Search results for: deep vein imaging

Authors: Yuanchao Sang, Zhihao Gong, Longsheng Chen, Long Chen

Abstract:

Clothing fashion represents a human’s aesthetic appreciation towards everyday outfits and appetite for fashion, and it reflects the development of status in society, humanity, and economics. However, modelling fashion by machine is extremely challenging because fashion is too abstract to be efficiently described by machines. Even human beings can hardly reach a consensus about fashion. In this paper, we are dedicated to answering a fundamental fashion-related problem: what image feature best describes clothing fashion? To address this issue, we have designed and evaluated various image features, ranging from traditional low-level hand-crafted features to mid-level style awareness features to various current popular deep neural network-based features, which have shown state-of-the-art performance in various vision tasks. In summary, we tested the following 9 feature representations: color, texture, shape, style, convolutional neural networks (CNNs), CNNs with distance metric learning (CNNs&DML), AutoEncoder, CNNs with multiple layer combination (CNNs&MLC) and CNNs with dynamic feature clustering (CNNs&DFC). Finally, we validated the performance of these features on two publicly available datasets. Quantitative and qualitative experimental results on both intra-domain and inter-domain fashion clothing image retrieval showed that deep learning based feature representations far outweigh traditional hand-crafted feature representation. Additionally, among all deep learning based methods, CNNs with explicit feature clustering performs best, which shows feature clustering is essential for discriminative fashion feature representation.

Keywords: convolutional neural network, feature representation, image processing, machine modelling

Procedia PDF Downloads 120

Authors: Bharatendra Rai

Abstract:

The sequence of words in text data has long-term dependencies and is known to suffer from vanishing gradient problems when developing deep learning models. Although recurrent networks such as long short-term memory networks help to overcome this problem, achieving high text classification performance is a challenging problem. Convolutional recurrent networks that combine the advantages of long short-term memory networks and convolutional neural networks can be useful for text classification performance improvements. However, arriving at suitable hyperparameter values for convolutional recurrent networks is still a challenging task where fitting a model requires significant computing resources. This paper illustrates the advantages of using convolutional recurrent networks for text classification with the help of statistically planned computer experiments for hyperparameter tuning.

Keywords: long short-term memory networks, convolutional recurrent networks, text classification, hyperparameter tuning, Tukey honest significant differences

Procedia PDF Downloads 100

Authors: A. Zecchin, E. Vallicella, I. Alberi, A. Dalle Carbonare, A. Festi, F. Galeone, S. Garzon, R. Raffaelli, P. Pomini, M. Franchi

Abstract:

Introduction: Severe endometriosis is a multiorgan disease, that involves bowel in 31% of cases. Disabling symptoms and deep infiltration can lead to bowel obstruction: surgical bowel treatment may be needed. In these cases, colorectal segment resection is usually performed by inferior mesenteric artery ligature, as radically as for oncological surgery. This study was made on surgery based on intestinal vascular axis’ preservation. It was assessed postoperative complications risks (mainly rate of dehiscence of intestinal anastomoses), and results were compared with the ones found in literature about classical colorectal resection. Materials and methods: This was a retrospective study based on 62 patients with deep infiltrating endometriosis of the bowel, which undergo segmental resection with intestinal vascular axis preservation, between 2013 and 2016. It was assessed complications related to the intervention both during hospitalization and 30-60 days after resection. Particular attention was paid to the presence of anastomotic dehiscence. 52 patients were finally telephonically interviewed in order to investigate the presence or absence of intestinal constipation. Results and Conclusion: Segmental intestinal resection performed in this study ensured a more conservative vascular approach, with lower rate of anastomotic dehiscence (1.6%) compared to classical literature data (10.0% to 11.4% ). No complications were observed regarding spontaneous recovery of intestinal motility and bladder emptying. Constipation in some patients, even after years of intervention, is not assessable in the absence of a preoperative constipation state assessment.

Keywords: anastomotic dehiscence, deep infiltrating endometriosis, colorectal resection, vascular axis preservation

Procedia PDF Downloads 182

Authors: Devendra Gupta, Vikash Arya, Prabhat K. Singh

Abstract:

Background: Ultrasound guidance could be beneficial in placing central venous catheters by improving the success rate, reducing the number of needle passes, and decreasing complications. Central venous cannulation set has a single puncture needle of a fixed length of 6.4 cm. However, the average distance of midpoint of IJV to the skin is around 1 cm to 2 cm. The long length needle has tendency to go in depth more than required and this is very common during learning period of any individual. Therefore, we devised a long needle with a guard which can be adjusted according to the required length. Methods: After approval from the institute ethics committee and patient’s written informed consent, a prospective, randomized, single-blinded controlled study was conducted. Adult patient aged of both sexes with ASA grade 1-2 undergoing surgery requiring internal jugular venous (IJV) access was included. After intubation, the head was rotated to the contralateral side at 30 degree head rotation on the position of the right IJV. The transducer probe a 6.5 to 13-MHz linear transducer (Sonosite, USA) had been placed at the apex of triangle with minimal pressure to avoid IJV compression. The distance from skin to midpoint of the right IJV and skin to anterior wall of Common Carotid Artery (CCA) had been done using B-mode duplex sonography with a 6.5 to 13-MHz linear transducer. Depending upon the results of randomization 420 patients had been divided into two groups of equal numbers (n=210). Group 1. USG guided right sided IJV cannulation was done with conventional (6.4 cm) needle; and Group 2. USG guided right sided IJV cannulation was done with conventional (6.4 cm) needle with guard fixed to a required length (length between skin and midpoint of IJV) by an experienced anesthesiologist. Independent observer has noted the number of attempts and occurrence of complications (CCA puncture, pneumothorax or adjacent tissue damage). Results: Demographic data were similar in both the group. The groups were comparable when considered for relationship of IJV to CCA. There was no significant difference between groups as regard to distance of midpoint of IJV to the skin (p<0.05). IJV cannulation was successfully done in single attempts in 180 (85.7%), in two attempts in 27 (12.9%) and three attempts in 3 (1.4%) in group I, whereas in single attempt in 207 (98.6%) and second attempts in 3 (1.4%) in group II (p <0.000). Incidence of carotid artery puncture was significantly more in group I (7.1%) compared to group II (0%) (p<0.000). Incidence of adjacent tissue puncture was significantly more in group I (8.6%) compared to group II (0%) (p<0.000). Conclusion: Therefore IJV catheterization using guard over the needle at predefined length with the help of real-time ultrasound results in better success rates and lower immediate complications.

Keywords: ultrasound guided, internal jugular vein cannulation, measured guided needle, common carotid artery puncture

Procedia PDF Downloads 201

Authors: Ying Han, Yuanxiang Chen, Yongtao Huang, Jia Fu, Kaile Li, Shangjing Lin, Jianguo Yu

Abstract:

In long-haul and high-speed optical transmission system, the orthogonal frequency division multiplexing (OFDM) signal suffers various linear and non-linear impairments. In recent years, researchers have proposed compensation schemes for specific impairment, and the effects are remarkable. However, different impairment compensation algorithms have caused an increase in transmission delay. With the widespread application of deep neural networks (DNN) in communication, multi-impairment compensation based on DNN will be a promising scheme. In this paper, we propose and apply DNN to compensate multi-impairment of 16-QAM coherent optical OFDM signal, thereby improving the performance of the transmission system. The trained DNN models are applied in the offline digital signal processing (DSP) module of the transmission system. The models can optimize the constellation mapping signals at the transmitter and compensate multi-impairment of the OFDM decoded signal at the receiver. Furthermore, the models reduce the peak to average power ratio (PAPR) of the transmitted OFDM signal and the bit error rate (BER) of the received signal. We verify the effectiveness of the proposed scheme for 16-QAM Coherent Optical OFDM signal and demonstrate and analyze transmission performance in different transmission scenarios. The experimental results show that the PAPR and BER of the transmission system are significantly reduced after using the trained DNN. It shows that the DNN with specific loss function and network structure can optimize the transmitted signal and learn the channel feature and compensate for multi-impairment in fiber transmission effectively.

Keywords: coherent optical OFDM, deep neural network, multi-impairment compensation, optical transmission

Procedia PDF Downloads 127

Authors: Seyedeh Bahar Hashemi, Alireza Rahimi, Mehdi Arjmand

Abstract:

Food is the source of energy and growth through the breakdown of its vital components and plays a vital role in human health and nutrition. Many natural compounds found in plant and animal materials play a special role in biological systems and the origin of many such compounds directly or indirectly is algae. Algae is an enormous source of polysaccharides and have gained much interest in human flourishing. In this study, algae biomass extraction is conducted using deep eutectic-based solvents (NADES) and Ultrasound-assisted extraction (UAE). The aim of this research is to extract bioactive compounds including total carotenoid, antioxidant activity, and polyphenolic contents. For this purpose, the influence of three important extraction parameters namely, biomass-to-solvent ratio, temperature, and time are studied with respect to their impact on the recovery of carotenoids, and phenolics, and on the extracts’ antioxidant activity. Here we employ the Response Surface Methodology for the process optimization. The influence of the independent parameters on each dependent is determined through Analysis of Variance. Our results show that Ultrasound-assisted extraction (UAE) for 50 min is the best extraction condition, and proline:lactic acid (1:1) and choline chloride:urea (1:2) extracts show the highest total phenolic contents (50.00 ± 0.70 mgGAE/gdw) and antioxidant activity [60.00 ± 1.70 mgTE/gdw, 70.00 ± 0.90 mgTE/gdw in 2.2-diphenyl-1-picrylhydrazyl (DPPH), and 2.2′-azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) (ABTS)]. Our results confirm that the combination of UAE and NADES provides an excellent alternative to organic solvents for sustainable and green extraction and has huge potential for use in industrial applications involving the extraction of bioactive compounds from algae. This study is among the first attempts to optimize the effects of ultrasonic-assisted extraction, ultrasonic devices, and deep natural eutectic point and investigate their application in bioactive compounds extraction from algae. We also study the future perspective of ultrasound technology which helps to understand the complex mechanism of ultrasonic-assisted extraction and further guide its application in algae.

Keywords: natural deep eutectic solvents, ultrasound-assisted extraction, algae, antioxidant activity, phenolic compounds, carotenoids

Procedia PDF Downloads 150

Authors: Reem El Chakik

Abstract:

The levels of heavy metals in agricultural lands in Lebanon have been witnessing a noticeable increase in the past few years, due to increased anthropogenic pollution sources. Heavy metals pose a serious threat to the environment for being non-biodegradable and persistent, accumulating thus to dangerous levels in the soil. Besides the traditional laboratory and chemical analysis methods, Hyperspectral Imaging (HSI) has proven its efficiency in the rapid detection of HMs contamination. In Lebanon, a continuous environmental monitoring, including the monitoring of levels of HMs in agricultural soils, is lacking. This is due in part to the high cost of analysis. Hence, this proposed research aims at defining the current national status of HMs contamination in agricultural soil, and to evaluate the effectiveness of using HSI in the detection of HM in contaminated agricultural fields. To achieve the two main objectives of this study, soil samples were collected from different areas throughout the country and were analyzed for HMs using Atomic Absorption Spectrophotometry (AAS). The results were compared to those obtained from the HSI technique that was applied using Hyspex SWIR-384 camera. The results showed that the Lebanese agricultural soils contain high contamination levels of Zn, and that the more clayey the soil is, the lower reflectance it has.

Keywords: agricultural soils in Lebanon, atomic absorption spectrophotometer, hyperspectral imaging., heavy metals contamination

Procedia PDF Downloads 93

Authors: Angelis P. Barlampas

Abstract:

Target: The (SARS-CoV-2) is still a threat. AI software could be useful, categorizing the disease into different severities and indicate the extent of the lesions. Materials and methods: AI is a new revolutionary technique, which uses powered computerized systems, to do what a human being does more rapidly, more easily, as accurate and diagnostically safe as the original medical report and, in certain circumstances, even better, saving time and helping the health system to overcome problems, such as work overload and human fatigue. Results: It will be given an effort to describe to the inexperienced reader (see figures), as simple as possible, how an artificial intelligence system diagnoses computed tomography pictures. First, the computerized machine learns the physiologic motives of lung parenchyma by being feeded with normal structured images of the lung tissue. Having being used to recognizing normal structures, it can then easily indentify the pathologic ones, as their images do not fit to known normal picture motives. It is the same way as when someone spends his free time in reading magazines with quizzes, such as <> and <>. General conclusion: The AI mimics the physiological processes of the human mind, but it does that more efficiently and rapidly and provides results in a few seconds, whereas an experienced radiologist needs many days to do that, or even worse, he is unable to accomplish such a huge task.

Keywords: covid-19, artificial intelligence, automated imaging, CT, chest imaging

Procedia PDF Downloads 37

Authors: A. Abdelnasser, M. Kumral, B. Zoheir, P. Weihed, M. Budakoglu, L. Gumus

Abstract:

Atud gold deposits located at the central part of the Egyptian Eastern Desert of Egypt. It represents the vein-type gold mineralization at the Arabian-Nubian Shield in North Africa. Furthermore, this Au mineralization was closely associated with intense hydrothermal alteration haloes along the NW-SE brittle-ductile shear zone at the mined area. This study reports new data about the mineral chemistry of the hydrothermal and metamorphic minerals as well as the geothermobarometry of the metamorphism and determines the paragenetic interrelationship between Au-bearing sulfides and gangue minerals in Atud gold mine by using the electron microprobe analyses (EMPA). These analyses revealed that the ore minerals associated with gold mineralization are arsenopyrite, pyrite, chalcopyrite, sphalerite, pyrrhotite, tetrahedrite and gersdorffite-cobaltite. Also, the gold is highly associated with arsenopyrite and As-bearing pyrite as well as sphalerite with an average ~70 wt.% Au (+26 wt.% Ag) whereas it occurred either as disseminated grains or along microfractures of arsenopyrite and pyrite in altered wallrocks and mineralized quartz veins. Arsenopyrite occurs as individual rhombic or prismatic zoned grains disseminated in the quartz veins and wallrock and is intergrown with euhedral arsenian pyrite (with ~2 atom % As). Pyrite is As-bearing pyrite that occurs as disseminated subhedral or anhedral zoned grains replacing by chalcopyrite in some samples. Inclusions of sphalerite and pyrrhotite are common in the large pyrite grains. Secondary minerals such as sericite, calcite, chlorite and albite are disseminated either in altered wallrocks or in quartz veins. Sericite is the main secondary and alteration mineral associated with Au-bearing sulfides and calcite. Electron microprobe data of the sericite show that its muscovite component is high in all analyzed flakes (XMs= an average 0.89) and the phengite content (Mg+Fe a.p.f.u.) varies from 0.10 to 0.55 and from 0.13 to 0.29 in wallrocks and mineralized veins respectively. Carbonate occurs either as thin veinlets or disseminated grains in the mineralized quartz vein and/or the wallrocks. It has higher amount of calcite (CaCO3) and low amount of MgCO3 as well as FeCO3 in the wallrocks relative to the quartz veins. Chlorite flakes are associated with arsenopyrite and their electron probe data revealed that they are generally Fe-rich composition (FeOt 20.64–20.10 wt.%) and their composition is clinochlore either pycnochlorite or ripidolite with Al (iv) = 2.30-2.36 pfu and 2.41-2.51 pfu and with narrow range of estimated formation temperatures are (289–295°C) and (301-312°C) for pycnochlorite and ripidolite respectively. Albite is accompanied with chlorite with an Ab content is high in all analyzed samples (Ab= 95.08-99.20).

Keywords: micro-analytical data, mineral chemistry, EMPA, Atud gold deposit, Egypt

Procedia PDF Downloads 311

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 196

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 296

Authors: Allaire Eric, Hauet Pascal, Floresco Jean, Beley Sebastien, Sussman Helene, Virag Ronald

Abstract:

Background: Caverno-venous leakage (CVL) is devastating, although barely known disease, the first cause of major physical impairment in men under 25, and responsible for 50% of resistances to phosphodiesterase 5-inhibitors (PDE5-I), affecting 30 to 40% of users in this medication class. In this condition, too early blood drainage from corpora cavernosa prevents penile rigidity and penetration during sexual intercourse. The role of conservative surgery in this disease remains controversial. Aim: Assess complications and results of combined open surgery and embolization for CVL. Method: Between June 2016 and September 2021, 133 consecutive patients underwent surgery in our institution for CVL, causing severe erectile dysfunction (ED) resistance to oral medical treatment. Procedures combined vein embolization and ligation with microsurgical techniques. We performed a pre-and post-operative clinical (Erection Harness Scale: EHS) hemodynamic evaluation by duplex sonography in all patients. Before surgery, the CVL network was visualized by computed tomography cavernography. Penile EMG was performed in case of diabetes or suspected other neurological conditions. All patients were optimized for hormonal status—data we prospectively recorded. Results: Clinical signs suggesting CVL were ED since age lower than 25, loss of erection when changing position, penile rigidity varying according to the position. Main complications were minor pulmonary embolism in 2 patients, one after airline travel, one with Factor V Leiden heterozygote mutation, one infection and three hematomas requiring reoperation, one decreased gland sensitivity lasting for more than one year. Mean pre-operative pharmacologic EHS was 2.37+/-0.64, mean pharmacologic post-operative EHS was 3.21+/-0.60, p<0.0001 (paired t-test). The mean EHS variation was 0.87+/-0.74. After surgery, 81.5% of patients had a pharmacologic EHS equal to or over 3, allowing for intercourse with penetration. Three patients (2.2%) experienced lower post-operative EHS. The main cause of failure was leakage from the deep dorsal aspect of the corpus cavernosa. In a 14 months follow-up, 83.2% of patients had a clinical EHS equal to or over 3, allowing for sexual intercourse with penetration, one-third of them without any medication. 5 patients had a penile implant after unsuccessful conservative surgery. Conclusion: Open surgery combined with embolization for CVL is an efficient approach to CVL causing severe erectile dysfunction.

Keywords: erectile dysfunction, cavernovenous leakage, surgery, embolization, treatment, result, complications, penile duplex sonography

Procedia PDF Downloads 128

Authors: Hossam Abdelrahman, Sama Rostom, Reem Yassein, Yara Mohamed, Salma Salah, Nour Awny

Abstract:

In today’s environment, people are becoming increasingly interested in their appearance. However, they are afraid of their unknown appearance after a plastic surgery or treatment. Accidents, burns and genetic problems such as bowing of body parts of people have a negative impact on their mental health with their appearance and this makes them feel uncomfortable and underestimated. The approach presents a revolutionary deep learning-based image inpainting method that analyses the various picture structures and corrects damaged images. In this study, A model is proposed based on the in-painting of medical images with Stable Diffusion Inpainting method. Reconstructing missing and damaged sections of an image is known as image inpainting is a key progress facilitated by deep neural networks. The system uses the input of the user of an image to indicate a problem, the system will then modify the image and output the fixed image, facilitating for the patient to see the final result.

Keywords: generative adversarial network, large mask inpainting, stable diffusion inpainting, plastic surgery

Procedia PDF Downloads 52

Authors: Mona Hassan Aburahma, Alaa Hamed Salama

Abstract:

Ufasomes “unsaturated fatty acids liposomes” are unique nano-sized self-assembled bilayered vesicles that can be easily created from the readily available unsaturated fatty acid. Ufasomes are formed due to weak associative interaction of the fully ionized and unionized fatty acids into bilayers structures. In the ufasomes constructs, the fatty acid molecules are oriented with their hydrocarbon tails directed toward the membrane interior and the carboxyl groups are in contact with water. Although ufasomes can be employed as a safe vesicular carrier for drugs, the extreme instability of their aqueous dispersions hinders their effective use in drug delivery field. Accordingly, in our study, lyophilized gels containing ufasomes were prepared using a simple assembling technique form the readily available oleic acid to overcome the colloidal instability of the ufasomes dispersions and convert them into accurate unit dosage forms. The influence of changing cholesterol percentage relative to oleic acid on the ufasomes vesicles were investigated using factorial design. The optimized oleic acid ufasomes comprised nanoscaled spherical vesicles. Scanning electron micrographs of the lyophilized gels revealed that the included ufasomes were intact, non-aggregating, and preserved their spherical morphology. Rheological characterization (viscosity and shear stress versus shear rate) of reconstituted ufasomal lyophilized gel ensured the ease of application. The capability of the ufasomes, included in the gel, to penetrate deep through the mucosa layers was illustrated using ex-vivo confocal laser imaging, thereby, highlighting the feasibility of stabilizing ufasomes using lyophilized gel platforms.

Keywords: ufasomes, lyophilized gel, confocal scanning microscopy, rheological characterization, oleic acid

Procedia PDF Downloads 391

Authors: Jiaying Zhang, Xin Mu, Chang Ni, Jeff L. Zhang

Abstract:

Magnetic resonance elastography (MRE) non-invasively assesses tissue elastic properties, such as shear modulus, by measuring tissue’s displacement in response to mechanical waves. The estimated metrics on tissue elasticity or stiffness have been shown to be valuable for monitoring physiologic or pathophysiologic status of tissue, such as a tumor or fatty liver. To quantify tissue shear modulus from MRE-acquired displacements (essentially an inverse problem), multiple approaches have been proposed, including Local Frequency Estimation (LFE) and Direct Inversion (DI). However, one common problem with these methods is that the estimates are severely noise-sensitive due to either the inverse-problem nature or noise propagation in the pixel-by-pixel process. With the advent of deep learning (DL) and its promise in solving inverse problems, a few groups in the field of MRE have explored the feasibility of using DL methods for quantifying shear modulus from MRE data. Most of the groups chose to use real MRE data for DL model training and to cut training images into smaller patches, which enriches feature characteristics of training data but inevitably increases computation time and results in outcomes with patched patterns. In this study, simulated wave images generated by Finite Differential Time Domain (FDTD) simulation are used for network training, and U-Net is used to extract features from each training image without cutting it into patches. The use of simulated data for model training has the flexibility of customizing training datasets to match specific applications. The proposed method aimed to estimate tissue shear modulus from MRE data with high robustness to noise and high model-training efficiency. Specifically, a set of 3000 maps of shear modulus (with a range of 1 kPa to 15 kPa) containing randomly positioned objects were simulated, and their corresponding wave images were generated. The two types of data were fed into the training of a U-Net model as its output and input, respectively. For an independently simulated set of 1000 images, the performance of the proposed method against DI and LFE was compared by the relative errors (root mean square error or RMSE divided by averaged shear modulus) between the true shear modulus map and the estimated ones. The results showed that the estimated shear modulus by the proposed method achieved a relative error of 4.91%±0.66%, substantially lower than 78.20%±1.11% by LFE. Using simulated data, the proposed method significantly outperformed LFE and DI in resilience to increasing noise levels and in resolving fine changes of shear modulus. The feasibility of the proposed method was also tested on MRE data acquired from phantoms and from human calf muscles, resulting in maps of shear modulus with low noise. In future work, the method’s performance on phantom and its repeatability on human data will be tested in a more quantitative manner. In conclusion, the proposed method showed much promise in quantifying tissue shear modulus from MRE with high robustness and efficiency.

Keywords: deep learning, magnetic resonance elastography, magnetic resonance imaging, shear modulus estimation

Procedia PDF Downloads 45

Authors: Shahab Uddin, Kazi M. Uddin, Hamamah Sadiqa

Abstract:

The paper deals with the Banghabandhu Multipurpose Bridge (BMB), the 11th longest bridge in the world was constructed in 1998 aimed at contributing to promote economic development in Bangladesh. In recent years, however, the high incidence of traffic accidents and injuries at the bridge sites looms as a great safety concern. Investigation into the derailment of nine bogies out of thirteen of Dinajpur-bound intercity train ‘Drutajan Express ’were derailed and inclined on the Banghabandhu Multipurpose Bridge on 28 April 2014. The train accident in Bridge will be deep concern for both structural safety of bridge and people than other vehicles accident. In this study we analyzed the disaster probability of the Banghabandhu Multipurpose Bridge for accidents by checking the fitness of Bridge structure. We found that train accident impact is more risky than other vehicles accidents. We also found that socio-economic impact on Bangladesh will be deep concerned.

Keywords: train accident, derailment, disaster, socio-economic

Procedia PDF Downloads 287

Authors: Panatda Intanin, Sangutid Thongsawad, Chirapha Tannanonta, Todsaporn Fuangrod

Abstract:

Stereotactic radiosurgery (SRS) is a highly precision delivery technique that requires comprehensive quality assurance (QA) tests prior to treatment delivery. An isocenter of delivery beam plays a critical role that affect the treatment accuracy. The uncertainty of isocenter is traditionally accessed using circular cone equipment, Winston-Lutz (WL) phantom and film. This technique is considered time consuming and highly dependent on the observer. In this work, the development of multileaf collimator (MLC)-based isocenter verification tool using electronic portal imaging device (EPID) was proposed and evaluated. A mechanical isocenter alignment with ball bearing diameter 5 mm and circular cone diameter 10 mm fixed to gantry head defines the radiation field was set as the conventional WL test method. The conventional setup was to compare to the proposed setup; using MLC (10 x 10 mm) to define the radiation filed instead of cone. This represents more realistic delivery field than using circular cone equipment. The acquisition from electronic portal imaging device (EPID) and radiographic film were performed in both experiments. The gantry angles were set as following: 0°, 90°, 180° and 270°. A software tool was in-house developed using MATLAB/SIMULINK programming to determine the centroid of radiation field and shadow of WL phantom automatically. This presents higher accuracy than manual measurement. The deviation between centroid of both cone-based and MLC-based WL tests were quantified. To compare between film and EPID image, the deviation for all gantry angle was 0.26±0.19mm and 0.43±0.30 for cone-based and MLC-based WL tests. For the absolute deviation calculation on EPID images between cone and MLC-based WL test was 0.59±0.28 mm and the absolute deviation on film images was 0.14±0.13 mm. Therefore, the MLC-based isocenter verification using EPID present high sensitivity tool for SRS QA.

Keywords: isocenter verification, quality assurance, EPID, SRS

Procedia PDF Downloads 132

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: convolutional neural network, discrete wavelet transform, deep learning, heart sound classification

Procedia PDF Downloads 328

Authors: Theresa Slump, Paula Neumeister, Katharina Feldker, Carina Y. Heitmann, Thomas Straube

Abstract:

A characteristic feature of post-traumatic stress disorder (PTSD) is the automatic processing of disorder-specific stimuli that expresses itself in intrusive symptoms such as intense physical and psychological reactions to trauma-associated stimuli. That automatic processing plays an essential role in the development and maintenance of symptoms. The aim of our study was, therefore, to investigate the behavioral and neural correlates of automatic processing of trauma-related stimuli in PTSD. Although interpersonal traumatization is a form of traumatization that often occurs, it has not yet been sufficiently studied. That is why, in our study, we focused on patients suffering from interpersonal traumatization. While previous imaging studies on PTSD mainly used faces, words, or generally negative visual stimuli, our study presented complex trauma-related and neutral visual scenes. We examined 19 female subjects suffering from PTSD and examined 19 healthy women as a control group. All subjects did a geometric comparison task while lying in a functional-magnetic-resonance-imaging (fMRI) scanner. Trauma-related scenes and neutral visual scenes that were not relevant to the task were presented while the subjects were doing the task. Regarding the behavioral level, there were not any significant differences between the task performance of the two groups. Regarding the neural level, the PTSD patients showed significant hyperactivation of the hippocampus for task-irrelevant trauma-related stimuli versus neutral stimuli when compared with healthy control subjects. Connectivity analyses revealed altered connectivity between the hippocampus and other anxiety-related areas in PTSD patients, too. Overall, those findings suggest that fear-related areas are involved in PTSD patients' processing of trauma-related stimuli even if the stimuli that were used in the study were task-irrelevant.

Keywords: post-traumatic stress disorder, automatic processing, hippocampus, functional magnetic resonance imaging

Procedia PDF Downloads 182

Authors: A. Nguyen, K. Nguyen, J. Jackson, E. Manlapig

Abstract:

With the recent advancement in core imaging systems, a large volume of high resolution drill core images can now be collected rapidly. This paper presents a method for rapid prediction of ore-specific breakage parameters from high resolution mineral classified core images. The aim is to allow for a rapid assessment of the variability in ore hardness within a mineral deposit with reduced amount of physical breakage tests. This method sees its application primarily in project evaluation phase, where proper evaluation of the variability in ore hardness of the orebody normally requires prolong and costly metallurgical test work program. Applying this image-based texture analysis method on mineral classified core images, the ores are classified according to their textural characteristics. A small number of physical tests are performed to produce a dataset used for developing the relationship between texture classes and measured ore hardness. The paper also presents a case study in which this method has been applied on core samples from a copper porphyry deposit to predict the ore-specific breakage A*b parameter, obtained from JKRBT tests.

Keywords: geometallurgy, hyperspectral drill core imaging, process simulation, texture analysis

Procedia PDF Downloads 337

Authors: Vijaya Yuvaram Singh V M, Kameshwar Rao J V

Abstract:

The challenge with development of neural network based methods for medical is the availability of data. Anatomical landmark detection in the medical domain is a process to find points on the x-ray scan report of the patient. Most of the time this task is done manually by trained professionals as it requires precision and domain knowledge. Traditionally object detection based methods are used for landmark detection. Here, we utilize reinforcement learning and query based method to train a single agent capable of detecting multiple landmarks. A deep Q network agent is trained to detect single and multiple landmarks present on hip and shoulder from x-ray scan of a patient. Here a single agent is trained to find multiple landmark making it superior to having individual agents per landmark. For the initial study, five images of different patients are used as the environment and tested the agents performance on two unseen images.

Keywords: reinforcement learning, medical landmark detection, multi target detection, deep neural network

Procedia PDF Downloads 126

Authors: O. J. G. Somsen

Abstract:

One of the tasks of optical surveillance is to detect anomalies in large amounts of image data. However, if the size of the anomaly is very small, limited information is available to distinguish it from the surrounding environment. Spectral detection provides a useful source of additional information and may help to detect anomalies with a size of a few pixels or less. Unfortunately, spectral cameras are expensive because of the difficulty of separating two spatial in addition to one spectral dimension. We investigate the possibility of modifying a simpler spectral line detector for outdoor detection. This may be especially useful if the area of interest forms a line, such as the horizon. We use a monochrome CCD that also enables detection into the near infrared. A simple camera is attached to the setup to determine which part of the environment is spectrally imaged. Our preliminary results indicate that sensitive detection of very small targets is indeed possible. Spectra could be taken from the various targets by averaging columns in the line image. By imaging a set of lines of various width we found narrow lines that could not be seen in the color image but remained visible in the spectral line image. A simultaneous analysis of the entire spectra can produce better results than visual inspection of the line spectral image. We are presently developing calibration targets for spatial and spectral focusing and alignment with the spatial camera. This will present improved results and more use in outdoor application

Keywords: anomaly detection, spectroscopic line imaging, image analysis, outdoor detection

Procedia PDF Downloads 464

Authors: Kenneth A. Rostowsky, Alexander S. Maher, Nahian F. Chowdhury, Andrei Irimia

Abstract:

The clinical significance of cerebral microbleeds (CMBs) due to mild traumatic brain injury (mTBI) remains unclear. Here we use magnetic resonance imaging (MRI), diffusion tensor imaging (DTI) and connectomic analysis to investigate the statistical association between mTBI-related CMBs, post-TBI changes to the human connectome and neurological/cognitive deficits. This study was undertaken in agreement with US federal law (45 CFR 46) and was approved by the Institutional Review Board (IRB) of the University of Southern California (USC). Two groups, one consisting of 26 (13 females) mTBI victims and another comprising 26 (13 females) healthy control (HC) volunteers were recruited through IRB-approved procedures. The acute Glasgow Coma Scale (GCS) score was available for each mTBI victim (mean µ = 13.2; standard deviation σ = 0.4). Each HC volunteer was assigned a GCS of 15 to indicate the absence of head trauma at the time of enrollment in our study. Volunteers in the HC and mTBI groups were matched according to their sex and age (HC: µ = 67.2 years, σ = 5.62 years; mTBI: µ = 66.8 years, σ = 5.93 years). MRI [including T1- and T2-weighted volumes, gradient recalled echo (GRE)/susceptibility weighted imaging (SWI)] and gradient echo (GE) DWI volumes were acquired using the same MRI scanner type (Trio TIM, Siemens Corp.). Skull-stripping and eddy current correction were implemented. DWI volumes were processed in TrackVis (http://trackvis.org) and 3D Slicer (http://www.slicer.org). Tensors were fit to DWI data to perform DTI, and tractography streamlines were then reconstructed using deterministic tractography. A voxel classifier was used to identify image features as CMB candidates using Microbleed Anatomic Rating Scale (MARS) guidelines. For each peri-lesional DTI streamline bundle, the null hypothesis was formulated as the statement that there was no neurological or cognitive deficit associated with between-scan differences in the mean FA of DTI streamlines within each bundle. The statistical significance of each hypothesis test was calculated at the α = 0.05 level, subject to the family-wise error rate (FWER) correction for multiple comparisons. Results: In HC volunteers, the along-track analysis failed to identify statistically significant differences in the mean FA of DTI streamline bundles. In the mTBI group, significant differences in the mean FA of peri-lesional streamline bundles were found in 21 out of 26 volunteers. In those volunteers where significant differences had been found, these differences were associated with an average of ~47% of all identified CMBs (σ = 21%). In 12 out of the 21 volunteers exhibiting significant FA changes, cognitive functions (memory acquisition and retrieval, top-down control of attention, planning, judgment, cognitive aspects of decision-making) were found to have deteriorated over the six months following injury (r = -0.32, p < 0.001). Our preliminary results suggest that acute post-TBI CMBs may be associated with cognitive decline in some mTBI patients. Future research should attempt to identify mTBI patients at high risk for cognitive sequelae.

Keywords: traumatic brain injury, magnetic resonance imaging, diffusion tensor imaging, connectomics

Procedia PDF Downloads 160

Authors: Jay L. Fu

Abstract:

Patients with Alzheimer's disease progressively lose their memory and thinking skills and, eventually, the ability to carry out simple daily tasks. The disease is irreversible, but early detection and treatment can slow down the disease progression. In this research, publicly available MRI data and demographic data from 373 MRI imaging sessions were utilized to build models to predict dementia. Various machine learning models, including logistic regression, k-nearest neighbor, support vector machine, random forest, and neural network, were developed. Data were divided into training and testing sets, where training sets were used to build the predictive model, and testing sets were used to assess the accuracy of prediction. Key risk factors were identified, and various models were compared to come forward with the best prediction model. Among these models, the random forest model appeared to be the best model with an accuracy of 90.34%. MMSE, nWBV, and gender were the three most important contributing factors to the detection of Alzheimer’s. Among all the models used, the percent in which at least 4 of the 5 models shared the same diagnosis for a testing input was 90.42%. These machine learning models allow early detection of Alzheimer’s with good accuracy, which ultimately leads to early treatment of these patients.

Keywords: Alzheimer's disease, clinical diagnosis, magnetic resonance imaging, machine learning prediction

Procedia PDF Downloads 124

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 103

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 21

Authors: Khaled M. Ali, Ayman A. Mostafa, Soliman M. Soliman

Abstract:

Objectives: To describe the most common clinical and endoscopic findings associated with complicated corneal ulcers in cats, and to determine the short-term outcomes after surgical treatment of these cats. Animals Eighteen client-owned cats of different breeds (52 females and 28 males), ranging in age from 3 months to 6 years, with corneal ulcers. Procedures: Cats were clinically evaluated to initially determine the concurrent corneal abnormalities. Endoscopic examination was performed to determine the anterior and posterior segments abnormalities. Superficial and deep stromal ulcers were treated using conjunctival flap. Corneal sequestrum was treated by partial keratectomy and conjunctival flap. Anterior synechia was treated via peripheral iridectomy and separation of the adhesion between the iris and the inner cornea. Symblepharon was treated by removal of the adhered conjunctival membrane from the cornea. Incurable endophthalmitis was treated surgically by extirpation. Short-term outcomes after surgical managements of selected corneal abnormalities were then assessed clinically and endoscopically. Results: Deep stromal ulcer with descemetocele, endophthalmitis, symblepharon, corneal sequestration and anterior synechia with secondary glaucoma and corneal scarring were the most common complications of corneal ulcer. FHV-1 was a common etiologic factor of corneal ulceration. Persistent corneal scars of varying shape and size developed in cats with deep stromal ulcer, anterior synechia, and corneal sequestration. Conclusions: Domestic shorthaired and Persian cats were the most predisposed breeds to FHV-1 infection and subsequent corneal ulceration. Immediate management of patients with corneal ulcer would prevent serious complications. No age or sex predisposition to complicated corneal ulceration in cats.

Keywords: cats, complicated corneal ulceration, clinical, endoscopic diagnosis, FHV-1

Procedia PDF Downloads 263

Authors: Wanchalerm Patanacharoenwong, Panaya Sudta, Prachya Bumrungkun

Abstract:

The paper focuses on the development of a system that combines Internet of Things (IoT) technologies and deep learning algorithms for anomaly detection in residential Electric Vehicle (EV) charging in smart cities. With the increasing number of EVs, ensuring efficient and reliable charging systems has become crucial. The aim of this research is to develop an integrated IoT and deep learning system for detecting anomalies in residential EV charging and enhancing EV load profiling and event detection in smart cities. This approach utilizes IoT devices equipped with infrared cameras to collect thermal images and household EV charging profiles from the database of Thailand utility, subsequently transmitting this data to a cloud database for comprehensive analysis. The methodology includes the use of advanced deep learning techniques such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) algorithms. IoT devices equipped with infrared cameras are used to collect thermal images and EV charging profiles. The data is transmitted to a cloud database for comprehensive analysis. The researchers also utilize feature-based Gaussian mixture models for EV load profiling and event detection. Moreover, the research findings demonstrate the effectiveness of the developed system in detecting anomalies and critical profiles in EV charging behavior. The system provides timely alarms to users regarding potential issues and categorizes the severity of detected problems based on a health index for each charging device. The system also outperforms existing models in event detection accuracy. This research contributes to the field by showcasing the potential of integrating IoT and deep learning techniques in managing residential EV charging in smart cities. The system ensures operational safety and efficiency while also promoting sustainable energy management. The data is collected using IoT devices equipped with infrared cameras and is stored in a cloud database for analysis. The collected data is then analyzed using RNN, LSTM, and feature-based Gaussian mixture models. The approach includes both EV load profiling and event detection, utilizing a feature-based Gaussian mixture model. This comprehensive method aids in identifying unique power consumption patterns among EV owners and outperforms existing models in event detection accuracy. In summary, the research concludes that integrating IoT and deep learning techniques can effectively detect anomalies in residential EV charging and enhance EV load profiling and event detection accuracy. The developed system ensures operational safety and efficiency, contributing to sustainable energy management in smart cities.

Keywords: cloud computing framework, recurrent neural networks, long short-term memory, Iot, EV charging, smart grids

Procedia PDF Downloads 41

Authors: Shanxiong Chen, Xu Han, Xiaolong Wang, Hui Ma

Abstract:

Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.

Keywords: recognition, CNN, Yi character, divergence

Procedia PDF Downloads 148

Authors: Luther Ollier, Sylvie Thiria, Anastase Charantonis, Carlos E. Mejia, Michel Crépon

Abstract:

Sea Surface Height Anomaly (SLA) is a signature of the sub-mesoscale dynamics of the upper ocean. Sea Surface Temperature (SST) is driven by these dynamics and can be used to improve the spatial interpolation of SLA fields. In this study, we focused on the temporal evolution of SLA fields. We explored the capacity of deep learning (DL) methods to predict short-term SLA fields using SST fields. We used simulated daily SLA and SST data from the Mercator Global Analysis and Forecasting System, with a resolution of (1/12)◦ in the North Atlantic Ocean (26.5-44.42◦N, -64.25–41.83◦E), covering the period from 1993 to 2019. Using a slightly modified image-to-image convolutional DL architecture, we demonstrated that SST is a relevant variable for controlling the SLA prediction. With a learning process inspired by the teaching-forcing method, we managed to improve the SLA forecast at five days by using the SST fields as additional information. We obtained predictions of a 12 cm (20 cm) error of SLA evolution for scales smaller than mesoscales and at time scales of 5 days (20 days), respectively. Moreover, the information provided by the SST allows us to limit the SLA error to 16 cm at 20 days when learning the trajectory.

Keywords: deep-learning, altimetry, sea surface temperature, forecast

Procedia PDF Downloads 71