Brain Shape Research Articles

Effects of sex and age on presumed inhibitory interactions in 6 areas of the human cerebral cortex as revealed by the fMRI Human Connectome Project.

Cortical inhibition is theorized to reflect an underlying property of human brain function, sharpening tuning and shaping connectivity. Although age and sex effects on large-scale resting-state brain connectivity have been well documented, effects on local cortical inhibition have received relatively limited attention. Here, we evaluated age and sex effects on presumed local inhibitory interactions in 6 lateral cortical areas using resting-state functional magnetic resonance imaging (fMRI) data acquired from 1054 young adults who participated in the Human Connectome Project. For each area, all possible pairwise crosscorrelations between prewhitened blood oxygenation level-dependent (BOLD) time series were calculated, and the highest value (CCmax) was retained to determine the mean and percentage of negative and positive CCmax. Here, we focused on the percentage of negative CCmax which we referred to as presumed "percent inhibition". The results documented regional differences in percent inhibition as well as age and sex effects, such that women's brains were characterized by significantly higher percent inhibition than men overall and in 4 of the 6 cortical areas, and the percent inhibition increased significantly with age in all 6 areas for women but in only one area for men. The findings from this young adult sample are presumed to reflect ongoing maturational processes involving local network connectivity that may be shaped by sex differences in brain structure, function, and neurochemistry.

Forward Model of Rat Electroencephalogram: Comparative Study of Numerical Simulations With Measurements on Rat Head Phantoms

In the paper, we propose a procedure to be used for the validation of software for forward modeling of rat electroencephalogram with scalp potentials measured on rat head phantoms. Measurements are performed on a cuboidal phantom, a simplified shape of a rat brain, and an anatomically realistic, computed tomography (CT)-based phantom considering the brain and the skull. The physical phantoms are composed of an agar mixture to mimic the rat brain, excitation dipoles for modeling the neural activity of the brain, electrodes for monitoring the surface electric potential and a 3D printed skull. To ensure correct positions of dipoles and electrodes for numerical simulations, the phantoms are scanned by a computed tomography. After that, reconstructed 3D models are simulated in three EM solvers and results are compared with EEG measurements. Differences between simulations and measurements are further analyzed by parametric simulations and discussed. Obtained results provide the software validation method for rat brain forward modeling. Properly validated computation of electric potentials is essential for development of electrical brain stimulation protocols as well as in optimization of electrode placement.

Cognitive and behavioral modernity in Homo erectus: skull globularity and hominin brain evolution

In this article we provide evidence that evolutionary pressures altered the cranial base and the mastoid region of the temporal bone more than the calvaria in the transition from H. erectus to H. sapiens. This process seems to have resulted in the evolution of more globular skull shape – but not as a result of expansion of the brain in the parietal regions but of reduction of the cranial base and the mastoid region relative to the parietals. Consequently, we argue that expansion of the parietals seems to be unrelated to brain evolution, but is more a by-product of reduction in other regions of the skull, reduction that may be related to dietary factors. Additionally, these findings suggest that cognitive and behavioural modernity may not necessarily be dependent on brain shape. Also, it cannot be attributed to the change in brain size because H. erectus and modern human cranial capacities overlap substantially. Consequently, we suggest H. erectus possessed the full suite of cognitive adaptations characteristic of modern humans without possessing a globular skull with flared parietals. Our results also support the theory that paedomorphic morphogenesis of the skull was important in the transition from H. erectus to H. sapiens and that such changes may be related to both dietary factors and social evolution.

Longitudinal brain atlases of early developing cynomolgus macaques from birth to 48 months of age

Longitudinal brain imaging atlases with densely sampled time-points and ancillary anatomical information are of fundamental importance in studying early developmental characteristics of human and non-human primate brains during infancy, which feature extremely dynamic imaging appearance, brain shape and size. However, for non-human primates, which are highly valuable animal models for understanding human brains, the existing brain atlases are mainly developed based on adults or adolescents, denoting a notable lack of temporally densely-sampled atlases covering the dynamic early brain development. To fill this critical gap, in this paper, we construct a comprehensive set of longitudinal brain atlases and associated tissue probability maps (gray matter, white matter, and cerebrospinal fluid) with totally 12 time-points from birth to 4 years of age (i.e., 1, 2, 3, 4, 5, 6, 9, 12, 18, 24, 36, and 48 months of age) based on 175 longitudinal structural MRI scans from 39 typically-developing cynomolgus macaques, by leveraging state-of-the-art computational techniques tailored for early developing brains. Furthermore, to facilitate region-based analysis using our atlases, we also provide two popular hierarchy parcellations, i.e., cortical hierarchy maps (6 levels) and subcortical hierarchy maps (6 levels), on our longitudinal macaque brain atlases. These early developing atlases, which have the densest time-points during infancy (to the best of our knowledge), will greatly facilitate the studies of macaque brain development.

Neuropathologic correlates of shape of subcortical brain structures

Age-related neuropathologies have devastating effects on subcortical brain structures. MRI can be used to explore patterns of atrophy associated with various diseases, however, definitive diagnosis of age-related neuropathologies is only possible at autopsy. The purpose of this work was to combine ex-vivo MRI and detailed neuropathology in a large community cohort of older adults to conduct the most comprehensive investigation to-date on the association of age-related neuropathologies with the shape of subcortical brain structures. Cerebral hemispheres were obtained from 814 participants of the Rush Memory and Aging Project and Religious Orders Study, two longitudinal cohort studies of aging (Fig. 1). A single brain hemisphere from each participant was imaged ex-vivo on a clinical 3T MRI scanner, while immersed in 4% formaldehyde solution. Following ex-vivo MRI, all hemispheres underwent detailed neuropathologic examination by a board-certified neuropathologist blinded to clinical and imaging findings (Fig. 2). T2-weighted images from all hemispheres were used to segment nucleus accumbens, amygdala, caudate, hippocampus, putamen, and thalamus. Subcortical shape measures were computed using the ENIGMA-Shape protocol. Vertex-wise linear regression was performed for each subcortical structure, modeling the logarithm of the Jacobian determinant at each vertex as a function of a comprehensive list of age-related neuropathologies controlling for demographics and scanners. The analysis first considered data from all hemispheres (left hemispheres were mirrored to appear like right hemispheres and the opposite), and then was repeated considering left and right hemispheres separately. When considering all hemispheres (Fig. 3), Alzheimer's pathology, atherosclerosis, and TDP-43 pathology were all associated with unique patterns of inward deformation of the hippocampus and amygdala. When considering left and right hemispheres separately (Fig. 4), the results were relatively similar to the combined analysis. Also, when considering the right hemispheres alone, arteriolosclerosis was associated with inward deformation of the putamen and thalamus. Lewy bodies, infarcts and cerebral amyloid angiopathy did not show any links to the shape of subcortical brain structures. Among the different age-related neuropathologies, Alzheimer's pathology, TDP-43 pathology, atherosclerosis and arteriolosclerosis are the ones that have independent contributions on shape abnormalities of subcortical brain structures that could potentially contribute towards in-vivo prediction of these neuropathologies.

Neuroanatomy of FTD: Whole‐brain correlations between symptoms and pathologies

Distinct pathologies accumulate in multiple brain regions (BR) and shape the heterogeneous clinical presentation of frontotemporal dementia (FTD). It is unknown how regional pathological burden links to symptoms, what the role of co-occurring pathologies is, and whether the localization of pathology might be a bigger contributor to symptoms than the type of pathology. Our aim is to investigate how early FTD symptoms correlate to the burden of multiple pathologies throughout the brain.Post-mortem brain tissue of frontotemporal lobar degeneration (FTLD) donors from the Netherlands brain bank was dissected into twenty standard BR and stained for TAR DNA-binding protein 43 (TDP-43), tau, fused-in-sarcoma (FUS), amyloid-beta (Aβ), and alpha-synuclein. The burden of each pathological protein in each BR was quantified. All clinical records were reviewed to assess psychiatric, behavioral, language, and motor symptoms in the first three years from disease onset. Whole-brain clinico-pathological partial correlations were assessed using the heterogeneous correlation function (R 3.6.1). The local false discovery rate threshold was set at 0.01.Eighty-eight FTLD brain donors were studied, including 46 TDP-43, 35 tau, and 7 FUS. Significant positive partial correlations (p < 0.01) were found between hippocampal TDP-43 pathology and hallucinations (R = 0.23), perseverative-compulsive behavior (R = 0.25), depression (R = 0.28), and mania (R = 0.32). Tau pathology in the substantia nigra and locus coeruleus was linked to depression (R = 0.25, R = 0.24). Both TDP-43 and Aβ in the subthalamus were associated with severe disinhibition (R = 0.23, R = 0.25), while apathy correlated with both TDP-43 and tau burden in the parietal lobe (R = 0.27, R = 0.24). Parkinsonism was linked to TDP-43 burden in the substantia nigra (R = 0.33).Neuropsychiatric symptoms of FTD are linked to pathology burden in BR beyond the frontal lobes, including subcortical structures such as the hippocampus, the substantia nigra and locus coeruleus. Co-occurring pathologies are not simple bystanders, but could play a role in configuring FTD clinical phenotype. Different pathologies in the same BR correlate with the same symptoms.

Efficacy of the SMR protocol in women with fibromyalgia for the improvement of chronic pain, sleep, and quality of life

The objective of the study was to analyze how the brain shaping provided by the sensorimotor rhythm protocol (SMR), applied on somatosensory areas, affects pain, sleep and the quality of life in women with fibromyalgia. Thirty-seven women with fibromyalgia who received an SMR protocol in 20 sessions participated and were evaluated before and after treatment. The data showed an increase in the amplitude of the SMR (p= .026) and a decrease in the amplitude of the theta band (p= .011) in the somatosensory cortex after the application of therapy, which caused an increase in the SMR/theta ratio (p= .048). In addition, the scores on the Chronic Pain Scale (p= .002), the Pittsburgh Sleep Quality Index (p= .001), and the SF-36 Health Survey (p= .000) improved significantly. The SMR protocol applied to the somatosensory cortex favors the shaping of SMRs, which has an impact on stimulating the inhibition of the central nervous system of patients with fibromyalgia, improving symptoms such as pain, sleep, and quality of life.

Connectivity-based parcellation of normal and anatomically distorted human cerebral cortex.

For over a century, neuroscientists have been working toward parcellating the human cortex into distinct neurobiological regions. Modern technologies offer many parcellation methods for healthy cortices acquired through magnetic resonance imaging. However, these methods are suboptimal for personalized neurosurgical application given that pathology and resection distort the cerebrum. We sought to overcome this problem by developing a novel connectivity‐based parcellation approach that can be applied at the single‐subject level. Utilizing normative diffusion data, we first developed a machine‐learning (ML) classifier to learn the typical structural connectivity patterns of healthy subjects. Specifically, the Glasser HCP atlas was utilized as a prior to calculate the streamline connectivity between each voxel and each parcel of the atlas. Using the resultant feature vector, we determined the parcel identity of each voxel in neurosurgical patients (n = 40) and thereby iteratively adjusted the prior. This approach enabled us to create patient‐specific maps independent of brain shape and pathological distortion. The supervised ML classifier re‐parcellated an average of 2.65% of cortical voxels across a healthy dataset (n = 178) and an average of 5.5% in neurosurgical patients. Our patient dataset consisted of subjects with supratentorial infiltrating gliomas operated on by the senior author who then assessed the validity and practical utility of the re‐parcellated diffusion data. We demonstrate a rapid and effective ML parcellation approach to parcellation of the human cortex during anatomical distortion. Our approach overcomes limitations of indiscriminately applying atlas‐based registration from healthy subjects by employing a voxel‐wise connectivity approach based on individual data.

Old Brains in Alcohol: The Usability of Legacy Collection Material to Study the Spider Neuroarchitecture

Natural history collections include rare and significant taxa that might otherwise be unavailable for comparative studies. However, curators must balance the needs of current and long-term research. Methods of data extraction that minimize the impact on specimens are therefore favored. Micro-CT has the potential to expose new character systems based on internal anatomy to taxonomic and phylogenetic analysis without dissection or thin sectioning for histology. However, commonly applied micro-CT protocols involve critical point drying, which permanently changes the specimen. Here, we apply a minimally destructive method of specimen preparation for micro-CT investigation of spider neuroanatomy suitable for application to legacy specimens in natural history collections. We used two groups of female spiders of the common species Araneus diadematus—freshly captured (n = 11) vs. legacy material between 70 and 90 years old (n = 10)—to qualitatively and quantitatively assess the viability of micro-CT scanning and the impact of aging on their neuroarchitecture. We statistically compared the volumes of the supraesophageal ganglion (syncerebrum) and used 2D geometric morphometrics to analyze variations in the gross shape of the brain. We found no significant differences in the brain shape or the brain volume relative to the cephalothorax size. Nonetheless, a significant difference was observed in the spider size. We considered such differences to be explained by environmental factors rather than preservation artifacts. Comparison between legacy and freshly collected specimens indicates that museum specimens do not degrade over time in a way that might bias the study results, as long as the basic preservation conditions are consistently maintained, and where lapses in preservation have occurred, these can be identified. This, together with the relatively low-impact nature of the micro-CT protocol applied here, could facilitate the use of old, rare, and valuable material from collections in studies of internal morphology.

High Encephalization in a Fossil Rorqual Illuminates Baleen Whale Brain Evolution

Baleen whales are considered underencephalized mammals due to their reduced brain size with respect to their body size (encephalization quotient [EQ] << 1). Despite their low EQ, mysticetes exhibit complex behavioral patterns in terms of motor abilities, vocal repertoire, and cultural learning. Very scarce information is available about the morphological evolution of the brain in this group; this makes it difficult to investigate the historical changes in brain shape and size in order to relate the origin of the complex mysticete behavioral repertoire to the evolution of specific neural substrates. Here, the first description of the virtual endocast of a fossil balaenopterid species, Marzanoptera tersillae from the Italian Pliocene, reveals an EQ of around 3, which is exceptional for baleen whales. The endocast showed a morphologically different organization of the brain in this fossil whale as the cerebral hemispheres are anteroposteriorly shortened, the cerebellum lacks the posteromedial expansion of the cerebellar hemispheres, and the cerebellar vermis is unusually reduced. The comparative reductions of the cerebral and cerebellar hemispheres suggest that the motor behavior of M. tersillae probably was less sophisticated than that exhibited by the extant rorqual and humpback species. The presence of an EQ value in this fossil species that is around 10 times higher than that of extant mysticetes opens new questions about brain evolution and provides new, invaluable information about the evolutionary path of morphological and size change in the brain of baleen whales.

Mapping Complex Brain Torque Components and Their Genetic Architecture and Phenomic Associations in 24,112 Individuals

BackgroundThe functional significance and mechanisms determining the development and individual variability of structural brain asymmetry remain unclear. Here, we systematically analyzed all relevant components of the most prominent structural asymmetry, brain torque (BT), and their relationships with potential genetic and nongenetic modifiers in a sample comprising 24,112 individuals from six cohorts. MethodsBT features, including petalia, bending, dorsoventral shift, brain tissue distribution asymmetries, and cortical surface positional asymmetries, were directly modeled using a set of automatic three-dimensional brain shape analysis approaches. Age-, sex-, and handedness-related effects on BT were assessed. The genetic architecture and phenomic associations of BT were investigated using genome- and phenome-wide association scans. ResultsOur results confirmed the population-level predominance of the typical counterclockwise torque and suggested a first attenuating, then enlarging dynamic across the life span (3–81 years) primarily for frontal, occipital, and perisylvian BT features. Sex/handedness, BT, and cognitive function of verbal-numerical reasoning were found to be interrelated statistically. We observed differential heritability of up to 56% for BT, especially in temporal language areas. Individual variations of BT were also associated with various phenotypic variables of neuroanatomy, cognition, lifestyle, sociodemographics, anthropometry, physical health, and adult and child mental health. Our genomic analyses identified a number of genetic associations at lenient significance levels, which need to be further validated using larger samples in the future. ConclusionsThis study provides a comprehensive description of BT and insights into biological and other factors that may contribute to the development and individual variations of BT.

Cover Image

COVER ILLUSTRATION The image presents a high-definition reconstruction obtained from an MRI that was de-identified using our novel method. The artwork aims to show that with current techniques it is possible to recreate with outstanding accuracy not only the brain but also the face of a subject, putting privacy at risk. In our study we present a new method, called AnonyMI, and validate it in terms of its de-identification performance in two behavioral experiments and also using a machine learning face recognition software; always comparing it to other state-of-the-art methods. In addition we performed an analysis of how well each method preserves the geometry of the brain and the head, which is crucial for maximizing data re-usability. Our results showed that all methods significantly decreased the re-identification risk, and that AnonyMI was the most performant in terms of the geometrical preservation of the brain and head shapes.

Neuroanatomical differences in the memory systems of intellectual giftedness and typical development

IntroductionStudying neuro‐structural markers of intellectual giftedness (IG) will inform scientific understanding of the processes helping children excel academically.MethodsStructural and diffusion‐weighted MRI was used to compare regional brain shape and connectivity of 12 children with average to high average IQ and 18 IG children, defined as having IQ greater than 145.ResultsIG had larger subcortical structures and more robust white matter microstructural organization between those structures in regions associated with explicit memory. TD had more connected, larger subcortical structures in regions associated with implicit memory.ConclusionsIt was found that the memory systems within brains of children with exceptional intellectual abilities are differently sized and connected compared to the brains of typically developing children. These different neurodevelopmental trajectories suggest different learning strategies. A spectrum of intelligence types is envisioned, facilitated by different ratios of implicit and explicit system, which was validated using a large external dataset.

A Robust Machine Learning Approach for Multiclass Alzheimer’s Disease Detection using 3D Brain Magnetic Resonance Images

Alzheimer’s disease (AD), a progressive dementia is the neurodegenerative disorder that worsens memory and mental capabilities mostly in aged people. Currently, clinical and psychometric assessments are being used to diagnose the disease in patients. In clinical procedures, 3D Magnetic Resonance Image qualitative parameters are analyzed to identify the abnormality in brain shape, volume, texture, and cortical thickness. This paper presents a robust approach for categorizing 3D MR images into multiple stages of AD using hybrid features viz., Gray Level Co-occurrence Matrix (GLCM), 3D Scale and rotation Invariant Feature Transform (3D SIFT), Histogram of Oriented Gradients – Three Orthogonal Planes (HOG-TOP) and Complete Local Binary Pattern of Sign and Magnitude – Three Orthogonal Planes (CLBPSM-TOP). The proposed algorithm is validated using Open Access Series of Imaging Studies (OASIS) datasets to classify the subjects into AD, Mild Cognitive Impairment (MCI) and Cognitive Normal (CN) categories using various classifiers. Moreover, this approach is also evaluated and compared with the state-of-the-art approaches. 87.84% diagnosis accuracy is achieved with Ensemble classifier using hybrid features to diagnose the severity of AD. This approach also outperforms majority of these techniques in key parameters viz., accuracy, precision, recall and F1-score.

Evolution of whale sensory ecology: Frontiers in nondestructive anatomical investigations.

Studies surrounding the evolution of sensory system anatomy in cetaceans over the last ~100 years have shed light on aspects of the early evolution of hearing sensitivities, the small relative size of the organ of balance (semicircular canals and vestibule), brain (endocast) shape and relative volume changes, and ontogenetic development of sensory-related structures. Here, I review advances in our knowledge of sensory system anatomy as informed by the use of nondestructive imaging techniques, with a focus on applied methods in computed tomography (CT and μCT), and identify the key questions that remain to be addressed. Of these, the most important are: Is lower frequency hearing sensitivity the ancestral condition for whales? Did echolocation evolve more than once in odontocetes; and if so, when and why? How has the structure of the cetacean brain changed, through the evolution of whales, and does this correspond to changes in hearing sensitivities? Finally, what are the general pathways of ontogenetic development of sensory systems in odontocetes and mysticetes? Answering these questions will allow us to understand important macroevolutionary patterns in a fully aquatic mammalian group and provides baseline data on species for which we have limited biological information because of logistical limitations.

Longitudinal Prediction of Infant MR Images With Multi-Contrast Perceptual Adversarial Learning.

The infant brain undergoes a remarkable period of neural development that is crucial for the development of cognitive and behavioral capacities (Hasegawa et al., 2018). Longitudinal magnetic resonance imaging (MRI) is able to characterize the developmental trajectories and is critical in neuroimaging studies of early brain development. However, missing data at different time points is an unavoidable occurrence in longitudinal studies owing to participant attrition and scan failure. Compared to dropping incomplete data, data imputation is considered a better solution to address such missing data in order to preserve all available samples. In this paper, we adapt generative adversarial networks (GAN) to a new application: longitudinal image prediction of structural MRI in the first year of life. In contrast to existing medical image-to-image translation applications of GANs, where inputs and outputs share a very close anatomical structure, our task is more challenging as brain size, shape and tissue contrast vary significantly between the input data and the predicted data. Several improvements over existing GAN approaches are proposed to address these challenges in our task. To enhance the realism, crispness, and accuracy of the predicted images, we incorporate both a traditional voxel-wise reconstruction loss as well as a perceptual loss term into the adversarial learning scheme. As the differing contrast changes in T1w and T2w MR images in the first year of life, we incorporate multi-contrast images leading to our proposed 3D multi-contrast perceptual adversarial network (MPGAN). Extensive evaluations are performed to assess the qualityand fidelity of the predicted images, including qualitative and quantitative assessments of the image appearance, as well as quantitative assessment on two segmentation tasks. Our experimental results show that our MPGAN is an effective solution for longitudinal MR image data imputation in the infant brain. We further apply our predicted/imputed images to two practical tasks, a regression task and a classification task, in order to highlight the enhanced task-related performance following image imputation. The results show that the model performance in both tasks is improved by including the additional imputed data, demonstrating the usability of the predicted images generated from our approach.

Gross variations in relative size of brain and its subdivisions among fishes: An overview

Fishes are the aquatic vertebrates inhabiting all the levels of the water column. Different species of fishes are well adapted to successfully live in all types of water bodies. They possess a well-developed nervous system to combat all the challenges they encounter in their specified habitat in the water column. Fishes that are migratory in nature are also able to overcome the problems faced by them in moving from one type of water body to the other. Although the sub divisions of the brain in different species of fish are same, there occurs a considerable variation among them owing to the whole brain size, shape and size of sub divisions etc. Studies have reported variations in whole brain size and enlargement of a particular brain subdivision that may be correlated with the body size, ecological niche or habitat of the species or cognitive ability of the species. Most of the studies performed with this objective reported interspecific variations among fishes. Fewer studies however, reported intraspecific morphological variations in brain/brain subdivisions among the fish population. Nevertheless, brains are energetically costly organs. Super class Pisces including all the fishes is a diverse group with respect to body size and habitat within water column and all such studies are so scattered that it is difficult to summarize them all. Therefore, the aim of this paper is to discuss and provide information about the variations in the brain size and in its subdivisions and unique brain structures found in fishes. Such studies were conducted in earlier times also and are gaining a great interest since past 10 years.

MNI-FTD templates, unbiased average templates of frontotemporal dementia variants

Standard templates are widely used in human neuroimaging processing pipelines to facilitate group-level analyses and comparisons across subjects/populations. MNI-ICBM152 template is the most commonly used standard template, representing an average of 152 healthy young adult brains. However, in patients with neurodegenerative diseases such as frontotemporal dementia (FTD), high atrophy levels lead to significant differences between individuals’ brain shapes and MNI-ICBM152 template. Such differences might inevitably lead to registration errors or subtle biases in downstream analyses and results. Disease-specific templates are therefore desirable to reflect the anatomical characteristics of the populations of interest and reduce potential registration errors. Here, we present MNI-FTD136, MNI-bvFTD70, MNI-svFTD36, and MNI-pnfaFTD30, four unbiased average templates of 136 FTD patients, 70 behavioural variant (bv), 36 semantic variant (sv), and 30 progressive nonfluent aphasia (pnfa) variant FTD patients and a corresponding age-matched template of 133 controls (MNI-CN133), along with probabilistic tissue maps for each template. Public availability of these templates will facilitate analyses of FTD cohorts and enable comparisons between different studies in an appropriate common standardized space.

Bird neurocranial and body mass evolution across the end-Cretaceous mass extinction: The avian brain shape left other dinosaurs behind.

Birds today are the most diverse clade of terrestrial vertebrates, and understanding why extant birds (Aves) alone among dinosaurs survived the Cretaceous-Paleogene mass extinction is crucial to reconstructing the history of life. Hypotheses proposed to explain this pattern demand identification of traits unique to Aves. However, this identification is complicated by a lack of data from non-avian birds. Here, we interrogate survivorship hypotheses using data from a new, nearly complete skull of Late Cretaceous (~70 million years) bird Ichthyornis and reassess shifts in bird body size across the Cretaceous-Paleogene boundary. Ichthyornis exhibited a wulst and segmented palate, previously proposed to have arisen within extant birds. The origin of Aves is marked by larger, reshaped brains indicating selection for relatively large telencephala and eyes but not by uniquely small body size. Sensory system differences, potentially linked to these shifts, may help explain avian survivorship relative to other dinosaurs.

Brain tumor segmentation and overall survival period prediction in glioblastoma multiforme using radiomic features

SummaryGlioblastoma multiforme (GBM or glioblastoma) is a fast‐growing glioma that are the most invasive type of glial tumors, rapidly growing and commonly spreading into nearby brain tissue. Due to its aggressive and fast growing nature, patients suffer from high grade glioma (GBM) survive very less time as compare to other tumors. Prediction of patient survival (OS) time helps the radiologist for better systematic treatment planning and clinical decision making. The OS rate depends on the tumor size, shape, and different imaging features of brain. In this study, the OS period prediction was performed using Random Forest, SVM, XgBoost, and LGBM taking radiomic features which represents fused deep features and hand crafted features of the tumor. Efficiency of the prediction depends on the tumor volume that is segmented from the different MRI modalities. Hence the whole tumor and its sub tumor are extracted from multi‐modal MR images using U‐Net++ deep model and stacked together for deep features extraction using convolutional neural networks. To increase the accuracy, the features are reduced using PCA and then this radiomic feature set was used for OS period prediction. Prediction performance was evaluated for both 2‐class and 3‐class survival groups. The experiment was performed on well‐known dataset BraTS 2017 and achieved a classification AUC value as 63% for 3‐class classification and 2‐class group using different classifier. Segmentation DOR is computed as 1269.29, 2033.99, and 648.00 for complete tumor, enhancing tumor, and necrotic tumor extraction, respectively. To achieve even more accuracy, bio inspired optimization methods GA and PSO are used on fused feature set. Finally, the method achieves the AUC score of 0.66 using fused feature+SVM+GA (3‐class group) and 0.70 using fused feature+SVM+PSO (2‐class group) which outperforms the state‐of‐the‐art.