. oedema, tumour progress or necrosis. The goal of this study was to investigate if such changes affect the segmentation accuracy of normal appearing brain and thus influence longitudinal volumetric measurements. Materials and methods T1-weighted MR images of 52 glioblastoma patients with unilateral tumours acquired before and three months after the end of radio(chemo)therapy were analysed. GM and WM volumes in the contralateral hemisphere were compared between segmenting the whole brain (full) and the contralateral hemisphere only (cl) with SPM and FSL. Relative GM and WM volumes were compared using paired t tests and correlated with the corresponding mean dose in GM and WM, respectively. Results Mean GM atrophy was significantly higher for full segmentation compared to cl segmentation when using SPM (mean ± std: ΔVGM,full = − 3.1% ± 3.7%, ΔVGM,cl = − 1.6% ± 2.7%; p d = 0.62). GM atrophy was significantly correlated with the mean GM dose with the SPM cl segmentation (r = − 0.4, p = 0.004), FSL full segmentation (r = − 0.4, p = 0.004) and FSL cl segmentation (r = -0.35, p = 0.012) but not with the SPM full segmentation (r = − 0.23, p = 0.1). Conclusions For accurate normal tissue volume measurements in brain tumour patients using SPM, abnormal tissue needs to be masked prior to segmentation, however, this is not necessary when using FSL.

We qualitatively compare three image segmentation techniques (filter and threshold-based segmentation, texture-based clustering and deep learning) for histologic images of intracranial aneurysms. Due to remodeling of the vessel wall and aneurysm formation, the tissue is highly diverse. Only the deep learning segmentation provided semantic information about the segmented tissue. The other segmentation techniques were designed to segment areas of different textures and tissues, respectively. Therefore, in contrast to the deep learning approach, they did not require knowledge of all tissue types possible occurring in intracranial aneurysms. Rare tissue classes were missed by the deep learning segmentation, but the resolution of the deep learning segmentation was better than the ground truth segmentation. Overall, the deep learning segmentation of ten classes achieved a test accuracy of 60.68%.

Digital analysis of cancer specimens using spectroscopic imaging coupled to machine learning is an emerging area that links spatially localized spectral signatures to tissue structure and disease. In this study, we examine the role of spatial-spectral tradeoffs in infrared spectroscopic imaging configurations for probing tumors and the associated microenvironment profiles at different levels of model complexity. We image breast tissue using standard and high-definition Fourier Transform Infrared (FT-IR) imaging and systematically examine the localization, spectral origins, and utility of data for classification. Results demonstrate that higher spatial detail provides high sensitivity and specificity of tissue segmentation, despite the increased subcellular variability. High definition imaging also allows accurate analysis of complex, multiclass models of breast tissue without compromising accuracy. A comparison of results also highlights the key differences in the data distributions and classification performance across modalities to better guide decision making for acquiring and analyzing IR imaging data for specific histopathological models.

Osteoarthritis (OA) is among the top 10 burdensome diseases, with the knee the most affected joint. Magnetic resonance imaging (MRI) allows whole-knee assessment, making it ideally suited for imaging OA, considered a multitissue disease. Three-dimensional (3D) MRI enables the comprehensive assessment of OA, including quantitative morphometry of various joint tissues. Manual tissue segmentation on 3D MRI is challenging but may be overcome by advanced automated image analysis methods including artificial intelligence (AI). This review presents examples of the utility of 3D MRI for knee OA, focusing on the articular cartilage, bone, meniscus, synovium, and infrapatellar fat pad, and it highlights several applications of AI that facilitate segmentation, lesion detection, and disease classification.

Electroencephalogram (EEG) is a method to monitor electrophysiological activity on the scalp, which represents the macroscopic activity of the brain. However, it is challenging to identify EEG source regions inside the brain based on data measured by a scalp-attached network of electrodes. The accuracy of EEG source localization significantly depends on the type of head modeling and inverse problem solver. In this study, we adopted different models with a resolution of 0.5 mm to account for thin tissues/fluids, such as the cerebrospinal fluid (CSF) and dura. In particular, a spatially dependent conductivity (segmentation-free) model created using deep learning was developed and used for more realist representation of electrical conductivity. We then adopted a multi-grid-based finite-difference method (FDM) for forward problem analysis and a sparse-based algorithm to solve the inverse problem. This enabled us to perform efficient source localization using high-resolution model with a reasonable computational cost. Results indicated that the abrupt spatial change in conductivity, inherent in conventional segmentation-based head models, may trigger source localization error accumulation. The accurate modeling of the CSF, whose conductivity is the highest in the head, was an important factor affecting localization accuracy. Moreover, computational experiments with different noise levels and electrode setups demonstrate the robustness of the proposed method with segmentation-free head model.

Pressure ulcers (PUs) are a common problem associated with great morbidity and cost. Because of the lack of professional personnel in the institutions or home care system, the diagnosis and treatment of PUs were sometimes delayed. We aim to develop an automatic tissue classification and severity evaluation system of PUs using AI technology. All PU images were collected from patients in the Far Eastern Memorial Hospital (FEMH) in recent 3 years and labeled according to different tissue types. The labeled images were used to train the tissue segmentation model with U-net convolutional neural network (CNN). The percentage of the different tissue can be calculated automatically and would be compared with the manually labeled one. The output of tissue classification was transformed to a clinical decision support system (CDSS) with a rule-base formula. Our study showed that proposed system can classify each tissue automatically and reach an accuracy about 93.6%. However, the CDSS's accuracy rate was only 64% for the referral suggestion and 62% for the care recommendation. Hence, the system should be modified with more data and information.

In this paper, we propose a multi-scale feature extraction with novel attention-based convolutional learning using the U-SegNet architecture to achieve segmentation of brain tissue from a magnetic resonance image (MRI). Although convolutional neural networks (CNNs) show enormous growth in medical image segmentation, there are some drawbacks with the conventional CNN models. In particular, the conventional use of encoder-decoder approaches leads to the extraction of similar low-level features multiple times, causing redundant use of information. Moreover, due to inefficient modeling of long-range dependencies, each semantic class is likely to be associated with non-accurate discriminative feature representations, resulting in low accuracy of segmentation. The proposed global attention module refines the feature extraction and improves the representational power of the convolutional neural network. Moreover, the attention-based multi-scale fusion strategy can integrate local features with their corresponding global dependencies. The integration of fire modules in both the encoder and decoder paths can significantly reduce the computational complexity owing to fewer model parameters. The proposed method was evaluated on publicly accessible datasets for brain tissue segmentation. The experimental results show that our proposed model achieves segmentation accuracies of 94.81% for cerebrospinal fluid (CSF), 95.54% for gray matter (GM), and 96.33% for white matter (WM) with a noticeably reduced number of learnable parameters. Our study shows better segmentation performance, improving the prediction accuracy by 2.5% in terms of dice similarity index while achieving a 4.5 times reduction in the number of learnable parameters compared to previously developed U-SegNet based segmentation approaches. This demonstrates that the proposed approach can achieve reliable and precise automatic segmentation of brain MRI images.

Due to the inevitable noise and intensity inhomogeneity during magnetic resonance (MR) imaging, brain MR image segmentation is still a challenging problem. Thus, a novel robust local anisotropic clustering energy minimization model is proposed to segment brain MR image corrupted by noise and intensity inhomogeneity. We first design an anisotropic weighting scheme and utilize the image patch to replace each pixel in original image, which can incorporate the local spatial information into the energy function to improve robustness. Then, a multiplicative framework that is composed of the true image and the bias field is used to correct the bias field and segment brain MR images. We represent bias field using a linear combination of the orthogonal basis functions to insure the smoothly and slowly varying property. Accordingly, brain tissue segmentation and bias field correction can be simultaneously performed in the energy minimization iterative process, and the experimental results testify that the proposed method obtains a satisfactory result compared with state-of-the-art models.

Accurate segmentation of infant brain images into different regions of interest is one of the most important fundamental steps in studying early brain development. In the isointense phase (approximately 6–8 months of age), white matter and gray matter exhibit similar levels of intensities in magnetic resonance (MR) images, due to the ongoing myelination and maturation. This results in extremely low tissue contrast and thus makes tissue segmentation very challenging. Existing methods for tissue segmentation in this isointense phase usually employ patch-based sparse labeling on single modality. To address the challenge, we propose a novel 3-D multimodal fully convolutional network (FCN) architecture for segmentation of isointense phase brain MR images. Specifically, we extend the conventional FCN architectures from 2-D to 3-D, and, rather than directly using FCN, we intuitively integrate coarse (naturally high-resolution) and dense (highly semantic) feature maps to better model tiny tissue regions, in addition, we further propose a transformation module to better connect the aggregating layers; we also propose a fusion module to better serve the fusion of feature maps. We compare the performance of our approach with several baseline and state-of-the-art methods on two sets of isointense phase brain images. The comparison results show that our proposed 3-D multimodal FCN model outperforms all previous methods by a large margin in terms of segmentation accuracy. In addition, the proposed framework also achieves faster segmentation results compared to all other methods. Our experiments further demonstrate that: 1) carefully integrating coarse and dense feature maps can considerably improve the segmentation performance; 2) batch normalization can speed up the convergence of the networks, especially when hierarchical feature aggregations occur; and 3) integrating multimodal information can further boost the segmentation performance.

Identification and treatment of chronic wounds (CWs) are considered economic and social challenges, especially with respect to bedridden and elderly persons. CWs do not follow a predictive course of healing within a particular period. Their treatment and management costs are very high. Also, CWs decrease quality of life for patients, which cause severe pain and discomfort. In this paper, we proposed a comprehensive wound healing assessment framework based on current appearance, texture, and prior visual appearance analysis to handle different types of CWs depending on extracting various tissue types. The framework provided an accurate evaluation tool for the CW healing process depending on extracting and fusing significant features from the CWs RGB images. Non-negative matrix factorization (NMF) was used to retrieve the most significant features to reduce computation time. The gradient boosted trees (GBT) classifier was used to classify different tissue types. Finally, the healing assessment of the CWs depended on calculating the improvement in the area of the necrotic eschar, slough, granulation, and healing epithelial tissues. The framework was trained and tested using 377 RGB images from Medetec wound database and national pressure ulcer advisory panel website. The proposed system achieved an average accuracy of 96% for tissue classification, which helps in obtaining an accurate CW healing assessment. This result can be considered as a promising result when compared to the other state-of-the-art techniques.

Accurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNNs) approaches. In particular, in this paper, we analyze a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs. Our study focuses on understanding the architectural strengths and weaknesses of literature-like approaches. We implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and use them within a standard pipeline. We evaluate them using the IBSR18, MICCAI2012, and iSeg2017 datasets as they contain infant and adult data and exhibit different voxel spacing, image quality, number of scans, and available imaging modalities. The discussion is driven in four directions: comparison between 2D and 3D approaches, the relevance of multiple imaging sequences, the effect of patch size, and the impact of patch overlap as a sampling strategy for training and testing models. Besides the aforementioned analysis, we show that the methods under evaluation can yield top performance on the three data collections. A public version is accessible to download from our research website to encourage other researchers to explore the evaluation framework This work was supported in part by the La Fundació la Marató de TV3 and in part by the Retos de Investigació under Grant TIN2014-55710-R, Grant TIN2015-73563-JIN, and Grant DPI2017-86696-R from the Ministerio de Ciencia y Tecnología. The work of J. Bernal and K. Kushibar was supported by the Catalan Government under Grant FI-DGR2017, Grant 2017FI B00476, and Grant 2017FI B00372. The work of M. Cabezas was supported by the Juan de la Cierva–Incorporación Grant from the Spanish Government under Grant IJCI-2016-29240

Background Segmentation of brain MR images of neonates is a primary step for assessment of brain evolvement. Advanced segmentation techniques used for adult brain MRI are not companionable for neonates, due to extensive dissimilarities in tissue properties and head structure. Existing segmentation methods for neonates utilizes brain atlases or requires manual elucidation, which results into improper and atlas dependent segmentation. Objective The primary objective of this work is to develop fully automatic, atlas free, and robust system to segment and classify brain tissues of newborn infants from magnetic resonance images. Study Design In this study, we propose a fully automatic, atlas-free pipeline based Neural Tree approach for segmentation of newborn brain MRI which utilizes resourceful local resemblance factor such as concerning, connectivity, structure, and relative tissue location. Physical collaboration and uses of an atlas are not required in proposed method and at the same time skirting atlas-associated bias which results in improved segmentation. Proposed technique segments and classify brain tissues both at global and tissue level. Results We examined our results through visual assessment by neonatologists and quantitative comparisons that show first-rate concurrence with proficient manual segmentations. The implementation results of the proposed technique provided a good overall accuracy of 91.82% for the segmentation of brain tissues as compared with other methods. Conclusion The pipelined-based neural tree approach along with local similarity factor segments and classify brain tissues. The proposed automated system have higher dice similarity coefficient as well as computational speed.

Background and ObjectiveMagnetic resonance (MR) technology enables physicians to employ digital imaging as a tool to identify and analyze brain tumors as well as to differentiate between healthy and tumor tissues. Since precisely defining the tumor position is a challenging task, segmentation is necessary stage in medical image processing. Segmentation is defined as the division of a given image into non-overlapping regions with relatively similar features. Recently, various techniques have been proposed for MR image segmentation. MethodsIn this paper, a new ensemble clustering technique based on neural network algorithm (NNA) was introduced for segmentation of MRI Brain tissues, which consists of two main phases: training phase and testing phase. In the former, pixels with the same amount of light intensity were put into one group via simple linear iterative clustering (SLIC) algorithm, creating superpixels. Then, the combination of GrowCut methods and Zernik’s feature extraction method and clustering and classification ensemble learning, including multi-layer perceptron neural network algorithm (MLP), Support vector machine (SVM) and K nearest neighbor (KNN), are based on geometric features in order to detect the division of MRI Brain tissues. The improved GrowCut method, based on the geometric properties of the images, has been used to segmentation the image of the brain from MRI images. Then, with the help of Zernik’s technique, image features were extracted based on the features of the edges and the texture of the images. Finally, the ensemble learning methods such as KNN, SVM, and MLP combine together for attempted to detect MRI Brain tissues. Results and ConclusionsThe performance of the proposed method was evaluated on the IBSR20 dataset and the obtained results were compared separately with the six basic clustering methods (that together are creating the ensemble clustering technique). The results demonstrated that the proposed technique outperforms other clustering algorithms in terms of segmentation accuracy in most of the experimental cases. Therefore, by presenting experiments to diagnose MRI Brain tissues, it was observed that the proposed method detected the MR with acceptable accuracy and the combination of ensemble learning methods and GrowCut and Zernik’s feature extraction methods was successful.

We assessed whether objectively measured low- and high-intensity physical activity (LPA and HPA) and sedentary time (ST) were associated with white matter connectivity, both throughout the whole brain and in brain regions involved in motor function. In the large population-based Maastricht Study (n = 1715, age 59.6 ± 8.1 (mean ± standard deviation) years, and 48% women), the amounts of LPA, HPA, and ST were objectively measured during 7 days by an activPAL accelerometer. In addition, using 3T structural and diffusion MRI, we calculated whole brain node degree and node degree of the basal ganglia and primary motor cortex. Multivariable linear regression analysis was performed, and we report standardized regression coefficients (stβ) adjusted for age, sex, education level, wake time, diabetes status, BMI, office systolic blood pressure, antihypertensive medication, total-cholesterol-to-HDL-cholesterol ratio, lipid-modifying medication, alcohol use, smoking status, and history of cardiovascular disease. Lower HPA was associated with lower whole brain node degree after full adjustment (stβ [95%CI] = − 0.062 [− 0.101, − 0.013]; p = 0.014), whereas lower LPA (stβ [95%CI] = − 0.013 [− 0.061, 0.034]; p = 0.580) and higher ST (stβ [95%CI] = − 0.030 [− 0.081, 0.021]; p = 0.250) was not. In addition, lower HPA was associated with lower node degree of the basal ganglia after full adjustment (stβ [95%CI] = − 0.070 [− 0.121, − 0.018]; p = 0.009). Objectively measured lower HPA, but not lower LPA and higher ST, was associated with lower whole brain node degree and node degree in specific brain regions highly specialized in motor function. Further research is needed to establish whether more HPA may preserve structural brain connectivity.

Highlights • A U-Net incorporating spatial prior information can successfully segment 6 brain tissue types. • The U-Net was able to segment gray and white matter in the presence of lesions. • The U-Net surpassed the performance of its source algorithm in an external dataset. • Segmentations were produced in a hundredth of the time of its predecessor algorithm., Delineation and quantification of normal and abnormal brain tissues on Magnetic Resonance Images is fundamental to the diagnosis and longitudinal assessment of neurological diseases. Here we sought to develop a convolutional neural network for automated multiclass tissue segmentation of brain MRIs that was robust at typical clinical resolutions and in the presence of a variety of lesions. We trained a 3D U-Net for full brain multiclass tissue segmentation from a prior atlas-based segmentation method on an internal dataset that consisted of 558 clinical T1-weighted brain MRIs (453/52/53; training/validation/test) of patients with one of 50 different diagnostic entities (n = 362) or with a normal brain MRI (n = 196). We then used transfer learning to refine our model on an external dataset that consisted of 7 patients with hand-labeled tissue types. We evaluated the tissue-wise and intra-lesion performance with different loss functions and spatial prior information in the validation set and applied the best performing model to the internal and external test sets. The network achieved an average overall Dice score of 0.87 and volume similarity of 0.97 in the internal test set. Further, the network achieved a median intra-lesion tissue segmentation accuracy of 0.85 inside lesions within white matter and 0.61 inside lesions within gray matter. After transfer learning, the network achieved an average overall Dice score of 0.77 and volume similarity of 0.96 in the external dataset compared to human raters. The network had equivalent or better performance than the original atlas-based method on which it was trained across all metrics and produced segmentations in a hundredth of the time. We anticipate that this pipeline will be a useful tool for clinical decision support and quantitative analysis of clinical brain MRIs in the presence of lesions.

Computer-aided detection (CAD) approaches have shown promising results for early esophageal cancer detection using Volumetric Laser Endoscopy (VLE) imagery. However, the relatively slow and computationally costly tissue segmentation employed in these approaches hamper their clinical applicability. In this paper, we propose to reframe the 2D tissue segmentation problem into a 1D tissue boundary detection problem. Instead of using an encoder-decoder architecture, we propose to follow the tissue boundary using a Recurrent Neural Network (RNN), exploiting the spatio-temporal relations within VLE frames. We demonstrate a near state-of-the-art performance using 18 times less floating point operations, enabling real-time execution in clinical practice.

Blood vessels 3D rendering has numerous applications, ranging from diagnosis to pre-procedural and surgical approaches as it enriches vessels visualization for the clinician. In this paper, we propose a 3D blood vessels segmentation method designed for use with a cone beam computed tomography (CBCT). The algorithm constitutes a module in the development of an angio-CT visualization system, based on augmented or virtual reality as instruments supporting and improving medical decisions.

Medical image segmentation is an essential and complex task due to the complexity of images obtained from different modalities. The basic methods used for segmentation are discussed in this chapter. For semiautomatic approaches, human intervention is needed as guidance of initial points. Fully automatic methods do not require the prior information for the segmentation process. The researcher used various machine learning algorithms to make the segmentation process automatic or semiautomatic. But the single method is insufficient to segment the medical images; hence, multiple algorithms with modification in original algorithms have been proposed by the researchers. These methods surely have been given more accurate results.

Pathology slides of malignancies are segmented using lightweight convolutional neural networks (CNNs) that may be deployed on mobile devices. This is made possible by preprocessing candidate images to make CNN analysis tractable and also to exclude regions unlikely to be diagnostically relevant. In a training phase, labeled whole-slide histopathology images are first downsampled and decomposed into square tiles. Tiles corresponding to diseased regions are analyzed to determine boundary values of a visual criterion, image entropy. A lightweight CNN is then trained to distinguish tiles of diseased and non-diseased tissue, and if more than one disease type is present, to discriminate among these as well. A segmentation is generated by downsampling and tiling a candidate image, and retaining only those tiles with values of the visual criterion falling within the previously established extrema. The sifted tiles, which now exclude much of the non-diseased image content, are efficiently and accurately classified by the trained CNN. Tiles classified as diseased tissue -- or in the case of multiple possible subtypes, as the dominant subtype in the tile set -- are combined, either as a simple union or at a pixel level, to produce a segmentation mask or map. This approach was applied successfully to two very different datasets of large whole-slide images, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast-cancer metastases. Scored using standard similarity metrics, the segmentations exhibited notably high recall, even when tiles were large relative to tumor features. With segmentations that can be generated locally and broadcast widely, efficiencies in utilizing expert resources can be achieved.

Summary Background A higher cognitive reserve and brain reserve could decrease mortality risk, but the interaction of these factors with general age-related loss of physical fitness (eg, frailty) remains unclear with regards to mortality. We investigated the associations of cognitive and brain reserve with mortality and the interaction of cognitive and brain reserve with frailty within these associations. Methods Within the observational population-based cohort of the Rotterdam Study, we included participants who visited the research centre for a cognitive assessment between March 2, 2009, and March 1, 2012. Participants with an incomplete assessment of cognition, no data on education attainment, no MRI or an MRI of insufficient quality, three or more missing frailty criteria, or a dementia diagnosis were excluded. Participants were followed up until their death or May 1, 2019. Cognitive reserve was defined as a latent variable that captures variance across five cognitive tests. Brain reserve was defined as the proportion of healthy-appearing brain volume relative to total intracranial volume measured with 1·5 Tesla MRI. Frailty was defined according to Fried's frailty phenotype; participants meeting at least one of the five criteria were considered frail. Hazard ratios (HRs) for associations of cognitive reserve, brain reserve, frailty, and reserve–frailty interactions with the risk of mortality were estimated using Cox regression models. Findings 2878 individuals in the Rotterdam Study who visited the research centre for a cognitive assessment were considered eligible. 1388 individuals were excluded due to incomplete or missing data or a dementia diagnosis. 1490 participants with valid information on cognitive reserve, brain reserve, and frailty were included (mean age 74·3 years [SD 5·5]; 815 [55%] female participants). 810 (54%) participants were classified as frail. A higher cognitive reserve (HR 0·87 per SD, 95% CI 0·76–0·99, p=0·036) and a higher brain reserve (0·85 per SD, 0·72–1·00, p=0·048) were associated with a lower risk of mortality, after adjusting for sex, age, educational level, body-mass index, smoking status, and number of comorbidities. The association between cognitive reserve and mortality was more pronounced (0·77 per SD, 0·66–0·90, p=0·0012) when the cognitive reserve–frailty interaction (p=0·0078) was included, indicating that higher cognitive reserve is related to lower mortality in individuals with frailty. The brain reserve–frailty interaction was non-significant. Interpretation Higher cognitive reserve and higher brain reserve were associated with a lower mortality risk. Additionally, cognitive reserve and frailty interact in the association with mortality, such that higher cognitive reserve is particularly associated with lower mortality in frail participants. Funding Netherlands Organization for Health Research and Development and EU Horizon 2020 research programme.

In pathology labs worldwide, we see an increasing number of tissue samples that need to be assessed without the same increase in the number of pathologists. Computational pathology, where digital scans of histological samples called whole-slide images (WSI) are processed by computational tools, can be of help for the pathologists and is gaining research interests. Most research effort has been given to classify slides as being cancerous or not, localization of cancerous regions, and to the “big-four” in cancer: breast, lung, prostate, and bowel. Urothelial carcinoma, the most common form of bladder cancer, is expensive to follow up due to a high risk of recurrence, and grading systems have a high degree of inter- and intra-observer variability. The tissue samples of urothelial carcinoma contain a mixture of damaged tissue, blood, stroma, muscle, and urothelium, where it is mainly muscle and urothelium that is diagnostically relevant. A coarse segmentation of these tissue types would be useful to i) guide pathologists to the diagnostic relevant areas of the WSI, and ii) use as input in a computer-aided diagnostic (CAD) system. However, little work has been done on segmenting tissue types in WSIs, and on computational pathology for urothelial carcinoma in particular. In this work, we are using convolutional neural networks (CNN) for multiscale tile-wise classification and coarse segmentation, including both context and detail, by using three magnification levels: 25x, 100x, and 400x. 28 models were trained on weakly labeled data from 32 WSIs, where the best model got an F1-score of 96.5% across six classes. The multiscale models were consistently better than the single-scale models, demonstrating the benefit of combining multiple scales. No tissue-class ground-truth for complete WSIs exist, but the best models were used to segment seven unseen WSIs where the results were manually inspected by a pathologist and are considered as very promising.

BACKGROUND AND PURPOSE: Neonatal MR imaging brain volume measurements can be used as biomarkers for long-term neurodevelopmental outcome, but quantitative volumetric MR imaging data are not usually available during routine radiologic evaluation. In the current study, the feasibility of automated quantitative brain volumetry and image reconstruction via synthetic MR imaging in very preterm infants was investigated. MATERIALS AND METHODS: Conventional and synthetic T1WIs and T2WIs from 111 very preterm infants were acquired at term-equivalent age. Overall image quality and artifacts of the conventional and synthetic images were rated on a 4-point scale. Legibility of anatomic structures and lesion conspicuity were assessed on a binary scale. Synthetic MR volumetry was compared with that generated via MANTiS, which is a neonatal tissue segmentation toolbox based on T2WI. RESULTS: Image quality was good or excellent for most conventional and synthetic images. The 2 methods did not differ significantly regarding image quality or diagnostic performance for focal and cystic WM lesions. Dice similarity coefficients had excellent overlap for intracranial volume (97.3%) and brain parenchymal volume (94.3%), and moderate overlap for CSF (75.6%). Bland-Altman plots demonstrated a small systematic bias in all cases (1.7%–5.9%) CONCLUSIONS: Synthetic T1WI and T2WI sequences may complement or replace conventional images in neonatal imaging, and robust synthetic volumetric results are accessible from a clinical workstation in less than 1 minute. Via the above-described methods, volume assessments could be routinely used in daily clinical practice.

Due to the extremely low intensity contrast between the white matter (WM) and the gray matter (GM) at around 6 months of age (the isointense phase), it is difficult for manual annotation, hence the number of training labels is highly limited. Consequently, it is still challenging to automatically segment isointense infant brain MRI. Meanwhile, the contrast of intensity images in the early adult phase, such as 24 months of age, is a relatively better, which can be easily segmented by the well-developed tools, e.g., FreeSurfer. Therefore, the question is how could we employ these high-contrast images (such as 24-month-old images) to guide the segmentation of 6-month-old images. Motivated by the above purpose, we propose a method to explore the 24-month-old images for a reliable tissue segmentation of 6-month-old images. Specifically, we design a 3D-cycleGAN-Seg architecture to generate synthetic images of the isointense phase by transferring appearances between the two time-points. To guarantee the tissue segmentation consistency between 6-month-old and 24-month-old images, we employ features from generated segmentations to guide the training of the generator network. To further improve the quality of synthetic images, we propose a feature matching loss that computes the cosine distance between unpaired segmentation features of the real and fake images. Then, the transferred of 24-month-old images is used to jointly train the segmentation model on the 6-month-old images. Experimental results demonstrate a superior performance of the proposed method compared with the existing deep learning-based methods.

BackgroundGray and white matter volume difference and change are important imaging markers of pathology and disease progression in neurology and psychiatry. Such measures are usually estimated from tissue segmentation maps produced by publicly available image processing pipelines. However, the reliability of the produced segmentations when using multi-center and multi-scanner data remains understudied. Here, we assess the robustness of six publicly available tissue classification pipelines across images acquired from different MR scanners and sites.MethodsWe used T1-weighted images of a single individual, scanned in 73 sessions across 27 different sites to assess the robustness of the tissue classification tools. Variability in Dice Kappa values and tissue volumes was assessed for Atropos, BISON, Classify_Clean, FAST, FreeSurfer, and SPM12. We also estimated the sample size necessary to detect a significant 1% volume reduction based on the variability of the estimates from each method within and across scanner models.ResultsBISON had the lowest overall variability in its volumetric estimates, followed by FreeSurfer, and SPM12. All methods also had significant differences between some of their estimates across different scanner manufacturers (e.g. BISON had significantly higher GM estimates and correspondingly lower WM estimates for GE scans compared to Philips and SIEMENs), and different signal-to-noise ratio (SNR) levels (e.g. FAST and FreeSurfer had significantly higher WM volume estimates for high versus medium and low SNR tertiles as well as correspondingly lower GM volume estimates). BISON also had the smallest sample size requirement across all scanners and tissue types, followed by FreeSurfer, and SPM12.ConclusionsOur comparisons provide a benchmark on the reliability of the publicly used tissue classification techniques and the amount of variability that can be expected when using large multi-center datasets and multi-scanner databases.

AIM To assess the feasibility and preliminary diagnostic performances of relaxation times derived from synthetic magnetic resonance imaging (syMRI) for differentiating nasopharyngeal carcinoma from nasopharyngeal benign lymphoid hyperplasia, and to assess the influence of tissue segmentation method on relaxation estimates. MATERIALS AND METHODS Fifty participants with nasopharyngeal carcinoma (NPC) and 40 participants with benign hyperplasia (NPH) who underwent syMRI examination were enrolled prospectively. T1, T2, and proton density (PD) values were obtained from four different regions of interest (ROIs), namely, partial‐section, single‐section, three‐sections, and whole‐lesion. The metrics between NPC and NPH or among different ROIs were compared using Student's t-test or one-way ANOVA. The area under curve (AUC) was calculated to assess the performance of metrics obtained from different ROIs to differentiate NPC and NPH. RESULTS The T1, T2, and PD values for NPH were significantly higher than those for NPC, regardless of the type of ROI used, except for the PD value obtained from the whole-lesion ROI. The T2 values obtained from the single-section ROI showed the highest diagnostic accuracy in distinguishing NPC from NPH, with an AUC of 0.894, sensitivity of 0.900, and specificity of 0.800. Additionally, the T1, T2, and PD values for nasopharyngeal lesions showed no statistical difference among different kinds of ROI, except for the difference in T1 value between partial‐section and other methods. CONCLUSION Quantitative analysis of syMRI has the potential to distinguish NPC from NPH. Moreover, different types of ROI showed limited influence on the relaxation time estimation for nasopharyngeal lesions.

PURPOSE: We present a novel computed tomography-based tissue segmentation methodology for determining volume and global uptake of FDG of the thigh muscles and correlate these parameters with age.MATERIALS AND METHODS: A total of 71 subjects from a prospective clinical trial (NCT01724749) were included. PET/CT scans were acquired 180 minutes after intravenous injection of FDG. A 3D growing region algorithm with neighborhood Hounsfield unit threshold between one and 150 was used to highlight the muscle. FDG uptake was expressed as the average mean standardized uptake value normalized for lean body mass (average SULmean). Femur volume was used to normalize thigh muscle volume to calculate normalized volume and correlate with age.RESULTS: We found a significant negative correlation between normalized volume and age (left side r = -0.262, P = 0.02; right side r = -0.286, P = 0.01). No statistically significant difference was found between SUL and age or between SUL and BMI. There was no statistically significant difference in muscle volume on the two sides. Statistically significant difference was noted in the global metabolic activity (SUL) between the two sides (left 0.39 ± 0.06, right 0.42 ± 0.08, P < 0.001), with 56/71 (78.8%) subjects having higher uptake on the right side.CONCLUSION: FDG-PET/CT using CT-based segmentation is a novel imaging modality assessing the volume and global metabolic activity of the thigh muscles. It could be possible to utilize this methodology for the research and understanding of lower limb muscle pathophysiology.

Brains with complex distortion of cerebral anatomy present several challenges to automatic tissue segmentation methods of T1-weighted MR images. First, the very high variability in the morphology of the tissues can be incompatible with the prior knowledge embedded within the algorithms. Second, the availability of MR images of distorted brains is very scarce, so the methods in the literature have not addressed such cases so far. In this work, we present the first evaluation of state-of-the-art automatic tissue segmentation pipelines on T1-weighted images of brains with different severity of congenital or acquired brain distortion. We compare traditional pipelines and a deep learning model, i.e. a 3D U-Net trained on normal-appearing brains. Unsurprisingly, traditional pipelines completely fail to segment the tissues with strong anatomical distortion. Surprisingly, the 3D U-Net provides useful segmentations that can be a valuable starting point for manual refinement by experts/neuroradiologists.

To characterize early cerebellum development, accurate segmentation of the cerebellum into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) tissues is one of the most pivotal steps. However, due to the weak tissue contrast, extremely folded tiny structures, and severe partial volume effect, infant cerebellum tissue segmentation is especially challenging, and the manual labels are hard to obtain and correct for learning-based methods. To the best of our knowledge, there is no work on the cerebellum segmentation for infant subjects less than 24 months of age. In this work, we develop a semi-supervised transfer learning framework guided by a confidence map for tissue segmentation of cerebellum MR images from 24-month-old to 6-month-old infants. Note that only 24-month-old subjects have reliable manual labels for training, due to their high tissue contrast. Through the proposed semi-supervised transfer learning, the labels from 24-month-old subjects are gradually propagated to the 18-, 12-, and 6-month-old subjects, which have a low tissue contrast. Comparison with the state-of-the-art methods demonstrates the superior performance of the proposed method, especially for 6-month-old subjects.

Cancer is one of the deadliest diseases of the world and affects both men and women. In 2018, Cancer rate has risen to 18.1 million new incidents and 9.6 million deaths [17]. About 90.5 million of people were suffering from cancer in 2015. The modern medical image processing has several strategies and methodologies for detection and grading of cancer. Digital pathology is considered as the rising domain in current diagnosis system. Image segmentation is one of the important steps before classifying the cancer. The major problem arises when there are touching nuclei or overlapping nuclei for separation. This paper presents review of state-of-art techniques proposed for nuclei or tissue segmentation in digital HIs.

OBJECTIVE Structural brain abnormalities are key risk factors for brain diseases, such as dementia, stroke, and depression, in type 2 diabetes. It is unknown whether structural brain abnormalities already occur in prediabetes. Therefore, we investigated whether both prediabetes and type 2 diabetes are associated with lacunar infarcts (LIs), white matter hyperintensities (WMHs), cerebral microbleeds (CMBs), and brain atrophy. RESEARCH DESIGN and METHODS We used data from 2,228 participants (1,373 with normal glucose metabolism [NGM], 347 with prediabetes, and 508 with type 2 diabetes (oversampled); mean age 59.2 ± 8.2 years; 48.3% women) of the Maastricht Study, a population-based cohort study. Diabetes status was determined with an oral glucose tolerance test. Brain imaging was performed with 3 Tesla MRI. Results were analyzed with multivariable logistic and linear regression analyses. RESULTS Prediabetes and type 2 diabetes were associated with the presence of LIs (odds ratio 1.61 [95% CI 0.98–2.63] and 1.67 [1.04–2.68], respectively; Ptrend = 0.027), larger WMH (β 0.07 log10-transformed mL [log-mL] [95% CI 0.00–0.15] and 0.21 log-mL [0.14–0.28], respectively; Ptrend CONCLUSIONS Prediabetes is associated with structural brain abnormalities, with further deterioration in type 2 diabetes. These results indicate that, in middle-aged populations, structural brain abnormalities already occur in prediabetes, which may suggest that the treatment of early dysglycemia may contribute to the prevention of brain diseases.

Background Accurate measurement and reconstruction of orbital soft tissue is important to diagnosis and treatment of orbital diseases. This study applied an interactive graph cut method to orbital soft tissue precise segmentation and calculation in computerized tomography (CT) images, and to estimate its application in orbital reconstruction. Methods The interactive graph cut method was introduced to segment extraocular muscle and intraorbital fat in CT images. Intra- and inter-observer variability of tissue volume measured by graph cut segmentation was validated. Accuracy and reliability of the method was accessed by comparing with manual delineation and commercial medical image software. Intraorbital structure of 10 patients after enucleation surgery was reconstructed based on graph cut segmentation and soft tissue volume were compared within two different surgical techniques. Results Both muscle and fat tissue segmentation results of graph cut method showed good consistency with ground truth in phantom data. There were no significant differences in muscle calculations between observers or segmental methods (p > 0.05). Graph cut results of fat tissue had coincidental variable trend with ground truth which could identify 0.1cm3 variation. The mean performance time of graph cut segmentation was significantly shorter than manual delineation and commercial software (p p p Conclusion The graph cut method was validated to have good accuracy, reliability and efficiency in orbit soft tissue segmentation. It could discern minor volume changes of soft tissue. The interactive segmenting technique would be a valuable tool for dynamic analysis and prediction of therapeutic effect and orbital reconstruction.

The Developing Human Connectome Project (dHCP) seeks to create the first 4-dimensional connectome of early life. Understanding this connectome in detail may provide insights into normal as well as abnormal patterns of brain development. Following established best practices adopted by the WU-MINN Human Connectome Project (HCP), and pioneered by FreeSurfer, the project utilises cortical surface-based processing pipelines. In this paper, we propose a fully automated processing pipeline for the structural Magnetic Resonance Imaging (MRI) of the developing neonatal brain. This proposed pipeline consists of a refined framework for cortical and sub-cortical volume segmentation, cortical surface extraction, and cortical surface inflation, which has been specifically designed to address considerable differences between adult and neonatal brains, as imaged using MRI. Using the proposed pipeline our results demonstrate that images collected from 465 subjects ranging from 28 to 45 weeks post-menstrual age (PMA) can be processed fully automatically; generating cortical surface models that are topologically correct, and correspond well with manual evaluations of tissue boundaries in 85% of cases. Results improve on state-of-the-art neonatal tissue segmentation models and significant errors were found in only 2% of cases, where these corresponded to subjects with high motion. Downstream, these surfaces will enhance comparisons of functional and diffusion MRI datasets, supporting the modelling of emerging patterns of brain connectivity.

Objective: The aim of this study was to provide a three-dimensional (3D) microscopic reconstruction of morphological modifications of the fallopian tube (FT) following surgical sterilization (including tuboperitoneal fistula) and ectopic pregnancy (EP) using confocal microtomography (micro-CT). Methods: Six specimens of FT from elective and emergency surgeries were selected: three remnants of the FT (RFT) from surgical sterilization, including one presenting tuboperitoneal fistula, and three FTs with EP. The specimens were fixed in formalin and stained with Lugol solution. Micro-CT studies were conducted on the specimens using protocols adapted from biological studies. Results: Three RFTs from surgical sterilization and three FTs affected by EPs were successfully scanned using micro-CT. There was good contrast impregnation, allowing tissue segmentation and analysis of different sections of the FTs. Three FT specimens from EP exhibited considerable distortion of the tubal anatomy, mainly from the blood clot in the tubal abortion. Three RFT specimens exhibited some features observed in traditional microscopy, such as tubal distension and loss of normal anatomical characteristics of a normal FT, and indicated the presence of a tuboperitoneal fistula in one of the three specimens. Conclusion: Micro-CT can identify morphological characteristics of FT pathologies previously described in a microscopic scale, with tissue contrast and the possibility of 3D reconstruction. Micro-CT is also useful in guiding traditional sectioning of specimens for histopathological studies.

The use of standard anatomical templates is common in human neuroimaging, as it facilitates data analysis and comparison across subjects and studies. For non-human primates, previous in vivo templates have lacked sufficient contrast to reliably validate known anatomical brain regions and have not provided tools for automated single-subject processing. Here we present the “National Institute of Mental Health Macaque Template”, or NMT for short. The NMT is a high-resolution in vivo MRI template of the average macaque brain generated from 31 subjects, as well as a neuroimaging tool for improved data analysis and visualization. From the NMT volume, we generated maps of tissue segmentation and cortical thickness. Surface reconstructions and transformations to previously published digital brain atlases are also provided. We further provide an analysis pipeline using the NMT that automates and standardizes the time-consuming processes of brain extraction, tissue segmentation, and morphometric feature estimation for anatomical scans of individual subjects. The NMT and associated tools thus provide a common platform for precise single-subject data analysis and for characterizations of neuroimaging results across subjects and studies.

To analyse and understand the characteristics of pressure injury images stored in the electronic health record.To improve the quality of pressure injury documentation, photographing pressure injuries and storing the images in the electronic health record are standard practices in many hospitals. As new technologies develop, the utilisation of computer-assisted image processing makes automatic measurement of pressure injury size and tissue segmentation through pressure injury images possible. The translation of new technological developments to pressure injury photography conducted in clinical environments faces obstacles such as the complexity of conditions in which photographs are taken.A cross-sectional descriptive study.A set of 360 pressure injury images were obtained from a hospital in western Pennsylvania. These images were taken in clinical settings during daily wound care service. The authors reviewed the pressure injury images to analyse the relative position of the pressure injury in the images, the shooting angle of the digital camera and the clinical objects in the background.Only 5.9% of the pressure injury images were confined to only the wound region. In 80.1% of the images, the pressure injury is located in the central part of the image. In 54.0% of the images, the lens of the digital camera was not pointed perpendicularly to the plane of the pressure injury.Bedside wound assessment of pressure injuries and assessment from photographs of pressure injuries display reasonable agreement with pressure injury staging. To extract wound information (e.g., size and tissue type) from pressure injury images through novel image processing technologies, the characteristics of pressure injury images in clinical settings should be better understood during the development of tools for pressure injury image processing.Our results can help image processing experts understand wound photography characteristics to shorten the gap between laboratory and clinical environments when translating new image processing technologies.