Search results for: cancer classification

Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara

Abstract:

In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.

Keywords: general metric, unsupervised learning, classification, intersection over union

Procedia PDF Downloads 37

Authors: Ali Hamza

Abstract:

Accurate segmentation of breast ultrasound images is of paramount importance in enhancing the diagnostic capabilities of breast cancer detection. This study presents an approach utilizing the U-Net architecture for segmenting breast ultrasound images aimed at improving the accuracy and reliability of mass identification within the breast tissue. The proposed method encompasses a multi-stage process. Initially, preprocessing techniques are employed to refine image quality and diminish noise interference. Subsequently, the U-Net architecture, a deep learning convolutional neural network (CNN), is employed for pixel-wise segmentation of regions of interest corresponding to potential breast masses. The U-Net's distinctive architecture, characterized by a contracting and expansive pathway, enables accurate boundary delineation and detailed feature extraction. To evaluate the effectiveness of the proposed approach, an extensive dataset of breast ultrasound images is employed, encompassing diverse cases. Quantitative performance metrics such as the Dice coefficient, Jaccard index, sensitivity, specificity, and Hausdorff distance are employed to comprehensively assess the segmentation accuracy. Comparative analyses against traditional segmentation methods showcase the superiority of the U-Net architecture in capturing intricate details and accurately segmenting breast masses. The outcomes of this study emphasize the potential of the U-Net-based segmentation approach in bolstering breast ultrasound image analysis. The method's ability to reliably pinpoint mass boundaries holds promise for aiding radiologists in precise diagnosis and treatment planning. However, further validation and integration within clinical workflows are necessary to ascertain their practical clinical utility and facilitate seamless adoption by healthcare professionals. In conclusion, leveraging the U-Net architecture for breast ultrasound image segmentation showcases a robust framework that can significantly enhance diagnostic accuracy and advance the field of breast cancer detection. This approach represents a pivotal step towards empowering medical professionals with a more potent tool for early and accurate breast cancer diagnosis.

Keywords: mage segmentation, U-Net, deep learning, breast cancer detection, diagnostic accuracy, mass identification, convolutional neural network

Procedia PDF Downloads 77

Authors: Esther Friedlander, Philip Friedlander

Abstract:

The use of immunotherapy that inhibits programmed death-1 (PD-1) or its ligand PD-L1 confers survival benefits in patients with non-small cell lung cancer (NSCLC). However, approximately 45% of patients experience primary treatment resistance, necessitating the development of strategies to improve efficacy. While the renin-angiotensin system (RAS) has systemic hemodynamic effects, tissue-specific regulation exists along with modulation of immune activity in part through regulation of myeloid cell activity, leading to the hypothesis that RAS inhibition may improve anti-PD-1/L-1 efficacy. A retrospective analysis was conducted that included 173 advanced solid tumor cancer patients treated at Valley Hospital, a community Hospital in New Jersey, USA, who were treated with a PD-1/L-1 inhibitor in a defined time period showing a statistically significant relationship between RAS pathway inhibition (RASi through concomitant treatment with an ACE inhibitor or angiotensin receptor blocker) and positive efficacy to the immunotherapy that was independent of age, gender and cancer type. Subset analysis revealed strong numerical benefit for efficacy in both patients with squamous and nonsquamous NSCLC as determined by documented clinician assessment of efficacy and by duration of therapy. A PUBMED literature search was now conducted to identify studies assessing the effect of RAS pathway inhibition on anti-PD-1/L1 efficacy in advanced solid tumor patients and compare these findings to those seen in the Valley Hospital retrospective study with a focus on NSCLC specifically. A total of 11 articles were identified assessing the effects of RAS pathway inhibition on the efficacy of checkpoint inhibitor immunotherapy in advanced cancer patients. Of the 11 studies, 10 assessed the effect on survival of RASi in the context of treatment with anti-PD-1/PD-L1, while one assessed the effect on CTLA-4 inhibition. Eight of the studies included patients with NSCLC, while the remaining 2 were specific to genitourinary malignancies. Of the 8 studies, two were specific to NSCLC patients, with the remaining 6 studies including a range of cancer types, of which NSCLC was one. Of these 6 studies, only 2 reported specific survival data for the NSCLC subpopulation. Patient characteristics, multivariate analysis data and efficacy data seen in the 2 NSLCLC specific studies and in the 2 basket studies, which provided data on the NSCLC subpopulation, were compared to that seen in the Valley Hospital retrospective study supporting a broader effect of RASi on anti-PD-1/L1 efficacy in advanced NSLCLC with the majority of studies showing statistically significant benefit or strong statistical trends but with one study demonstrating worsened outcomes. This comparison of studies extends published findings to the community hospital setting and supports prospective assessment through randomized clinical trials of efficacy in NSCLC patients with pharmacodynamic components to determine the effect on immune cell activity in tumors and on the composition of the tumor microenvironment.

Keywords: immunotherapy, cancer, angiotensin, efficacy, PD-1, lung cancer, NSCLC

Procedia PDF Downloads 66

Authors: Jihen Bennaceur, Wissem Zouaghi, Ali Mabrouk

Abstract:

The major aim of cyber threat intelligence (CTI) is to provide sophisticated knowledge about cybersecurity threats to ensure internal and external safeguards against modern cyberattacks. Inaccurate, incomplete, outdated, and invaluable threat intelligence is the main problem. Therefore, data analysis based on AI algorithms is one of the emergent solutions to overcome the threat of information-sharing issues. In this paper, we propose a supervised machine learning-based algorithm to improve threat information sharing by providing a sophisticated classification of cyber threats and data. Extensive simulations investigate the accuracy, precision, recall, f1-score, and support overall to validate the designed algorithm and to compare it with several supervised machine learning algorithms.

Keywords: threat information sharing, supervised learning, data classification, performance evaluation

Procedia PDF Downloads 142

Authors: Chia-Yen Lee, Hao-Jen Wang, Jhih-Hao Lai

Abstract:

In recent years, infrared (IR) imaging has been considered as a potential tool to assess the efficacy of chemotherapy and early detection of breast cancer. Regions of tumor growth with high metabolic rate and angiogenesis phenomenon lead to the high temperatures. Observation of differences between the heat maps in long term is useful to help assess the growth of breast cancer cells and detect breast cancer earlier, wherein the multi-time infrared image alignment technology is a necessary step. Representative feature points detection and matching are essential steps toward the good performance of image registration and quantitative analysis. However, there is no clear boundary on the infrared images and the subject's posture are different for each shot. It cannot adhesive markers on a body surface for a very long period, and it is hard to find anatomic fiducial markers on a body surface. In other words, it’s difficult to detect and match features in an IR sequence images. In this study, automated feature detection and matching algorithms with two type of automatic feature points (i.e., vascular branch points and modified Harris corner) are developed respectively. The preliminary results show that the proposed method could identify the representative feature points on the IR breast images successfully of 98% accuracy and the matching results of 93% accuracy.

Keywords: Harris corner, infrared image, feature detection, registration, matching

Procedia PDF Downloads 296

Authors: Belaynesh Chekol, Numan Çelebi

Abstract:

The main purpose of this work is to recognize individual characters extracted from natural scene images using scale invariant feature transform (SIFT) features as an input to K-nearest neighbor (KNN); a classification learner algorithm. For this task, 1,068 and 78 images of English alphabet characters taken from Chars74k data set is used to train and test the classifier respectively. For each character image, We have generated describing features by using SIFT algorithm. This set of features is fed to the learner so that it can recognize and label new images of English characters. Two types of KNN (fine KNN and weighted KNN) were trained and the resulted classification accuracy is 56.9% and 56.5% respectively. The training time taken was the same for both fine and weighted KNN.

Keywords: character recognition, KNN, natural scene image, SIFT

Procedia PDF Downloads 275

Authors: Aleksandra Twarda, Dobrosława Krzemień, Grzegorz Dubin, Tad A. Holak

Abstract:

Stabilin-2 belongs to the group of scavenger receptors and plays a crucial role in clearance of more than 10 ligands from the bloodstream, including hyaluronic acid, products of degradation of extracellular matrix and metabolic products. The Link domain, a defining feature of stabilin-2, has a sequence similar to Link domains in other hyaluronic acid receptors, such as CD44 or TSG-6, and is responsible for most of ligands binding. Present knowledge of signal transduction by stabilin-2, as well as ligands’ recognition and binding mechanism, is limited. Until now, no experimental structures have been solved for any segments of stabilin-2. It has recently been demonstrated that the stabilin-2 knock-out or blocking of the receptor by an antibody effectively opposes cancer metastasis by elevating the level of circulating hyaluronic acid. Moreover, loss of expression of stabilin-2 in a peri-tumourous liver correlates with increased survival. Solving of the crystal structure of stabilin-2 and elucidation of the binding mechanism of hyaluronic acid could enable the precise characterization of the interactions in the binding site. These results may allow for designing specific small-molecule inhibitors of stabilin-2 that could be used in cancer therapy. To carry out screening for crystallization of stabilin-2, we cloned constructs of the Link domain of various lengths with or without surrounding domains. The folding properties of the constructs were checked by nuclear magnetic resonance (NMR). It is planned to show the binding of hyaluronic acid to the Link domain using several biochemical methods, i.a. NMR, isothermal titration calorimetry and fluorescence polarization assay.

Keywords: stabilin-2, Link domain, X-ray crystallography, NMR, hyaluronic acid, cancer

Procedia PDF Downloads 396

Authors: Lea Lenhardt, Ivana Zeković, Tatjana Dramićanin, Miroslav D. Dramićanin

Abstract:

Fluorescence spectroscopy coupled with parallel factor analysis (PARAFAC) and artificial neural networks (ANN) were used for characterization and classification of honey. Excitation emission spectra were obtained for 95 honey samples of different botanical origin (acacia, sunflower, linden, meadow, and fake honey) by recording emission from 270 to 640 nm with excitation in the range of 240-500 nm. Fluorescence spectra were described with a six-component PARAFAC model, and PARAFAC scores were further processed with two types of ANN’s (feed-forward network and self-organizing maps) to obtain algorithms for classification of honey on the basis of their botanical origin. Both ANN’s detected fake honey samples with 100% sensitivity and specificity.

Keywords: honey, fluorescence, PARAFAC, artificial neural networks

Procedia PDF Downloads 948

Authors: Hayrettin Eroglu, Adem Kara

Abstract:

Recently there has been significant attention given to imaging of the biological tissues via microwave imaging techniques. In this study, a phantom for the test and calibration of Microwave imaging used in detecting unhealthy breast structure or tumors was produced by using sol gel method. The liquid and gel phantoms being used nowadays are not durable due to evaporation and their organic ingredients, hence a new design was proposed. This phantom was fabricated from materials that were widely available (water, salt, gelatin, and glycerol) and was easy to make. This phantom was aimed to be better from the ones already proposed in the literature in terms of its durability and stability. S Parameters of phantom was measured with 1-18 GHz Probe Kit and permittivity was calculated via Debye method in “85070” commercial software. One, three, and five-week measurements were taken for this phantom. Finally, it was verified that measurement results were very close to the real biological tissue measurement results.

Keywords: phantom, breast tissue, cancer, microwave imaging

Procedia PDF Downloads 347

Authors: Ziad Abdallah, Mohamad Oueidat, Ali El-Zaart

Abstract:

Image Multi-label Classification (IMC) assigns a label or a set of labels to an image. The big demand for image annotation and archiving in the web attracts the researchers to develop many algorithms for this application domain. The existing techniques for IMC have two drawbacks: The description of the elementary characteristics from the image and the correlation between labels are not taken into account. In this paper, we present an algorithm (MIML-HOGLPP), which simultaneously handles these limitations. The algorithm uses the histogram of gradients as feature descriptor. It applies the Label Priority Power-set as multi-label transformation to solve the problem of label correlation. The experiment shows that the results of MIML-HOGLPP are better in terms of some of the evaluation metrics comparing with the two existing techniques.

Keywords: data mining, information retrieval system, multi-label, problem transformation, histogram of gradients

Procedia PDF Downloads 369

Authors: Agnė Mikalauskaitė, Renata Karpicz, Vitalijus Karabanovas, Arūnas Jagminas

Abstract:

The use of biocompatible precursors for the synthesis and stabilization of fluorescent gold nanoclusters (NCs) with strong red photoluminescence creates an important link between natural sciences and nanotechnology. Herein, we report the cost-effective synthesis of Au nanoclusters by templating and reduction of chloroauric acid with the cheap amino acid food supplements. This synthesis under the optimized conditions leads to the formation of biocompatible Au NCs having good stability and intense red photoluminescence, peaked at 680 to 705 nm, with a quantum yield (QY) of ≈7% and the average lifetime of up to several µs. The composition and luminescent properties of the obtained NCs were compared with ones formed via well-known bovine serum albumin reduction approach. Our findings implied that synthesized Au NCs tend to accumulate in more tumorigenic breast cancer cells (line MDA-MB-213) and after dialysis can be prospective for bio imagining.

Keywords: gold nanoclusters, proteins, materials chemistry, red-photoluminescence, bioimaging

Procedia PDF Downloads 263

Authors: Ming Ze Kao

Abstract:

Static magnetic fields (SMF) are widely used in several medical applications, especially in diagnosis of tumors. However, biological effects of the SMFs on modulating cell physiology through the Lorentz force, which is highly frequency and magnitude dependent, remain to be elucidated. Specific patterns from SMFs of static MF, delivered by means of Halbach array magnets with a gradient increment of 6.857mT/mm from center to border, were found to have profound inhibitory effect on the growth rate of human cell line derived from Nasopharyngeal carcinoma patients. The SMFs, which were shown to be noncontact, selectively impact rapid dividing cells while quiescent cells stay intact. The phenomenon acts in two modes: the arrest of cell proliferation in the G2/M phase and destruction of cell mitosis in cell division. First mode is manifested by impacting the proper formation of mitotic spindle, whereas the second results in disintegration of the cancer cell. Both modes are demonstrated when SMF was applied for 24 hours to cancer cells, the results revealed that metaphase arrest during mitosis due to activation of DNA damage response (DDR), resulting in high expression of ATM-NBS1-CHEK signaling pathways and higher G2/M phase ratio compared with control group. Here, experimental data suggest that the SMFs cause activation of cell cycle checkpoints, which implies the MFs as a potential therapeutic modality as a sensitizer for radiotherapy or chemotherapy.

Keywords: static magnetic field, DNA damage response, Halbach array, magnetic therapy

Procedia PDF Downloads 112

Authors: Alper Taner, Yesim Benal Oztekin, Huseyin Duran

Abstract:

In this study, an Artificial Neural Network (ANN) was developed in order to classify barley varieties. For this purpose, physical properties of barley varieties were determined and ANN techniques were used. The physical properties of 8 barley varieties grown in Turkey, namely thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain, were determined and it was found that these properties were statistically significant with respect to varieties. As ANN model, three models, N-l, N-2 and N-3 were constructed. The performances of these models were compared. It was determined that the best-fit model was N-1. In the N-1 model, the structure of the model was designed to be 11 input layers, 2 hidden layers and 1 output layer. Thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain were used as input parameter; and varieties as output parameter. R2, Root Mean Square Error and Mean Error for the N-l model were found as 99.99%, 0.00074 and 0.009%, respectively. All results obtained by the N-l model were observed to have been quite consistent with real data. By this model, it would be possible to construct automation systems for classification and cleaning in flourmills.

Keywords: physical properties, artificial neural networks, barley, classification

Procedia PDF Downloads 175

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 158

Authors: Sastry Y. Kandukuri, Isak Andersen

Abstract:

Despite recent advances in the manufacturing sector, quality issues remain a frequent occurrence, and can result in fatal accidents, equipment downtime, and loss of life. Adequate quality is of high importance in high-risk industries such as sea-going vessels and offshore installations in which third party quality assurance and product control play an important essential role in ensuring manufacturing quality of critical components. Classification societies play a vital role in mitigating risk in these industries by making sure that all the stakeholders i.e. manufacturers, builders, and end users are provided with adequate rules and standards that effectively ensures components produced at a high level of quality based on the area of application and risk of its failure. Quality issues have also been linked to the lack of competence or negligence of stakeholders in supply value chain. However, continued actions and regulatory reforms through modernization of rules and requirements has provided additional tools for purchasers and manufacturers to confront these issues. Included among these tools are updated ‘approval of manufacturer class programs’ aimed at developing and implementing a set of standardized manufacturing quality metrics for use by the manufacturer and verified by the classification society. The establishment and collection of manufacturing and testing requirements described in these programs could provide various stakeholders – from industry to vessel owners – with greater insight into the state of quality at a given manufacturing facility, and allow stakeholders to anticipate better and address quality issues while simultaneously reducing unnecessary failures that are costly to the industry. The publication introduces, explains and discusses critical manufacturing and testing requirements set in a leading class society’s approval of manufacturer regime and its rationale and some case studies.

Keywords: classification society, manufacturing, materials processing, materials testing, quality control

Procedia PDF Downloads 348

Authors: Vincent Murray

Abstract:

The chromatin structure at the transcription start sites (TSSs) of genes is very important in the control of gene expression. In order for gene expression to occur, the chromatin structure at the TSS has to be altered so that the transcriptional machinery can be assembled and RNA transcripts can be produced. In particular, the nucleosome structure and positioning around the TSS has to be changed. Bleomycin is utilized as an anti-tumor agent to treat Hodgkin's lymphoma, squamous cell carcinoma, and testicular cancer. Bleomycin produces DNA damage in human cells and DNA strand breaks, especially double-strand breaks, are thought to be responsible for the cancer chemotherapeutic activity of bleomycin. Bleomycin is a large glycopeptide with molecular weight of approximately 1500 Daltons and hence its DNA strand cleavage activity can be utilized as a probe of chromatin structure. In this project, Illumina next-generation DNA sequencing technology was used to determine the position of DNA double-strand breaks at the TSSs of genes in intact cells. In this genome-wide study, it was found that bleomycin cleavage preferentially occurred at the TSSs of actively transcribed human genes in comparison with non-transcribed genes. There was a correlation between the level of enhanced bleomycin cleavage at TSSs and the degree of transcriptional activity. In addition, bleomycin was able to determine the position of nucleosomes at the TSSs of human genes. Bleomycin analogues were also utilized as probes of chromatin structure at the TSSs of human genes. In a similar manner to bleomycin, the bleomycin analogues 6′-deoxy-BLM Z and zorbamycin preferentially cleaved at the TSSs of human genes. Interestingly this degree of enhanced TSS cleavage inversely correlated with the cytotoxicity (IC50 values) of BLM analogues. This indicated that the degree of cleavage by bleomycin analogues at the TSSs of human genes was very important in the cytotoxicity of bleomycin and analogues. It also provided a deeper insight into the mechanism of action of this cancer chemotherapeutic agent since actively transcribed genes were preferentially targeted.

Keywords: anti-cancer activity, chromatin structure, cytotoxicity, gene expression, next-generation DNA sequencing

Procedia PDF Downloads 111

Authors: Adebisi Adunola Demehin, Wanlaya Thamnarak, Jaruwan Chatwichien, Chatchakorn Eurtivong, Kiattawee Choowongkomon, Somsak Ruchirawat, Nopporn Thasana

Abstract:

The epidermal growth factor receptor (EGFR) is a transmembrane glycoprotein involved in cellular signalling processes and, its aberrant activity is crucial in the development of many cancers such as lung cancer. Selaginellaceae are fern allies that have long been used in Chinese traditional medicine to treat various cancer types, especially lung cancer. Biflavonoids, the major secondary metabolites in Selaginellaceae, have numerous pharmacological activities, including anti-cancer and anti-inflammatory. For instance, amentoflavone induces a cytotoxic effect in the human NSCLC cell line via the inhibition of PARP-1. However, to the best of our knowledge, there are no studies on biflavonoids as EGFR inhibitors. Thus, this study aims to investigate the EGFR inhibitory activities of biflavonoids isolated from Selaginella siamensis and Selaginella bryopteris. Amentoflavone, tetrahydroamentoflavone, sciadopitysin, robustaflavone, robustaflavone-4-methylether, delicaflavone, and chrysocauloflavone were isolated from the ethyl-acetate extract of the whole plants. The structures were determined using NMR spectroscopy and mass spectrometry. In vitro study was conducted to evaluate their cytotoxicity against A549, HEPG2, and T47D human cancer cell lines using the MTT assay. In addition, a target-based assay was performed to investigate their EGFR inhibitory activity using the kinase inhibition assay. Finally, a molecular docking study was conducted to predict the binding modes of the compounds. Robustaflavone-4-methylether and delicaflavone showed the best cytotoxic activity on all the cell lines with IC50 (µM) values of 18.9 ± 2.1 and 22.7 ± 3.3 on A549, respectively. Of these biflavonoids, delicaflavone showed the most potent EGFR inhibitory activity with an 84% relative inhibition at 0.02 nM using erlotinib as a positive control. Robustaflavone-4-methylether showed a 78% inhibition at 0.15 nM. The docking scores obtained from the molecular docking study correlated with the kinase inhibition assay. Robustaflavone-4-methylether and delicaflavone had a docking score of 72.0 and 86.5, respectively. The inhibitory activity of delicaflavone seemed to be linked with the C2”=C3” and 3-O-4”’ linkage pattern. Thus, this study suggests that the structural features of these compounds could serve as a basis for developing new EGFR-TK inhibitors.

Keywords: anticancer, biflavonoids, EGFR, molecular docking, Selaginellaceae

Procedia PDF Downloads 192

Authors: Li-Ting Chen, Chih-Tao Cheng, I-Ping Huang, Jen-Ho Chang, Nien-Tzu Chang, Fei-Hsiu Hsiao

Abstract:

Background: Insecurity adult attachment style may be triggered by cancer threat, which in turn influences depression symptoms. Dispositional mindfulness may have benefits of insecure attachment on depression for colorectal patient transfer to survivor. Objective: This study examined the mediating and moderating effects of quality of life (QOL) and dispositional mindfulness on the relationship between insecure attachment style and depression symptoms. Methods: A cross-sectional study design was used. Data were collected using the QOL functional and symptoms (EORTC-C30 and EORTC CR29), dispositional mindfulness (FFMQ), Short form of Experience in Close Relationships Revised Questionnaire (SF-ECRRQ), and depressive symptoms (BDI-II scale). Results: Of the 90 CRC survivors who participated, the indirect effect of both ECR anxiety (β=0.23, CI=0.05-0.44) and ECR avoidance (β=0.12, CI=0.02-0.24) on depression were significantly mediated through EORTC-C29 colorectal symptoms. Three components of dispositional mindfulness (i.e., acting of awareness, non-judging, non-reactivity) as the moderator in the relationship between ECR anxiety and depressive symptoms. Acting of awareness was a moderator in the relationship between ECR avoidance and depressive symptoms. Conclusions: There are two pathways from insecure attachment to depression: through the mediator of colorectal symptoms and the moderator of dispositional mindfulness. Cancer symptom management and mindfulness practices could improve the impact of insecure attachment on depression among CRC patients in a post-treatment transition period.

Keywords: acting of awareness, attachment style, colorectal cancer, disposisitonal mindfulness, depression

Procedia PDF Downloads 58

Authors: G. Meccariello, L. Della Ragione

Abstract:

The exposure to outdoor air pollution causes lung cancer and increases the risk of bladder cancer. Because air pollution in urban areas is mainly caused by transportation, it is necessary to evaluate pollutant exhaust emissions from vehicles during their real-world use. Nevertheless their evaluation and reduction is a key problem, especially in the cities, that account for more than 50% of world population. A particular attention was given to the slope variability along the streets during each journey performed by the instrumented vehicle. In this paper we dealt with the problem of describing a quantitatively approach for the reconstruction of GPS coordinates and altitude, in the context of correlation study between driving cycles / emission / geographical location, during an experimental campaign realized with some instrumented cars. Finally the slope analysis can be correlated to the emission and consumption values in a specific road position, and it could be evaluated its influence on their behaviour.

Keywords: air pollution, driving cycles, GPS signal, slope, emission factor, fuel consumption

Procedia PDF Downloads 385

Authors: C. Manjula, Lilly Florence

Abstract:

Software technology is developing rapidly which leads to the growth of various industries. Now-a-days, software-based applications have been adopted widely for business purposes. For any software industry, development of reliable software is becoming a challenging task because a faulty software module may be harmful for the growth of industry and business. Hence there is a need to develop techniques which can be used for early prediction of software defects. Due to complexities in manual prediction, automated software defect prediction techniques have been introduced. These techniques are based on the pattern learning from the previous software versions and finding the defects in the current version. These techniques have attracted researchers due to their significant impact on industrial growth by identifying the bugs in software. Based on this, several researches have been carried out but achieving desirable defect prediction performance is still a challenging task. To address this issue, here we present a machine learning based hybrid technique for software defect prediction. First of all, Genetic Algorithm (GA) is presented where an improved fitness function is used for better optimization of features in data sets. Later, these features are processed through Decision Tree (DT) classification model. Finally, an experimental study is presented where results from the proposed GA-DT based hybrid approach is compared with those from the DT classification technique. The results show that the proposed hybrid approach achieves better classification accuracy.

Keywords: decision tree, genetic algorithm, machine learning, software defect prediction

Procedia PDF Downloads 326

Authors: Janet Wing-Chong Wai, Alex Chiu-Wing Lee, Hailey Hoi-Ching Tsang, Jeffrey Chiu, Kwok-Wing Tang

Abstract:

Background: Mammography has limited sensitivity and specificity though it is the primary imaging technique for detection of early breast cancer. Ultrasound imaging and contrast-enhanced MRI are useful adjunct tools to mammography. The advantage of breast MRI is high sensitivity for invasive breast cancer. Therefore, indications for and use of breast magnetic resonance imaging have increased over the past decade. Objectives: 1. Cases demonstration on different indications for breast MR imaging. 2. To review of the common artifacts and pitfalls in breast MR imaging. Materials and Methods: This is a retrospective study including all patients underwent dynamic contrast-enhanced breast MRI examination in our centre, performed from Jan 2011 to Dec 2017. The clinical data and radiological images were retrieved from the EPR (electronic patient record), RIS (Radiology Information System) and PACS (Picture Archiving and Communication System). Results and Discussion: Cases including (1) Screening of the contralateral breast in patient with a new breast malignancy (2) Breast augmentation with free injection of unknown foreign materials (3) Finding of axillary adenopathy with an unknown site of primary malignancy (4) Neo-adjuvant chemotherapy: before, during, and after chemotherapy to evaluate treatment response and extent of residual disease prior to operation. Relevant images will be included and illustrated in the presentation. As with other types of MR imaging, there are different artifacts and pitfalls that can potentially limit interpretation of the images. Because of the coils and software specific to breast MR imaging, there are some other technical considerations that are unique to MR imaging of breast regions. Case demonstration images will be available in presentation. Conclusion: Breast MR imaging is a highly sensitive and reasonably specific method for the detection of breast cancer. Adherent to appropriate clinical indications and technical optimization are crucial for achieving satisfactory images for interpretation.

Keywords: MRI, breast, clinical, cancer

Procedia PDF Downloads 233

Authors: Dingyang Hu, Dan Liu

Abstract:

DNN (Deep Neural Network) deep learning models are widely used in classification, prediction, and other task scenarios. To address the difficulties of generic adversarial perturbation generation for deep learning models under black-box conditions, a generic adversarial ingestion generation method based on a saliency map (CJsp) is proposed to obtain salient image regions by counting the factors that influence the input features of an image on the output results. This method can be understood as a saliency map attack algorithm to obtain false classification results by reducing the weights of salient feature points. Experiments also demonstrate that this method can obtain a high success rate of migration attacks and is a batch adversarial sample generation method.

Keywords: adversarial sample, gradient, probability, black box

Procedia PDF Downloads 91

Authors: Vivek Bhat, Rohini Kelkar, Sanjay Biswas

Abstract:

Introduction: Cancer patients are at increased risk of bacterial infections. This may due to the disease process itself, the effect of chemotherapeutic drugs or invasive procedures such as catheterization. A wide variety of bacteria including some emerging pathogens are increasingly being reported from these patients. The incidence of multidrug-resistant organisms particularly in the Gram negative group is also increasing, with higher resistance rates seen to cephalosporins, β-lactam/β-lactam inhibitor combinations, and the carbapenems. This study documents the bacteriological spectrum of infections and their resistance patterns in cancer patients. Methods: This study includes all bacterial isolates recovered from infections cancer patients over a period of 18 months. Samples included Blood cultures, Pus/wound swabs, urine, tissue biopsies, body fluids, catheter tips and respiratory specimens such as sputum and bronchoalveolar lavage (BAL). All samples were processed in the microbiology laboratory as per standard laboratory protocols. Organisms were identified to species level and antimicrobial susceptibility testing was performed manually by the disc diffusion technique or in the Vitek-2 (Biomereux, France) instrument. Interpretations were as per Clinical laboratory Standards Institute (CLSI) guidelines. Results: A total of 1150 bacterial isolates were cultured from 884 test samples during the study period. Of these 227 were Gram-positive and 923 were Gram-negative organisms. Staphylococcus aureus (99 isolates) was the commonest Gram-positive isolate followed by Enterococcus (79) and Gr A Streptococcus (30). Among the Gram negatives, E. coli (304), Pseudomonas aeruginosa (201) and Klebsiella pneumoniae (190) were the most common. Of the Staphylococcus aureus isolates 27.2% were methicillin resistant. Only 5.06% enterococci were vancomycin resistant. High rates of resistance to cefotaxime and ciprofloxacin were seen amongst E. coli (84.8% & 83.55%) and Klebsiella pneumoniae (71 & 62.1%) respectively. Resistance to carbapenems (meropenem) was high at 70% in Acinetobacter spp.; however all isolates were sensitive to colistin. Among the aminoglycosides, amikacin retained good efficacy against Escherichia coli (82.9%) and Pseudomonas aeruginosa (78.1%). Occasional isolates of emerging pathogens such as Chryseobacterium indologens, Roseomonas, and Achromobacter xyloxidans were also recovered. Conclusion: The common infections in cancer patients include respiratory, wound, tract infections and sepsis. The commonest isolates include Staphylococcus aureus, Enterococci, Escherichia coli, Klebsiella pneumoniae and Pseudomonas aeruginosa. There is a high level of resistance to the commonly used antibiotics among Gram-negative organisms.

Keywords: bacteria, resistance, infection, cancer

Procedia PDF Downloads 294

Authors: Fuad M. Alkoot

Abstract:

DNA data have been used in forensics for decades. However, current research looks at using the DNA as a biometric identity verification modality. The goal is to improve the speed of identification. We aim at using gene data that was initially used for autism detection to find if and how accurate is this data for identification applications. Mainly our goal is to find if our data preprocessing technique yields data useful as a biometric identification tool. We experiment with using the nearest neighbor classifier to identify subjects. Results show that optimal classification rate is achieved when the test set is corrupted by normally distributed noise with zero mean and standard deviation of 1. The classification rate is close to optimal at higher noise standard deviation reaching 3. This shows that the data can be used for identity verification with high accuracy using a simple classifier such as the k-nearest neighbor (k-NN). 

Keywords: biometrics, genetic data, identity verification, k nearest neighbor

Procedia PDF Downloads 248

Authors: Mohamed Saad, Huda Ismail

Abstract:

The purpose of this research is to examine the impact of cryptocurrency classification on money laundering crimes and to analyze how the preferences of criminals differ according to the type of digital currency used. Specifically, we aim to explore the roles of stablecoins, utility coins, and privacy tokens in facilitating or hindering money laundering activities and to identify the key factors that influence the choices of criminals in using these cryptocurrencies. To achieve our research objectives, we used a dataset for the most highly traded cryptocurrencies (32 currencies) that were published on the coin market cap for 2022. In addition to conducting a comprehensive review of the existing literature on cryptocurrency and money laundering, with a focus on stablecoins, utility coins, and privacy tokens, Furthermore, we conducted several Multivariate analyses. Our study reveals that the classification of cryptocurrency plays a significant role in money laundering activities, as criminals tend to prefer certain types of digital currencies over others, depending on their specific needs and goals. Specifically, we found that stablecoins are more commonly used in money laundering due to their relatively stable value and low volatility, which makes them less risky to hold and transfer. Utility coins, on the other hand, are less frequently used in money laundering due to their lack of anonymity and limited liquidity. Finally, privacy tokens, such as Monero and Zcash, are increasingly becoming a preferred choice among criminals due to their high degree of privacy and untraceability. In summary, our study highlights the importance of understanding the nuances of cryptocurrency classification in the context of money laundering and provides insights into the preferences of criminals in using digital currencies for illegal activities. Based on our findings, our recommendation to the policymakers is to address the potential misuse of cryptocurrencies for money laundering. By implementing measures to regulate stable coins, strengthening cross-border cooperation, fostering public-private partnerships, and increasing cooperation, policymakers can help prevent and detect money laundering activities involving digital currencies.

Keywords: crime, cryptocurrency, money laundering, tokens.

Procedia PDF Downloads 82

Authors: Ruqayya Naheed Khan, Romaisa Shamim, Awais Amjad Malik, Awais Naeem, Amina Iqbal Khan, Asad Parvaiz

Abstract:

Objective: Patients undergoing axillary lymph node dissection (ALND) for metastatic lymph nodes in our hospital usually have drains placed in their axilla for a period of 6-10 days. We evaluated the post-op course of patients who underwent breast conservation surgery (BCS) along with ALND. Methods: A prospective cohort study was conducted at Shaukat Khanam Memorial Cancer Hospital from April 2017 to August 2017 including all lymph node positive breast cancer patients undergoing BCS with ALND. Patients were divided into two groups. Group A had no axillary drain while in Group B a drain was placed in axilla. Results: A total of 76 patients were included. 41 patients were included in group A and 35 patients in Group B. Median number of LNs dissected in group A was 17 and in group B was 15 (p value 0.443). Median operative time in group A was 84 min and in group B was 79 min (p value 0.223). Median hospital stay in both groups was 1 day (p value 0.78). At 2 weeks all patients in group A developed seroma as compared to none in group B (p value < 0.001). 3 of these patients in group A required aspiration of seroma due to pressure effects. Rest were managed conservatively. At 6 weeks only 50% patients had a seroma radiologically in Group A as compared to 33% in group B (p value 0.023). No intervention was required in any patients at week 6. QOL at 2 weeks was much better in Group A (7/41 patients had unsatisfactory response) as compared to group B (10/31 had unsatisfactory response). Results were statistically significant (p value 0.045). However, there wasn’t much difference in QOL at 6 weeks. Only 1 patient in group A had an unsatisfactory response. Average pain score at 2 weeks was similar in both groups (4.2 v/s 4.1 p value 0.73). Infection was seen in 1 patient in each group at 2 weeks (p value 0.668) and in only 1 patient in group A at 6 weeks (p value 0.067). Conclusion: We conclude from our study that there isn’t much difference in drain and no drain group in terms of wound infection and pain scores. No drain group is however associated with a better QOL in early post-op period.

Keywords: axillary drainage, axillary lymph node dissection, breast cancer, no drain in axilla

Procedia PDF Downloads 184

Authors: Moein Izadi, Ali Mohammadzadeh

Abstract:

Detection of damaged parts of roads after earthquake is essential for coordinating rescuers. In this study, an approach is presented for the semi-automatic detection of damaged roads in a city using pre-event vector maps and both pre- and post-earthquake QuickBird satellite images. Damage is defined in this study as the debris of damaged buildings adjacent to the roads. Some spectral and texture features are considered for SVM classification step to detect damages. Finally, the proposed method is tested on QuickBird pan-sharpened images from the Bam City earthquake and the results show that an overall accuracy of 81% and a kappa coefficient of 0.71 are achieved for the damage detection. The obtained results indicate the efficiency and accuracy of the proposed approach.

Keywords: SVM classifier, disaster management, road damage detection, quickBird images

Procedia PDF Downloads 619

Authors: Ella Sèdé Maforikan

Abstract:

Accurate land cover mapping is essential for effective environmental monitoring and natural resources management. This study focuses on assessing the classification performance of two satellite datasets and evaluating the impact of different input feature combinations on classification accuracy in the Beterou catchment, situated in the northern part of Benin. Landsat-8 and Sentinel-2 images from June 1, 2020, to March 31, 2021, were utilized. Employing the Random Forest (RF) algorithm on Google Earth Engine (GEE), a supervised classification categorized the land into five classes: forest, savannas, cropland, settlement, and water bodies. GEE was chosen due to its high-performance computing capabilities, mitigating computational burdens associated with traditional land cover classification methods. By eliminating the need for individual satellite image downloads and providing access to an extensive archive of remote sensing data, GEE facilitated efficient model training on remote sensing data. The study achieved commendable overall accuracy (OA), ranging from 84% to 85%, even without incorporating spectral indices and terrain metrics into the model. Notably, the inclusion of additional input sources, specifically terrain features like slope and elevation, enhanced classification accuracy. The highest accuracy was achieved with Sentinel-2 (OA = 91%, Kappa = 0.88), slightly surpassing Landsat-8 (OA = 90%, Kappa = 0.87). This underscores the significance of combining diverse input sources for optimal accuracy in land cover mapping. The methodology presented herein not only enables the creation of precise, expeditious land cover maps but also demonstrates the prowess of cloud computing through GEE for large-scale land cover mapping with remarkable accuracy. The study emphasizes the synergy of different input sources to achieve superior accuracy. As a future recommendation, the application of Light Detection and Ranging (LiDAR) technology is proposed to enhance vegetation type differentiation in the Beterou catchment. Additionally, a cross-comparison between Sentinel-2 and Landsat-8 for assessing long-term land cover changes is suggested.

Keywords: land cover mapping, Google Earth Engine, random forest, Beterou catchment

Procedia PDF Downloads 56

Authors: Yaojun Wang, Yaoqing Wang

Abstract:

Stock selection is an important decision-making problem. Many machine learning and data mining technologies are employed to build automatic stock-selection system. A profitable stock-selection system should consider the stock’s investment value and the market timing. In this paper, we present a hybrid system including both engage for stock selection. This system uses a case-based reasoning (CBR) model to execute the stock classification, uses a decision-tree model to help with market timing and stock selection. The experiments show that the performance of this hybrid system is better than that of other techniques regarding to the classification accuracy, the average return and the Sharpe ratio.

Keywords: case-based reasoning, decision tree, stock selection, machine learning

Procedia PDF Downloads 412

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 176