RESUMO
PURPOSE: Hyperpolarized 129Xe MRI benefits from non-Cartesian acquisitions that sample k-space efficiently and rapidly. However, their reconstructions are complex and burdened by decay processes unique to hyperpolarized gas. Currently used gridded reconstructions are prone to artifacts caused by magnetization decay and are ill-suited for undersampling. We present a compressed sensing (CS) reconstruction approach that incorporates magnetization decay in the forward model, thereby producing images with increased sharpness and contrast, even in undersampled data. METHODS: Radio-frequency, T1, and T 2 * $$ {\mathrm{T}}_2^{\ast } $$ decay processes were incorporated into the forward model and solved using iterative methods including CS. The decay-modeled reconstruction was validated in simulations and then tested in 2D/3D-spiral ventilation and 3D-radial gas-exchange MRI. Quantitative metrics including apparent-SNR and sharpness were compared between gridded, CS, and twofold undersampled CS reconstructions. Observations were validated in gas-exchange data collected from 15 healthy and 25 post-hematopoietic-stem-cell-transplant participants. RESULTS: CS reconstructions in simulations yielded images with threefold increases in accuracy. CS increased sharpness and contrast for ventilation in vivo imaging and showed greater accuracy for undersampled acquisitions. CS improved gas-exchange imaging, particularly in the dissolved-phase where apparent-SNR improved, and structure was made discernable. Finally, CS showed repeatability in important global gas-exchange metrics including median dissolved-gas signal ratio and median angle between real/imaginary components. CONCLUSION: A non-Cartesian CS reconstruction approach that incorporates hyperpolarized 129Xe decay processes is presented. This approach enables improved image sharpness, contrast, and overall image quality in addition to up-to threefold undersampling. This contribution benefits all hyperpolarized gas MRI through improved accuracy and decreased scan durations.
Assuntos
Algoritmos , Simulação por Computador , Processamento de Imagem Assistida por Computador , Imageamento por Ressonância Magnética , Isótopos de Xenônio , Imageamento por Ressonância Magnética/métodos , Humanos , Processamento de Imagem Assistida por Computador/métodos , Masculino , Razão Sinal-Ruído , Feminino , Imageamento Tridimensional/métodos , Adulto , Imagens de Fantasmas , Artefatos , Compressão de Dados/métodos , Reprodutibilidade dos Testes , Pulmão/diagnóstico por imagem , Meios de Contraste/químicaRESUMO
Efficient and rapid auxiliary diagnosis of different grades of lung adenocarcinoma is conducive to helping doctors accelerate individualized diagnosis and treatment processes, thus improving patient prognosis. Currently, there is often a problem of large intra-class differences and small inter-class differences between pathological images of lung adenocarcinoma tissues under different grades. If attention mechanisms such as Coordinate Attention (CA) are directly used for lung adenocarcinoma grading tasks, it is prone to excessive compression of feature information and overlooking the issue of information dependency within the same dimension. Therefore, we propose a Dimension Information Embedding Attention Network (DIEANet) for the task of lung adenocarcinoma grading. Specifically, we combine different pooling methods to automatically select local regions of key growth patterns such as lung adenocarcinoma cells, enhancing the model's focus on local information. Additionally, we employ an interactive fusion approach to concentrate feature information within the same dimension and across dimensions, thereby improving model performance. Extensive experiments have shown that under the condition of maintaining equal computational expenses, the accuracy of DIEANet with ResNet34 as the backbone reaches 88.19%, with an AUC of 96.61%, MCC of 81.71%, and Kappa of 81.16%. Compared to seven other attention mechanisms, it achieves state-of-the-art objective metrics. Additionally, it aligns more closely with the visual attention of pathology experts under subjective visual assessment.
Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Compressão de Dados , Neoplasias Pulmonares , Humanos , Benchmarking , Neoplasias Pulmonares/diagnósticoRESUMO
PURPOSE: To evaluate the feasibility of a free-breathing sequence (4D FreeBreathing) combined with Compressed SENSE in dynamic contrast-enhanced pancreatic MRI and compare it with a breath-holding sequence (eTHRIVE). METHOD: Patients who underwent pancreatic MRI, either eTHRIVE or 4D FreeBreathing, from April 2022 to November 2023 were included in this retrospective study. Two radiologists, who were unaware of the scan sequence, independently and randomly reviewed the images at the precontrast, pancreatic, portal venous, and equilibrium phases and assigned confidence scores for motion and streaking artifacts, pancreatic sharpness, and overall image quality using a 5-point scale. Furthermore, the radiologists assessed the appropriateness of the scan timing of the pancreatic phase. Mann-Whitney U and Fisher's exact tests were conducted to compare the confidence scores and adequacy of the pancreatic phase scan timing between eTHRIVE and 4D FreeBreathing. RESULTS: Overall, 48 patients (median age, 71 years; interquartile range, 64-77 years; 24 women) were included. Among them, 20 patients (42%) were scanned using 4D FreeBreathing. The 4D FreeBreathing showed moderate streaking artifact but improved motion artifact (P <.001-.17) at all phases. Pancreatic sharpness and overall image quality were almost comparable between two sequences (P = .17-.96). All 20 examinations in 4D FreeBreathing showed appropriate pancreatic phase images, but only 16 (57%; P <.001 for reviewer 1) and 18 (64%; P = .003 for reviewer 2) examinations showed it in eTHRIVE. CONCLUSION: The use of 4D FreeBreathing combined with Compressed SENSE was feasible in pancreatic MRI and provided appropriate pancreatic phase images in all examinations.
Assuntos
Meios de Contraste , Estudos de Viabilidade , Imageamento por Ressonância Magnética , Humanos , Feminino , Masculino , Pessoa de Meia-Idade , Idoso , Estudos Retrospectivos , Imageamento por Ressonância Magnética/métodos , Artefatos , Respiração , Aumento da Imagem/métodos , Suspensão da Respiração , Compressão de Dados/métodos , Neoplasias Pancreáticas/diagnóstico por imagem , Pâncreas/diagnóstico por imagem , Pancreatopatias/diagnóstico por imagemRESUMO
Este estudo avaliou o reconhecimento (imitação, identidade e identificação) e a nomeação de estímulos emocionais de valência negativa (raiva e tristeza) e positiva (alegria e surpresa) em conjunto com a influência dos tipos de estímulos utilizados (social-feminino, social-masculino, familiar e emoji) em crianças e jovens adultos com autismo ou síndrome de Down, por meio de tarefas aplicadas pela família e mediadas por recursos tecnológicos durante a pandemia de covid-19. Participaram cinco crianças e dois jovens adultos com autismo e uma criança e dois jovens adultos com síndrome de Down. Foram implementadas tarefas de identidade, reconhecimento, nomeação e imitação, com estímulos faciais de função avaliativa (sem consequência diferencial) e de ensino (com consequência diferencial, uso de dicas e critério de aprendizagem), visando a emergência da nomeação emocional por meio do ensino das tarefas de reconhecimento. Os resultados da linha de base identificaram que, para os participantes que apresentaram menor tempo de resposta para o mesmo gênero, a diferença de tempo de resposta foi em média 57,28% menor. Em relação à valência emocional, 50% dos participantes apresentaram diferenças nos acertos, a depender da valência positiva e negativa, sendo que 66,66% apresentaram diferenças para o tempo de resposta a depender da valência emocional. Após o procedimento de ensino, os participantes mostraram maior número de acertos nas tarefas, independentemente do gênero de estímulo e valência emocional, criando ocasião para generalização da aprendizagem de reconhecimento e nomeação de emoções, além de consolidar a viabilidade de estratégias de ensino mediadas por recursos tecnológicos e aplicadas por familiares.(AU)
This study evaluated the recognition (imitation, identity, and identification) and naming of negative (anger and sadness) and positive (joy and surprise) emotional stimuli alongside the influence of the types of stimuli (social-female, social-male, family, and emoji) in children and young adults with autism and Down syndrome, via tasks applied by the family and mediated by technological resources, during the COVID-19 pandemic. Five children and two young adults with autism and one child and two young adults with Down syndrome participated. Identity, recognition, naming, and imitation tasks were planned and implemented using facial stimuli with evaluative (without differential consequence) and teaching (with differential consequence, tips, and learning criteria) functions, aiming at the emergence of emotional naming from the recognition teaching tasks. The baseline results showed that, for participants who had a shorter response time for the same gender, the response time difference was on average 57.28% lower. Regarding the emotional valence, 50% of the participants showed differences in the correct answers, depending on the positive and negative valence, and 66.66% showed differences in the response time depending on the emotional valence. After the teaching procedure, the participants showed a greater number of correct answers in the tasks, regardless of the stimulus type and emotional valence, creating an opportunity for generalizing learning of emotion recognition and naming, in addition to consolidating the feasibility of teaching strategies mediated by technological resources and applied by family members.(AU)
Este estudio evaluó el reconocimiento (imitación, identidad e identificación) y la denominación de estímulos emocionales negativos (enfado y tristeza) y positivos (alegría y sorpresa) y la influencia de los tipos de estímulos utilizados (social-femenino, social-masculino, familiar y emoji ) de niños y jóvenes con autismo o síndrome de Down, a través de tareas aplicadas por la familia, mediadas por recursos tecnológicos durante la pandemia de la covid-19. Participaron cinco niños y dos adultos jóvenes con autismo, y un niño y dos adultos jóvenes con síndrome de Down. Se planificaron e implementaron tareas de identidad, reconocimiento, nombramiento e imitación con estímulos faciales con función evaluativa (sin consecuencia diferencial) y enseñanza (con consecuencia diferencial, uso de ayudas y criterios de aprendizaje), buscando la emergencia del nombramiento emocional después de la enseñanza de tareas de reconocimiento. Los resultados de la línea de base identificaron que para los participantes que tenían un tiempo de respuesta más corto para el mismo género, la diferencia en el tiempo de respuesta fue un 57,28% menor. En cuanto a la valencia emocional, el 50% de los participantes mostraron diferencias en las respuestas correctas, en función de la valencia positiva y negativa, y el 66,66% tuvieron diferencias en el tiempo de respuesta, en función de la valencia emocional. Después del procedimiento de enseñanza, los participantes mostraron mayor número de aciertos en las tareas evaluadas, independientemente del tipo de estímulo o valencia emocional, lo que genera una oportunidad para la generalización del aprendizaje de reconocimiento y denominación de emociones, además de consolidar la viabilidad de estrategias de enseñanza mediadas por recursos tecnológicos y aplicadas por la familia.(AU)
Assuntos
Humanos , Masculino , Feminino , Pré-Escolar , Criança , Adolescente , Adulto , Adulto Jovem , Transtorno Autístico , Família , Síndrome de Down , Emoções Manifestas , Emoções , Ansiedade , Relações Pais-Filho , Pais , Percepção , Distorção da Percepção , Personalidade , Jogos e Brinquedos , Preconceito , Psiquiatria , Psicologia , Psicologia Social , Atenção , Recursos Audiovisuais , Sinais e Sintomas , Desejabilidade Social , Meio Social , Valores Sociais , Socialização , Estereotipagem , Análise e Desempenho de Tarefas , Percepção Visual , Mulheres , Comportamento , Imagem Corporal , Processamento de Imagem Assistida por Computador , Simbolismo , Atividades Cotidianas , Inteligência Artificial , Adaptação Psicológica , Pesar , Atitude , Terapia Cognitivo-Comportamental , Criança , Educação Infantil , Cromossomos , Ensaio Clínico , Competência Mental , Cuidadores , Cognição , Detecção de Sinal Psicológico , Comunicação , Consciência , Intuição , Observação , Transtorno de Movimento Estereotipado , Transtornos Cromossômicos , Autonomia Pessoal , Filhos Adultos , Confiança , Compreensão , Designação de Pessoal , Compressão de Dados , Educação , Educação de Pessoa com Deficiência Intelectual , Educação Inclusiva , Ego , Empatia , Comportamento Exploratório , Face , Expressão Facial , Competência Cultural , Adulto Jovem , Medo , Retroalimentação , Inteligência Emocional , Estigma Social , Pandemias , Habilidades Sociais , Normas Sociais , Ajustamento Emocional , Otimismo , Metacognição , Reconhecimento Facial , Transtorno do Espectro Autista , Análise do Comportamento Aplicada , Autogestão , Respeito , Regulação Emocional , Generalização Psicológica , Genética , Interação Social , Reconhecimento de Identidade , COVID-19 , Gestos , Treino Cognitivo , Apoio Familiar , Velocidade de Processamento , Manobra Psicológica , Imaginação , Relações Interpessoais , Idioma , Acontecimentos que Mudam a Vida , Memória de Curto Prazo , Homens , Transtornos Mentais , Processos Mentais , Deficiência Intelectual , Doenças do Sistema Nervoso , Manifestações Neurológicas , Neurologia , Testes Neuropsicológicos , Comunicação não VerbalRESUMO
Hospitals and medical laboratories create a tremendous amount of genome sequence data every day for use in research, surgery, and illness diagnosis. To make storage comprehensible, compression is therefore essential for the storage, monitoring, and distribution of all these data. A novel data compression technique is required to reduce the time as well as the cost of storage, transmission, and data processing. General-purpose compression techniques do not perform so well for these data due to their special features: a large number of repeats (tandem and palindrome), small alphabets, and highly similar, and specific file formats. In this study, we provide a method for compressing FastQ files that uses a reference genome as a backup without sacrificing data quality. FastQ files are initially split into three streams (identifier, sequence, and quality score), each of which receives its own compression technique. A novel quick and lightweight mapping mechanism is also presented to effectively compress the sequence stream. As shown by experiments, the suggested methods, both the compression ratio and the compression/decompression duration of NGS data compressed using RBFQC, are superior to those achieved by other state-of-the-art genome compression methods. In comparison to GZIP, RBFQC may achieve a compression ratio of 80-140% for fixed-length datasets and 80-125% for variable-length datasets. Compared to domain-specific FastQ file referential genome compression techniques, RBFQC has a compression and decompression speed (total) improvement of 10-25%.
Assuntos
Compressão de Dados , Compressão de Dados/métodos , Algoritmos , Software , Sequenciamento de Nucleotídeos em Larga Escala/métodos , Genoma , Análise de Sequência de DNA/métodosRESUMO
Incorporating T-shaped steel and square steel tubes into a cross shaped concrete column can significantly improve the seismic performance of the cross shaped column. However, the experimental samples are limited, so ABAQUS finite element (FE) analysis method was adopted in this paper to study the seismic performance of this cross shaped column, calculate and verify three specimens in the existing reference. Based on the reliable model, parameter analysis was carried out (25 specimens in total). The results show that the established model has a high degree of coincidence in the hysteretic curve, skeleton curve and failure mode, and the error of ultimate bearing capacity and ductility is within 10%. The configuration of T-shaped steel and square steel tubes inside the cross column can meet the ductility requirements specified in the standard under high axial compression ratio. The ultimate bearing capacity of the cross shaped column increases with the increase of the thickness of the square steel tube, but the ductility deteriorates. The increase in steel tube size increases the strength of the concrete in the core area, and the seismic performance of the cross shaped column was improved. Increasing the thickness of the T-shaped steel flange can better improve the seismic performance of the cross shaped column compared to increasing the thickness of the T-shaped steel web plate. Increasing the height of the specimen will significantly reduce its seismic performance. When the shear span ratio is not greater than 4.1, the ductility can meet the standard requirements. The error of the formula for calculating the compression-bending bearing capacity proposed based on existing calculation methods is less than 5%.
Assuntos
Placas Ósseas , Compressão de Dados , Análise de Elementos Finitos , Compostos Radiofarmacêuticos , AçoRESUMO
PURPOSE: Non-Hodgkin lymphoma (NHL) is the most common type of lymphoma, and its extranodal manifestation is rare. Skeletal muscle involvement is noted in only 1.1% of patients with NHL. Here, we present a case of high-grade B-cell lymphoma (HGBL); it infiltrated the left neural foramina from the left psoas muscle before encroaching on the whole spinal canal and subsequently invading the contralateral neural foramina from T12 to L3. CASE REPORT: A 43-year-old man with HGBL who could function independently presented with numbness and weakness of the left thigh 2 months after a diagnosis of infiltrative lymphoma in the left psoas muscle. His symptoms were urine incontinence and unsteady gait. A neurological examination revealed weakness in the left psoas and quadriceps with hyporeflexia and hypesthesia. Lumbar spine magnetic resonance imaging (MRI) revealed intraspinal extradural invasion from T12 to L3 with multiple left-sided root compression despite the resolution of primary psoas lymphoma. At 6 weeks after symptom onset, his symptoms progressed to weakness, numbness, and hyporeflexia of the bilateral lower extremities with preserved anal sensation. Follow- up MRI revealed the progression of intraspinal invasion, which spread through the spinal canal and invaded the contralateral neural foramina from T12 to L3. The patient was finally bound to a wheelchair. CONCLUSION: Clinicians must check for possible intraspinal involvement in patients with HGBL, particularly patients with known paraspinal soft-tissue involvement. The resolved infiltration of the soft tissue does not preclude the possibility of further neurological involvement. Additionally, MRI may provide higher resolution findings for clarifying the structure of the neural foramina and thecal sac. Keyword: Non-Hodgkin's Lymphoma, high-grade B-cell lymphoma, plexopathy.
Assuntos
Compressão de Dados , Linfoma de Células B , Linfoma não Hodgkin , Masculino , Humanos , Adulto , Hipestesia/etiologia , Reflexo Anormal , Linfoma não Hodgkin/diagnóstico por imagem , Linfoma de Células B/diagnóstico , Linfoma de Células B/diagnóstico por imagemRESUMO
Significance: Hyperspectral microscopy grants the ability to characterize unique properties of tissues based on their spectral fingerprint. The ability to label and measure multiple molecular probes simultaneously provides pathologists and oncologists with a powerful tool to enhance accurate diagnostic and prognostic decisions. As the pathological workload grows, having an objective tool that provides companion diagnostics is of immense importance. Therefore, fast whole-slide spectral imaging systems are of immense importance for automated cancer prognostics that meet current and future needs. Aim: We aim to develop a fast and accurate hyperspectral microscopy system that can be easily integrated with existing microscopes and provide flexibility for optimizing measurement time versus spectral resolution. Approach: The method employs compressive sensing (CS) and a spectrally encoded illumination device integrated into the illumination path of a standard microscope. The spectral encoding is obtained using a compact liquid crystal cell that is operated in a fast mode. It provides time-efficient measurements of the spectral information, is modular and versatile, and can also be used for other applications that require rapid acquisition of hyperspectral images. Results: We demonstrated the acquisition of breast cancer biopsies hyperspectral data of the whole camera area within â¼1 s. This means that a typical 1×1 cm2 biopsy can be measured in â¼10 min. The hyperspectral images with 250 spectral bands are reconstructed from 47 spectrally encoded images in the spectral range of 450 to 700 nm. Conclusions: CS hyperspectral microscopy was successfully demonstrated on a common lab microscope for measuring biopsies stained with the most common stains, such as hematoxylin and eosin. The high spectral resolution demonstrated here in a rather short time indicates the ability to use it further for coping with the highly demanding needs of pathological diagnostics, both for cancer diagnostics and prognostics.
Assuntos
Compressão de Dados , Neoplasias , Microscopia , Fenômenos Físicos , Biópsia , Corantes , Neoplasias/diagnóstico por imagemRESUMO
This study focuses on systematically revealing how cutting parameters influence the surface integrity of ball-end hard milled surface of AISI D2 steel and proposing optimization scheme from surface integrity, wear resistance and fatigue resistance perspective based on response surface methodology respectively. Results can be summarized into three aspects. Firstly, radial depth of cut with percent contribution ratio (PCR) 62.05% has a decisive influence on surface roughness, followed by spindle speed 13.25% and feed per tooth 6.63%. The work hardening degree was raised from 12.5% to 38.4% when spindle speed changed from 8000 rpm to 2000 rpm. Spindle speed and radial depth of cut are the most significant factor influencing residual stress. The PCR of spindle speed and radial depth of cut reached 73.47% and 18.63% for residual stress in feed direction, 47.11% and 37.51% in step-over direction, respectively. High residual compressive stress can be generated by lowering spindle speed and radial depth of cut benefiting from the aggravated squeeze between ball-end milling cutter and workpiece. Secondly, too small feed per tooth or too small radial depth of cut should be avoided from wear resistance point because though the surface microhardness can be improved, the surface quality will also be deteriorated. The combination of high spindle speed, small feed per tooth together with small radial depth of cut can meet the wear resistance and the machining efficiency requirement. Finally, a medium-sized cutting parameter combination should be adopted to realize satisfying material removal rate and fatigue resistance. This study can be used to guide the selection of cutting parameters during ball-end milling of hardened AISI D2 steel for dies/molds manufacturing industries.
Assuntos
Lesões Acidentais , Compressão de Dados , Humanos , Comércio , Dente Canino , AçoRESUMO
The article describes the production steps and accuracy assessment of an analysis-ready, open-access European data cube consisting of 2000-2020+ Landsat data, 2017-2021+ Sentinel-2 data and a 30 m resolution digital terrain model (DTM). The main purpose of the data cube is to make annual continental-scale spatiotemporal machine learning tasks accessible to a wider user base by providing a spatially and temporally consistent multidimensional feature space. This has required systematic spatiotemporal harmonization, efficient compression, and imputation of missing values. Sentinel-2 and Landsat reflectance values were aggregated into four quarterly averages approximating the four seasons common in Europe (winter, spring, summer and autumn), as well as the 25th and 75th percentile, in order to retain intra-seasonal variance. Remaining missing data in the Landsat time-series was imputed with a temporal moving window median (TMWM) approach. An accuracy assessment shows TMWM performs relatively better in Southern Europe and lower in mountainous regions such as the Scandinavian Mountains, the Alps, and the Pyrenees. We quantify the usability of the different component data sets for spatiotemporal machine learning tasks with a series of land cover classification experiments, which show that models utilizing the full feature space (30 m DTM, 30 m Landsat, 30 m and 10 m Sentinel-2) yield the highest land cover classification accuracy, with different data sets improving the results for different land cover classes. The data sets presented in the article are part of the EcoDataCube platform, which also hosts open vegetation, soil, and land use/land cover (LULC) maps created. All data sets are available under CC-BY license as Cloud-Optimized GeoTIFFs (ca. 12 TB in size) through SpatioTemporal Asset Catalog (STAC) and the EcoDataCube data portal.
Assuntos
Síndrome Linfoproliferativa Autoimune , Compressão de Dados , Humanos , Europa (Continente) , Estações do Ano , ClimaRESUMO
A 8-year-old schoolgirl from West Africa with no previous pathological history was admitted to the haematology department of the Brazzaville University Hospital for the management of cervical adenopathy. The diagnosis of sinus histiocytosis or Destombes-Rosaï-Dorfman disease was retained and the patient was treated with PO corticosteroids (methylprednisolone 32 mg/d then 16 mg/d). Given the rarity and uncertain aetiopathogeny of this syndrome, treatment is poorly codified. It includes corticosteroid therapy, immunomodulators and sometimes chemotherapy, radiotherapy or surgery, indicated in case of clinical manifestations of local organ compression. The disease may regress spontaneously. Its benignity does not justify systematic treatment in the absence of complications.
Assuntos
Compressão de Dados , Histiocitose Sinusal , Humanos , Criança , Congo , Adjuvantes Imunológicos , África Ocidental , Hospitais UniversitáriosRESUMO
Because of the recent progress in materials properties, specifically high-strength concrete, further research is needed to evaluate its suitability, understanding, and performance in the modern-day world. This research aims to enhance the performance of ultra-high-strength geopolymer concrete (UHS-GPC) by adding nano-silica (NS) and polypropylene fibers (PPFs). Three 1%, 2%, and 3% different amounts of PPFs and three NS 5%, 10%, and 15% were utilized in the samples. Various performance parameters of UHS-GPC were evaluated, such as fresh property, compressive strength, modulus of elasticity split tensile, flexural and bonding strength, drying shrinkage, load-displacement test, fracture performance, and elevated temperature. The test outcomes showed that by raising the percentage of PPFs and NS to the allowable limit, the performance of UHS-GPC can be improved significantly. The most improved performance of UHS-GPC was obtained at 2% polypropylene fibers and 10% nano-silica, as the compressive, splitting tensile, flexural. Bond strength was improved by 17.07%, 47.1%, 36.52, and 37.58%, and the modulus of elasticity increased by 31.4% at 56 days. The study showed that the sample with 2% PPFs and 10% NS had excellent performance in the load-displacement test, drying shrinkage, fracture behavior, and elevated temperature. At 750°C elevated temperature, the samples' strength was reduced drastically, but at 250°C, the modified samples showed good resistance to heat by retaining their compressive strength to some degree. The present work showed the suitability of PPFs and NS to develop ultra-high-strength geopolymer concrete, which can be used as a possible alternate material for Portland cement-based concrete.
Assuntos
Compressão de Dados , Fraturas Ósseas , Gastrópodes , Animais , Polipropilenos , Força Compressiva , Dessecação , Elasticidade , Febre , Dióxido de SilícioRESUMO
The growing use of multimodal high-resolution volumetric data in pre-clinical studies leads to challenges related to the management and handling of the large amount of these datasets. Contrarily to the clinical context, currently there are no standard guidelines to regulate the use of image compression in pre-clinical contexts as a potential alleviation of this problem. In this work, the authors study the application of lossy image coding to compress high-resolution volumetric biomedical data. The impact of compression on the metrics and interpretation of volumetric data was quantified for a correlated multimodal imaging study to characterize murine tumor vasculature, using volumetric high-resolution episcopic microscopy (HREM), micro-computed tomography (µCT), and micro-magnetic resonance imaging (µMRI). The effects of compression were assessed by measuring task-specific performances of several biomedical experts who interpreted and labeled multiple data volumes compressed at different degrees. We defined trade-offs between data volume reduction and preservation of visual information, which ensured the preservation of relevant vasculature morphology at maximum compression efficiency across scales. Using the Jaccard Index (JI) and the average Hausdorff Distance (HD) after vasculature segmentation, we could demonstrate that, in this study, compression that yields to a 256-fold reduction of the data size allowed to keep the error induced by compression below the inter-observer variability, with minimal impact on the assessment of the tumor vasculature across scales.
Assuntos
Compressão de Dados , Neoplasias , Humanos , Animais , Camundongos , Compressão de Dados/métodos , Microtomografia por Raio-X , Imageamento por Ressonância Magnética , Imagem Multimodal , Processamento de Imagem Assistida por Computador/métodosRESUMO
Accurate identification of lesions is a key step in surgical planning. However, this task mainly exists two challenges: 1) Due to the complex anatomical shapes of different lesions, most segmentation methods only achieve outstanding performance for a specific structure, rather than other lesions with location differences. 2) The huge number of parameters limits existing transformer-based segmentation models. To overcome these problems, we propose a novel slight dual-path network (SDPN) to segment variable location lesions or organs with significant differences accurately. First, we design a dual-path module to integrate local with global features without obvious memory consumption. Second, a novel Multi-spectrum attention module is proposed to pay further attention to detailed information, which can automatically adapt to the variable segmentation target. Then, the compression module based on tensor ring decomposition is designed to compress convolutional and transformer structures. In the experiment, four datasets, including three benchmark datasets and a clinical dataset, are used to evaluate SDPN. Results of the experiments show that SDPN performs better than other start-of-the-art methods for brain tumor, liver tumor, endometrial tumor and cardiac segmentation. To ensure the generalizability, we train the network on Kvasir-SEG and test on CVC-ClinicDB which collected from a different institution. The quantitative analysis shows that the clinical evaluation results are consistent with the experts. Therefore, this model may be a potential candidate for the segmentation of lesions and organs segmentation with variable locations in clinical applications.
Assuntos
Neoplasias Encefálicas , Compressão de Dados , Processamento de Imagem Assistida por Computador , Humanos , Fontes de Energia ElétricaRESUMO
OBJECTIVE: Voice disorders significantly compromise individuals' ability to speak in their daily lives. Without early diagnosis and treatment, these disorders may deteriorate drastically. Thus, automatic classification systems at home are desirable for people who are inaccessible to clinical disease assessments. However, the performance of such systems may be weakened due to the constrained resources and domain mismatch between the clinical data and noisy real-world data. METHODS: This study develops a compact and domain-robust voice disorder classification system to identify the utterances of health, neoplasm, and benign structural diseases. Our proposed system utilizes a feature extractor model composed of factorized convolutional neural networks and subsequently deploys domain adversarial training to reconcile the domain mismatch by extracting domain-invariant features. RESULTS: The results show that the unweighted average recall in the noisy real-world domain improved by 13% and remained at 80% in the clinic domain with only slight degradation. The domain mismatch was effectively eliminated. Moreover, the proposed system reduced the usage of both memory and computation by over 73.9%. CONCLUSION: By deploying factorized convolutional neural networks and domain adversarial training, domain-invariant features can be derived for voice disorder classification with limited resources. The promising results confirm that the proposed system can significantly reduce resource consumption and improve classification accuracy by considering the domain mismatch. SIGNIFICANCE: To the best of our knowledge, this is the first study that jointly considers real-world model compression and noise-robustness issues in voice disorder classification. The proposed system is intended for application to embedded systems with limited resources.
Assuntos
Compressão de Dados , Distúrbios da Voz , Humanos , Distúrbios da Voz/diagnóstico , Redes Neurais de ComputaçãoRESUMO
Recently, compressive sensing (CS) schemes have been studied as a new compression modality that exploits the sensing matrix in the measurement scheme and the reconstruction scheme to recover the compressed signal. In addition, CS is exploited in medical imaging (MI) to support efficient sampling, compression, transmission, and storage of a large amount of MI. Although CS of MI has been extensively investigated, the effect of color space in CS of MI has not yet been studied in the literature. To fulfill these requirements, this article proposes a novel CS of MI based on hue-saturation value (HSV), using spread spectrum Fourier sampling (SSFS) and sparsity averaging with reweighted analysis (SARA). An HSV loop that performs SSFS is proposed to obtain a compressed signal. Next, HSV-SARA is proposed to reconstruct MI from the compressed signal. A set of color MIs is investigated, such as colonoscopy, magnetic resonance imaging of the brain and eye, and wireless capsule endoscopy images. Experiments were performed to show the superiority of HSV-SARA over benchmark methods in terms of signal-to-noise ratio (SNR), structural similarity (SSIM) index, and measurement rate (MR). The experiments showed that a color MI, with a resolution of 256×256 pixels, could be compressed by the proposed CS at MR of 0.1, and could be improved in terms of SNR being 15.17% and SSIM being 2.53%. The proposed HSV-SARA can be a solution for color medical image compression and sampling to improve the image acquisition of medical devices.
Assuntos
Compressão de Dados , Diagnóstico por Imagem , Cor , Compressão de Dados/métodos , Razão Sinal-Ruído , Diagnóstico por Imagem/métodos , Processamento de Imagem Assistida por Computador/métodos , Radiografia/métodosRESUMO
Objective. In mammography, breast compression forms an essential part of the examination and is achieved by lowering a compression paddle on the breast. Compression force is mainly used as parameter to estimate the degree of compression. As the force does not consider variations of breast size or tissue composition, over- and undercompression are a frequent result. This causes a highly varying perception of discomfort or even pain in the case of overcompression during the procedure. To develop a holistic, patient specific workflow, as a first step, breast compression needs to be thoroughly understood. The aim is to develop a biomechanical finite element breast model that accurately replicates breast compression in mammography and tomosynthesis and allows in-depth investigation. The current work focuses thereby, as a first step, to replicate especially the correct breast thickness under compression.Approach. A dedicated method for acquiring ground truth data of uncompressed and compressed breasts within magnetic resonance (MR) imaging is introduced and transferred to the compression within x-ray mammography. Additionally, we created a simulation framework where individual breast models were generated based on MR images.Main results. By fitting the finite element model to the results of the ground truth images, a universal set of material parameters for fat and fibroglandular tissue could be determined. Overall, the breast models showed high agreement in compression thickness with a deviation of less than ten percent from the ground truth.Significance. The introduced breast models show a huge potential for a better understanding of the breast compression process.
Assuntos
Neoplasias da Mama , Compressão de Dados , Humanos , Feminino , Mama/diagnóstico por imagem , Mama/patologia , Mamografia/métodos , Pressão , Simulação por Computador , Neoplasias da Mama/patologiaRESUMO
BACKGROUND: In recent years, advances in high-throughput sequencing technologies have enabled the use of genomic information in many fields, such as precision medicine, oncology, and food quality control. The amount of genomic data being generated is growing rapidly and is expected to soon surpass the amount of video data. The majority of sequencing experiments, such as genome-wide association studies, have the goal of identifying variations in the gene sequence to better understand phenotypic variations. We present a novel approach for compressing gene sequence variations with random access capability: the Genomic Variant Codec (GVC). We use techniques such as binarization, joint row- and column-wise sorting of blocks of variations, as well as the image compression standard JBIG for efficient entropy coding. RESULTS: Our results show that GVC provides the best trade-off between compression and random access compared to the state of the art: it reduces the genotype information size from 758 GiB down to 890 MiB on the publicly available 1000 Genomes Project (phase 3) data, which is 21% less than the state of the art in random-access capable methods. CONCLUSIONS: By providing the best results in terms of combined random access and compression, GVC facilitates the efficient storage of large collections of gene sequence variations. In particular, the random access capability of GVC enables seamless remote data access and application integration. The software is open source and available at https://github.com/sXperfect/gvc/ .
Assuntos
Compressão de Dados , Compressão de Dados/métodos , Algoritmos , Estudo de Associação Genômica Ampla , Genômica/métodos , Software , Sequenciamento de Nucleotídeos em Larga Escala/métodos , Análise de Sequência de DNA/métodosRESUMO
The deep learning models such as AlexNet, VGG, and ResNet achieved a good performance in classifying the breast cancer histopathological images in BreakHis dataset. However, these models are not practically appropriate due to their computational complexity and too many parameters; as a result, they are rarely utilized on devices with limited computational resources. This paper develops a lightweight learning model based on knowledge distillation to classify the histopathological images of breast cancer in BreakHis. This method employs two teacher models based on VGG and ResNext to train two student models, which are similar to the teacher models in development but have fewer deep layers. In the proposed method, the adaptive joint learning approach is adopted to transfer the knowledge in the final-layer output of a teacher model along with the feature maps of its middle layers as the dark knowledge to a student model. According to the experimental results, the student model designed by ResNeXt architecture obtained the recognition rate 97.09% for all histopathological images. In addition, this model has â¼69.40 million fewer parameters, â¼0.93 G less GPU memory use, and 268.17 times greater compression rate than its teacher model. While in the student model the recognition rate merely dropped down to 1.75%. The comparisons indicated that the student model had a rather acceptable outputs compared with state-of-the-art methods in classifying the images of breast cancer in BreakHis.
Assuntos
Neoplasias da Mama , Compressão de Dados , Humanos , Feminino , Mama , EstudantesRESUMO
PURPOSE: To develop and test compressed sensing-based multiframe 3D MRI of grid-tagged hyperpolarized gas in the lung. THEORY AND METHODS: Applying grid-tagging RF pulses to inhaled hyperpolarized gas results in images in which signal intensity is predictably and sparsely distributed. In the present work, this phenomenon was used to produce a sampling pattern in which k-space is undersampled by a factor of approximately seven, yet regions of high k-space energy remain densely sampled. Three healthy subjects received multiframe 3D 3 He tagging MRI using this undersampling method. Images were collected during a single exhalation at eight timepoints spanning the breathing cycle from end-of-inhalation to end-of-exhalation. Grid-tagged images were used to generate 3D displacement maps of the lung during exhalation, and time-resolved maps of principal strains and fractional volume change were generated from these displacement maps using finite-element analysis. RESULTS: Tags remained clearly resolvable for 4-6 timepoints (5-8 s) in each subject. Displacement maps revealed noteworthy temporal and spatial nonlinearities in lung motion during exhalation. Compressive normal strains occurred along all three principal directions but were primarily oriented in the head-foot direction. Fractional volume changes displayed clear bilateral symmetry, but with the lower lobes displaying slightly higher change than the upper lobes in 2 of the 3 subjects. CONCLUSION: We developed a compressed sensing-based method for multiframe 3D MRI of grid-tagged hyperpolarized gas in the lung during exhalation. This method successfully overcomes previous challenges for 3D dynamic grid-tagging, allowing time-resolved biomechanical readouts of lung function to be generated.