RESUMEN
Background: A significant number of frames captured by the wireless capsule endoscopy are involved with varying amounts of bubbles. Whereas different studies have considered bubbles as nonuseful agents due to the fact that they reduce the visualization quality of the small intestine mucosa, this research aims to develop a practical way of assessing the rheological capability of the circular bubbles as a suggestion for future clinical diagnostic purposes. Methods: From the Kvasir-capsule endoscopy dataset, frames with varying levels of bubble engagements were chosen in two categories based on bubble size. Border reflections are present on the edges of round-shaped bubbles in their boundaries, and in the frequency domain, high-frequency bands correspond to these edges in the spatial domain. The first step is about high-pass filtering of border reflections using wavelet transform (WT) and Differential of Gaussian, and the second step is related to applying the Fast Circlet Transform (FCT) and the Hough transform as circle detection tools on extracted borders and evaluating the distribution and abundance of all bubbles with the variety of radii. Results: Border's extraction using WT as a preprocessing approach makes it easier for circle detection tool for better concentration on high-frequency circular patterns. Consequently, applying FCT with predefined parameters can specify the variety and range of radius and the abundance for all bubbles in an image. The overall discrimination factor (ODF) of 15.01, and 7.1 showing distinct bubble distributions in the gastrointestinal (GI) tract. The discrimination in ODF from datasets 1-2 suggests a relationship between the rheological properties of bubbles and their coverage area plus their abundance, highlighting the WT and FCT performance in determining bubbles' distributions for diagnostic objectives. Conclusion: The implementation of an object-oriented attitude in gastrointestinal analysis makes it intelligible for gastroenterologists to approximate the constituent features of intra-intestinal fluids. this can't be evaluated until the bubbles are considered as non-useful agents. The obtained results from the datasets proved that the difference between the calculated ODF can be used as an indicator for the quality estimation of intraintestinal fluids' rheological features like viscosity, which helps gastroenterologists evaluate the quality of patient digestion.
RESUMEN
PURPOSE: Early detection of retinal disorders using optical coherence tomography (OCT) images can prevent vision loss. Since manual screening can be time-consuming, tedious, and fallible, we present a reliable computer-aided diagnosis (CAD) software based on deep learning. Also, we made efforts to increase the interpretability of the deep learning methods, overcome their vague and black box nature, and also understand their behavior in the diagnosis. METHODS: We propose a novel method to improve the interpretability of the used deep neural network by embedding the rich semantic information of abnormal areas based on the ophthalmologists' interpretations and medical descriptions in the OCT images. Finally, we trained the classification network on a small subset of the online publicly available University of California San Diego (UCSD) dataset with an overall of 29,800 OCT images. RESULTS: The experimental results on the 1000 test OCT images show that the proposed method achieves the overall precision, accuracy, sensitivity, and f1-score of 97.6%, 97.6%, 97.6%, and 97.59%, respectively. Also, the heat map images provide a clear region of interest which indicates that the interpretability of the proposed method is increased dramatically. CONCLUSION: The proposed software can help ophthalmologists in providing a second opinion to make a decision, and primitive automated diagnoses of retinal diseases and even it can be used as a screening tool, in eye clinics. Also, the improvement of the interpretability of the proposed method causes to increase in the model generalization, and therefore, it will work properly on a wide range of other OCT datasets.
Asunto(s)
Aprendizaje Profundo , Enfermedades de la Retina , Humanos , Tomografía de Coherencia Óptica/métodos , Enfermedades de la Retina/diagnóstico , Diagnóstico por Computador/métodos , ComputadoresRESUMEN
BACKGROUND: Magnetic resonance imaging (MRI) is commonly used in conjunction with a gadolinium-based contrast agent (GBCA) to distinguish active multiple sclerosis (MS) lesions. However, recent studies have raised concerns regarding the long-term effects of the accumulation of GBCA in the body. Thus, the purpose of this study is to investigate the possibility of using texture analysis in diffusion-weighted imaging (DWI) and machine learning algorithms to discriminate active from inactive MS lesions without the use of GBCA. METHODS: To achieve this purpose, we introduce an image processing pipeline. In the proposed pipeline, following registration and alignment of slices, MS lesions from DWI images are segmented and quantized. Next, different texture analysis methods are employed to extract texture features from the lesions. Then, a two-stage feature reduction method is applied, in which the first stage involves a statistical t-test and the second stage relies on principal component analysis (PCA), sequential forward selection (SFS), sequential backward selection (SBS), and ReliefF algorithms. Finally, we use five classifiers logistic regression (LR), support vector machine (SVM), decision tree (DT), K nearest neighbor (KNN), and linear discriminant analysis (LDA) in a 5-fold cross-validation procedure to determine active and inactive MS lesions. RESULTS: In this study, we collected and prepared 255 active/inactive MS lesions from MRI scans of 34 patients diagnosed with MS, with a mean age of 35.56±10.89. Among 89 texture features extracted, 63 features showed statistically significant differences between the means of active and inactive lesions (P<0.05). The SVM classifier with the PCA feature reduction algorithm demonstrated the best performance with an average accuracy of 0.960 (±0.024), specificity and precision of 1.0, sensitivity of 0.913 (±0.053), and AUC of 0.957 (±0.027). CONCLUSION: Our study indicates that DWI changes detected using texture analysis-based machine learning models can precisely differentiate active from inactive MS lesions. This finding provides valuable clinical information for the early diagnosis and effective monitoring of MS disease.
Asunto(s)
Imagen de Difusión por Resonancia Magnética , Esclerosis Múltiple , Humanos , Adulto Joven , Adulto , Persona de Mediana Edad , Estudios de Factibilidad , Imagen por Resonancia Magnética/métodos , Esclerosis Múltiple/diagnóstico por imagen , Aprendizaje AutomáticoRESUMEN
Artificial intelligence (AI) algorithms, encompassing machine learning and deep learning, can assist ophthalmologists in early detection of various ocular abnormalities through the analysis of retinal optical coherence tomography (OCT) images. Despite considerable progress in these algorithms, several limitations persist in medical imaging fields, where a lack of data is a common issue. Accordingly, specific image processing techniques, such as time-frequency transforms, can be employed in conjunction with AI algorithms to enhance diagnostic accuracy. This research investigates the influence of non-data-adaptive time-frequency transforms, specifically X-lets, on the classification of OCT B-scans. For this purpose, each B-scan was transformed using every considered X-let individually, and all the sub-bands were utilized as the input for a designed 2D Convolutional Neural Network (CNN) to extract optimal features, which were subsequently fed to the classifiers. Evaluating per-class accuracy shows that the use of the 2D Discrete Wavelet Transform (2D-DWT) yields superior outcomes for normal cases, whereas the circlet transform outperforms other X-lets for abnormal cases characterized by circles in their retinal structure (due to the accumulation of fluid). As a result, we propose a novel transform named CircWave by concatenating all sub-bands from the 2D-DWT and the circlet transform. The objective is to enhance the per-class accuracy of both normal and abnormal cases simultaneously. Our findings show that classification results based on the CircWave transform outperform those derived from original images or any individual transform. Furthermore, Grad-CAM class activation visualization for B-scans reconstructed from CircWave sub-bands highlights a greater emphasis on circular formations in abnormal cases and straight lines in normal cases, in contrast to the focus on irrelevant regions in original B-scans. To assess the generalizability of our method, we applied it to another dataset obtained from a different imaging system. We achieved promising accuracies of 94.5% and 90% for the first and second datasets, respectively, which are comparable with results from previous studies. The proposed CNN based on CircWave sub-bands (i.e. CircWaveNet) not only produces superior outcomes but also offers more interpretable results with a heightened focus on features crucial for ophthalmologists.
Asunto(s)
Inteligencia Artificial , Tomografía de Coherencia Óptica , Tomografía de Coherencia Óptica/métodos , Redes Neurales de la Computación , Retina , AlgoritmosRESUMEN
PURPOSE: Quantitative measurement of various anatomical regions of the brain and spinal cord (SC) in MRI images are used as unique biomarkers to consider progress and effects of demyelinating diseases of the central nervous system. This paper presents a fully-automated image processing pipeline which quantifies the SC volume of MRI images. METHODS: In the proposed pipeline, after conducting some pre-processing tasks, a deep convolutional network is utilized to segment the spinal cord cross-sectional area (SCCSA) of each slice. After full segmentation, certain extra slices interpolate between each two adjacent slices using the shape-based interpolation method. Then, a 3D model of the SC is reconstructed, and, by counting the voxels of it, the SC volume is calculated. The performance of the proposed method for the SCCSA segmentation is evaluated on 140 MRI images. Subsequently, to demonstrate the application of the proposed pipeline, we study the differentiations of SC atrophy between 38 Multiple Sclerosis (MS) and 25 Neuromyelitis Optica Spectrum Disorder (NMOSD) patients. RESULTS: The experimental results of the SCCSA segmentation indicate that the proposed method, adapted by Mask R-CNN, presented the most satisfactory result with the average Dice coefficient of 0.96. For this method, statistical metrics including sensitivity, specificity, accuracy, and precision are 97.51%, 99.98%, 99.92%, and 98.04% respectively. Moreover, the t-test result (p-value = 0.00089) verified a significant difference between the SC atrophy of MS and NMOSD patients. CONCLUSION: The pipeline efficiently quantifies the SC volume of MRI images and can be utilized as an affordable computer-aided tool for diagnostic purposes.
Asunto(s)
Aprendizaje Profundo , Esclerosis Múltiple , Neuromielitis Óptica , Atrofia/diagnóstico por imagen , Atrofia/patología , Humanos , Procesamiento de Imagen Asistido por Computador , Imagen por Resonancia Magnética , Esclerosis Múltiple/diagnóstico por imagen , Esclerosis Múltiple/patología , Neuromielitis Óptica/patología , Médula Espinal/diagnóstico por imagenRESUMEN
PURPOSE: To quantitatively analyze the C2/C3 segments of the spinal cord on magnetic resonance imaging (MRI) scans of neuromyelitis optica spectrum disorder (NMOSD) and relapsing-remitting multiple sclerosis (RRMS) patients in their first five years of the disease and to investigate the intergroup differences regarding markers of spinal cord atrophy and their correlations with expanded disability status scale (EDSS). MATERIALS AND METHODS: Twenty NMOSD patients and twenty RRMS patients, within their first five years of the disease, were enrolled in this cross-sectional study. All patients underwent spinal cord MR imaging using 1.5 Tesla systems, and C2/C3 portions of the spinal cord were segmented in the obtained scans. C2/C3 anteroposterior diameter (C2/C3 SC-APD), transversal diameter (C2/C3 SC-TD), and cross-sectional area (C2/C3 SC-CSA) were quantitatively measured using Spinal Cord Toolbox v.4.3. RESULTS: Three NMOSD patients were seropositive for anti-AQP4 IgG. The mean C2/C3 SC-CSA in NMOSD patients was significantly lower than in RRMS patients. NMOSD patients had significantly lower C2/C3 SC-TDs than RRMS patients. With the three anti-AQP4+ patients excluded from the analysis, C2/C3 SC-TD was negatively correlated with EDSS. CONCLUSION: In the early stages of the disease, quantitative evaluation of C2/C3 spinal cord parameters, including cross-sectional area and transversal diameter in NMOSD patients, appears to be of potential diagnostic and prognostic value.
RESUMEN
This paper presents a simple and efficient computer-aided diagnosis method to classify Chronic Myeloid Leukemia (CML) cells based on microscopic image processing. In the proposed method, a novel combination of both typical and new features is introduced for classification of CML cells. Next, an effective decision tree classifier is proposed to classify CML cells into eight groups. The proposed method was evaluated on 1730 CML cell images containing 714 cells of non-cancerous bone marrow aspiration and 1016 cells of cancerous peripheral blood smears. The performance of the proposed classification method was compared to manual labels made by two experts. The average values of accuracy, specificity and sensitivity were 99.0 %, 99.4 % and 98.3 %, respectively for all groups of CML. In addition, Cohen's kappa coefficient demonstrated high conformity, 0.99, between joint diagnostic results of two experts and the obtained results of the proposed approach. According to the obtained results, the suggested method has a high capability to classify effective cells of CML and can be applied as a simple, affordable and reliable computer-aided diagnosis tool to help pathologists to diagnose CML.
RESUMEN
BACKGROUND: Cancer is a complex disease which can engages the immune system of the patient. In this regard, determination of distinct immunosignatures for various cancers has received increasing interest recently. However, prediction accuracy and reproducibility of the computational methods are limited. In this article, we introduce a robust method for predicting eight types of cancers including astrocytoma, breast cancer, multiple myeloma, lung cancer, oligodendroglia, ovarian cancer, advanced pancreatic cancer, and Ewing sarcoma. METHODS: In the proposed scheme, at first, the database is normalized with a dictionary of normalization methods that are combined with particle swarm optimization (PSO) for selecting the best normalization method for each feature. Then, statistical feature selection methods are used to separate discriminative features and they were further improved by PSO with appropriate weights as the inputs of the classification system. Finally, the support vector machines, decision tree, and multilayer perceptron neural network were used as classifiers. RESULTS: The performance of the hybrid predictor was assessed using the holdout method. According to this method, the minimum sensitivity, specificity, precision, and accuracy of the proposed algorithm were 92.4 ± 1.1, 99.1 ± 1.1, 90.6 ± 2.1, and 98.3 ± 1.0, respectively, among the three types of classification that are used in our algorithm. CONCLUSION: The proposed algorithm considers all the circumstances and works with each feature in its special way. Thus, the proposed algorithm can be used as a promising framework for cancer prediction with immunosignature.
RESUMEN
BACKGROUND: Claustrophobia or fear of closed spaces is the most common of phobias that is typically categorized as an anxiety disorder. Different methods have been proposed for treatment of phobias that one of the most recent and successful of these methods is applying virtual reality (VR) technology and simulating computer-generated environment. In this regard, the purpose of this research is design and development of a software game called "Claustrophobia Game" for treatment of claustrophobia using VR. METHODS: In the Claustrophobia Game project, two closed spaces, including an elevator and a magnetic resonance imaging (MRI) device, were designed and implemented in the form of a VR computer game. To design this game, environments and scenario of the game were prepared in collaboration with a psychiatrist expert. Implementation of the software game was developed in the unity three-dimensional (3D) game engine and the programming of it was done by the C# language. In addition, a personal computer and the Oculus Rift VR glasses were utilized for running and testing the Claustrophobia Game. RESULTS: To evaluate, we tested the game by 33 participants (14 men, 19 women, average age 24.6 years). In this regard, the Claustrophobia Game was considered from two aspects: psychology and playability using two questionnaires. Statistical analysis of the obtained data by the Excel software showed that all playability factors were "good" performance. In addition, the mean of obvious anxiety was decreased after playing the game. CONCLUSION: The promising results demonstrate that the game has an appropriate performance and can help to treat the Claustrophobia.
RESUMEN
Vulvovaginal candidiasis (VVC) is a common gynecologic infection and it occurs when there is overgrowth of the yeast called Candida. VVC diagnosis is usually done by observing a Pap smear sample under a microscope and searching for the conidium and mycelium components of Candida. This manual method is time consuming, subjective and tedious. Any diagnosis tools that detect VVC, semi- or full-automatically, can be very helpful to pathologists. This article presents a computer aided diagnosis (CAD) software to improve human diagnosis of VVC from Pap smear samples. The proposed software is designed based on phenotypic and morphology features of the Candida in Pap smear sample images. This software provide a user-friendly interface which consists of a set of image processing tools and analytical results that helps to detect Candida and determine severity of illness. The software was evaluated on 200 Pap smear sample images and obtained specificity of 91.04% and sensitivity of 92.48% to detect VVC. As a result, the use of the proposed software reduces diagnostic time and can be employed as a second objective opinion for pathologists.
Asunto(s)
Candidiasis Vulvovaginal/diagnóstico , Diagnóstico por Computador/métodos , Prueba de Papanicolaou/estadística & datos numéricos , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Micelio/citología , Sensibilidad y Especificidad , Programas Informáticos , Esporas Fúngicas/citología , Vagina/microbiologíaRESUMEN
A mosaiced image is the result of merging two or more images with overlapping area in order to generate a high resolution panorama of a large scene. A wide view of Optical Coherence Tomography (OCT) images can help clinicians in diagnosis by enabling simultaneous analysis of different portions of the gathered information. In this paper, we present a novel method for mosaicing of 3D OCT images of macula and Optic Nerve Head (ONH) that is carried out in two phases; registration of OCT projections and mosaicing of B-scans. In the first phase, in order to register the OCT projection images of macula and ONH, their corresponding color fundus image is considered as the main frame and the geometrical features of their curvelet-based extracted vessels are employed for registration. The registration parameters obtained are then applied on all x-y slices of the 3D OCT images of macula and ONH. In the B-scan mosaicing phase, the overlapping areas of corresponding reprojected B-scans are extracted and the best registration model is obtained based on line-by-line matching of corresponding A-scans in overlapping areas. This registration model is then applied to the remaining A-scans of the ONH-based B-scan. The aligned B-scans of macular OCT and OCT images of ONH are finally blended and 3D mosaiced OCT images are obtained. Two criteria are considered for assessment of mosaiced images; the quality of alignment/mosaicing of B-scans and the loss of clinical information from the B-scans after mosaicing. The average grading values of 3.5 ± 0.74 and 3.63 ± 0.55 (out of 4) are obtained for the first and second criteria, respectively.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Mácula Lútea/diagnóstico por imagen , Disco Óptico/diagnóstico por imagen , Tomografía de Coherencia Óptica/métodos , Algoritmos , HumanosRESUMEN
Recognition of white blood cells (WBCs) is the first step to diagnose some particular diseases such as acquired immune deficiency syndrome, leukemia, and other blood-related diseases that are usually done by pathologists using an optical microscope. This process is time-consuming, extremely tedious, and expensive and needs experienced experts in this field. Thus, a computer-aided diagnosis system that assists pathologists in the diagnostic process can be so effective. Segmentation of WBCs is usually a first step in developing a computer-aided diagnosis system. The main purpose of this paper is to segment WBCs from microscopic images. For this purpose, we present a novel combination of thresholding, k-means clustering, and modified watershed algorithms in three stages including (1) segmentation of WBCs from a microscopic image, (2) extraction of nuclei from cell's image, and (3) separation of overlapping cells and nuclei. The evaluation results of the proposed method show that similarity measures, precision, and sensitivity respectively were 92.07, 96.07, and 94.30% for nucleus segmentation and 92.93, 97.41, and 93.78% for cell segmentation. In addition, statistical analysis presents high similarity between manual segmentation and the results obtained by the proposed method.
RESUMEN
This paper presents a fully automated approach to detect the intima and media-adventitia borders in intravascular ultrasound images based on parametric active contour models. To detect the intima border, we compute a new image feature applying a combination of short-term autocorrelations calculated for the contour pixels. These feature values are employed to define an energy function of the active contour called normalized cumulative short-term autocorrelation. Exploiting this energy function, the intima border is separated accurately from the blood region contaminated by high speckle noise. To extract media-adventitia boundary, we define a new form of energy function based on edge, texture and spring forces for the active contour. Utilizing this active contour, the media-adventitia border is identified correctly even in presence of branch openings and calcifications. Experimental results indicate accuracy of the proposed methods. In addition, statistical analysis demonstrates high conformity between manual tracing and the results obtained by the proposed approaches.