RESUMO
Early-life immune development is critical to long-term host health. However, the mechanisms that determine the pace of postnatal immune maturation are not fully resolved. Here, we analyzed mononuclear phagocytes (MNPs) in small intestinal Peyer's patches (PPs), the primary inductive site of intestinal immunity. Conventional type 1 and 2 dendritic cells (cDC1 and cDC2) and RORgt+ antigen-presenting cells (RORgt+ APC) exhibited significant age-dependent changes in subset composition, tissue distribution, and reduced cell maturation, subsequently resulting in a lack in CD4+ T cell priming during the postnatal period. Microbial cues contributed but could not fully explain the discrepancies in MNP maturation. Type I interferon (IFN) accelerated MNP maturation but IFN signaling did not represent the physiological stimulus. Instead, follicle-associated epithelium (FAE) M cell differentiation was required and sufficient to drive postweaning PP MNP maturation. Together, our results highlight the role of FAE M cell differentiation and MNP maturation in postnatal immune development.
Assuntos
Células M , Nódulos Linfáticos Agregados , Intestinos , Intestino Delgado , Diferenciação Celular , Mucosa IntestinalRESUMO
A globally invasive form of the mosquito Aedes aegypti specializes in biting humans, making it an efficient disease vector1. Host-seeking female mosquitoes strongly prefer human odour over the odour of animals2,3, but exactly how they distinguish between the two is not known. Vertebrate odours are complex blends of volatile chemicals with many shared components4-7, making discrimination an interesting sensory coding challenge. Here we show that human and animal odours evoke activity in distinct combinations of olfactory glomeruli within the Ae. aegypti antennal lobe. One glomerulus in particular is strongly activated by human odour but responds weakly, or not at all, to animal odour. This human-sensitive glomerulus is selectively tuned to the long-chain aldehydes decanal and undecanal, which we show are consistently enriched in human odour and which probably originate from unique human skin lipids. Using synthetic blends, we further demonstrate that signalling in the human-sensitive glomerulus significantly enhances long-range host-seeking behaviour in a wind tunnel, recapitulating preference for human over animal odours. Our research suggests that animal brains may distil complex odour stimuli of innate biological relevance into simple neural codes and reveals targets for the design of next-generation mosquito-control strategies.
Assuntos
Aedes , Encéfalo , Comportamento de Busca por Hospedeiro , Odorantes , Aedes/fisiologia , Animais , Encéfalo/fisiologia , Feminino , Humanos , Controle de Mosquitos , Mosquitos Vetores/fisiologiaRESUMO
Modern microscopy techniques can be used to investigate soft nano-objects at the nanometer scale. However, time-consuming microscopy measurements combined with low numbers of observable polydisperse objects often limit the statistics. We propose a method for identifying the most representative objects from their respective point clouds. These point cloud data are obtained, for example, through the localization of single emitters in super-resolution fluorescence microscopy. External stimuli, such as temperature, can cause changes in the shape and properties of adaptive objects. Due to the demanding and time-consuming nature of super-resolution microscopy experiments, only a limited number of temperature steps can be performed. Therefore, we propose a deep generative model that learns the underlying point distribution of temperature-dependent microgels, enabling the reliable generation of unlimited samples with an arbitrary number of localizations. Our method greatly cuts down the data collection effort across diverse experimental conditions, proving invaluable for soft condensed matter studies.
RESUMO
INTRODUCTION: Sheep are frequently used in translational surgical orthopedic studies. Naturally, a good pain management is mandatory for animal welfare, although it is also important with regard to data quality. However, methods for adequate severity assessment, especially considering pain, are rather rare regarding large animal models. Therefore, in the present study, accompanying a surgical pilot study, telemetry and the Sheep Grimace Scale (SGS) were used in addition to clinical scoring for severity assessment after surgical interventions in sheep. METHODS: Telemetric devices were implanted in a first surgery subcutaneously into four German black-headed mutton ewes (4-5 years, 77-115 kg). After 3-4 weeks of recovery, sheep underwent tendon ablation of the left M. infraspinatus. Clinical scoring and video recordings for SGS analysis were performed after both surgeries, and the heart rate (HR) and general activity were monitored by telemetry. RESULTS: Immediately after surgery, clinical score and HR were slightly increased, and activity was decreased in individual sheep after both surgeries. The SGS mildly elevated directly after transmitter implantation but increased to higher levels after tendon ablation immediately after surgery and on the following day. CONCLUSION: In summary, SGS- and telemetry-derived data were suitable to detect postoperative pain in sheep with the potential to improve individual pain recognition and postoperative management, which consequently contributes to refinement.
Assuntos
Procedimentos Ortopédicos , Dor , Telemetria , Animais , Feminino , Modelos Animais , Projetos Piloto , Próteses e Implantes , Ovinos , Procedimentos Ortopédicos/veterináriaRESUMO
BACKGROUND: Nephropathologic analyses provide important outcomes-related data in experiments with the animal models that are essential for understanding kidney disease pathophysiology. Precision medicine increases the demand for quantitative, unbiased, reproducible, and efficient histopathologic analyses, which will require novel high-throughput tools. A deep learning technique, the convolutional neural network, is increasingly applied in pathology because of its high performance in tasks like histology segmentation. METHODS: We investigated use of a convolutional neural network architecture for accurate segmentation of periodic acid-Schiff-stained kidney tissue from healthy mice and five murine disease models and from other species used in preclinical research. We trained the convolutional neural network to segment six major renal structures: glomerular tuft, glomerulus including Bowman's capsule, tubules, arteries, arterial lumina, and veins. To achieve high accuracy, we performed a large number of expert-based annotations, 72,722 in total. RESULTS: Multiclass segmentation performance was very high in all disease models. The convolutional neural network allowed high-throughput and large-scale, quantitative and comparative analyses of various models. In disease models, computational feature extraction revealed interstitial expansion, tubular dilation and atrophy, and glomerular size variability. Validation showed a high correlation of findings with current standard morphometric analysis. The convolutional neural network also showed high performance in other species used in research-including rats, pigs, bears, and marmosets-as well as in humans, providing a translational bridge between preclinical and clinical studies. CONCLUSIONS: We developed a deep learning algorithm for accurate multiclass segmentation of digital whole-slide images of periodic acid-Schiff-stained kidneys from various species and renal disease models. This enables reproducible quantitative histopathologic analyses in preclinical models that also might be applicable to clinical studies.
Assuntos
Aprendizado Profundo , Diagnóstico por Computador , Rim/fisiopatologia , Reconhecimento Automatizado de Padrão , Algoritmos , Animais , Modelos Animais de Doenças , Processamento de Imagem Assistida por Computador/métodos , Nefropatias/patologia , Glomérulos Renais/patologia , Masculino , Camundongos , Camundongos Endogâmicos C57BL , Redes Neurais de Computação , Ácido Periódico/química , Reprodutibilidade dos Testes , Bases de Schiff , Pesquisa Translacional BiomédicaRESUMO
Fabric anomaly detection (AD) tries to detect anomalies (i.e., defects) in fabrics, and fabric AD approaches are continuously improved with respect to their AD performance. However, developed solutions are known to generalize poorly to previously unseen fabrics, posing a crucial limitation to their applicability. Moreover, current research focuses on adapting converged models to previously unseen fabrics in a post hoc manner, rather than training models that generalize better in the first place. In our work, we explore this potential for the first time. Specifically, we propose that previously unseen fabrics can be regarded as shifts in the underlying data distribution. We therefore argue that factors which reportedly improve a model's resistance to distribution shifts should also improve the performance of supervised fabric AD methods on unseen fabrics. Hence, we assess the potential benefits of: (I) vicinal risk minimization (VRM) techniques adapted to the fabric AD use-case, (II) different loss functions, (III) ImageNet pre-training, (IV) dataset diversity, and (V) model architecture as well as model complexity. The subsequently performed large-scale analysis reveals that (I) only the VRM technique, AugMix, consistently improves performance on unseen fabrics; (II) hypersphere classifier outperforms other loss functions when combined with AugMix and (III) ImageNet pre-training, which is already beneficial on its own; (IV) increasing dataset diversity improves performance on unseen fabrics; and (V) architectures with better ImageNet performance also perform better on unseen fabrics, yet the same does not hold for more complex models. Notably, the results show that not all factors and techniques which reportedly improve a model's resistance to distribution shifts in natural images also improve the generalization of supervised fabric AD methods to unseen fabrics, demonstrating the necessity of our work. Additionally, we also assess whether the performance gains of models which generalize better propagate to post hoc adaptation methods and show this to be the case. Since no suitable fabric dataset was publicly available at the time of this work, we acquired our own fabric dataset, called OLP, as the basis for the above experiments. OLP consists of 38 complex, patterned fabrics, more than 6400 images in total, and is made publicly available.
Assuntos
TêxteisRESUMO
An adaptive transition from exploring the environment in search of vital resources to exploiting these resources once the search was successful is important to all animals. Here we study the neuronal circuitry that allows larval Drosophila melanogaster of either sex to negotiate this exploration-exploitation transition. We do so by combining Pavlovian conditioning with high-resolution behavioral tracking, optogenetic manipulation of individually identified neurons, and EM data-based analyses of synaptic organization. We find that optogenetic activation of the dopaminergic neuron DAN-i1 can both establish memory during training and acutely terminate learned search behavior in a subsequent recall test. Its activation leaves innate behavior unaffected, however. Specifically, DAN-i1 activation can establish associative memories of opposite valence after paired and unpaired training with odor, and its activation during the recall test can terminate the search behavior resulting from either of these memories. Our results further suggest that in its behavioral significance DAN-i1 activation resembles, but does not equal, sugar reward. Dendrogram analyses of all the synaptic connections between DAN-i1 and its two main targets, the Kenyon cells and the mushroom body output neuron MBON-i1, further suggest that the DAN-i1 signals during training and during the recall test could be delivered to the Kenyon cells and to MBON-i1, respectively, within previously unrecognized, locally confined branching structures. This would provide an elegant circuit motif to terminate search on its successful completion.SIGNIFICANCE STATEMENT In the struggle for survival, animals have to explore their environment in search of food. Once food is found, however, it is adaptive to prioritize exploiting it over continuing a search that would now be as pointless as searching for the glasses you are wearing. This exploration-exploitation trade-off is important for animals and humans, as well as for technical search devices. We investigate which of the only 10,000 neurons of a fruit fly larva can tip the balance in this trade-off, and identify a single dopamine neuron called DAN-i1 that can do so. Given the similarities in dopamine neuron function across the animal kingdom, this may reflect a general principle of how search is terminated once it is successful.
Assuntos
Aprendizagem por Associação/fisiologia , Comportamento Animal/fisiologia , Neurônios Dopaminérgicos/fisiologia , Memória/fisiologia , Animais , Condicionamento Clássico , Drosophila melanogaster , Feminino , Masculino , Rememoração Mental/fisiologia , Corpos Pedunculados/fisiologia , Optogenética , Desempenho Psicomotor/fisiologia , Olfato/fisiologia , Sinapses/fisiologiaRESUMO
Cross-scanner and cross-protocol variability of diffusion magnetic resonance imaging (dMRI) data are known to be major obstacles in multi-site clinical studies since they limit the ability to aggregate dMRI data and derived measures. Computational algorithms that harmonize the data and minimize such variability are critical to reliably combine datasets acquired from different scanners and/or protocols, thus improving the statistical power and sensitivity of multi-site studies. Different computational approaches have been proposed to harmonize diffusion MRI data or remove scanner-specific differences. To date, these methods have mostly been developed for or evaluated on single b-value diffusion MRI data. In this work, we present the evaluation results of 19 algorithms that are developed to harmonize the cross-scanner and cross-protocol variability of multi-shell diffusion MRI using a benchmark database. The proposed algorithms rely on various signal representation approaches and computational tools, such as rotational invariant spherical harmonics, deep neural networks and hybrid biophysical and statistical approaches. The benchmark database consists of data acquired from the same subjects on two scanners with different maximum gradient strength (80 and 300 âmT/m) and with two protocols. We evaluated the performance of these algorithms for mapping multi-shell diffusion MRI data across scanners and across protocols using several state-of-the-art imaging measures. The results show that data harmonization algorithms can reduce the cross-scanner and cross-protocol variabilities to a similar level as scan-rescan variability using the same scanner and protocol. In particular, the LinearRISH algorithm based on adaptive linear mapping of rotational invariant spherical harmonics features yields the lowest variability for our data in predicting the fractional anisotropy (FA), mean diffusivity (MD), mean kurtosis (MK) and the rotationally invariant spherical harmonic (RISH) features. But other algorithms, such as DIAMOND, SHResNet, DIQT, CMResNet show further improvement in harmonizing the return-to-origin probability (RTOP). The performance of different approaches provides useful guidelines on data harmonization in future multi-site studies.
Assuntos
Algoritmos , Encéfalo/diagnóstico por imagem , Aprendizado Profundo , Imagem de Difusão por Ressonância Magnética/métodos , Processamento de Imagem Assistida por Computador/métodos , Neuroimagem/métodos , Adulto , Imagem de Difusão por Ressonância Magnética/instrumentação , Imagem de Difusão por Ressonância Magnética/normas , Humanos , Processamento de Imagem Assistida por Computador/normas , Neuroimagem/instrumentação , Neuroimagem/normas , Análise de RegressãoRESUMO
Spectral reconstruction from RGB or spectral super-resolution (SSR) offers a cheap alternative to otherwise costly and more complex spectral imaging devices. In recent years, deep learning based methods consistently achieved the best reconstruction quality in terms of spectral error metrics. However, there are important properties that are not maintained by deep neural networks. This work is primarily dedicated to scale invariance, also known as brightness invariance or exposure invariance. When RGB signals only differ in their absolute scale, they should lead to identical spectral reconstructions apart from the scaling factor. Scale invariance is an essential property that signal processing must guarantee for a wide range of practical applications. At the moment, scale invariance can only be achieved by relying on a diverse database during network training that covers all possibly occurring signal intensities. In contrast, we propose and evaluate a fundamental approach for deep learning based SSR that holds the property of scale invariance by design and is independent of the training data. The approach is independent of concrete network architectures and instead focuses on reevaluating what neural networks should actually predict. The key insight is that signal magnitudes are irrelevant for acquiring spectral reconstructions from camera signals and are only useful for a potential signal denoising.
RESUMO
Solid-liquid interfaces play an important role for functional devices. Hence, a detailed understanding of the interaction of soft matter objects with solid supports and of the often concomitant structural deformations is of great importance. We address this topic in a combined experimental and simulation approach. We investigated thermoresponsive poly(N-isopropylmethacrylamide) microgels (µGs) at different surfaces in an aqueous environment. As super-resolution fluorescence imaging method, three-dimensional direct stochastical optical reconstruction microscopy (dSTORM) allowed for visualizing µGs in their three-dimensional (3D) shape, for example, in a "fried-egg" conformation depending on the hydrophilicity of the surface (strength of adsorption). The 3D shape, as defined by point clouds obtained from single-molecule localizations, was analyzed. A new fitting algorithm yielded an isosurface of constant density which defines the deformation of µGs at the different surfaces. The presented methodology quantifies deformation of objects with fuzzy surfaces and allows for comparison of their structures, whereby it is completely independent from the data acquisition method. Finally, the experimental data are complemented with mesoscopic computer simulations in order to (i) rationalize the experimental results and (ii) to track the evolution of the shape with changing surface hydrophilicity; a good correlation of the shapes obtained experimentally and with computer simulations was found.
RESUMO
Diffusion MRI is being used increasingly in studies of the brain and other parts of the body for its ability to provide quantitative measures that are sensitive to changes in tissue microstructure. However, inter-scanner and inter-protocol differences are known to induce significant measurement variability, which in turn jeopardises the ability to obtain 'truly quantitative measures' and challenges the reliable combination of different datasets. Combining datasets from different scanners and/or acquired at different time points could dramatically increase the statistical power of clinical studies, and facilitate multi-centre research. Even though careful harmonisation of acquisition parameters can reduce variability, inter-protocol differences become almost inevitable with improvements in hardware and sequence design over time, even within a site. In this work, we present a benchmark diffusion MRI database of the same subjects acquired on three distinct scanners with different maximum gradient strength (40, 80, and 300â¯mT/m), and with 'standard' and 'state-of-the-art' protocols, where the latter have higher spatial and angular resolution. The dataset serves as a useful testbed for method development in cross-scanner/cross-protocol diffusion MRI harmonisation and quality enhancement. Using the database, we compare the performance of five different methods for estimating mappings between the scanners and protocols. The results show that cross-scanner harmonisation of single-shell diffusion data sets can reduce the variability between scanners, and highlight the promises and shortcomings of today's data harmonisation techniques.
Assuntos
Algoritmos , Benchmarking/métodos , Mapeamento Encefálico/métodos , Imagem de Difusão por Ressonância Magnética/normas , Processamento de Imagem Assistida por Computador/métodos , Adulto , Benchmarking/normas , Mapeamento Encefálico/normas , Bases de Dados como Assunto , Imagem de Difusão por Ressonância Magnética/métodos , Feminino , Humanos , Processamento de Imagem Assistida por Computador/normas , Masculino , Adulto JovemRESUMO
Purpose To compare the diagnostic performance of radiomic analysis (RA) and a convolutional neural network (CNN) to radiologists for classification of contrast agent-enhancing lesions as benign or malignant at multiparametric breast MRI. Materials and Methods Between August 2011 and August 2015, 447 patients with 1294 enhancing lesions (787 malignant, 507 benign; median size, 15 mm ± 20) were evaluated. Lesions were manually segmented by one breast radiologist. RA was performed by using L1 regularization and principal component analysis. CNN used a deep residual neural network with 34 layers. All algorithms were also retrained on half the number of lesions (n = 647). Machine interpretations were compared with prospective interpretations by three breast radiologists. Standard of reference was histologic analysis or follow-up. Areas under the receiver operating curve (AUCs) were used to compare diagnostic performance. Results CNN trained on the full cohort was superior to training on the half-size cohort (AUC, 0.88 vs 0.83, respectively; P = .01), but there was no difference for RA and L1 regularization (AUC, 0.81 vs 0.80, respectively; P = .76) or RA and principal component analysis (AUC, 0.78 vs 0.78, respectively; P = .93). By using the full cohort, CNN performance (AUC, 0.88; 95% confidence interval: 0.86, 0.89) was better than RA and L1 regularization (AUC, 0.81; 95% confidence interval: 0.79, 0.83; P < .001) and RA and principal component analysis (AUC, 0.78; 95% confidence interval: 0.76, 0.80; P < .001). However, CNN was inferior to breast radiologist interpretation (AUC, 0.98; 95% confidence interval: 0.96, 0.99; P < .001). Conclusion A convolutional neural network was superior to radiomic analysis for classification of enhancing lesions as benign or malignant at multiparametric breast MRI. Both approaches were inferior to radiologists' performance; however, more training data will further improve performance of convolutional neural network, but not that of radiomics algorithms. © RSNA, 2018 Online supplemental material is available for this article.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Mama/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Redes Neurais de Computação , Feminino , Humanos , Estudos ProspectivosRESUMO
BACKGROUND: Fat-fraction has been established as a relevant marker for the assessment and diagnosis of neuromuscular diseases. For computing this metric, segmentation of muscle tissue in MR images is a first crucial step. PURPOSE: To tackle the high degree of variability in combination with the high annotation effort for training supervised segmentation models (such as fully convolutional neural networks). STUDY TYPE: Prospective. SUBJECTS: In all, 41 patients consisting of 20 patients showing fatty infiltration and 21 healthy subjects. Field Strength/Sequence: The T1 -weighted MR-pulse sequences were acquired on a 1.5T scanner. ASSESSMENT: To increase performance with limited training data, we propose a domain-specific technique for simulating fatty infiltrations (i.e., texture augmentation) in nonaffected subjects' MR images in combination with shape augmentation. For simulating the fatty infiltrations, we make use of an architecture comprising several competing networks (generative adversarial networks) that facilitate a realistic artificial conversion between healthy and infiltrated MR images. Finally, we assess the segmentation accuracy (Dice similarity coefficient). STATISTICAL TESTS: A Wilcoxon signed rank test was performed to assess whether differences in segmentation accuracy are significant. RESULTS: The mean Dice similarity coefficients significantly increase from 0.84-0.88 (P < 0.01) using data augmentation if training is performed with mixed data and from 0.59-0.87 (P < 0.001) if training is conducted with healthy subjects only. DATA CONCLUSION: Domain-specific data adaptation is highly suitable for facilitating neural network-based segmentation of thighs with feasible manual effort for creating training data. The results even suggest an approach completely bypassing manual annotations. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 3.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética , Doenças Neuromusculares/diagnóstico por imagem , Gordura Subcutânea/diagnóstico por imagem , Coxa da Perna/diagnóstico por imagem , Algoritmos , Simulação por Computador , Bases de Dados Factuais , Feminino , Voluntários Saudáveis , Humanos , Masculino , Redes Neurais de Computação , Estudos Prospectivos , Reprodutibilidade dos TestesRESUMO
OBJECTIVE: To evaluate whether the response to loading of cartilage samples as assessed ex vivo by quantitative MRI (qMRI) mapping techniques can differentiate intact and early degenerative cartilage. METHODS: Upon IRB approval and written informed consent, 59 macroscopically intact osteochondral samples were obtained from the central lateral femoral condyles of patients undergoing total knee replacement. Spatially resolved T1, T2, T2*, and T1ρ maps were generated prior to and during displacement-controlled quasi-static indentation loading to 405 µm (Δ1/2) and 810 µm (Δ1). Upon manual segmentation, absolute qMRI parameters and loading-induced relative changes (δ1/2, δ1) were determined for the entire cartilage sample and distinct zones and regions. Based on their histologically determined degeneration as quantified according to Mankin (Mankin sum scores [MSS], range 0-14), samples were dichotomised into intact (int; MSS 0-4, n = 35) and early degenerative (ed, MSS 5-8, n = 24). RESULTS: For T1ρ, consistent loading-induced increases were found for δ1/2 and δ1. Throughout the entire sample, increases in T1ρ were significantly higher in early degenerative than in intact samples (Δ1/2(ed) = 23.8 [q25 = 18.1, q75 = 29.0] %; Δ1/2(int) = 12.7 [q25 = 5.9, q75 = 19.5] %; p < 0.0005), according to Wilcoxon's signed-rank test). Zonal and regional analysis revealed these changes to be most pronounced in the sub-pistonal area. No significant degeneration-dependent loading-induced changes were found for T1, T2, or T2*. CONCLUSION: Aberrant load-bearing of early degenerative cartilage may be detected using T1ρ mapping as a function of loading. Hence, the diagnostic differentiation of intact versus early degenerative cartilage may allow the reliable identification of early and potentially reversible cartilage degeneration, thereby opening new opportunities for diagnosis and treatment of cartilage pathologies. KEY POINTS: ⢠T1ρ mapping of the cartilage response to loading allows the reliable identification of early degenerative changes ex vivo. ⢠Distinct response-to-loading patterns of cartilage tissue as assessed by functional MRI techniques are associated with biomechanical and histological tissue properties. ⢠Non-invasive functional MR imaging techniques may facilitate the more sensitive monitoring of therapeutic outcomes and treatment strategies.
Assuntos
Doenças das Cartilagens/diagnóstico , Cartilagem Articular/patologia , Articulação do Joelho/patologia , Imageamento por Ressonância Magnética/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Feminino , Humanos , Masculino , Pessoa de Meia-IdadeRESUMO
We present a system that utilizes a range of image processing algorithms to allow fully automated thermal face analysis under both laboratory and real-world conditions. We implement methods for face detection, facial landmark detection, face frontalization and analysis, combining all of these into a fully automated workflow. The system is fully modular and allows implementing own additional algorithms for improved performance or specialized tasks. Our suggested pipeline contains a histogtam of oriented gradients support vector machine (HOG-SVM) based face detector and different landmark detecion methods implemented using feature-based active appearance models, deep alignment networks and a deep shape regression network. Face frontalization is achieved by utilizing piecewise affine transformations. For the final analysis, we present an emotion recognition system that utilizes HOG features and a random forest classifier and a respiratory rate analysis module that computes average temperatures from an automatically detected region of interest. Results show that our combined system achieves a performance which is comparable to current stand-alone state-of-the-art methods for thermal face and landmark datection and a classification accuracy of 65.75% for four basic emotions.
Assuntos
Face , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Reconhecimento Facial/fisiologia , Máquina de Vetores de SuporteRESUMO
BACKGROUND: In neuroscience research, mouse models are valuable tools to understand the genetic mechanisms that advance evidence-based discovery. In this context, large-scale studies emphasize the need for automated high-throughput systems providing a reproducible behavioral assessment of mutant mice with only a minimum level of manual intervention. Basic element of such systems is a robust tracking algorithm. However, common tracking algorithms are either limited by too specific model assumptions or have to be trained in an elaborate preprocessing step, which drastically limits their applicability for behavioral analysis. RESULTS: We present an unsupervised learning procedure that is basically built as a two-stage process to track mice in an enclosed area using shape matching and deformable segmentation models. The system is validated by comparing the tracking results with previously manually labeled landmarks in three setups with different environment, contrast and lighting conditions. Furthermore, we demonstrate that the system is able to automatically detect non-social and social behavior of interacting mice. The system demonstrates a high level of tracking accuracy and clearly outperforms the MiceProfiler, a recently proposed tracking software, which serves as benchmark for our experiments. CONCLUSIONS: The proposed method shows promising potential to automate behavioral screening of mice and other animals. Therefore, it could substantially increase the experimental throughput in behavioral assessment automation.
Assuntos
Comportamento Animal/fisiologia , Aprendizado de Máquina não Supervisionado , Algoritmos , Animais , Processamento Eletrônico de Dados , Feminino , Camundongos , Camundongos Endogâmicos C57BL , Modelos Animais , Comportamento SocialRESUMO
BACKGROUND: Global Plants, a collaborative between JSTOR and some 300 herbaria, now contains about 2.48 million high-resolution images of plant specimens, a number that continues to grow, and collections that are digitizing their specimens at high resolution are allocating considerable recourses to the maintenance of computer hardware (e.g., servers) and to acquiring digital storage space. We here apply machine learning, specifically the training of a Support-Vector-Machine, to classify specimen images into categories, ideally at the species level, using the 26 most common tree species in Germany as a test case. RESULTS: We designed an analysis pipeline and classification system consisting of segmentation, normalization, feature extraction, and classification steps and evaluated the system in two test sets, one with 26 species, the other with 17, in each case using 10 images per species of plants collected between 1820 and 1995, which simulates the empirical situation that most named species are represented in herbaria and databases, such as JSTOR, by few specimens. We achieved 73.21% accuracy of species assignments in the larger test set, and 84.88% in the smaller test set. CONCLUSIONS: The results of this first application of a computer vision algorithm trained on images of herbarium specimens shows that despite the problem of overlapping leaves, leaf-architectural features can be used to categorize specimens to species with good accuracy. Computer vision is poised to play a significant role in future rapid identification at least for frequently collected genera or species in the European flora.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador/métodos , Árvores/classificação , Bases de Dados Factuais , Alemanha , Folhas de Planta/anatomia & histologia , Folhas de Planta/classificação , Plantas/anatomia & histologia , Plantas/classificação , Árvores/anatomia & histologiaRESUMO
BACKGROUND: Protein function in eukaryotic cells is often controlled in a cell cycle-dependent manner. Therefore, the correct assignment of cellular phenotypes to cell cycle phases is a crucial task in cell biology research. Nuclear proteins whose localization varies during the cell cycle are valuable and frequently used markers of cell cycle progression. Proliferating cell nuclear antigen (PCNA) is a protein which is involved in DNA replication and has cell cycle dependent properties. In this work, we present a tool to identify cell cycle phases and in particular, sub-stages of the DNA replication phase (S-phase) based on the characteristic patterns of PCNA distribution. Single time point images of PCNA-immunolabeled cells are acquired using confocal and widefield fluorescence microscopy. In order to discriminate different cell cycle phases, an optimized processing pipeline is proposed. For this purpose, we provide an in-depth analysis and selection of appropriate features for classification, an in-depth evaluation of different classification algorithms, as well as a comparative analysis of classification performance achieved with confocal versus widefield microscopy images. RESULTS: We show that the proposed processing chain is capable of automatically classifying cell cycle phases in PCNA-immunolabeled cells from single time point images, independently of the technique of image acquisition. Comparison of confocal and widefield images showed that for the proposed approach, the overall classification accuracy is slightly higher for confocal microscopy images. CONCLUSION: Overall, automated identification of cell cycle phases and in particular, sub-stages of the DNA replication phase (S-phase) based on the characteristic patterns of PCNA distribution, is feasible for both confocal and widefield images.
Assuntos
Algoritmos , Anticorpos Monoclonais , Ciclo Celular/fisiologia , Proliferação de Células , Replicação do DNA , Antígeno Nuclear de Célula em Proliferação/metabolismo , Anticorpos Monoclonais/imunologia , Núcleo Celular/genética , Células HeLa , Humanos , Processamento de Imagem Assistida por Computador , Microscopia Confocal , Microscopia de Fluorescência , Antígeno Nuclear de Célula em Proliferação/imunologia , Máquina de Vetores de SuporteRESUMO
The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range dependencies and spatial correlations, which is a clear advantage over convolutional neural networks (CNNs), which have been the de facto standard in Computer Vision problems so far. Thus, Transformers have become an integral part of modern medical image analysis. In this review, we provide an encyclopedic review of the applications of Transformers in medical imaging. Specifically, we present a systematic and thorough review of relevant recent Transformer literature for different medical image analysis tasks, including classification, segmentation, detection, registration, synthesis, and clinical report generation. For each of these applications, we investigate the novelty, strengths and weaknesses of the different proposed strategies and develop taxonomies highlighting key properties and contributions. Further, if applicable, we outline current benchmarks on different datasets. Finally, we summarize key challenges and discuss different future research directions. In addition, we have provided cited papers with their corresponding implementations in https://github.com/mindflow-institue/Awesome-Transformer.
Assuntos
Benchmarking , Aprendizagem , Humanos , Redes Neurais de ComputaçãoRESUMO
Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model has received tremendous attention from academic and industrial researchers who have extended it to address the scale and complexity created by medical tasks. These extensions are commonly related to enhancing the U-Net's backbone, bottleneck, or skip connections, or including representation learning, or combining it with a Transformer architecture, or even addressing probabilistic prediction of the segmentation map. Having a compendium of different previously proposed U-Net variants makes it easier for machine learning researchers to identify relevant research questions and understand the challenges of the biological tasks that challenge the model. In this work, we discuss the practical aspects of the U-Net model and organize each variant model into a taxonomy. Moreover, to measure the performance of these strategies in a clinical application, we propose fair evaluations of some unique and famous designs on well-known datasets. Furthermore, we provide a comprehensive implementation library with trained models. In addition, for ease of future studies, we created an online list of U-Net papers with their possible official implementation. All information is gathered in a GitHub repository https://github.com/NITR098/Awesome-U-Net.