Organ Shape Research Articles

Cost-Efficient Video Synthesis and Evaluation for Development of Virtual 3D Endoscopy.

Objective: 3D reconstruction of the shape and texture of hollow organs captured by endoscopy is important for the diagnosis and surveillance of early and recurrent cancers. Better evaluation of 3D reconstruction pipelines developed for such applications requires easy access to extensive datasets and associated ground truths, cost-efficient and scalable simulations of a range of possible clinical scenarios, and more reliable and insightful metrics to assess performance. Methods: We present a computer-aided simulation platform for cost-effective synthesis of monocular endoscope videos and corresponding ground truths that mimic a range of potential settings and situations one might encounter during acquisition of clinical endoscopy videos. Using cystoscopy of the bladder as model case, we generated an extensive dataset comprising several synthesized videos of a bladder phantom. We then introduce a novel evaluation procedure to reliably assess an individual 3D reconstruction pipeline or to compare different pipelines. Results: To illustrate the use of the proposed platform and evaluation procedure, we use the aforementioned dataset and ground truths to evaluate a proprietary 3D reconstruction pipeline (CYSTO3D) for bladder cystoscopy videos and compared it with a general-purpose 3D reconstruction pipeline (COLMAP). The evaluation results provide insight into the suggested clinical acquisition protocol and several potential areas for refinement of the pipeline to improve future performance. Conclusion: Our work proposes an endoscope video synthesis and reconstruction evaluation toolset and presents experimental results that illustrate usage of the toolset to efficiently assess performance and reveal possible problems of any given 3D reconstruction pipeline, to compare different pipelines, and to provide technically or clinically actionable insights.

Herbarium – Summer 2021

Introduction. Medicinal plants are perfectly suited to interact with biological macromolecules like proteins and nucleic acids. All sources of natural products such as plants, microorganisms, animals, etc. are therefore biochemical potential. Aim. The goal was to present a typical plant often found in abandoned places, fields, meadows in the Podkarpacie region of Poland. Medicinal plants presented here were collected in Summer 2021 close to the city Jarosław. Material and methods. Plants collected for herbarium, immediately after harvest, are laid out between paper sheets that absorb moisture. Dried plants retain the shape of individual organs and usually also the colors. As the result of our collection, in this article are presented Papaver rhoeas L., Centaurea cyanus L., Capsella bursa – pastoris L., Taraxacum officinalle F.H., Wigg Coll and Lamium album L. Analysis of the literature. The desire to summarize information for future generations and to present the writings of the classical scholars to a wide audience was the major stimulations for presenting a most popular medicinal plants to the reader. The plants most often obtained for pharmaceutical purposes include: chamomile, fennel, St. John’s wort, nettle, mint, dandelion, yarrow, marshmallow, sage, foxglove, lemon balm, dandelion, rosehip, aloe, ginseng, and milk thistle. Conclusion. The history of plants collections is well documented.

A Simple Generic Method for Effective Boundary Extraction in Medical Image Segmentation

Accurate identification of the shape and position of organs and abnormal objects (e.g., tumors) in medical images plays an important role in surgical planning as well as in the diagnosis and prognosis of diseases. However, this is difficult to achieve from two-dimensional medical images as these images present inaccurate and ambiguous organ boundaries. Further, traditional image processing-based boundary detection methods such as the Canny edge detector and Sobel operator exhibit poor boundary detection performance for images with substantial noise. Recently, the use of deep learning has resulted in improvements in semantic segmentation in medical images. In this paper, we propose a generic boundary-aware loss function to facilitate the effective discernment of the boundaries of organs and abnormal objects in medical images. Specifically, the proposed loss function introduces a boundary area and assigns higher weights to the loss of pixels located in the boundary area than to those in the non-boundary areas, thereby promoting effective learning in the boundary area. The results of experiments conducted using public medical datasets comprising colon polyp, skin lesion, and chest X-ray data indicate that the standard loss functions, such as cross-entropy loss and Dice loss, combined with the proposed boundary-aware loss function, achieve comparable or better performance than those without the boundary-aware loss function.

Study on the spatial distribution patterns of histone modifications in Hippo pathway genes.

Hippo pathway can regulate cell division, differentiation and apoptosis, and control the shape and size of organs. To study the distribution patterns of histone modifications of Hippo pathway genes in embryonic stem cells is helpful to understand the molecular regulation mechanism of histone modification and Hippo pathway on stem cell self-renewal. In this study, 19 genes of Hippo pathway including YAP, TAZ, LATS1/2, MST1 and SAV1, and eight histone modifications in embryonic stem cells were chosen to study the spatial distribution patterns of histone modifications. It was found that there were obvious type specificity and the location preference of target regions in the distributions of histone modifications, and H3K4me3 and H3K36me3 played the most important regulatory roles. Through the correlation analysis of histone modifications, a histone modification functional cluster composed of H3K4ac, H3K4me3, H3K9ac and H3K27ac was detected in YAP. In addition, the spatial distribution patterns of histone modifications in Hippo pathway genes were obtained, which provided a new theoretical reference for elucidating the mechanism of histone modifications regulating the gene expression of Hippo pathway, and for revealing the molecular regulatory mechanism of histone modifications affecting the self-renewal of embryonic stem cells by regulating the Hippo pathway.

The effects of the sex chromosomes on the inheritance of species-specific traits of the copulatory organ shape in Drosophila virilis and Drosophila lummei.

The shape of the male genitalia in many taxa is the most rapidly evolving morphological structure, often driving reproductive isolation, and is therefore widely used in systematics as a key character to distinguish between sibling species. However, only a few studies have used the genital arch of the male copulatory organ as a model to study the genetic basis of species-specific differences in the Drosophila copulatory system. Moreover, almost nothing is known about the effects of the sex chromosomes on the shape of the male mating organ. In our study, we used a set of crosses between D. virilis and D. lummei and applied the methods of quantitative genetics to assess the variability of the shape of the male copulatory organ and the effects of the sex chromosomes and autosomes on its variance. Our results showed that the male genital shape depends on the species composition of the sex chromosomes and autosomes. Epistatic interactions of the sex chromosomes with autosomes and the species origin of the Y-chromosome in a male in interspecific crosses also influenced the expression of species-specific traits in the shape of the male copulatory system. Overall, the effects of sex chromosomes were comparable to the effects of autosomes despite the great differences in gene numbers between them. It may be reasonably considered that sexual selection for specific genes associated with the shape of the male mating organ prevents the demasculinization of the X chromosome.

Weed invasive

Biological invasions are increasingly attracting the attention of ecologists, so it seems that this phenomenon is relatively new. However, the beginning of the study of biological invasions is publication of the book "The Ecology of Invasions by Animals and Plants" (1958), which is classified as classic works of invasions. Research of biological invasion is focused on the study of crucial biological and ecological characteristics which enable species invasiveness, as well as the characteristics of the recipient community. Despite the intensive study of this phenomenon, there are still differing views whether only introduced alien species or even native species can be considered as invasive species. While some researchers consider that native species cannot belong to the invasive category, others thought that a species that is native, when expend to adjacent habitats, may also be considered as invasive. Understanding biological invasions as if there no difference between native and introduced allochthonous species eliminates the dilemma that arises in the case of cryptogenic species (species that cannot be clearly classified into one of these two groups), whether it is native or introduced species, the success of the spreading depends on ecological adaptations. In addition, there is also disagreement about the stages of biological invasions. One point of view is, invasion processes take place through three phases (introduction, colonization and naturalization), while to other, the introduction is an elementary requirement for invasion, colonization is an integral part of the concept of naturalization, and naturalization which is referred in to previous point of view, is the phase that corresponds to the term "invasiveness". The time and route of introduction, as well as the mode and pathways of spreading for a large number of adventitious weed species have not been precisely established. Depending on whether weed species are introduce accidentally or intentionally, they are divided into boyletophytes (intentionally introduce) and aboyletophytes (accidentally introduce), while according to period of introduction they are divided into archeophytes (introduced in the Paleozoic to Neolithic period), paleophytes (introduced during the Old and Middle Ages until the discovery of America), neophytes (introduced after the discovery of America until to World War II), and neotophytes (introduced from the World War II until nowadays). Invasive processes are very complex, and it is not easy to predict and evaluate the behavior of introduced species in a new environment. Depending on the shape, structure and size of the reproductive organs, invasive weeds can be spread in several ways: autochthonous (selfpropagating), anemohoric (spreading through the wind), hydrohorn (spreading through water), zohornous (spreading by animals) and anthroporous (spreading by human). The success of invasive processes depends on the ecological characteristics of species, environmental resources and degree of ecosystem damage into which species has reached. According to success of survival in the new environment, allochthonous species can have status of the ephemeral (species which temporarily retained in the new environment and do not form stable populations), naturalized (species that are maintained in the new habitat but do not have an expansive character) and invasive (species that are adapted to the new habitat, spreading, forming indigenous part of flora and leave fertile offspring). The ecological-genetic potential of these species is the result of genetic diversity and their capacity for ecological adaptation; mutations, recombination, hybridization and introgression are the main processes responsible for genetic diversity. In the area of introduction, allochthonous species manifest numerous negative impacts on agriculture, ecosystems, human and domestic animal health, socioeconomic relationships and can jeopardize the survival of native species. Invasions are generally classified as negative occurrences, although in some circumstances they may also have a positive effect on the environment. For example, introduction of allochthonous species can enrich biodiversity, in case when number of introduced species far exceeds the number of extinct species. Despite the great scientific and technological progress, the problem of biological invasions cannot be completely resolved, but it is possible to limit these processes and reduce their negative consequences. The European and Mediterranean Plant Protection Organization (EPPO) dedicate special attention to the risks of invasive plant species and recommends measures to prevent their introduction and spread, with special reference to organisms that cause damage in agriculture. Control of these species implies application of all available preventive and direct measures, integrated into a system of integral measures.

Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-D deep learning approach.

Automatic sigmoid colon segmentation in CT for radiotherapy treatment planning is challenging due to complex organ shape, close distances to other organs, and large variations in size, shape, and filling status. The patient bowel is often not evacuated, and CT contrast enhancement is not used, which further increase problem difficulty. Deep learning (DL) has demonstrated its power in many segmentation problems. However, standard 2-D approaches cannot handle the sigmoid segmentation problem due to incomplete geometry information and 3-D approaches often encounters the challenge of a limited training data size. Motivated by human's behavior that segments the sigmoid slice by slice while considering connectivity between adjacent slices, we proposed an iterative 2.5-D DL approach to solve this problem. We constructed a network that took an axial CT slice, the sigmoid mask in this slice, and an adjacent CT slice to segment as input and output the predicted mask on the adjacent slice. We also considered other organ masks as prior information. We trained the iterative network with 50 patient cases using five-fold cross validation. The trained network was repeatedly applied to generate masks slice by slice. The method achieved average Dice similarity coefficients of 0.82 0.06 and 0.88 0.02 in 10 test cases without and with using prior information.

The PEAPOD Pathway and Its Potential To Improve Crop Yield.

A key strategy to increase plant productivity is to improve intrinsic organ growth. Some of the regulatory networks underlying organ growth and development, as well as the interconnections between these networks, are highly conserved. An example of such a growth-regulatory module with a highly conserved role in final organ size and shape determination in eudicot species is the PEAPOD (PPD)/KINASE-INDUCIBLE DOMAIN INTERACTING (KIX)/STERILE APETALA (SAP) module. We review the proteins constituting the PPD pathway and their roles in different plant developmental processes, and explore options for future research. We also speculate on strategies to exploit knowledge about the PPD pathway for targeted yield improvement to engineer crop traits of agronomic interest, such as leaf, fruit, and seed size.

PEMANFAATAN BERBAGAI JENIS PUPUK BERBAHAN LIMBAH RUMAH TANGGA TERHADAP PERTUMBUHAN TANAMAN

The research objective was to describe the types of household waste that can be used as fertilizer in increasing plant growth. This type of research is descriptive research with literature study by discussing household waste that can be used as organic fertilizer. The independent variable in this study is the type of fertilizer from household waste, the dependent variable in this study is plant growth. In this study, the operational variable is plant vegetative growth. In plant growth there will be an increase in the volume, number, shape and size of the vegetative organs. Meanwhile, vegetative growth of plants starts from the growth of roots, stems and leaves. In this phase, plants need a lot of food reserves which will be converted into energy for growth. Waste that can be used as fertilizer can be fertilized into solid or liquid organic fertilizers to help plant growth. The waste includes, among others, bagasse, duck egg shells, chicken egg shells, peanut shells, tea dregs, coconut dregs, green bean sprouts.

The genetic control of leaf and petal allometric variations in Arabidopsis thaliana

BackgroundOrgan shape and size covariation (allometry) factors are essential concepts for the study of evolution and development. Although ample research has been conducted on organ shape and size, little research has considered the correlated variation of these two traits and quantitatively measured the variation in a common framework. The genetic basis of allometry variation in a single organ or among different organs is also relatively unknown.ResultsA principal component analysis (PCA) of organ landmarks and outlines was conducted and used to quantitatively capture shape and size variation in leaves and petals of multiparent advanced generation intercross (MAGIC) populations of Arabidopsis thaliana. The PCA indicated that size variation was a major component of allometry variation and revealed negatively correlated changes in leaf and petal size. After quantitative trait loci (QTL) mapping, five QTLs for the fourth leaf, 11 QTLs for the seventh leaf, and 12 QTLs for petal size and shape were identified. These QTLs were not identical to those previously identified, with the exception of the ER locus. The allometry model was also used to measure the leaf and petal allometry covariation to investigate the evolution and genetic coordination between homologous organs. In total, 12 QTLs were identified in association with the fourth leaf and petal allometry covariation, and eight QTLs were identified to be associated with the seventh leaf and petal allometry covariation. In these QTL confidence regions, there were important genes associated with cell proliferation and expansion with alleles unique to the maximal effects accession. In addition, the QTLs associated with life-history traits, such as days to bolting, stem length, and rosette leaf number, which were highly coordinated with climate change and local adaption, were QTL mapped and showed an overlap with leaf and petal allometry, which explained the genetic basis for their correlation.ConclusionsThis study explored the genetic basis for leaf and petal allometry and their interaction, which may provide important information for investigating the correlated variation and evolution of organ shape and size in Arabidopsis.

Changes in the Fluctuating Asymmetry of the Leaf and Reproductive Capacity of Betula pendula Roth Reflect Pessimization of Anthropogenically Transformed Environment

We have estimated the reproductive capacity of Betulapendula Roth and its relationship with an integrated measure of developmental stability, i.e., fluctuating asymmetry (FA) of the leaf. On the territory of a city with moderate anthropogenic pollution, a change has been detected in the integrated fluctuating asymmetry (IFA) of the morphology of the female reproductive sphere and reproductive capacity of Betula pendula. In conditions of anthropogenic stress, the birch is observed to produce a large yield of fruits annually, which is not subject to year-to-year fluctuations. Morphological variety of size and shape of fruit-producing organs increases along the gradient of industrial and transport pollution; part of morphotypes of infructescences and seeds is characterized by lowered or zero capacity for reproduction determined by seed quality (germination energy and germination capacity). The statistical data processing involved correlation, Shapiro–Wilk test, Levene’s test, factorial ANOVA, Scheffe test, Kruskal–Wallis ANOVA, Mann–Whitney test, χ2 method. Analysis of IFA has allowed us to reasonably well assess the state of the plant organism and to characterize environmental quality. A negative correlation between IFA and quantitative parameters of the functions of the reproductive sphere of B. pendula (infructescence diameter, seed quality) has been found, and positive correlation with qualitative parameters (the number of morphs of infructescences and seeds, the share of rare morphs of infructescences). Pessimization of urban environment creates the conditions for an increase in the share of defective infructescences and non-germinating seeds; a compensatory mechanism for this is an increase in reproductive effort of B. pendula. The consistency of responses in the vegetative and reproductive spheres reflects the disturbances in developmental stability of plants in urban communities.

Spicoid ontogeny in Diplasia (Mapanioideae, Cyperaceae): an approach on the developmental processes operating in Mapanioideae spicoids

Mapanioideae (besides Cyperoideae the other subfamily of Cyperaceae) is divided in two tribes (Hypolytreae and Chrysitricheae) in which the reproductive units (spicoids) are interpreted either as flowers or as inflorescences. Little is known about the ontogenetic factors operating during the spicoid development and how they may contribute to the spicoid final morphology. In this context, we studied the spicoid development in the monotypic genus Diplasia and compared it with other developmental studies in Mapanioideae. Our results show that the main developmental variations are related to the sequence of organ formation, the size and shape of the spicoid primordium and the influence of the subtending bract constraints in different sides of such primordium. Our hypotheses to explain the spicoid’s morphological variation in Mapanioideae are: that size and shape of the spicoid primordium contribute to changes in the number and position of organs to be formed, and spatial constraints of the subtending bracts influence the reduction of adaxial parts. Developmental features of the spicoids showed to be stable within the tribe. Our observations of the nature of spicoids in Diplasia give arguments for both, floral and inflorescence interpretations, sustaining the uncertainty towards a satisfactory definition. The difficulty in distinguishing the boundaries of flower and inflorescence nature in the spicoids raised a third hypothesis where the spicoid could be interpreted as a de novo structure, due to a reorganisation of regulatory genes resulting in a single unit with flower and inflorescence features combined, considered a synapomorphy of Mapanioideae.

PD-0556: Using multiple planning scans to predict organ shape variability during RT for prostate cancer

PD-0556: Using multiple planning scans to predict organ shape variability during RT for prostate cancer

Transcriptome-wide single nucleotide polymorphisms related to electric organ discharge differentiation among African weakly electric fish species.

African weakly electric fish of the mormyrid genus Campylomormyrus generate pulse-type electric organ discharges (EODs) for orientation and communication. Their pulse durations are species-specific and elongated EODs are a derived trait. So far, differential gene expression among tissue-specific transcriptomes across species with different pulses and point mutations in single ion channel genes indicate a relation of pulse duration and electrocyte geometry/excitability. However, a comprehensive assessment of expressed Single Nucleotide Polymorphisms (SNPs) throughout the entire transcriptome of African weakly electric fish, with the potential to identify further genes influencing EOD duration, is still lacking. This is of particular value, as discharge duration is likely based on multiple cellular mechanisms and various genes. Here we provide the first transcriptome-wide SNP analysis of African weakly electric fish species (genus Campylomormyrus) differing by EOD duration to identify candidate genes and cellular mechanisms potentially involved in the determination of an elongated discharge of C. tshokwe. Non-synonymous substitutions specific to C. tshokwe were found in 27 candidate genes with inferred positive selection among Campylomormyrus species. These candidate genes had mainly functions linked to transcriptional regulation, cell proliferation and cell differentiation. Further, by comparing gene annotations between C. compressirostris (ancestral short EOD) and C. tshokwe (derived elongated EOD), we identified 27 GO terms and 2 KEGG pathway categories for which C. tshokwe significantly more frequently exhibited a species-specific expressed substitution than C. compressirostris. The results indicate that transcriptional regulation as well cell proliferation and differentiation take part in the determination of elongated pulse durations in C. tshokwe. Those cellular processes are pivotal for tissue morphogenesis and might determine the shape of electric organs supporting the observed correlation between electrocyte geometry/tissue structure and discharge duration. The inferred expressed SNPs and their functional implications are a valuable resource for future investigations on EOD durations.

Automatic Segmentation Using Deep Learning for Online Dose Optimization During Adaptive Radiotherapy of Cervical Cancer

A phase II clinical trial was designed to propose daily online dose optimization to eliminate need for ITV expansions in order to reduce toxicity events of EBRT for cervical cancer. This study investigates deep learning models for automatic segmentation. The cervix-uterus, vagina, bladder, rectum, sigmoid, femoral heads, kidneys, spinal cord, and bowel bag were delineated on 223 CT scans from 157 patients. The data were divided into 149 training, 36 validation and 38 test CTs. Two models were investigated: the multiclass 2D DeepLabV3+ and the 2-steps 3D U-net of RayStation. The 2D model was trained with a window optimizer of 3 channels, triangular cyclic learning rate, no dropout and no augmentation. The 3D model was trained with batch normalization, data augmentation (translation, rotation and deformation) and no dropout. Both models were trained with the Adam optimizer. Three IMRT plans were generated on the planning CT of 20 unique cases from the test set using the manual, 2D or 3D model contours following the EMBRACE II constraints with reduced PTVT/N margins of 5/3 mm. Both models were compared with manual contours on the validation and test sets using the Dice coefficient (DC). Using manual contours as reference, clinical dose indices were extracted on the manual, 2D and 3D model optimized doses for comparison. The mean (min – max) of the average DC of all organs on the validation and test sets were 0.86 (0.61 – 0.93) and 0.85 (0.67 – 0.93) for the 2D model and 0.84 (0.70 – 0.93) and 0.82 (0.65 – 0.92) for the 3D model. The sigmoid and vagina were the most challenging organs with a DC range of 0.61 – 0.72 for both models on the validation and test sets. The 2D model provided better DC for the spinal and bowel on all cases (p< 0.001). The 3D model provided a significantly better DC for the sigmoid on the validation set (p = 0.001), otherwise no difference was found. Removing the spinal and bowel from analysis, the 3D model provided a superior DC for 60% of all cases. The mean (min – max) DC of the CTVT on the 20 test cases were 0.89 (0.75 – 0.93) and 0.88 (0.69 – 0.95) for the 2D and 3D models. Using the manual CTVT on the 2D and 3D model optimized doses, 90% and 80% passed the V42.75Gy>98% (p = 0.07). The remaining 10% and 20% cases had a mean V42.75Gy of 95.6% for 2D and 93.7% for 3D model. The V42.75Gy decrease of the 3D model was significantly correlated with the DC of the CTVT and PTVT (R2 = 0.56 and R2 = 0.5 p<0.001). A decrease of 0.1 in DC was equivalent to a decrease of 3.1% and 5.5% of the V42.75Gy for the CTVT and PTVT. For all organs, 91%, 80%, and 80% of clinical constraints were met for the manual, 2D and 3D model optimized doses. The 2D model showed better robustness while the 3D model provided better representation of complex organ shape. Deep learning model-based segmentation is promising for implementing reduced margin online dose optimization during EBRT of cervical cancer.

Variation in the expression of a transmembrane protein influences cell growth in Arabidopsis thaliana petals by altering auxin responses

BackgroundThe same species of plant can exhibit very diverse sizes and shapes of organs that are genetically determined. Characterising genetic variation underlying this morphological diversity is an important objective in evolutionary studies and it also helps identify the functions of genes influencing plant growth and development. Extensive screens of mutagenised Arabidopsis populations have identified multiple genes and mechanisms affecting organ size and shape, but relatively few studies have exploited the rich diversity of natural populations to identify genes involved in growth control.ResultsWe screened a relatively well characterised collection of Arabidopsis thaliana accessions for variation in petal size. Association analyses identified sequence and gene expression variation on chromosome 4 that made a substantial contribution to differences in petal area. Variation in the expression of a previously uncharacterised gene At4g16850 (named as KSK) had a substantial role on variation in organ size by influencing cell size. Over-expression of KSK led to larger petals with larger cells and promoted the formation of stamenoid features. The expression of auxin-responsive genes known to limit cell growth was reduced in response to KSK over-expression. ANT expression was also reduced in KSK over-expression lines, consistent with altered floral identities. Auxin responses were reduced in KSK over-expressing cells, consistent with changes in auxin-responsive gene expression. KSK may therefore influence auxin responses during petal development.ConclusionsUnderstanding how genetic variation influences plant growth is important for both evolutionary and mechanistic studies. We used natural populations of Arabidopsis thaliana to identify sequence variation in a promoter region of Arabidopsis accessions that mediated differences in the expression of a previously uncharacterised membrane protein. This variation contributed to altered auxin responses and cell size during petal growth.

FocusNetv2: Imbalanced large and small organ segmentation with adversarial shape constraint for head and neck CT images.

Radiotherapy is a treatment where radiation is used to eliminate cancer cells. The delineation of organs-at-risk (OARs) is a vital step in radiotherapy treatment planning to avoid damage to healthy organs. For nasopharyngeal cancer, more than 20 OARs are needed to be precisely segmented in advance. The challenge of this task lies in complex anatomical structure, low-contrast organ contours, and the extremely imbalanced size between large and small organs. Common segmentation methods that treat them equally would generally lead to inaccurate small-organ labeling. We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation. In addition to our original FocusNet, we employ a novel adversarial shape constraint on small organs to ensure the consistency between estimated small-organ shapes and organ shape prior knowledge. Our proposed framework is extensively tested on both self-collected dataset of 1,164 CT scans and the MICCAI Head and Neck Auto Segmentation Challenge 2015 dataset, which shows superior performance compared with state-of-the-art head and neck OAR segmentation methods.

Shape prior model via dual subspace segment projection learning

Background and Objective: Shape prior models play a vital role for segmentation in medical image analysis. These models are most effective when shape variations can be captured by a parametric distribution, and sufficient training data is available. However, in the absence of these conditions, results are invariably much poorer. In this paper, we propose a novel shape prior model, via dual subspace segment projection learning (DSSPL), to address these challenges.Methods: DSSPL serves to compose shapes from an ensemble of shape segments where each segment is formed using two subspaces: global shape subspace and segment-specific subspace, each necessary for extracting global shape patterns and local patterns, respectively. This ensures the proposed approach has general shape plausibility in regions of signal drop-out or missing boundary information, and also more localized flexibility. The learned projections are constrained with l2,1 sparse norm terms to extract the most distinguishable features, while the reconstructive properties of DSSPL reduces information loss and leverages the subspaces to provide contiguous shapes without any post-processing.Results: Extensive analysis is performed on three databases from different medical imaging systems across X-Ray, MRI, and ultrasound. DSSPL outperforms all compared benchmarks in terms of shape generalization ability and segmentation performance.Conclusions: We propose a new shape prior model for segmentation in medical image analysis to address the challenges of modelling complex organ shapes with low sample size training data.

MULTIRESOLUTION ANALYSIS USING WAVELET TRANSFORMS FOR MEDICAL IMAGE SEGMENTATION

The experimental study presented in this paper is aimed at the development of an automatic image segmentation system for classifying region of interest (ROI) in medical images which are obtained from medical scanners like MRI. Multiresolution analysis (MRA) using wavelet transforms has been used in the proposed segmentation system. It is particularly a challenging task to classify cancers in human organs in scanners output using shape or gray-level information; organs shape changes throw different slices in medical stack and the gray-level intensity overlap in soft tissues. This paper presents the application of wavelet transform to perform these task using the three dimensional waveletdecomposition, coefficients thresholding and object reconstruction. The proposed method is verified for simulated data at first and then applied for processing of brain parts to emphasize its selected components. The goal of the paper is in (i) the presentation of the three-dimensional wavelet transform, (ii) discussion of its use for volume data denoising, and (iii) proposal of the following data extraction to allow their classification. The paper compares numerical results achieved by the use of different wavelet functions and thresholding methods with the experience of an expert to propose the best algorithmic approach to this problem.

Ultrastructural and immunocytochemical studies on the olfactory receptor neurons in the Ichthyosaura alpestris

AbstractMorphological and immunohistochemical studies were conducted on the alpine newt Ichthyosaura alpestris, which is representative of the family Salamandridae. The aim of the study was to determine the differences in olfactory organs structural properties, especially in the olfactory epithelium (OE) of the main olfactory chamber (MOC) and the vomeronasal organ (VNO) between breeding and non‐breeding seasons in this species. A change in environments occurs for alpine newts in the course of the annual cycle because of its aquatic adaptations for reproduction. The results confirmed the variability in the shape and size of olfactory organs between breeding and non‐breeding seasons. The presence of the ovoid cells with microvilli at its apical part was determined in the OE of males and females during breeding season. Giant ORNs, a subtype of ciliated ORNs, were observed only during the newt's non‐breeding season. The presence of the ovoid cells during the terrestrial phase was not determined. Thus, its role might be associated with reproduction.