Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 40.571
Filtrar
1.
Comput Biol Med ; 122: 103869, 2020 07.
Artículo en Inglés | MEDLINE | ID: mdl-32658740

RESUMEN

With the recent outbreak of COVID-19, fast diagnostic testing has become one of the major challenges due to the critical shortage of test kit. Pneumonia, a major effect of COVID-19, needs to be urgently diagnosed along with its underlying reasons. In this paper, deep learning aided automated COVID-19 and other pneumonia detection schemes are proposed utilizing a small amount of COVID-19 chest X-rays. A deep convolutional neural network (CNN) based architecture, named as CovXNet, is proposed that utilizes depthwise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. Since the chest X-ray images corresponding to COVID-19 caused pneumonia and other traditional pneumonias have significant similarities, at first, a large number of chest X-rays corresponding to normal and (viral/bacterial) pneumonia patients are used to train the proposed CovXNet. Learning of this initial training phase is transferred with some additional fine-tuning layers that are further trained with a smaller number of chest X-rays corresponding to COVID-19 and other pneumonia patients. In the proposed method, different forms of CovXNets are designed and trained with X-ray images of various resolutions and for further optimization of their predictions, a stacking algorithm is employed. Finally, a gradient-based discriminative localization is integrated to distinguish the abnormal regions of X-ray images referring to different types of pneumonia. Extensive experimentations using two different datasets provide very satisfactory detection performance with accuracy of 97.4% for COVID/Normal, 96.9% for COVID/Viral pneumonia, 94.7% for COVID/Bacterial pneumonia, and 90.2% for multiclass COVID/normal/Viral/Bacterial pneumonias. Hence, the proposed schemes can serve as an efficient tool in the current state of COVID-19 pandemic. All the architectures are made publicly available at: https://github.com/Perceptron21/CovXNet.


Asunto(s)
Técnicas de Laboratorio Clínico/métodos , Infecciones por Coronavirus/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Neumonía Viral/diagnóstico por imagen , Radiografía Torácica/métodos , Algoritmos , Betacoronavirus , Infecciones por Coronavirus/diagnóstico , Bases de Datos Factuales , Aprendizaje Profundo , Humanos , Redes Neurales de la Computación , Pandemias , Reproducibilidad de los Resultados
2.
Medicine (Baltimore) ; 99(27): e20880, 2020 Jul 02.
Artículo en Inglés | MEDLINE | ID: mdl-32629676

RESUMEN

To determine the value of 3T magnetic resonance imaging (MRI) texture analysis in differentiating high- from low-grade soft-tissue sarcoma.Forty-two patients with soft-tissue sarcomas who underwent 3T MRI were analyzed. Qualitative and texture analysis were performed on T1-, T2- and fat-suppressed contrast-enhanced (CE) T1-weighted images. Various features of qualitative and texture analysis were compared between high- and low-grade sarcoma. Areas under the receiver operating characteristic curves (AUC) were calculated for texture features. Multivariate logistic regression analysis was used to analyze the value of qualitative and texture analysis.There were 11 low- and 31 high-grade sarcomas. Among qualitative features, signal intensity on T1-weighted images, tumor margin on T2-weighted images, tumor margin on fat-suppressed CE T1-weighted images and peritumoral enhancement were significantly different between high- and low-grade sarcomas. Among texture features, T2 mean, T1 SD, CE T1 skewness, CE T1 mean, CE T1 difference variance and CE T1 contrast were significantly different between high- and low-grade sarcomas. The AUCs of the above texture features were > 0.7: T2 mean, .710 (95% confidence interval [CI] .543-.876); CE T1 mean, .768 (.590-.947); T1 SD, .730 (.554-.906); CE T1 skewness, .751 (.586-.916); CE T1 difference variance, .721 (.536-.907); and CE T1 contrast, .727 (.530-.924). The multivariate logistic regression model of both qualitative and texture features had numerically higher AUC than those of only qualitative or texture features.Texture analysis at 3T MRI may provide additional diagnostic value to the qualitative MRI imaging features for the differentiation of high- and low-grade sarcomas.


Asunto(s)
Imagen por Resonancia Magnética/métodos , Sarcoma/diagnóstico por imagen , Sarcoma/patología , Neoplasias de los Tejidos Blandos/diagnóstico por imagen , Neoplasias de los Tejidos Blandos/patología , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Persona de Mediana Edad , Clasificación del Tumor , Reconocimiento de Normas Patrones Automatizadas , Adulto Joven
3.
Int J Med Sci ; 17(12): 1773-1782, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32714080

RESUMEN

Rationale: Acute respiratory distress syndrome (ARDS) is one of the major reasons for ventilation and intubation management of COVID-19 patients but there is no noninvasive imaging monitoring protocol for ARDS. In this study, we aimed to develop a noninvasive ARDS monitoring protocol based on traditional quantitative and radiomics approaches from chest CT. Methods: Patients diagnosed with COVID-19 from Jan 20, 2020 to Mar 31, 2020 were enrolled in this study. Quantitative and radiomics data were extracted from automatically segmented regions of interest (ROIs) of infection regions in the lungs. ARDS existence was measured by Pa02/Fi02 <300 in artery blood samples. Three different models were constructed by using the traditional quantitative imaging metrics, radiomics features and their combinations, respectively. Receiver operating characteristic (ROC) curve analysis was used to assess the effectiveness of the models. Decision curve analysis (DCA) was used to test the clinical value of the proposed model. Results: The proposed models were constructed using 352 CT images from 86 patients. The median age was 49, and the male proportion was 61.9%. The training dataset and the validation dataset were generated by randomly sampling the patients with a 2:1 ratio. Chi-squared test showed that there was no significant difference in baseline of the enrolled patients between the training and validation datasets. The areas under the ROC curve (AUCs) of the traditional quantitative model, radiomics model and combined model in the validation dataset was 0.91, 0.91 and 0.94, respectively. Accordingly, the sensitivities were 0.55, 0.82 and 0.58, while the specificities were 0.97, 0.86 and 0.98. The DCA curve showed that when threshold probability for a doctor or patients is within a range of 0 to 0.83, the combined model adds more net benefit than "treat all" or "treat none" strategies, while the traditional quantitative model and radiomics model could add benefit in all threshold probability. Conclusions: It is feasible to monitor ARDS from CT images using radiomics or traditional quantitative analysis in COVID-19. The radiomics model seems to be the most practical one for possible clinical use. Multi-center validation with a larger number of samples is recommended in the future.


Asunto(s)
Betacoronavirus , Infecciones por Coronavirus/complicaciones , Pulmón/diagnóstico por imagen , Modelos Teóricos , Pandemias , Neumonía Viral/complicaciones , Síndrome de Dificultad Respiratoria del Adulto/diagnóstico por imagen , Tomografía Computarizada por Rayos X , Adulto , Algoritmos , Área Bajo la Curva , China/epidemiología , Infecciones por Coronavirus/epidemiología , Conjuntos de Datos como Asunto , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Persona de Mediana Edad , Neumonía Viral/epidemiología , Curva ROC , Síndrome de Dificultad Respiratoria del Adulto/etiología , Estudios Retrospectivos , Muestreo , Sensibilidad y Especificidad , Investigación en Medicina Traslacional/métodos , Flujo de Trabajo
4.
J Comput Assist Tomogr ; 44(4): 553-558, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32697525

RESUMEN

OBJECTIVE: To assess the limitations of single-energy metal artifact reduction algorithm in the oral cavity and evaluate the availability of a solution by setting the patient in a lateral position (LP) with the use of a gantry tilt (GT). METHODS: We analyzed 88 patients with dental metals retrospectively in study 1, and 74 patients prospectively in study 2. Patients were classified: metal I with dental metals in 1 region, metal II in 2 regions, and metal III in 3 regions. Patients underwent neck computed tomography examinations in a supine position (SP) in study 1, and 2 positions, an LP with a GT and an SP, in study 2. All images were reconstructed with this algorithm. Image quality was scored using a 4-point scale: 1 = severe artifact, 2 = moderate artifact, 3 = slight artifact, 4 = no artifact. The scores were compared between metal I, metal II, and metal III using the Mann-Whitney U test in study 1, and between an LP with a GT and an SP using the Wilcoxon signed ranks test in study 2. RESULTS: The scores outside the dental arch were significantly higher in metal I than in metal II and metal III (3.0 ± 0.6 vs 2.3 ± 0.5 vs 2.2 ± 0.4; P < 0.0001 for metal I vs metal II and for metal I vs metal III) and significantly higher in an LP with a GT than an SP (3.2 ± 0.4 vs 2.3 ± 0.4; P < 0.0001). CONCLUSIONS: Single-energy metal artifact reduction algorithm could reduce metal artifacts adequately in patients with dental metals in 1 region, but not in 2 or more regions. However, even for the latter, combination of this algorithm and an LP with a GT could further improve the image quality.


Asunto(s)
Boca/diagnóstico por imagen , Posicionamiento del Paciente/métodos , Tomografía Computarizada por Rayos X/métodos , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , Medios de Contraste , Materiales Dentales , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Metales , Persona de Mediana Edad , Fantasmas de Imagen , Estudios Retrospectivos , Posición Supina
5.
PLoS One ; 15(5): e0232433, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32459811

RESUMEN

In order to cope with the problems of high frequency and multiple causes of mountain fires, it is very important to adopt appropriate technologies to monitor and warn mountain fires through a few surface parameters. At the same time, the existing mobile terminal equipment is insufficient in image processing and storage capacity, and the energy consumption is high in the data transmission process, which requires calculation unloading. For this circumstance, first, a hierarchical discriminant analysis algorithm based on image feature extraction is introduced, and the image acquisition software in the mobile edge computing environment in the android system is designed and installed. Based on the remote sensing data, the land surface parameters of mountain fire are obtained, and the application of image recognition optimization algorithm in the mobile edge computing (MEC) environment is realized to solve the problem of transmission delay caused by traditional mobile cloud computing (MCC). Then, according to the forest fire sensitivity index, a forest fire early warning model based on MEC is designed. Finally, the image recognition response time and bandwidth consumption of the algorithm are studied, and the occurrence probability of mountain fire in Muli county, Liangshan prefecture, Sichuan is predicted. The results show that, compared with the MCC architecture, the algorithm presented in this study has shorter recognition and response time to different images in WiFi network environment; compared with MCC, MEC architecture can identify close users and transmit less data, which can effectively reduce the bandwidth pressure of the network. In most areas of Muli county, Liangshan prefecture, the probability of mountain fire is relatively low, the probability of mountain fire caused by non-surface environment is about 8 times that of the surface environment, and the influence of non-surface environment in the period of high incidence of mountain fire is lower than that in the period of low incidence. In conclusion, the surface parameters of MEC can be used to effectively predict the mountain fire and provide preventive measures in time.


Asunto(s)
Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Incendios Forestales/prevención & control , China , Nube Computacional , Sistemas de Computación , Conservación de los Recursos Naturales/métodos , Conservación de los Recursos Naturales/estadística & datos numéricos , Análisis Discriminante , Fenómenos Geológicos , Humanos , Procesamiento de Imagen Asistido por Computador/estadística & datos numéricos , Programas Informáticos , Propiedades de Superficie , Incendios Forestales/estadística & datos numéricos
6.
PLoS One ; 15(5): e0232319, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32369515

RESUMEN

Aiming at the problem of fast certification for a constrained iris in the same category caused by the unstable iris features caused by the change of the iris acquisition environment and shooting status under lightweight training samples, a one-to-one fast certification algorithm for constrained unsteady-state iris based on the scale change stable feature and multi-algorithm voting is proposed. Scale change stable features are found by constructing an isometric differential Gaussian space, and a local binary pattern algorithm with extended statistics (ES-LBP), the Haar wavelet with over threshold detection and the Gabor filter algorithm with immune particle swarm optimization (IPSO) are used to represent the stable features as binary feature codes. Iris certification is performed by the Hamming distance. According to the certification results of three algorithms, the final result is obtained by multi-algorithm voting. Experiments with the JLU and CASIA iris libraries under the iris prerequisite conditions show that the correct recognition rate of this algorithm can reach a high level of 98% or more, indicating that this algorithm can improve the operation speed, accuracy and robustness of certification.


Asunto(s)
Algoritmos , Identificación Biométrica/métodos , Iris , Reconocimiento de Normas Patrones Automatizadas/métodos , Humanos , Procesamiento de Imagen Asistido por Computador/métodos
7.
PLoS One ; 15(5): e0232403, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32374774

RESUMEN

We present novel multi-energy X-ray imaging methods for direct radiography and computed tomography. The goal is to determine the contribution of thickness, mass density and atomic composition to the measured X-ray absorption in the sample. Algorithms have been developed by our own to calculate new X-ray images using data from an unlimited amount of scans/images of different tube voltages by pixelwise fitting of the detected gray levels. The resulting images then show a contrast that is influenced either by the atomic number of the elements in the sample (photoelectric interactions) or by the mass density (Compton scattering). For better visualization, those images can be combined to a color image where different materials can easily be distinguished. In the case of computed tomography no established true multi-energy methodology that does not require an energy sensitive detector is known to the authors. The existing dual-energy methods often yield noisy results that need spatial averaging for clear interpretation. The goal of the method presented here is to qualitatively calculate atomic number and mass density images without loosing resolution while reducing the noise by the use of more than two X-ray energies. The resulting images are generated without the need of calibration stan-dards in an automatic and fast data processing routine. They provide additional information that might be of special interest in cases like archaeology where the destruction of a sample to determine its composition is no option, but a increase in measurement time is of little concern.


Asunto(s)
Radiografía/métodos , Tomografía Computarizada por Rayos X/métodos , Algoritmos , Simulación por Computador , Procesamiento de Imagen Asistido por Computador/métodos , Procesamiento de Imagen Asistido por Computador/estadística & datos numéricos , Imagenología Tridimensional/métodos , Imagenología Tridimensional/estadística & datos numéricos , Ciencia de los Materiales , Minerales/química , Radiografía/estadística & datos numéricos , Dispersión de Radiación , Tomografía Computarizada por Rayos X/estadística & datos numéricos , Rayos X
8.
PLoS One ; 15(5): e0231155, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32365124

RESUMEN

People's perceptions about health risks, including their risk of acquiring HIV, are impacted in part by who they see portrayed as at risk in the media. Viewers in these cases are asking themselves "do those portrayed as at risk look like me?" An accurate perception of risk is critical for high-risk populations, who already suffer from a range of health disparities. Yet, to date no study has evaluated the demographic representation of health-related content from social media. The objective of this case study was to apply automated image recognition software to examine the demographic profile of faces in Instagram posts containing the hashtag #HIV (obtained from January 2017 through July 2018) and compare this to the demographic breakdown of those most at risk of a new HIV diagnosis (estimates of incidence of new HIV diagnoses from the 2017 US Centers for Disease Control HIV Surveillance Report). We discovered 26,766 Instagram posts containing #HIV authored in American English with 10,036 (37.5%) containing a detectable human face with a total of 18,227 faces (mean = 1.8, standard deviation [SD] = 1.7). Faces skewed older (47% vs. 11% were 35-39 years old), more female (41% vs. 19%), more white (43% vs. 26%), less black (31% vs 44%), and less Hispanic (13% vs 25%) on Instagram than for new HIV diagnoses. The results were similarly skewed among the subset of #HIV posts mentioning pre-exposure prophylaxis (PrEP). This disparity might lead Instagram users to potentially misjudge their own HIV risk and delay prophylactic behaviors. Social media managers and organic advocates should be encouraged to share images that better reflect at-risk populations so as not to further marginalize these populations and to reduce disparity in risk perception. Replication of our methods for additional diseases, such as cancer, is warranted to discover and address other misrepresentations.


Asunto(s)
Comunicación , Infecciones por VIH/transmisión , Conductas de Riesgo para la Salud , Procesamiento de Imagen Asistido por Computador/métodos , Percepción/fisiología , Salud Pública , Medios de Comunicación Sociales , Adolescente , Adulto , Factores de Edad , Anciano , Grupos Étnicos , Femenino , VIH/fisiología , Promoción de la Salud/métodos , Promoción de la Salud/normas , Humanos , Procesamiento de Imagen Asistido por Computador/normas , Masculino , Persona de Mediana Edad , Redes Neurales de la Computación , Salud Pública/métodos , Salud Pública/normas , Asunción de Riesgos , Factores Sexuales , Medios de Comunicación Sociales/normas , Estados Unidos/epidemiología , Adulto Joven
9.
PLoS One ; 15(5): e0231602, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32469877

RESUMEN

Reversible Data Hiding (RDH) techniques have gained popularity over the last two decades, where data is embedded in an image in such a way that the original image can be restored. Earlier works on RDH was based on the Image Histogram Modification that uses the peak point to embed data in the image. More recent works focus on the Difference Image Histogram Modification that exploits the fact that the neighbouring pixels of an image are highly correlated and therefore the difference of image makes more space to embed large amount of data. In this paper we propose a framework to increase the embedding capacity of reversible data hiding techniques that use a difference of image to embed data. The main idea is that, instead of taking the difference of the neighboring pixels, we rearrange the columns (or rows) of the image in a way that enhances the smooth regions of an image. Any difference based technique to embed data can then be used in the transformed image. The proposed method is applied on different types of images including textures, patterns and publicly available images. Experimental results demonstrate that the proposed method not only increases the message embedding capacity of a given image by more than 50% but also the visual quality of the marked image containing the message is more than the visual quality obtained by existing state-of-the-art reversible data hiding technique. The proposed technique is also verified by Pixel Difference Histogram (PDH) Stegoanalysis and results demonstrate that marked images generated by proposed method is undetectable by PDH analysis.


Asunto(s)
Algoritmos , Seguridad Computacional/normas , Simulación por Computador , Bases de Datos Factuales , Técnicas Histológicas/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Humanos , Registros
10.
Ultrasonics ; 107: 106163, 2020 Sep.
Artículo en Inglés | MEDLINE | ID: mdl-32353739

RESUMEN

Singular value decomposition (SVD)-based clutter filters can robustly reject the tissue clutter as compared with the conventional high pass filter-based clutter filters. However, the computational burden of SVD makes real time SVD-based clutter filtering challenging (e.g. frame rate at least 10-15 Hz with region of interest of about 4 × 4 cm2). Recently, we proposed an acceleration method based on randomized SVD (rSVD) clutter filtering and randomized spatial downsampling, which can significantly reduce the computational complexity without compromising the clutter rejection capability. However, this method has not been implemented on an ultrasound scanner and tested for its performance. In this study, we implement this acceleration method on a Verasonics scanner using a multi-core CPU architecture, and evaluate the selections of the imaging and processing parameters to enable real time micro-vessel imaging. The Blood-to-Clutter Ratio (BCR) performance was evaluated on a Verasonics machine with different settings of parameters such as block size and ensemble size. The demonstration of real time process was implemented on a 12-core CPU (downsampling factor of 12, 12-threads in this study) host computer. The processing time of the rSVD-based clutter filter was less than 30 ms and BCRs were higher than 20 dB as the block size, ensemble size and the rank of tissue clutter subspace were set as 30 × 30, 45 and 26 respectively. We also demonstrate that the micro-vessel imaging frame rate of the proposed architecture can reach approximately 22 Hz when the block size, ensemble size and the rank of tissue clutter subspace were set as 20 × 20 pixels, 45 and 26 respectively (using both images and supplementary videos). The proposed method may be important for real time 2D scanning of tumor microvessels in 3D to select and store the most representative 2D view with most abnormal micro-vessels for better diagnosis.


Asunto(s)
Vasos Sanguíneos/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Ultrasonografía Doppler/métodos , Velocidad del Flujo Sanguíneo , Simulación por Computador , Fantasmas de Imagen , Ultrasonografía Doppler/instrumentación
11.
Medicine (Baltimore) ; 99(18): e20074, 2020 May.
Artículo en Inglés | MEDLINE | ID: mdl-32358390

RESUMEN

The objective of this study was to develop a venous computed tomography (CT)-based radiomics model to predict the lymph node metastasis (LNM) in patients with non-small cell lung cancer (NSCLC). A total of 411 consecutive patients with NSCLC underwent tumor resection and lymph node (LN) dissection from January 2018 to September 2018 in our hospital. A radiologist with 20 years of diagnostic experience retrospectively reviewed all CT scans and classified all visible LNs into LNM and non-LNM groups without the knowledge of pathological diagnosis. A logistic regression model (radiomics model) in classification of pathology-confirmed NSCLC patients with and without LNM was developed on radiomics features for NSCLC patients. A morphology model was also developed on qualitative morphology features in venous CT scans. A training group included 288 patients (99 with and 189 without LNM) and a validation group included 123 patients (42 and 81, respectively). The receiver operating characteristic curve was performed to discriminate LNM (+) from LNM (-) for CT-reported status, the morphology model and the radiomics model. The area under the curve value in LNM classification on the training group was significantly greater at 0.79 (95% confidence interval [CI]: 0.77-0.81) by use of the radiomics model (build by best 10 features in predicting LNM) compared with 0.51 by CT-reported LN status (P < .001) or 0.66 (95% CI: 0.64-0.68) by morphology model (build by tumor size and spiculation) (P < .001). Similarly, the area under the curve value on the validation group was 0.73 (95% CI: 0.70-0.76) by the radiomics model, compared with 0.52 or 0.63 (95% CI: 0.60-0.66) by the other 2 (both P < .001). A radiomics model shows excellent performance for predicting LNM in NSCLC patients. This predictive radiomics model may benefit patients to get better treatments such as an appropriate surgery.


Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas/patología , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias Pulmonares/patología , Metástasis Linfática , Tomografía Computarizada por Rayos X/métodos , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , Carcinoma de Pulmón de Células no Pequeñas/cirugía , Femenino , Humanos , Modelos Logísticos , Neoplasias Pulmonares/cirugía , Escisión del Ganglio Linfático , Masculino , Persona de Mediana Edad , Estadificación de Neoplasias , Valor Predictivo de las Pruebas , Curva ROC , Estudios Retrospectivos
12.
Medicine (Baltimore) ; 99(18): e20093, 2020 May.
Artículo en Inglés | MEDLINE | ID: mdl-32358396

RESUMEN

Identification of histologic grading of urothelial carcinoma still depends on histopathologic examination. As an emerging and promising imaging technology, radiomic texture analysis is a noninvasive technique and has been studied to differentiate various tumors. This study explored the value of computed tomography (CT) texture analysis for the differentiation of low-grade urothelial carcinoma (LGUC), high-grade urothelial carcinoma (HGUC), and their invasive properties.Radiologic data were analyzed retrospectively for 94 patients with pathologically proven urothelial carcinomas from November 2016 to April 2019. Pathologic examination demonstrated that tumors were: high grade in 43 cases, and low grade in 51 cases; and nonmuscle invasive (NMI) in 37 cases, and muscle invasive (MI) in 37 cases. Maximum tumor diameters on CT scan were manually outlined as regions of interest and 78 texture features were extracted automatically. Three-phasic CT images were used to measure texture parameters, which were compared with postoperative pathologic grading and invasive results. The independent sample t test or Mann-Whitney U test was used to compare differences in parameters. Receiver-operating characteristic curves for statistically significant parameters were used to confirm efficacy.Of the 78 features extracted from each phase of CT images, 26 (33%), 20 (26%), and 22 (28%) texture parameters were significant (P < .05) for differentiating LGUC from HGUC, while 19 (24%), 16 (21%), and 30 (38%) were significant (P < .05) for differentiating NMI from MI urothelial carcinoma. Highest areas the under curve for differentiating grading and invasive properties were obtained by variance (0.761, P < .001) and correlation (0.798, P < .001) on venous-phase CT images.Texture analysis has the potential to distinguish LGUC and HGUC, or NMI from MI urothelial carcinoma, before surgery.


Asunto(s)
Carcinoma de Células Transicionales/patología , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía Computarizada por Rayos X/métodos , Neoplasias de la Vejiga Urinaria/patología , Anciano , Anciano de 80 o más Años , Carcinoma de Células Transicionales/diagnóstico por imagen , Femenino , Humanos , Masculino , Persona de Mediana Edad , Clasificación del Tumor , Invasividad Neoplásica , Curva ROC , Estudios Retrospectivos , Neoplasias de la Vejiga Urinaria/diagnóstico por imagen
13.
Niger J Clin Pract ; 23(5): 596-602, 2020 May.
Artículo en Inglés | MEDLINE | ID: mdl-32367864

RESUMEN

Aim: The aim of this retrospective study is to evaluate and compare the 3-dimensional (3D) crown sizes of the left and right sides of upper and lower dental arches in patients with unilateral cleft lip and palate (UCLP). Materials and Methods: Dental casts of 94 patients all in permanent dentition were included in this study. Dental casts were divided into three groups as 36 casts with unilateral left cleft lip and palate (ULCLP), 18 casts with unilateral right cleft lip and palate (URCLP), and 40 casts without cleft (control). Mesiodistal (MD), buccolingual (BL), and gingiva incisal (GI) values of each tooth were measured by scanning the dental models with a high-precision optical 3D scanner. Paired t-test and independent t-test were used for statistical analysis. Results: U1 MD, U6 MD (P = 0.001) and BL (P = 0.01), L3 GI (P = 0.05) were greater in UCLP patients on the non-cleft side while U1 GI, L1 BL, L5 MD (P = 0.001), L4 MD, and BL (P = 0.01) values were found to be greater on the cleft side. Comparison of the cleft-sides and the control group showed that MD, BL, and GI dimensions of teeth on the cleft sides were generally found to be smaller, excluding the UR7 GI values for URCLP group (P = 0.05). Conclusion: In the measurements of teeth size, reliable and repeatable results were acquired through 3D software. Tooth size asymmetries can occur non-syndromic UCLP patients in both jaws. MD, BL, and GI dimensions of teeth are mostly found to be smaller in patients with CLP.


Asunto(s)
Labio Leporino , Imagenología Tridimensional/métodos , Odontometría/métodos , Corona del Diente/diagnóstico por imagen , Estudios de Casos y Controles , Niño , Fisura del Paladar/patología , Oclusión Dental , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Maxilar , Estudios Retrospectivos , Corona del Diente/patología
14.
Cancer Imaging ; 20(1): 33, 2020 May 01.
Artículo en Inglés | MEDLINE | ID: mdl-32357923

RESUMEN

During the last decade, there is an increasing usage of quantitative methods in Radiology in an effort to reduce the diagnostic variability associated with a subjective manner of radiological interpretation. Combined approaches where visual assessment made by the radiologist is augmented by quantitative imaging biomarkers are gaining attention. Advances in machine learning resulted in the rise of radiomics that is a new methodology referring to the extraction of quantitative information from medical images. Radiomics are based on the development of computational models, referred to as "Radiomic Signatures", trying to address either unmet clinical needs, mostly in the field of oncologic imaging, or to compare radiomics performance with that of radiologists. However, to explore this new technology, initial publications did not consider best practices in the field of machine learning resulting in publications with questionable clinical value. In this paper, our effort was concentrated on how to avoid methodological mistakes and consider critical issues in the workflow of the development of clinically meaningful radiomic signatures.


Asunto(s)
Interpretación de Imagen Asistida por Computador/métodos , Neoplasias/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Automático , Guías de Práctica Clínica como Asunto
17.
PLoS One ; 15(4): e0231468, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32287288

RESUMEN

We present a case study for implementing a machine learning algorithm with an incremental value framework in the domain of lung cancer research. Machine learning methods have often been shown to be competitive with prediction models in some domains; however, implementation of these methods is in early development. Often these methods are only directly compared to existing methods; here we present a framework for assessing the value of a machine learning model by assessing the incremental value. We developed a machine learning model to identify and classify lung nodules and assessed the incremental value added to existing risk prediction models. Multiple external datasets were used for validation. We found that our image model, trained on a dataset from The Cancer Imaging Archive (TCIA), improves upon existing models that are restricted to patient characteristics, but it was inconclusive about whether it improves on models that consider nodule features. Another interesting finding is the variable performance on different datasets, suggesting population generalization with machine learning models may be more challenging than is often considered.


Asunto(s)
Neoplasias Pulmonares/clasificación , Neoplasias Pulmonares/diagnóstico , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Algoritmos , Bases de Datos Factuales , Aprendizaje Profundo , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Pulmón , Aprendizaje Automático , Redes Neurales de la Computación , Lesiones Precancerosas , Tomografía Computarizada por Rayos X
18.
Radiology ; 295(3): 562-571, 2020 06.
Artículo en Inglés | MEDLINE | ID: mdl-32228294

RESUMEN

Background The recently described "macrotrabecular-massive" (MTM) histologic subtype of hepatocellular carcinoma (HCC) (MTM-HCC) represents an aggressive form of HCC and is associated with poor survival. Purpose To investigate whether preoperative MRI can help identify MTM-HCCs in patients with HCC. Materials and Methods This retrospective study included patients with HCC treated with surgical resection between January 2008 and February 2018 and who underwent preoperative multiphase contrast material-enhanced MRI. Least absolute shrinkage and selection operator (LASSO)-penalized and multivariable logistic regression analyses were performed to identify clinical, biologic, and imaging features associated with the MTM-HCC subtype. Early recurrence (within 2 years) and overall recurrence were evaluated by using Kaplan-Meier analysis. Multivariable Cox regression analysis was performed to determine predictors of early and overall recurrence. Results One hundred fifty-two patients (median age, 64 years; interquartile range, 56-72 years; 126 men) with 152 HCCs were evaluated. Twenty-six of the 152 HCCs (17%) were MTM-HCCs. LASSO-penalized logistic regression analysis identified substantial necrosis, high serum α-fetoprotein (AFP) level (>100 ng/mL), and Barcelona Clinic Liver Cancer (BCLC) stage B or C as independent features associated with MTM-HCCs. At multivariable analysis, substantial necrosis (odds ratio = 32; 95% confidence interval [CI] = 8.9, 114; P < .001), high serum AFP level (odds ratio = 4.4; 95% CI = 1.3, 16; P = .02), and BCLC stage B or C (odds ratio = 4.2; 95% CI = 1.2, 15; P = .03) were independent predictors of MTM-HCC subtype. Substantial necrosis helped identify 65% (17 of 26; 95% CI: 44%, 83%) of MTM-HCCs (sensitivity) with a specificity of 93% (117 of 126; 95% CI: 87%, 97%). In adjusted models, only the presence of satellite nodules was independently associated with both early (hazard ratio = 3.7; 95% CI: 1.5, 9.4; P = .006) and overall (hazard ratio = 3.0; 95% CI: 1.3, 7.2; P = .01) tumor recurrence. Conclusion At multiphase contrast-enhanced MRI, substantial necrosis helped identify macrotrabecular-massive hepatocellular carcinoma subtype with high specificity. © RSNA, 2020.


Asunto(s)
Carcinoma Hepatocelular/diagnóstico por imagen , Neoplasias Hepáticas/diagnóstico por imagen , Imagen por Resonancia Magnética/métodos , Anciano , Carcinoma Hepatocelular/clasificación , Carcinoma Hepatocelular/patología , Femenino , Humanos , Aumento de la Imagen/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Estimación de Kaplan-Meier , Hígado/diagnóstico por imagen , Hígado/patología , Neoplasias Hepáticas/clasificación , Neoplasias Hepáticas/patología , Masculino , Persona de Mediana Edad , Recurrencia Local de Neoplasia/clasificación , Recurrencia Local de Neoplasia/diagnóstico por imagen , Recurrencia Local de Neoplasia/patología , Pronóstico , Estudios Retrospectivos , Sensibilidad y Especificidad
19.
PLoS One ; 15(4): e0231440, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32287298

RESUMEN

BACKGROUND AND PURPOSE: There is limited standardization of acquisition and processing methods in diffusion tractography for pre-surgical planning, leading to a range of approaches. In this study, a number of representative acquisition variants and post processing methods are considered, to assess their importance when implementing a clinical tractography program. METHODS: Diffusion MRI was undertaken in ten healthy volunteers, using protocols typical of clinical and research scanning: a 32-direction diffusion acquisition with and without peripheral gating, and a non-gated 64 diffusion direction acquisition. All datasets were post-processed using diffusion tensor reconstruction with streamline tractography, and with constrained spherical deconvolution (CSD) with both streamline and probabilistic tractography, to delineate the cortico-spinal tract (CST) and optic radiation (OR). The accuracy of tractography results was assessed against a histological atlas using a novel probabilistic Dice overlap technique, together with direct comparison to tract volumes and distance of Meyer's loop to temporal pole (ML-TP) from dissections studies. Three clinical case studies of patients with space occupying lesions were also investigated. RESULTS: Tracts produced by CSD with probabilistic tractography provided the greatest overlap with the histological atlas (overlap scores of 44% and 52% for the CST and OR, respectively) and best matched tract volume and ML-TP distance from dissection studies. The acquisition protocols investigated had limited impact on the accuracy of the tractography. In all patients, the CSD based probabilistic tractography created tracts with greatest anatomical plausibility, although in one case anatomically plausible pathways could not be reconstructed without reducing the probabilistic threshold, leading to an increase in false positive tracts. CONCLUSIONS: Advanced post processing techniques such as CSD with probabilistic tractography are vital for pre-surgical planning. However, overall accuracy relative to dissection studies remains limited.


Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Cirugía Asistida por Computador/métodos , Adolescente , Adulto , Imagen de Difusión por Resonancia Magnética , Femenino , Ganglioglioma/diagnóstico por imagen , Ganglioglioma/cirugía , Humanos , Masculino , Persona de Mediana Edad , Oligodendroglioma/diagnóstico por imagen , Oligodendroglioma/cirugía , Adulto Joven
20.
PLoS One ; 15(4): e0230415, 2020.
Artículo en Inglés | MEDLINE | ID: mdl-32271777

RESUMEN

Accurate segmentation of myocardial in cardiac MRI (magnetic resonance image) is key to effective rapid diagnosis and quantitative pathology analysis. However, a low-quality CMR (cardiac magnetic resonance) image with a large amount of noise makes it extremely difficult to accurately and quickly manually segment the myocardial. In this paper, we propose a method for CMR segmentation based on U-Net and combined with image sequence information. The method can effectively segment from the top slice to the bottom slice of the CMR. During training, each input slice depends on the slice below it. In other words, the predicted segmentation result depends on the existing segmentation label of the previous slice. 3D sequence information is fully utilized. Our method was validated on the ACDC dataset, which included CMR images of 100 patients (1700 2D MRI). Experimental results show that our method can segment the myocardial quickly and efficiently and is better than the current state-of-the-art methods. When evaluating 340 CMR image, our model yielded an average dice score of 85.02 ± 0.15, which is much higher than the existing classical segmentation method(Unet, Dice score = 0.78 ± 0.3).


Asunto(s)
Técnicas de Imagen Cardíaca/métodos , Aprendizaje Profundo , Corazón/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Conjuntos de Datos como Asunto , Corazón/anatomía & histología , Ventrículos Cardíacos/anatomía & histología , Ventrículos Cardíacos/diagnóstico por imagen , Ventrículos Cardíacos/patología , Humanos , Imagenología Tridimensional/métodos , Miocardio/patología , Redes Neurales de la Computación
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA