Current Issue : April - June Volume : 2019 Issue Number : 2 Articles : 6 Articles
Background. Atypical vascular pattern is one of the most important features by differentiating between benign and malignant\npigmented skin lesions. Detection and analysis of vascular structures is a necessary initial step for skin mole assessment; it is a\nprerequisite step to provide an accurate outcomefor thewidely used 7-point checklist diagnostic algorithm. Methods. In this research\nwe present a fully automated machine learning approach for segmenting vascular structures in dermoscopy colour images.The UNet\narchitecture is based on convolutional networks and designed for fast and precise segmentation of images. After preprocessing\nthe images are randomly divided into 146516 patches of 64 Ã? 64 pixels each. Results. On the independent validation dataset\nincluding 74 images our implemented method showed high segmentation accuracy. For the U-Net convolutional neural network,\nan average DSC of 0.84, sensitivity 0.85, and specificity 0.81 has been achieved. Conclusion. Vascular structures due to small size\nand similarity to other local structures create enormous difficulties during the segmentation and assessment process. The use of\nadvanced segmentation methods like deep learning, especially convolutional neural networks, has the potential to improve the\naccuracy of advanced local structure detection....
Background: Accurately detecting and examining lung nodules early is key in diagnosing lung cancers and thus\none of the best ways to prevent lung cancer deaths. Radiologists spend countless hours detecting small\nspherical-shaped nodules in computed tomography (CT) images. In addition, even after detecting nodule candidates,\na considerable amount of effort and time is required for them to determine whether they are real nodules. The aim of\nthis paper is to introduce a high performance nodule classification method that uses three dimensional deep\nconvolutional neural networks (DCNNs) and an ensemble method to distinguish nodules between non-nodules.\nMethods: In this paper, we use a three dimensional deep convolutional neural network (3D DCNN) with shortcut\nconnections and a 3D DCNN with dense connections for lung nodule classification. The shortcut connections and\ndense connections successfully alleviate the gradient vanishing problem by allowing the gradient to pass quickly and\ndirectly. Connections help deep structured networks to obtain general as well as distinctive features of lung nodules.\nMoreover, we increased the dimension of DCNNs from two to three to capture 3D features. Compared with shallow\n3D CNNs used in previous studies, deep 3D CNNs more effectively capture the features of spherical-shaped nodules.\nIn addition, we use an alternative ensemble method called the checkpoint ensemble method to boost performance.\nResults: The performance of our nodule classification method is compared with that of the state-of-the-art methods\nwhich were used in the LUng Nodule Analysis 2016 Challenge. Our method achieves higher competition\nperformance metric (CPM) scores than the state-of-the-art methods using deep learning. In the experimental setup\nESB-ALL, the 3D DCNN with shortcut connections and the 3D DCNN with dense connections using the checkpoint\nensemble method achieved the highest CPM score of 0.910.\nConclusion: The result demonstrates that our method of using a 3D DCNN with shortcut connections, a 3D DCNN\nwith dense connections, and the checkpoint ensemble method is effective for capturing 3D features of nodules and\ndistinguishing nodules between non-nodules....
Background: Diffusion weighted imaging (DWI) has a good diagnostic value for malignant thyroid nodules, but\nthe published protocols suffer from flaws and focus on the apparent diffusion coefficient (ADC). This study\ninvestigated the diagnostic performance of multiple MRI parameters in differentiating malignant from benign\nthyroid nodules.\nMethods: This was a retrospective study of 181 consecutive patients (148 benign and 111 malignant nodules,\nconfirmed by pathological results). The patients underwent conventional MRI, DWI, and dynamic contrast-enhanced\nMRI before surgery. The chi-square test and the Student t test were used to compare the conventional features\nand ADC value between malignant and benign groups. Multivariate logistic regression was used to identify the\nindependent predictors and to construct a model. Receiver operator characteristic (ROC) curve analysis was used\nto assess the diagnostic performance of the independent variables and model.\nResults: Tumor diameter, ADC value, cystic degeneration, pseudocapsule sign, high signal cystic area on T1-\nweighted imaging, ring sign in the delayed phase, and irregular shape showed significant differences between\ntwo groups (all P < 0.05). The multivariable analysis revealed that ADC value (OR = 694.006, P < 0.001), irregular\nshape (OR = 32.798, P < 0.001), ring sign in the delayed phase (OR = 20.381, P = 0.004), and cystic degeneration\n(OR = 8.468, P = 0.016) were independent predictors. Among them, ADC performed the best in discriminating\nbenign from malignant nodules, with an area under the curve (AUC) of 0.95, 0.90 sensitivity, and 0.91 specificity.\nWhen the independent factors were combined, the diagnostic performance was improved with an AUC of 0.99, 0.\n97 sensitivity, and 0.95 specificity.\nConclusions: ADC value could discriminate between benign and malignant thyroid nodules with a good\nperformance. Subjective features such as the ring sign, irregular shape, and cystic degeneration associated\nwith malignant thyroid nodules could provide complementary information for differentiation....
Background: The purpose of this study is to explore the potential of phase contrast\nimaging to detect fibrotic progress in its early stage; to investigate the feasibility of texture\nfeatures for quantified diagnosis of liver fibrosis; and to evaluate the performance\nof back propagation (BP) neural net classifier for characterization and classification of\nliver fibrosis.\nMethods: Fibrous mouse liver samples were imaged by X-ray phase contrast imaging,\nnine texture measures based on gray-level co-occurrence matrix were calculated\nand the feasibility of texture features in the characterization and discrimination of liver\nfibrosis at early stages was investigated. Furthermore, 36 or 18 features were applied to\nthe input of BP classifier; the classification performance was evaluated using receiver\noperating characteristic curve.\nResults: The phase contrast images displayed a vary degree of texture pattern from\nnormal to severe fibrosis stages. The BP classifier could distinguish liver fibrosis among\nnormal, mild, moderate and severe stages; the average accuracy was 95.1% for 36\nfeatures, and 91.1% for 18 features.\nConclusion: The study shows that early stages of liver fibrosis can be discriminated by\nthe morphological features on the phase contrast images. BP network model based on\ncombination of texture features is demonstrated effective for staging liver fibrosis....
Background: Chest X-ray is frequently performed for evaluation of chest\ndisease in both adults and children. Children are more exposed to the adverse\neffects of radiation as compared to adults. During our daily practice, we noticed\nthat most of childrenâ??s chest X-ray results were normal. Purpose: This\nstudy aimed to evaluate the indications, the technic, the irradiation and the\nresult of chest X-rays in children in order to know if the practice of these\nX-rays was relevant. Method: Cross-sectional and descriptive study conducted\nat the Imaging Regional Center of Ngaoundere from April to August\n2017. A total number of 145 radiographs and 140 X-ray requests of 140 children\nwere considered in this work. The conformity of the request were verified\naccording to the recommendations of the National Agency for Accreditation\nand Health Evaluation in France (NAAHE), technical condition of realization\nand results were appreciated and the entrance surface dose (ESD) of\nthe patients was estimated using a mathematical algorithm. Results: Children\nunder 5 years (63.5%) were more represented in our study. The main indications\nwere: cough (22.1%), suspicion of pneumonia (16.4%) and bronchitis\n(15.7%). No indication was mentioned on 69.3% of the request forms. After\nconfrontation to the â??Guide for proper use of medical imaging examinationsâ?\n(GPU), we only had 24% conformity of indications. 82.7% of the examinations\nrequired immobilization assistance by the parents. Most of the children\nwere imaged in a standing-up position (82.9%) and the anterior-posterior\nview (77.9%) was more practiced. After the analysis of the pictures, 62% of\nthem presented an optimal contrast, while 42.1% of X-ray were performed\nwithout beam collimation. 25 X-rays were repeated: 12 (48%) because of patientâ??s\nmotion and 13 (52%) of mispositionning. After interpretation, 87\n(62.14%) chest X-ray were normal. Main lesion observed were pneumonia (17.14%) followed by bronchopeumopathy (5.71%) and bronchitis (5%). The\nobtained ESD values were 0.11, 0.15 and 0.17 mGy respectively for the 0 - 1\nyear, 1 - 5 year and 5 - 10 year age groups; 0.2 and 0.57 respectively for postero-\nanterior (PA) and lateral (LAT) view for the age group 10 - 15 years,\nwhich were slightly greater than the values in internationally published studies.\nConclusion: The request for children chest X-ray is not relevant in terms\nof indication, technical conditions of realization and irradiation....
Background: Hereditary hemochromatosis is the most frequent, identified, genetic disorder in Caucasians affecting\nabout 1 in 1000 people of Northern European ancestry, where the associated genetic defect (homozygosity for the\np.Cys282Tyr polymorphism in the HFE gene) has a prevalence of approximately 1:200. The disorder is characterized\nby excess iron stores in the body. Due to the incomplete disease penetrance of disease-associated genotype,\ngenetic testing and accurate quantification of hepatic iron content by histological grading of stainable iron,\nquantitative chemical determination of iron, or imaging procedures are important in the evaluation and staging of\nhereditary hemochromatosis.\nMethods: We here established novel laser ablation inductively coupled plasma mass spectrometry protocols for\nhepatic metal bio-imaging for diagnosis of iron overload.\nResults: We demonstrate that these protocols are a significant asset in the diagnosis of iron overload allowing iron\nmeasurements and simultaneous determination of various other metals and metalloids with high sensitivity, spatial\nresolution, and quantification ability.\nConclusions: The simultaneous measurement of various metals and metalloids offers unique opportunities for\ndeeper understanding of metal imbalances. Laser ablation inductively coupled plasma mass spectrometry (LA-ICPMS)\nis a highly powerful and sensitive technique for the analysis of a variety of solid samples with high spatial\nresolution. We conclude that this method is an important add-on to routine diagnosis of iron overload and\nassociated hepatic metal dysbalances resulting thereof....
Loading....