Precise and Rapid Whole-Head Segmentation from Magnetic Resonance Images of Older Adults using Deep Learning.

Whole-head segmentation from Magnetic Resonance Images (MRI) establishes the foundation for individualized computational models using finite element method (FEM). This foundation paves the path for computer-aided solutions in fields, particularly in non-invasive brain stimulation. Most current automatic head segmentation tools are developed using healthy young adults. Thus, they may neglect the older population that is more prone to age-related structural decline such as brain atrophy. In this work, we present a new deep learning method called GRACE, which stands for General, Rapid, And Comprehensive whole-hEad tissue segmentation. GRACE is trained and validated on a novel dataset that consists of 177 manually corrected MR-derived reference segmentations that have undergone meticulous manual review. Each T1-weighted MRI volume is segmented into 11 tissue types, including white matter, grey matter, eyes, cerebrospinal fluid, air, blood vessel, cancellous bone, cortical bone, skin, fat, and muscle. To the best of our knowledge, this work contains the largest manually corrected dataset to date in terms of number of MRIs and segmented tissues. GRACE outperforms five freely available software tools and a traditional 3D U-Net on a five-tissue segmentation task. On this task, GRACE achieves an average Hausdorff Distance of 0.21, which exceeds the runner-up at an average Hausdorff Distance of 0.36. GRACE can segment a whole-head MRI in about 3 seconds, while the fastest software tool takes about 3 minutes. In summary, GRACE segments a spectrum of tissue types from older adults T1-MRI scans at favorable accuracy and speed. The trained GRACE model is optimized on older adult heads to enable high-precision modeling in age-related brain disorders. To support open science, the GRACE code and trained weights are made available online and open to the research community at https://github.com/lab-smile/GRACE.

The segmentation effect of style transfer on fetal head ultrasound image: a study of multi-source data.

The generalization ability of the fetal head segmentation method is reduced due to the data obtained by different machines, settings, and operations. To keep the generalization ability, we proposed a Fourier domain adaptation (FDA) method based on amplitude and phase to achieve better multi-source ultrasound data segmentation performance. Given the source/target image, the Fourier domain information was first obtained using fast Fourier transform. Secondly, the target information was mapped to the source Fourier domain through the phase adjustment parameter α and the amplitude adjustment parameter ß. Thirdly, the target image and the preprocessed source image obtained through the inverse discrete Fourier transform were used as the input of the segmentation network. Finally, the dice loss was computed to adjust α and ß. In the existing transform methods, the proposed method achieved the best performance. The adaptive-FDA method provides a solution for the automatic preprocessing of multi-source data. Experimental results show that it quantitatively improves the segmentation results and model generalization performance.

Bench to bore ramifications of inter-subject head differences on RF shimming and specific absorption rates at 7T.

PURPOSE: This study shows how inter-subject variation over a dataset of 72 head models results in specific absorption rate (SAR) and B1+ field homogeneity differences using common shim scenarios. METHODS: MR-CT datasets were used to segment 71 head models into 10 tissue compartments. These head models were affixed to the shoulders and neck of the virtual family Duke model and placed within an 8 channel transmit surface-loop array to simulate the electromagnetic fields of a 7T imaging experiment. Radio frequency (RF) shimming using the Gerchberg-Saxton algorithm and Circularly Polarized shim weights over the entire brain and select slices of each model was simulated. Various SAR metrics and B1+ maps were calculated to demonstrate the contribution of head variation to transmit inhomogeneity and SAR variability. RESULTS: With varying head geometries the loading for each transmit loop changes as evidenced by changes in S-parameters. The varying shim conditions and head geometries are shown to affect excitation uniformity, spatial distributions of local SAR, and SAR averaging over different pulse sequences. The Gerchberg-Saxton RF shimming algorithm outperforms circularly polarized shimming for all head models. Peak local SAR within the coil most often occurs nearest the coil on the periphery of the body. Shim conditions vary the spatial distribution of SAR. CONCLUSION: The work gives further support to the need for fast and more subject specific SAR calculations to maintain safety. Local SAR10g is shown to vary spatially given shim conditions, subject geometry and composition, and position within the coil.

Segmentation of MRI head anatomy using deep volumetric networks and multiple spatial priors.

Purpose: Conventional automated segmentation of the head anatomy in magnetic resonance images distinguishes different brain and nonbrain tissues based on image intensities and prior tissue probability maps (TPMs). This works well for normal head anatomies but fails in the presence of unexpected lesions. Deep convolutional neural networks (CNNs) leverage instead spatial patterns and can learn to segment lesions but often ignore prior probabilities. Approach: We add three sources of prior information to a three-dimensional (3D) convolutional network, namely, spatial priors with a TPM, morphological priors with conditional random fields, and spatial context with a wider field-of-view at lower resolution. We train and test these networks on 3D images of 43 stroke patients and 4 healthy individuals which have been manually segmented. Results: We demonstrate the benefits of each source of prior information, and we show that the new architecture, which we call Multiprior network, improves the performance of existing segmentation software, such as SPM, FSL, and DeepMedic for abnormal anatomies. The relevance of the different priors was compared, and the TPM was found to be most beneficial. The benefit of adding a TPM is generic in that it can boost the performance of established segmentation networks such as the DeepMedic and a UNet. We also provide an out-of-sample validation and clinical application of the approach on an additional 47 patients with disorders of consciousness. We make the code and trained networks freely available. Conclusions: Biomedical images follow imaging protocols that can be leveraged as prior information into deep CNNs to improve performance. The network segmentations match human manual corrections performed in 3D and are comparable in performance to human segmentations obtained from scratch in 2D for abnormal brain anatomies.

Cephalochordates: A window into vertebrate origins.

How vertebrates evolved from their invertebrate ancestors has long been a central topic of discussion in biology. Evolutionary developmental biology (evodevo) has provided a new tool-using gene expression patterns as phenotypic characters to infer homologies between body parts in distantly related organisms-to address this question. Combined with micro-anatomy and genomics, evodevo has provided convincing evidence that vertebrates evolved from an ancestral invertebrate chordate, in many respects resembling a modern amphioxus. The present review focuses on the role of evodevo in addressing two major questions of chordate evolution: (1) how the vertebrate brain evolved from the much simpler central nervous system (CNS) in of this ancestral chordate and (2) whether or not the head mesoderm of this ancestor was segmented.

Automated Head Tissue Modelling Based on Structural Magnetic Resonance Images for Electroencephalographic Source Reconstruction.

In the last years, technological advancements for the analysis of electroencephalography (EEG) recordings have permitted to investigate neural activity and connectivity in the human brain with unprecedented precision and reliability. A crucial element for accurate EEG source reconstruction is the construction of a realistic head model, incorporating information on electrode positions and head tissue distribution. In this paper, we introduce MR-TIM, a toolbox for head tissue modelling from structural magnetic resonance (MR) images. The toolbox consists of three modules: 1) image pre-processing - the raw MR image is denoised and prepared for further analyses; 2) tissue probability mapping - template tissue probability maps (TPMs) in individual space are generated from the MR image; 3) tissue segmentation - information from all the TPMs is integrated such that each voxel in the MR image is assigned to a specific tissue. MR-TIM generates highly realistic 3D masks, five of which are associated with brain structures (brain and cerebellar grey matter, brain and cerebellar white matter, and brainstem) and the remaining seven with other head tissues (cerebrospinal fluid, spongy and compact bones, eyes, muscle, fat and skin). Our validation, conducted on MR images collected in healthy volunteers and patients as well as an MR template image from an open-source repository, demonstrates that MR-TIM is more accurate than alternative approaches for whole-head tissue segmentation. We hope that MR-TIM, by yielding an increased precision in head modelling, will contribute to a more widespread use of EEG as a brain imaging technique.

Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling.

Transcranial brain stimulation (TBS) has been established as a method for modulating and mapping the function of the human brain, and as a potential treatment tool in several brain disorders. Typically, the stimulation is applied using a one-size-fits-all approach with predetermined locations for the electrodes, in electric stimulation (TES), or the coil, in magnetic stimulation (TMS), which disregards anatomical variability between individuals. However, the induced electric field distribution in the head largely depends on anatomical features implying the need for individually tailored stimulation protocols for focal dosing. This requires detailed models of the individual head anatomy, combined with electric field simulations, to find an optimal stimulation protocol for a given cortical target. Considering the anatomical and functional complexity of different brain disorders and pathologies, it is crucial to account for the anatomical variability in order to translate TBS from a research tool into a viable option for treatment. In this article we present a new method, called CHARM, for automated segmentation of fifteen different head tissues from magnetic resonance (MR) scans. The new method compares favorably to two freely available software tools on a five-tissue segmentation task, while obtaining reasonable segmentation accuracy over all fifteen tissues. The method automatically adapts to variability in the input scans and can thus be directly applied to clinical or research scans acquired with different scanners, sequences or settings. We show that an increase in automated segmentation accuracy results in a lower relative error in electric field simulations when compared to anatomical head models constructed from reference segmentations. However, also the improved segmentations and, by implication, the electric field simulations are affected by systematic artifacts in the input MR scans. As long as the artifacts are unaccounted for, this can lead to local simulation differences up to 30% of the peak field strength on reference simulations. Finally, we exemplarily demonstrate the effect of including all fifteen tissue classes in the field simulations against the standard approach of using only five tissue classes and show that for specific stimulation configurations the local differences can reach 10% of the peak field strength.

Semantic segmentation of the multiform proximal femur and femoral head bones with the deep convolutional neural networks in low quality MRI sections acquired in different MRI protocols.

Medical image segmentation is one of the most crucial issues in medical image processing and analysis. In general, segmentation of the various structures in medical images is performed for the further image analyzes such as quantification, assessment, diagnosis, prognosis and classification. In this paper, a research study for the 2D semantic segmentation of the multiform, both spheric and aspheric, femoral head and proximal femur bones in magnetic resonance imaging (MRI) sections of the patients with Legg-Calve-Perthes disease (LCPD) with the deep convolutional neural networks (CNNs) is presented. In the scope of the proposed study, bilateral hip MRI sections acquired in coronal plane were used. The main characteristic of the MRI sections that were used is to be low quality images which were obtained in different MRI protocols by using 3 different MRI scanners with 1.5 T imaging capability. In performance evaluations, promising segmentation results were achieved with deep CNNs in low quality MRI sections acquired in different MRI protocols. A success rate about 90% was observed in semantic segmentation of the multiform femoral head and proximal femur bones in a total of 194 MRI sections obtained from 33 MRI sequences of 13 patients with deep CNNs.

Candidate gene screen for potential interaction partners and regulatory targets of the Hox gene labial in the spider Parasteatoda tepidariorum.

The Hox gene labial (lab) governs the formation of the tritocerebral head segment in insects and spiders. However, the morphology that results from lab action is very different in the two groups. In insects, the tritocerebral segment (intercalary segment) is reduced and lacks appendages, whereas in spiders the corresponding segment (pedipalpal segment) is a proper segment including a pair of appendages (pedipalps). It is likely that this difference between lab action in insects and spiders is mediated by regulatory targets or interacting partners of lab. However, only a few such genes are known in insects and none in spiders. We have conducted a candidate gene screen in the spider Parasteatoda tepidariorum using as candidates Drosophila melanogaster genes known to (potentially) interact with lab or to be expressed in the intercalary segment. We have studied 75 P. tepidariorum genes (including previously published and duplicated genes). Only 3 of these (proboscipedia-A (pb-A) and two paralogs of extradenticle (exd)) showed differential expression between leg and pedipalp. The low success rate points to a weakness of the candidate gene approach when it is applied to lineage specific organs. The spider pedipalp has no counterpart in insects, and therefore relying on insect data apparently cannot identify larger numbers of factors implicated in its specification and formation. We argue that in these cases a de novo approach to gene discovery might be superior to the candidate gene approach.

Gene profiling of head mesoderm in early zebrafish development: insights into the evolution of cranial mesoderm.

BACKGROUND: The evolution of the head was one of the key events that marked the transition from invertebrates to vertebrates. With the emergence of structures such as eyes and jaws, vertebrates evolved an active and predatory life style and radiated into diversity of large-bodied animals. These organs are moved by cranial muscles that derive embryologically from head mesoderm. Compared with other embryonic components of the head, such as placodes and cranial neural crest cells, our understanding of cranial mesoderm is limited and is restricted to few species. RESULTS: Here, we report the expression patterns of key genes in zebrafish head mesoderm at very early developmental stages. Apart from a basic anterior-posterior axis marked by a combination of pitx2 and tbx1 expression, we find that most gene expression patterns are poorly conserved between zebrafish and chick, suggesting fewer developmental constraints imposed than in trunk mesoderm. Interestingly, the gene expression patterns clearly show the early establishment of medial-lateral compartmentalisation in zebrafish head mesoderm, comprising a wide medial zone flanked by two narrower strips. CONCLUSIONS: In zebrafish head mesoderm, there is no clear molecular regionalisation along the anteroposterior axis as previously reported in chick embryos. In contrast, the medial-lateral regionalisation is formed at early developmental stages. These patterns correspond to the distinction between paraxial mesoderm and lateral plate mesoderm in the trunk, suggesting a common groundplan for patterning head and trunk mesoderm. By comparison of these expression patterns to that of amphioxus homologues, we argue for an evolutionary link between zebrafish head mesoderm and amphioxus anteriormost somites.

Automatic detection and segmentation of sperm head, acrosome and nucleus in microscopic images of human semen smears.

BACKGROUND AND OBJECTIVE: Manual assessment of sperm morphology is subjective and error prone so developing automatic methods is vital for a more accurate assessment. The first step in automatic evaluation of sperm morphology is sperm head detection and segmentation. In this paper a complete framework for automatic sperm head detection and segmentation is presented. METHODS: After an initial thresholding step, the histogram of the Hue channel of HSV color space is used, in addition to size criterion, to discriminate sperm heads in microscopic images. To achieve an improved segmentation of sperm heads, an edge-based active contour method is used. Also a novel tail point detection method is proposed to refine the segmentation by locating and removing the midpiece from the segmented head. An algorithm is also proposed to separate the acrosome and nucleus using morphological operations. Dice coefficient is used to evaluate the segmentation performance. The proposed methods are evaluated using a publicly available dataset. RESULTS: The proposed method has achieved segmentation accuracy of 0.92 for sperm heads, 0.84 for acrosomes and 0.87 for nuclei, with the standard deviation of 0.05, which significantly outperforms the current state-of-the-art. Also our tail detection method achieved true detection rate of 96%. CONCLUSIONS: In this paper we presented a complete framework for sperm detection and segmentation which is totally automatic. It is shown that using active contours can improve the segmentation results of sperm heads. Our proposed algorithms for tail detection and midpiece removal further improved the segmentation results. The results indicate that our method achieved higher Dice coefficients with less dispersion compared to the existing solutions.

What are Head Cavities? - A History of Studies on Vertebrate Head Segmentation.

Motivated by the discovery of segmental epithelial coeloms, or "head cavities," in elasmobranch embryos toward the end of the 19th century, the debate over the presence of mesodermal segments in the vertebrate head became a central problem in comparative embryology. The classical segmental view assumed only one type of metamerism in the vertebrate head, in which each metamere was thought to contain one head somite and one pharyngeal arch, innervated by a set of cranial nerves serially homologous to dorsal and ventral roots of spinal nerves. The non-segmental view, on the other hand, rejected the somite-like properties of head cavities. A series of small mesodermal cysts in early Torpedo embryos, which were thought to represent true somite homologs, provided a third possible view on the nature of the vertebrate head. Recent molecular developmental data have shed new light on the vertebrate head problem, explaining that head mesoderm evolved, not by the modification of rostral somites of an amphioxus-like ancestor, but through the polarization of unspecified paraxial mesoderm into head mesoderm anteriorly and trunk somites posteriorly.

Comparative morphology and development of extra-ocular muscles in the lamprey and gnathostomes reveal the ancestral state and developmental patterns of the vertebrate head.

The ancestral configuration of the vertebrate head has long been an intriguing topic in comparative morphology and evolutionary biology. One peculiar component of the vertebrate head is the presence of extra-ocular muscles (EOMs), the developmental mechanism and evolution of which remain to be determined. The head mesoderm of elasmobranchs undergoes local epithelialization into three head cavities, precursors of the EOMs. In contrast, in avians, these muscles appear to develop mainly from the mesenchymal head mesoderm. Importantly, in the basal vertebrate lamprey, the head mesoderm does not show overt head cavities or signs of segmental boundaries, and the development of the EOMs is not well described. Furthermore, the disposition of the lamprey EOMs differs from those the rest of vertebrates, in which the morphological pattern of EOMs is strongly conserved. To better understand the evolution and developmental origins of the vertebrate EOMs, we explored the development of the head mesoderm and EOMs of the lamprey in detail. We found that the disposition of lamprey EOM primordia differed from that in gnathostomes, even during the earliest period of development. We also found that three components of the paraxial head mesoderm could be distinguished genetically (premandibular mesoderm: Gsc+/TbxA-; mandibular mesoderm: Gsc-/TbxA-; hyoid mesoderm: Gsc-/TbxA+), indicating that the genetic mechanisms of EOMs are conserved in all vertebrates. We conclude that the tripartite developmental origin of the EOMs is likely to have been possessed by the latest common ancestor of the vertebrates. This ancestor's EOM developmental pattern was also suggested to have resembled more that of the lamprey, and the gnathostome EOMs' disposition is likely to have been established by a secondary modification that took place in the common ancestor of crown gnathostomes.

Gold-standard and improved framework for sperm head segmentation.

Semen analysis is the first step in the evaluation of an infertile couple. Within this process, an accurate and objective morphological analysis becomes more critical as it is based on the correct detection and segmentation of human sperm components. In this paper, we present an improved two-stage framework for detection and segmentation of human sperm head characteristics (including acrosome and nucleus) that uses three different color spaces. The first stage detects regions of interest that define sperm heads, using k-means, then candidate heads are refined using mathematical morphology. In the second stage, we work on each region of interest to segment accurately the sperm head as well as nucleus and acrosome, using clustering and histogram statistical analysis techniques. Our proposal is also characterized by being fully automatic, where a user intervention is not required. Our experimental evaluation shows that our proposed method outperforms the state-of-the-art. This is supported by the results of different evaluation metrics. In addition, we propose a gold-standard built with the cooperation of a referent expert in the field, aiming to compare methods for detecting and segmenting sperm cells. Our results achieve notable improvement getting above 98% in the sperm head detection process at the expense of having significantly fewer false positives obtained by the state-of-the-art method. Our results also show an accurate head, acrosome and nucleus segmentation achieving over 80% overlapping against hand-segmented gold-standard. Our method achieves higher Dice coefficient, lower Hausdorff distance and less dispersion with respect to the results achieved by the state-of-the-art method.

The evolutionary origin of the vertebrate body plan: the problem of head segmentation.

The basic body plan of vertebrates, as typified by the complex head structure, evolved from the last common ancestor approximately 530 Mya. In this review, we present a brief overview of historical discussions to disentangle the various concepts and arguments regarding the evolutionary development of the vertebrate body plan. We then explain the historical transition of the arguments about the vertebrate body plan from merely epistemological comparative morphology to comparative embryology as a scientific treatment on this topic. Finally, we review the current progress of molecular evidence regarding the basic vertebrate body plan, focusing on the link between the basic vertebrate body plan and the evolutionarily conserved developmental stages (phylotypic stages).

Head segmentation in the embryo of the Colorado beetleLeptinotarsa decemlineata as seen with anti-en immunostaining.

Segmentation in the head of the embryo of the Colorado beetleLeptinotarsa decemlineata is described on the basis of anti-engrailed (en) immunostaining of germ band stages. Six segmental units can be identified with this technique. Three segmentalen stripes can be distinguished in the gnathal region, a weak stripe interrupted medially shows the intercalary segment rudiment, a pair of oblique stripes indicate the antennal segment, and one pair of preantennalen spots are taken to indicate a sixth segment. In the broad head lobes of the beetle the spacing of the six segmental units as demarcated byen regions is similar to that in other parts of the germ band. The results are discussed with respect to old and new data concerning the number of head segments and origin of the compound eye in insects.

Segmental organisation of the head in the embryo of Drosophila melanogaster : A blastoderm fate map of the cuticle structures of the larval head.

Embryos of Drosophila melanogaster were irradiated in the presumptive head region with a UV-laser microbeam of 20 µm diameter at two developmental stages, the cellular blastoderm and the extended germ band. The ensuing defects were scored in the cuticle pattern of the head of the first-instar larva, which is described in detail in this paper. The defects caused by irradiating germ band embryos when morphologically recognisable lobes appear in the head region were used to establish the segmental origin of various head structures. This information enabled us to translate the spatial distribution of blastoderm defects into a fate map of segment anlagen. The gnathal segments derive from a region of the blastoderm between 60% and 70% egg length (EL) dorsally and 60% and 80% ventrally. The area anterior to the mandibular anlage and posterior to the stomodaeum is occupied by the small anlagen of the intercalary and antennal segments ventrally and dorsally, respectively. The labrum, which originates from a paired anlage dorsally at 90% EL, is separated from the remaining head segments by an area for which we did not observe cuticle defects following blastoderm irradiation, presumably because those cells give rise to the brain. The dorsal and lateral parts of the cephalo-pharyngeal skeleton appear to be the only cuticle derivatives of the non-segmental acron. These structures derive from a dorso-lateral area just behind the putative brain anlage and may overlap the latter. In addition to the segment anlagen, the regions of the presumptive dorsal pouch, anterior lobe and post-oral epithelium, whose morphogenetic movements during head involution result in the characteristic acephalic appearance of the larva, have been projected onto the blastoderm fate map. The results suggest that initially the head of the Drosophila embryo does not differ substantially from the generalised insect head as judged by comparison of fate map and segmental organisation.