Recent studies show that pulmonary vascular diseases may specifically affect arteries or veins through different physiologic mechanisms. To detect changes in the two vascular trees, physicians ...manually analyze the chest computed tomography (CT) image of the patients in search of abnormalities. This process is time consuming, difficult to standardize, and thus not feasible for large clinical studies or useful in real-world clinical decision making. Therefore, automatic separation of arteries and veins in CT images is becoming of great interest, as it may help physicians to accurately diagnose pathological conditions. In this paper, we present a novel, fully automatic approach to classify vessels from chest CT images into arteries and veins. The algorithm follows three main steps: first, a scale-space particles segmentation to isolate vessels; then a 3-D convolutional neural network (CNN) to obtain a first classification of vessels; finally, graph-cuts' optimization to refine the results. To justify the usage of the proposed CNN architecture, we compared different 2-D and 3-D CNNs that may use local information from bronchus- and vessel-enhanced images provided to the network with different strategies. We also compared the proposed CNN approach with a random forests (RFs) classifier. The methodology was trained and evaluated on the superior and inferior lobes of the right lung of 18 clinical cases with noncontrast chest CT scans, in comparison with manual classification. The proposed algorithm achieves an overall accuracy of 94%, which is higher than the accuracy obtained using other CNN architectures and RF. Our method was also validated with contrast-enhanced CT scans of patients with chronic thromboembolic pulmonary hypertension to demonstrate that our model generalizes well to contrast-enhanced modalities. The proposed method outperforms state-of-the-art methods, paving the way for future use of 3-D CNN for artery/vein classification in CT images.
Background and objectives The scarcity of data for training deep learning models in pediatrics has prompted questions about the feasibility of employing CNNs trained with adult images for pediatric ...populations. In this work, a pneumonia classification CNN was used as an exploratory example to showcase the adaptability and efficacy of such models in pediatric healthcare settings despite the inherent data constraints. Methods To develop a curated training dataset with reduced biases, 46,947 chest X-ray images from various adult datasets were meticulously selected. Two preprocessing approaches were tried to assess the impact of thoracic segmentation on model attention outside the thoracic area. Evaluation of our approach was carried out on a dataset containing 5,856 chest X-rays of children from 1 to 5 years old. Results An analysis of attention maps indicated that networks trained with thorax segmentation placed less attention on regions outside the thorax, thus eliminating potential bias. The ensuing network exhibited impressive performance when evaluated on an adult dataset, achieving a pneumonia discrimination AUC of 0.95. When tested on a pediatric dataset, the pneumonia discrimination AUC reached 0.82. Conclusions The results of this study show that adult-trained CNNs can be effectively applied to pediatric populations. This could potentially shift focus towards validating adult models over pediatric population instead of training new CNNs with limited pediatric data. To ensure the generalizability of deep learning models, it is important to implement techniques aimed at minimizing biases, such as image segmentation or low-quality image exclusion.
Peripheral lung nodules remain challenging for accurate localization and diagnosis. Once identified, there are many strategies for diagnosis with heterogeneous risk benefit analysis. Traditional ...strategies such as conventional bronchoscopy have poor performance in locating and acquiring the required tissue. Similarly, while computerized-assisted transthoracic needle biopsy is currently the favored diagnostic procedure, it is associated with complications such as pneumothorax and hemorrhage. Video-assisted thoracoscopic and open surgical biopsies are invasive, require general anesthesia and are therefore not a first-line approach. New techniques such as ultrathin bronchoscopy and image-based guidance technologies are evolving to improve the diagnosis of peripheral lung lesions. Virtual bronchoscopy and electromagnetic navigation systems are novel technologies based on assisted-computerized tomography images that guide the bronchoscopist toward the target peripheral lesion. This article provides a comprehensive review of these emerging technologies.
Cryptocurrencies are a novel phenomenon in the finance world that is gaining more attention from the general public, banks, investors, and academic research lately. A characteristic of ...cryptocurrencies is to be the target of investments that, due to the volatility of most of the cryptocurrencies, tends to be at high risk and behave very differently from traditional currencies. A way of reducing this risk is to look at the history of existing cryptocurrencies and compare them to spot promising trends for increased gain. This paper introduces CryptoComparator, a Visual Analytics tool designed to analyze the correlations and trends of cryptocurrencies. The system exploits an initial proposal for a double elliptic graph layout, reconfigurable with three different ordering functions, to support a fast visual search of cryptocurrencies by correlation strength. Two use cases developed with a domain expert in cryptocurrency financial activities demonstrate qualitatively the support it provides for analyzing cryptocurrencies.
Display omitted
•A visual analytics solution for interactive analysis of cryptocurrencies.•Novel double ellipse graph layout.•Different graph orderings for correlation-based grouping of cryptocurrencies.•Correlation stability score to help the user in decision-making.•Two use cases on helping reducing volatility and building a crypto-wallet.
•Deep learning enables accurate and precise measurement of pulmonary airways and vessels.•Deep learning applied to bronchial and vascular trees outperforms traditional measurement techniques.•Pi10 ...measured with deep-learning technique improves correlation to FEV1%pred.•Total blood volume and blood volume of vessels < 5mm 2 computed from deep-learning vessel measurement correlates to DLCO.
Display omitted
Accurately and precisely characterizing the morphology of small pulmonary structures from Computed Tomography (CT) images, such as airways and vessels, is becoming of great importance for diagnosis of pulmonary diseases. The smaller conducting airways are the major site of increased airflow resistance in chronic obstructive pulmonary disease (COPD), while accurately sizing vessels can help identify arterial and venous changes in lung regions that may determine future disorders. However, traditional methods are often limited due to image resolution and artifacts.
We propose a Convolutional Neural Regressor (CNR) that provides cross-sectional measurement of airway lumen, airway wall thickness, and vessel radius. CNR is trained with data created by a generative model of synthetic structures which is used in combination with Simulated and Unsupervised Generative Adversarial Network (SimGAN) to create simulated and refined airways and vessels with known ground-truth.
For validation, we first use synthetically generated airways and vessels produced by the proposed generative model to compute the relative error and directly evaluate the accuracy of CNR in comparison with traditional methods. Then, in-vivo validation is performed by analyzing the association between the percentage of the predicted forced expiratory volume in one second (FEV1%) and the value of the Pi10 parameter, two well-known measures of lung function and airway disease, for airways. For vessels, we assess the correlation between our estimate of the small-vessel blood volume and the lungs’ diffusing capacity for carbon monoxide (DLCO).
The results demonstrate that Convolutional Neural Networks (CNNs) provide a promising direction for accurately measuring vessels and airways on chest CT images with physiological correlates.
Bronchiectasis is frequent in smokers with COPD; however, there are only limited data on objective assessments of this process. The objective was to assess bronchovascular morphology, calculate the ...ratio of the diameters of bronchial lumen and adjacent artery (BA ratio), and identify those measurements able to discriminate bronchiectasis.
We collected quantitative CT (QCT) measures of BA ratios, peak wall attenuation, wall thickness (WT), wall area, and wall area percent (WA%) at matched fourth through sixth airway generations in 21 ever smokers with bronchiectasis (cases) and 21 never-smoking control patients (control airways). In cases, measurements were collected at both bronchiectatic and nonbronchiectatic airways. Logistic analysis and the area under receiver operating characteristic curve (AUC) were used to assess the predictive ability of QCT measurements for bronchiectasis.
The whole-lung and fourth through sixth airway generation BA ratio, WT, and WA% were significantly greater in bronchiectasis cases than control patients. The AUCs for the BA ratio to predict bronchiectasis ranged from 0.90 (whole lung) to 0.79 (fourth-generation). AUCs for WT and WA% ranged from 0.72 to 0.75 and from 0.71 to 0.75. The artery diameters but not bronchial diameters were smaller in bronchiectatic than both nonbronchiectatic and control airways (P < .01 for both).
Smoking-related increases in the BA ratio appear to be driven by reductions in vascular caliber. QCT measures of BA ratio, WT, and WA% may be useful to objectively identify and quantify bronchiectasis in smokers.
ClinicalTrials.gov; No.: NCT00608764; URL: www.clinicaltrials.gov.
Abstract
The RestArt method is an innovative mechatronic-based procedure for high-precision reassembly of stone fragments intended to improve the restoration of ancient statues and architectural ...elements. The procedure comprises high-accuracy 3D laser scanning of two fragments positioned on the RestArt machine. After software simulated best-fitting of the two homologous fractured faces, the calculated roto-translation matrix is sent to the machine control system that moves one fragment to match the other one. The machine integrates a numeric-controlled moving drilling device for high-precision boring of the fractured surfaces at selected points for optimal rods insertion. This permits a very effective fixing of the fragments and allows multi-point fixing, which is practically impossible with conventional methods. Several stone specimens were experimentally recomposed through the RestArt and the traditional method. Then, they were compared in terms of mechanical resistance by shaking table tests, reproducing extreme strong-motion vibrations. The specimens recomposed through the RestArt method resulted less time-consuming and much more resistant to vibration excitation than the ones by traditional reassembly method. The RestArt method was applied to reassemble some original ancient statues currently exhibited at several Italian museums.