Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 257.261
Filtrar
1.
Gene ; 766: 145096, 2021 Jan 15.
Artículo en Inglés | MEDLINE | ID: mdl-32919006

RESUMEN

The phylogenetic analysis based on sequence similarity targeted to real biological taxa is one of the major challenging tasks. In this paper, we propose a novel alignment-free method, CoFASA (Codon Feature based Amino acid Sequence Analyser), for similarity analysis of nucleotide sequences. At first, we assign numerical weights to the four nucleotides. We then calculate a score of each codon based on the numerical value of the constituent nucleotides, termed as degree of codons. Accordingly, we obtain the degree of each amino acid based on the degree of codons targeted towards a specific amino acid. Utilizing the degree of twenty amino acids and their relative abundance within a given sequence, we generate 20-dimensional features for every coding DNA sequence or protein sequence. We use the features for performing phylogenetic analysis of the set of candidate sequences. We use multiple protein sequences derived from Beta-globin (BG), NADH dehydrogenase subunit 5 (ND5), Transferrins (TFs), Xylanases, low identity (<40%) and high identity (⩾40%) protein sequences (encompassing 533 and 1064 protein families) for experimental assessments. We compare our results with sixteen (16) well-known methods, including both alignment-based and alignment-free methods. Various assessment indices are used, such as the Pearson correlation coefficient, RF (Robinson-Foulds) distance and ROC score for performance analysis. While comparing the performance of CoFASA with alignment-based methods (ClustalW, ClustalΩ, MAFFT, and MUSCLE), it shows very similar results. Further, CoFASA shows better performance in comparison to well-known alignment-free methods, including LZW-Kernal, jD2Stat, FFP, spaced, and AFKS-D2s in predicting taxonomic relationship among candidate taxa. Overall, we observe that the features derived by CoFASA are very much useful in isolating the sequences according to their taxonomic labels. While our method is cost-effective, at the same time, produces consistent and satisfactory outcomes.


Asunto(s)
Secuencia de Aminoácidos/genética , Aminoácidos/genética , Codón/genética , Alineación de Secuencia/métodos , Análisis de Secuencia de Proteína/métodos , Algoritmos , Animales , Humanos , Nucleótidos/genética , Filogenia , Proteínas/genética
2.
Food Chem ; 335: 127681, 2021 Jan 15.
Artículo en Inglés | MEDLINE | ID: mdl-32739803

RESUMEN

In this study the Lagrange interpolation optimization algorithm based on two variables with respect to all experimental replicates (POA), was compared with two other heuristics methods (WOA and GOA). Modification of the apple surface by an edible nano coating solution in food packaging was used as case study. The experiment was performed as a factorial test based on completely randomized design by 100 permutations data sets. Results showed a significant difference between the three optimization methods (POA, WOA and GOA) which indicates the necessity of optimization and also efficiency of the present POA. The optimum result by POA, similar to a rose petal property, could rise 72% in surface contact angle (CA). The scanning electron microscopy (SEM) images of the derived surfaces showed almost a uniform spherical nanoparticles morphology. Remarkable advantages of this new approach are no additional material requirement, healthful, easy, inexpensive, fast and affordable technique for surface improvement.


Asunto(s)
Algoritmos , Quitosano , Embalaje de Alimentos , Nanopartículas/química , Quitosano/química , Heurística Computacional , Interacciones Hidrofóbicas e Hidrofílicas , Microscopía Electrónica de Rastreo
3.
Kardiologiia ; 60(9): 46-54, 2020 Oct 14.
Artículo en Ruso | MEDLINE | ID: mdl-33131474

RESUMEN

Aim        To compare assessments of epicardial adipose tissue (EAT) volumes obtained with a semi-automatic, physician-performed analysis and an automatic analysis using a machine-learning algorithm by data of low-dose (LDCT) and standard computed tomography (CT) of chest organs.Material and methods        This analytical, retrospective, transversal study randomly included 100 patients from a database of a united radiological informational service (URIS). The patients underwent LDCT as a part of the project "Low-dose chest computed tomography as a screening method for detection of lung cancer and other diseases of chest organs" (n=50) and chest CT according to a standard protocol (n=50) in outpatient clinics of Moscow. Each image was read by two radiologists on a Syngo. via VB20 workstation. In addition, each image was evaluated with a developed machine-learning algorithm, which provides a completely automatic measurement of EAT.Results   Comparison of EAT volumes obtained with chest LDCT and CT showed highly consistent results both for the expert-performed semi-automatic analyses (correlation coefficient >98 %) and between the expert layout and the machine-learning algorithm (correlation coefficient >95 %). Time of performing segmentation and volumetry on one image with the machine-learning algorithm was not longer than 40 sec, which was 30 times faster than the quantitative analysis performed by an expert and potentially facilitated quantification of the EAT volume in the clinical conditions.Conclusion            The proposed method of automatic volumetry will expedite the analysis of EAT for predicting the risk of ischemic heart disease.


Asunto(s)
Algoritmos , Aprendizaje Automático , Tejido Adiposo/diagnóstico por imagen , Humanos , Moscú , Estudios Retrospectivos
4.
Sensors (Basel) ; 20(21)2020 Oct 29.
Artículo en Inglés | MEDLINE | ID: mdl-33138092

RESUMEN

Since its beginning at the end of 2019, the pandemic spread of the severe acute respiratory syndrome coronavirus 2 (Sars-CoV-2) caused more than one million deaths in only nine months. The threat of emerging and re-emerging infectious diseases exists as an imminent threat to human health. It is essential to implement adequate hygiene best practices to break the contagion chain and enhance society preparedness for such critical scenarios and understand the relevance of each disease transmission route. As the unconscious hand-face contact gesture constitutes a potential pathway of contagion, in this paper, the authors present a prototype system based on low-cost depth sensors able to monitor in real-time the attitude towards such a habit. The system records people's behavior to enhance their awareness by providing real-time warnings, providing for statistical reports for designing proper hygiene solutions, and better understanding the role of such route of contagion. A preliminary validation study measured an overall accuracy of 91%. A Cohen's Kappa equal to 0.876 supports rejecting the hypothesis that such accuracy is accidental. Low-cost body tracking technologies can effectively support monitoring compliance with hygiene best practices and training people in real-time. By collecting data and analyzing them with respect to people categories and contagion statistics, it could be possible to understand the importance of this contagion pathway and identify for which people category such a behavioral attitude constitutes a significant risk.


Asunto(s)
Personal de Salud , Procesamiento de Imagen Asistido por Computador/métodos , Dispositivos Electrónicos Vestibles , Algoritmos , Betacoronavirus/aislamiento & purificación , Infecciones por Coronavirus/diagnóstico , Infecciones por Coronavirus/prevención & control , Infecciones por Coronavirus/virología , Desinfección/economía , Desinfección/métodos , Humanos , Procesamiento de Imagen Asistido por Computador/economía , Procesamiento de Imagen Asistido por Computador/instrumentación , Salud Laboral , Pandemias/prevención & control , Equipo de Protección Personal , Neumonía Viral/diagnóstico , Neumonía Viral/prevención & control , Neumonía Viral/virología
6.
PLoS One ; 15(11): e0241949, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-33170871

RESUMEN

The ongoing COVID-19 pandemic has overwhelmingly demonstrated the need to accurately evaluate the effects of implementing new or altering existing nonpharmaceutical interventions. Since these interventions applied at the societal level cannot be evaluated through traditional experimental means, public health officials and other decision makers must rely on statistical and mathematical epidemiological models. Nonpharmaceutical interventions are typically focused on contacts between members of a population, and yet most epidemiological models rely on homogeneous mixing which has repeatedly been shown to be an unrealistic representation of contact patterns. An alternative approach is individual based models (IBMs), but these are often time intensive and computationally expensive to implement, requiring a high degree of expertise and computational resources. More often, decision makers need to know the effects of potential public policy decisions in a very short time window using limited resources. This paper presents a computation algorithm for an IBM designed to evaluate nonpharmaceutical interventions. By utilizing recursive relationships, our method can quickly compute the expected epidemiological outcomes even for large populations based on any arbitrary contact network. We utilize our methods to evaluate the effects of various mitigation measures in the District of Columbia, USA, at various times and to various degrees. Rcode for our method is provided in the supplementry material, thereby allowing others to utilize our approach for other regions.


Asunto(s)
Infecciones por Coronavirus/diagnóstico , Modelos Teóricos , Neumonía Viral/diagnóstico , Algoritmos , Betacoronavirus/aislamiento & purificación , Infecciones por Coronavirus/epidemiología , Infecciones por Coronavirus/prevención & control , Infecciones por Coronavirus/virología , Brotes de Enfermedades , District of Columbia/epidemiología , Humanos , Máscaras , Pandemias/prevención & control , Neumonía Viral/epidemiología , Neumonía Viral/prevención & control , Neumonía Viral/virología , Cuarentena
7.
Chaos ; 30(10): 103120, 2020 Oct.
Artículo en Inglés | MEDLINE | ID: mdl-33138458

RESUMEN

We present a phenomenological procedure of dealing with the COVID-19 (coronavirus disease 2019) data provided by government health agencies of 11 different countries. Usually, the exact or approximate solutions of susceptible-infected-recovered (or other) model(s) are obtained fitting the data by adjusting the time-independent parameters that are included in those models. Instead of that, in this work, we introduce dynamical parameters whose time-dependence may be phenomenologically obtained by adequately extrapolating a chosen subset of the daily provided data. This phenomenological approach works extremely well to properly adjust the number of infected (and removed) individuals in time for the countries we consider. Besides, it can handle the sub-epidemic events that some countries may experience. In this way, we obtain the evolution of the pandemic without using any a priori model based on differential equations.


Asunto(s)
Infecciones por Coronavirus/epidemiología , Susceptibilidad a Enfermedades , Neumonía Viral/epidemiología , Algoritmos , Betacoronavirus , Recolección de Datos , Salud Global , Humanos , Modelos Estadísticos , Pandemias , Cuarentena , Factores de Tiempo
8.
Chaos ; 30(10): 101103, 2020 Oct.
Artículo en Inglés | MEDLINE | ID: mdl-33138460

RESUMEN

Although there are various models of epidemic diseases, there are a few individual-based models that can guide susceptible individuals on how they should behave in a pandemic without its appropriate treatment. Such a model would be ideal for the current coronavirus disease 2019 (COVID-19) pandemic. Thus, here, we propose a topological model of an epidemic disease, which can take into account various types of interventions through a time-dependent contact network. Based on this model, we show that there is a maximum allowed number of persons one can see each day for each person so that we can suppress the epidemic spread. Reducing the number of persons to see for the hub persons is a key countermeasure for the current COVID-19 pandemic.


Asunto(s)
Infecciones por Coronavirus/epidemiología , Susceptibilidad a Enfermedades/epidemiología , Neumonía Viral/epidemiología , Algoritmos , Betacoronavirus , Control de Enfermedades Transmisibles/legislación & jurisprudencia , Control de Enfermedades Transmisibles/métodos , Simulación por Computador , Infecciones por Coronavirus/transmisión , Humanos , Modelos Teóricos , Pandemias , Neumonía Viral/transmisión , Probabilidad , Salud Pública
9.
BMC Bioinformatics ; 21(1): 500, 2020 Nov 04.
Artículo en Inglés | MEDLINE | ID: mdl-33148180

RESUMEN

BACKGROUND: High throughput experiments have generated a significantly large amount of protein interaction data, which is being used to study protein networks. Studying complete protein networks can reveal more insight about healthy/disease states than studying proteins in isolation. Similarly, a comparative study of protein-protein interaction (PPI) networks of different species reveals important insights which may help in disease analysis and drug design. The study of PPI network alignment can also helps in understanding the different biological systems of different species. It can also be used in transfer of knowledge across different species. Different aligners have been introduced in the last decade but developing an accurate and scalable global alignment algorithm that can ensures the biological significance alignment is still challenging. RESULTS: This paper presents a novel global pairwise network alignment algorithm, SAlign, which uses topological and biological information in the alignment process. The proposed algorithm incorporates sequence and structural information for computing biological scores, whereas previous algorithms only use sequence information. The alignment based on the proposed technique shows that the combined effect of structure and sequence results in significantly better pairwise alignments. We have compared SAlign with state-of-art algorithms on the basis of semantic similarity of alignment and the number of aligned nodes on multiple PPI network pairs. The results of SAlign on the network pairs which have high percentage of proteins with available structure are 3-63% semantically better than all existing techniques. Furthermore, it also aligns 5-14% more nodes of these network pairs as compared to existing aligners. The results of SAlign on other PPI network pairs are comparable or better than all existing techniques. We also introduce [Formula: see text], a Monte Carlo based alignment algorithm, that produces multiple network alignments with similar semantic similarity. This helps the user to pick biologically meaningful alignments. CONCLUSION: The proposed algorithm has the ability to find the alignments that are more biologically significant/relevant as compared to the alignments of existing aligners. Furthermore, the proposed method is able to generate alternate alignments that help in studying different genes/proteins of the specie.


Asunto(s)
Algoritmos , Mapas de Interacción de Proteínas , Proteínas/metabolismo , Animales , Bases de Datos de Proteínas , Humanos , Ratones , Método de Montecarlo , Proteínas/química , Levaduras/metabolismo
10.
BMC Bioinformatics ; 21(1): 503, 2020 Nov 05.
Artículo en Inglés | MEDLINE | ID: mdl-33153432

RESUMEN

BACKGROUND: The formation of contacts among protein secondary structure elements (SSEs) is an important step in protein folding as it determines topology of protein tertiary structure; hence, inferring inter-SSE contacts is crucial to protein structure prediction. One of the existing strategies infers inter-SSE contacts directly from the predicted possibilities of inter-residue contacts without any preprocessing, and thus suffers from the excessive noises existing in the predicted inter-residue contacts. Another strategy defines SSEs based on protein secondary structure prediction first, and then judges whether each candidate SSE pair could form contact or not. However, it is difficult to accurately determine boundary of SSEs due to the errors in secondary structure prediction. The incorrectly-deduced SSEs definitely hinder subsequent prediction of the contacts among them. RESULTS: We here report an accurate approach to infer the inter-SSE contacts (thus called as ISSEC) using the deep object detection technique. The design of ISSEC is based on the observation that, in the inter-residue contact map, the contacting SSEs usually form rectangle regions with characteristic patterns. Therefore, ISSEC infers inter-SSE contacts through detecting such rectangle regions. Unlike the existing approach directly using the predicted probabilities of inter-residue contact, ISSEC applies the deep convolution technique to extract high-level features from the inter-residue contacts. More importantly, ISSEC does not rely on the pre-defined SSEs. Instead, ISSEC enumerates multiple candidate rectangle regions in the predicted inter-residue contact map, and for each region, ISSEC calculates a confidence score to measure whether it has characteristic patterns or not. ISSEC employs greedy strategy to select non-overlapping regions with high confidence score, and finally infers inter-SSE contacts according to these regions. CONCLUSIONS: Comprehensive experimental results suggested that ISSEC outperformed the state-of-the-art approaches in predicting inter-SSE contacts. We further demonstrated the successful applications of ISSEC to improve prediction of both inter-residue contacts and tertiary structure as well.


Asunto(s)
Algoritmos , Proteínas/química , Bases de Datos de Proteínas , Proteínas de la Membrana/química , Conformación Proteica en Lámina beta , Estructura Secundaria de Proteína
13.
Gastroenterol Nurs ; 43(5): 375-381, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-33003024

RESUMEN

Elective surgical and endoscopic procedures were suspended nationwide during the March 2020 COVID-19 pandemic to minimize exposure and healthcare resource utilization. This resulted in an unprecedented backlog of procedures in most clinical practices including pediatrics. Our group developed an internal process toward the rational development of an algorithm prioritizing elective procedures. This was based on patient disease severity defined by the presence of alert symptoms, symptom severity for dysphagia and abdominal pain, and diagnostic investigation findings. The underlying rationale is to prioritize patients in whom suspected disease course would be greatest impacted by endoscopy. We developed a nurse phone call-based process utilizing REDCap®, identifying relevant symptoms categorized by severity, and a validated functional impairment questionnaire for abdominal pain. We abstracted key laboratory and radiological findings also categorized by severity. The order of priority of procedures was established on the basis of a 4-tiered system factoring both presence and severity of symptoms or prior diagnostic testing results. We present the framework that we have adopted toward prioritizing procedures with the assumption that it offers an objective methodology and that can be efficiently and more broadly applied to other similar practice scenarios. Our tool may have wide-ranging implications both in the current COVID-19 pandemic and in other scenarios of limited resource allocation and deserves further investigation.


Asunto(s)
Citas y Horarios , Betacoronavirus , Control de Enfermedades Transmisibles/organización & administración , Infecciones por Coronavirus/prevención & control , Procedimientos Quirúrgicos del Sistema Digestivo , Procedimientos Quirúrgicos Electivos , Pandemias/prevención & control , Neumonía Viral/prevención & control , Adolescente , Algoritmos , Niño , Infecciones por Coronavirus/epidemiología , Infecciones por Coronavirus/transmisión , Endoscopía , Femenino , Humanos , Masculino , Selección de Paciente , Neumonía Viral/epidemiología , Neumonía Viral/transmisión , Evaluación de Síntomas , Triaje
14.
Prog Orthod ; 21(1): 36, 2020 Oct 01.
Artículo en Inglés | MEDLINE | ID: mdl-33000308

RESUMEN

OBJECTIVE: To compare the accuracy of complete-arch scans and quadrant scans obtained using a direct chairside intraoral scanner. MATERIAL AND METHODS: Intraoral scans were obtained from 20 adults without missing teeth except for the third molar. Maxillary and mandibular complete-arch scans were carried out, and 4 quadrant scans for each arch were performed to obtain right posterior, right anterior, left anterior, and left posterior quadrant scans. Complete-arch scans and quadrant scans were compared with corresponding model scans using best-fit surface-based registration. Shell/shell deviations were computed for complete-arch scans and quadrant scans and compared between the complete-arch scans and each quadrant scans. In addition, shell/shell deviations were calculated also for each individual tooth in complete-arch scans to evaluate factors which influence the accuracy of intraoral scans. RESULTS: Complete-arch scans showed relatively greater errors (0.09 ~ 0.10 mm) when compared to quadrant scans (0.05 ~ 0.06 mm). The errors were greater in the maxillary scans than in the mandibular scans. The evaluation of errors for each tooth showed that the errors were greater in posterior teeth than in anterior teeth. Comparing the right and left errors, the right side posterior teeth showed a more substantial variance than the left side in the mandibular scans. CONCLUSION: The scanning accuracy has a difference between complete-arch scanning and quadrant scanning, particularly in the posterior teeth. Careful consideration is needed to avoid scanning inaccuracy for maxillary or mandibular complete-arch, particularly in the posterior area because a complete-arch scan might have potential error than a quadrant scan.


Asunto(s)
Anodoncia , Mandíbula/diagnóstico por imagen , Adulto , Algoritmos , Humanos
15.
Lancet Oncol ; 21(10): e463-e476, 2020 10.
Artículo en Inglés | MEDLINE | ID: mdl-33002442

RESUMEN

Immunotherapy represents a paradigm shift in oncology treatment. The goal of immunotherapy is to overcome immunosuppression induced by a tumour and its microenvironment, thereby allowing the immune system to target and kill cancer cells. The immunotherapy era began when the first immune checkpoint inhibitor, ipilimumab, was approved for use almost a decade ago. This therapeutic approach is associated with distinct types of response, including processes such as pseudoprogression (ie, increased tumour burden via radiology, which is not accompanied by clinical deterioration) and hyperprogression (ie, rapid progression of the disease as a result of immunotherapy). In this Review, we focus on therapeutic approaches for patients who progress on immunotherapy. We review the different types of clinical responses associated with immunotherapy and describe treatment options for this population.


Asunto(s)
Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos/terapia , Inmunoterapia/efectos adversos , Neoplasias/terapia , Algoritmos , Antineoplásicos Inmunológicos/efectos adversos , Progresión de la Enfermedad , Resistencia a Antineoplásicos , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos/diagnóstico , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos/inmunología , Humanos , Criterios de Evaluación de Respuesta en Tumores Sólidos , Terapia Recuperativa
16.
Oecologia ; 194(1-2): 283-298, 2020 Oct.
Artículo en Inglés | MEDLINE | ID: mdl-33006076

RESUMEN

Information on ecological systems often comes from diverse sources with varied levels of complexity, bias, and uncertainty. Accordingly, analytical techniques continue to evolve that address these challenges to reveal the characteristics of ecological systems and inform conservation actions. We applied multiple statistical learning algorithms (i.e., machine learning) with a range of information sources including fish tracking data, environmental data, and visual surveys to identify potential spawning aggregation sites for a marine fish species, permit (Trachinotus falcatus), in the Florida Keys. Recognizing the potential complementarity and some level of uncertainty in each information source, we applied supervised (classic and conditional random forests; RF) and unsupervised (fuzzy k-means; FKM) algorithms. The two RF models had similar predictive performance, but generated different predictor variable importance structures and spawning site predictions. Unsupervised clustering using FKM identified unique site groupings that were similar to the likely spawning sites identified with RF. The conservation of aggregate spawning fish species depends heavily on the protection of key spawning sites; many of these potential sites were identified here for permit in the Florida Keys, which consisted of relatively deep-water natural and artificial reefs with high mean permit residency periods. The application of multiple machine learning algorithms enabled the integration of diverse information sources to develop models of an ecological system. Faced with increasingly complex and diverse data sources, ecologists, and conservation practitioners should find increasing value in machine learning algorithms, which we discuss here and provide resources to increase accessibility.


Asunto(s)
Ecosistema , Aprendizaje Automático , Algoritmos , Animales , Florida , Reproducción
17.
Nat Commun ; 11(1): 4952, 2020 10 02.
Artículo en Inglés | MEDLINE | ID: mdl-33009368

RESUMEN

We present the Danish Disease Trajectory Browser (DTB), a tool for exploring almost 25 years of data from the Danish National Patient Register. In the dataset comprising 7.2 million patients and 122 million admissions, users can identify diagnosis pairs with statistically significant directionality and combine them to linear disease trajectories. Users can search for one or more disease codes (ICD-10 classification) and explore disease progression patterns via an array of functionalities. For example, a set of linear trajectories can be merged into a disease trajectory network displaying the entire multimorbidity spectrum of a disease in a single connected graph. Using data from the Danish Register for Causes of Death mortality is also included. The tool is disease-agnostic across both rare and common diseases and is showcased by exploring multimorbidity in Down syndrome (ICD-10 code Q90) and hypertension (ICD-10 code I10). Finally, we show how search results can be customized and exported from the browser in a format of choice (i.e. JSON, PNG, JPEG and CSV).


Asunto(s)
Progresión de la Enfermedad , Programas Informáticos , Algoritmos , Dinamarca , Humanos , Factores de Tiempo
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1507-1511, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018277

RESUMEN

Pain is a subjective experience and clinicians need to treat patients with accurate pain levels. EEG has emerged as a useful tool for objective pain assessment, but due to the low signal-to-noise ratio of pain-related EEG signals, the prediction accuracy of EEG-based pain prediction models is still unsatisfactory. In this paper, we proposed an autoencoder model based on convolutional neural networks for feature extraction of pain-related EEG signals. More precisely, we used EEGNet to build an autoencoder model to extract a small set of features from high-density pain-evoked EEG potentials and then establish a machine learning models to predict pain levels (high pain vs. low pain) from extracted features. Experimental results show that the new autoencoder-based approach can effectively identify pain-related features and can achieve better classification results than conventional methods.


Asunto(s)
Algoritmos , Electroencefalografía , Percepción del Dolor , Humanos , Redes Neurales de la Computación , Dolor
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1516-1519, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018279

RESUMEN

Brain insults such as cerebral ischemia and intracranial hemorrhage are critical stroke conditions with high mortality rates. Currently, medical image analysis for critical stroke conditions is still largely done manually, which is time-consuming and labor-intensive. While deep learning algorithms are increasingly being applied in medical image analysis, the performance of these methods still needs substantial improvement before they can be widely used in the clinical setting. Among other challenges, the lack of sufficient labelled data is one of the key problems that has limited the progress of deep learning methods in this domain. To mitigate this bottleneck, we propose an integrated method that includes a data augmentation framework using a conditional Generative Adversarial Network (cGAN) which is followed by a supervised segmentation with a Convolutional Neural Network (CNN). The adopted cGAN generates meaningful brain images from specially altered lesion masks as a form of data augmentation to supplement the training dataset, while the CNN incorporates depth-wise-convolution based X-blocks as well as Feature Similarity Module (FSM) to ease and aid the training process, resulting in better lesion segmentation. We evaluate the proposed deep learning strategy on the Anatomical Tracings of Lesions After Stroke (ATLAS) dataset and show that this approach outperforms the current state-of-art methods in task of stroke lesion segmentation.


Asunto(s)
Aprendizaje Profundo , Neuroimagen , Algoritmos , Encéfalo , Redes Neurales de la Computación
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1536-1539, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-33018284

RESUMEN

Semi-automatic measurements are performed on 18FDG PET-CT images to monitor the evolution of metastatic sites in the clinical follow-up of metastatic breast cancer patients. Apart from being time-consuming and prone to subjective approximation, semi-automatic tools cannot make the difference between cancerous regions and active organs, presenting a high 18FDG uptake.In this work, we combine a deep learning-based approach with a superpixel segmentation method to segment the main active organs (brain, heart, bladder) from full-body PET images. In particular, we integrate a superpixel SLIC algorithm at different levels of a convolutional network. Results are compared with a deep learning segmentation network alone. The methods are cross-validated on full-body PET images of 36 patients and tested on the acquisitions of 24 patients from a different study center, in the context of the ongoing EPICUREseinmeta study. The similarity between the manually defined organ masks and the results is evaluated with the Dice score. Moreover, the amount of false positives is evaluated through the positive predictive value (PPV).According to the computed Dice scores, all approaches allow to accurately segment the target organs. However, the networks integrating superpixels are better suited to transfer knowledge across datasets acquired on multiple sites (domain adaptation) and are less likely to segment structures outside of the target organs, according to the PPV.Hence, combining deep learning with superpixels allows to segment organs presenting a high 18FDG uptake on PET images without selecting cancerous lesion, and thus improves the precision of the semi-automatic tools monitoring the evolution of breast cancer metastasis.Clinical relevance- We demonstrate the utility of combining deep learning and superpixel segmentation methods to accurately find the contours of active organs from metastatic breast cancer images, to different dataset distributions.


Asunto(s)
Neoplasias de la Mama , Aprendizaje Profundo , Algoritmos , Encéfalo , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/patología , Humanos , Metástasis de la Neoplasia , Tomografía Computarizada por Tomografía de Emisión de Positrones
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA