Search

Lung cancer is one of the life-threatening diseases that records a large number of incidences and a high mortality rate and most often is diagnosed at an advanced stage. Computed Tomography (CT) scans are widely used in lung cancer diagnosis. The image segmentation algorithms help to segment the Region of Interest (RoI) from the lung medical images to accurately identify and isolate lung tissue and nodules from CT scan images. The proposed method for lung CT image segmentation and identification of lung tumors consists of two phases: Spatial Statistics and Connected Component based lung lobe Segmentation (SCS) and Thresholded Bounding box-based lung nodule Extraction (TBE). The phase 1 SCS, uses symmetric division of lung CT image histogram, binarization and complementing process to segment the lung lobe region and phase 2 TBE, uses threshold-based bounding box method to identify the lung nodules. The proposed method is named as SCS-TBE. This SCS-TBE was evaluated on the LIDC dataset. The algorithm's performance was analyzed using Dice Coefficient (DC) and Jaccard Coefficient (JC), with an average DC of 0.93 and an average JC of 0.91, indicating better accuracy segmentation which helps in the identification of lung tumors in CT scan images. The SCT-TBE has outperformed other methods, as evaluated in terms of DC and JC values. The DC and JC values of SCS-TBE are 0.93 and 0.91 respectively. [ABSTRACT FROM AUTHOR]

Deep learning can perform image classification but requires vast amounts of input data. Meanwhile, the data for x-rays of lung cancer is very limited due to the expensive cost of collecting these images and asking competent doctors to evaluate them before they are used for training. We propose Transfer Learning Deep Boltzmann Machine to detect lung cancer based on x-ray images with few labeled data. This method used MNIST and cifar10 data as source data on pre-training to obtain the weighting parameters used for deep Boltzmann machine (DBM) training Next, we evaluated the correlation between the target and the source image. Deep Boltzmann Machine training was performed by taking into account iteration mean-field interferences. The results show that transfer learning deep Boltzmann machine can be used to detect lung cancer. A large source-target correlation and a large number of mean-field iterations shows better results. In this study, the best results were given by cifar10 source data with 10-step Mean-Field of 89.4% accuracy. [ABSTRACT FROM AUTHOR]

The primary goal of Exploratory Data Analysis (EDA) is exploring and understanding data in order to gain insights and guide for further analysis. It allows for data cleaning which involves removing redundancies, handling missing values, correcting errors and transforming data if necessary as it is an important part of overall data preparation process. The aim of this study is to conduct a preliminary study before applying the survival method of analysis to censored lung cancer observations. The Kaplan-Meier survival curve, proportional hazard assumption, time varying covariate assumption via Scaled Schoenfeld residuals, Cox-Snell residuals for overall goodness of fit of the model assumption, and normality assumption via quantile-quantile (Q-Q) plot were all used in this study. The study discovered that the lung cancer censored observations were not violated with the parametric assumption among semi-parametric, and non-parametric assumptions. Thus, future work is recommended to include a comparison of the parametric method of survivals using the lung cancer data. The application of survival analysis would be ambiguous and mislead the researcher if the fundamental part of survival being left out. As a result, this study may aid in identifying appropriate assumptions for prior application on the survival analysis of censored observations. [ABSTRACT FROM AUTHOR]

Lung cancer diagnosis can be done using histopathology techniques. A biopsy is performed on body tissue suspected of having cancer, and the biopsy results are observed through a microscope by a pathologist. This study utilized medical imaging results from lung cancer histopathology. The research aims to classify lung cancer histopathology images. Experimental data comes from the public dataset LC25000. The data has three classes: adenocarcinoma, normal, and squamous cell carcinoma. Each class has 1,000 images. The research steps consist of preprocessing and classification. The preprocessing includes image resizing 224, converting BGR to RGB image format, and splitting training, validation, and testing data. Training vs. testing data has a percentage of 80:20. Meanwhile, for training and validation, 5-fold cross-validation is used. We use Transfer Learning Convolutional Neural Network (CNN) with Visual Geometry Group architecture (VGG16 and VGG19) for classification. Network optimization was done by initializing the learning rate 64, batch-size 32, learning rate 0.0001, and the Adaptive Moment Estimation (Adam) optimizer. Also, using early-stop in the training process when validation accuracy does not improve along with increasing epochs. The experimental results show the best accuracy, precision, recall, and f1-score of 0.97. [ABSTRACT FROM AUTHOR]

Segmenting lung diseases from computed tomography (CT) images is an essential task that involves the identification and treatment of lung tumors. However, this process is challenging due to various factors such as uneven presence, fuzzy borders, diverse densities, shapes, and sizes of lesions. To address this difficulty, our focus primarily revolves around employing deep learning algorithms for accurate lung and tumor segmentation from abdominal CT scan images. This approach aims to minimize the time and energy required for diagnosing lung diseases. To achieve this, we propose an automatic segmentation method that utilizes a modified ResUNet model to accurately segment the lung and its tumors. Notably, our system demonstrates superior performance in terms of precision and automated tumor segmentation, as evidenced by the highest achieved Dice Similarity Coefficient (DSC) metric compared to existing approaches for tumor and lung segmentation. The algorithm employed in our study is based on the modified ResUNet architecture. In this work, we present an automatic method that utilizes a semantic segmentation convolutional neural network (CNNs) to segment the lung from CT scans and lesions from the segmented lung region. [ABSTRACT FROM AUTHOR]

Cancer is one the most hastily increasing diseases that is one of the major reasons for death nowadays. Especially lung cancer, which is increasing at a very speedy rate. One defining feature of cancer is the rapid creation of abnormal cells that grow beyond their usual boundaries, and which can then invade adjoining parts of the body and spread to other organs; the latter process is referred to as metastasis. Many of the researchers are working on finding solutions to this vastly increasing disease, but it will surely take at least a decade to find a proper solution to such a problem. In the meantime, we can work on the early detection of this disease so that the treatment can be started at an early state and therefore save the precious lives of the patient. In this project, the aim is to work and develop different algorithms with the help of Machine Learning, and therefore deploy these models to predict if the patient is suffering from lung Cancer or not. In this project, I have implemented a Random Forest model using machine learning and analysis of lung cancer tissues which gave a good accuracy. I have also worked on CNN model and Image segmentation model and found their respective accuracies. Furthermore, I have compared each model based on their precision, f1-score, recall and accuracy and I have shown which model predicts most accurately that patients have lung cancer or not. [ABSTRACT FROM AUTHOR]

Significant progress has been made in the field of lung cancer over the years (chemical rehabilitation, radiotherapy, individualized treatment). Nevertheless, lung cancer remains a threat to society and a leading cause of death for thousands of people worldwide. The subject of this paper is the diagnosis of lung cancer. Lung cancer is diagnosed using computerized tomography (CT) scans. To accurately diagnose lung cancer, different algorithms are used. The image is filtered through a sharp hidden filter in this case. The edges and areas of the cancer are detected using a flexible canvas method. To identify the features andpredict the risk of lung cancer, using the neural network. The K-Nearest Neighbors method is used to separate cancerand lungs. Lung cancer is diagnosed using computerized tomography (CT) scans. To accurately diagnose lung cancer, different algorithms are used. The image is filtered through a sharp hidden filter in this case. The edges and areas of the cancer are detected using a flexible canvas method. To identify the features and predict the risk of the Using a neural network to study lung cancer. The K-Nearest Neighbors method is used to separate cancer and lungs. Lung cancer has been growing in recent years, so it is very important to know if tumor has turned into cancer. Prognosis occurs early and Accurate predictions can save many lives and assist doctors in starting therapy. CT (computed tomography) is a type of imaging that uses a is important in determining the condition of a plant by determining its size, location, and other factors. [ABSTRACT FROM AUTHOR]

Aim-The aim of the study is to perform innovative detection of lung cancer using the Decision Tree classifier and also comparing it with the K-Nearest Neighbor classifier. Materials and methods-The lung cancer database includes records 32 samples (patients) and is therefore compiled with 32 ∗ 6 numerical data. The G power for samples is calculated from clincalc which contains two different groups where group 1 is taken as (n1=16) and for group 2 (n2=16), alpha (0.05), power (80 %) and enrollment ratio. Results-Implementation based on the MATLAB toolbox is done on CT lung images and the classification of these images is performed. In the proposed method, D-Tree numbers of samples are selected for each iteration and 90 % phase accuracy is obtained. There is a significant difference in Accuracy rate (P=0.072). Conclusion-The results of the study suggest that the accuracy of the decision tree algorithm is significantly higher than the nearest k-neighboring algorithm. [ABSTRACT FROM AUTHOR]

The primary objective of this study is to use Support Vector Machine (SVM) instead of the traditional Naive Bayes technique to extract patient-specific information from a dataset of lung cancer patients in order to calculate diagnostic accuracy (NB). The methods of Naive Bayes and Support Vector Machine are used in this study. Using the G power programme, we arrive at a sample size of 10 individuals per group with a pretest power of 80%, a significance level of 0.05, and a confidence interval (CI) of 95%. The innovative data analysis provided by Support Vector Machine for determining the likelihood of cancer is 92.45 percent, which is greater than the 84.67 percent provided by the Naive Bayes method. With a significance score of 0.88 (p>0.05), there is no statistically significant difference between the two groups. By extracting patient-specific information, the Support Vector Machine method outperforms the Naive bayes algorithm in making accurate cancer predictions. [ABSTRACT FROM AUTHOR]

Metrics such as accuracy, recall, and f-score will be used to compare the results of a decision tree approach to detecting lung cancer with those achieved by a novel polynomial support vector machine (SVM). The researchers have access to 1339 lung cancer patient samples because to the Kaggle collection. In order to determine the G power for samples, we need clinical data, which consists of two groups: group 1, with (n1=670) and group 2, with (n2=670), both with (alpha=0.05) and (power=80%) values. The f-score, recall, and precision were all computed. The collected data is split into two collections, one including 937 samples (representing 75% of the total) and the other containing 402 samples (representing the remaining 25%). (representing 25 percent). When comparing the decision tree with the polynomial support vector machine (SVM), the decision tree performed better, with values of 78.36%, 80.66%, and 79.54% for accuracy, recall, and f-score, respectively, while the innovative polynomial SVM performed worse, with values of 63.63%, 70%, and 66.66%. P0.001 is determined to be the threshold of significance. Based on the calculated f-score, we may conclude that the decision tree outperforms the novel polynomial SVM. [ABSTRACT FROM AUTHOR]

The primary objective of this research is to diagnose lung cancer more accurately utilizing the Support Vector Machine (SVM) method and K-Nearest Neighbors classification (KNN) technique. Materials and Methods - SVM was used in this study to detect lung cancer using 10 samples (N=10), while KNN was used to classify the samples using 10 samples (N=10). The accuracy of the two approaches is contrasted. Results: The SVM method outperforms the KNN approach in accuracy (96% vs. 68%). Conclusion - It is clear from the results of the experimental testing that SVM performs better on lung imaging datasets than existing classifiers. The findings indicate that, for the identification of lung cancer, the SVM algorithm appears to be significantly better (p<0.05). [ABSTRACT FROM AUTHOR]

To enhance lung cancer CT scan picture categorization utilising algorithms. Materials and Methods: Training dataset (n=185 [70%]) and test dataset (n=80 [30%]) are created from 265 lung cancer CT scan pictures. Weka tool uses Decision tree algorithm and KNN classifier for classification. Results and Discussions: Decision tree method classified lung cancer CT scan pictures with 99 percent accuracy and KNN classifier with 92 percent. Statistically, decision tree algorithms and KNN classifiers meet independent sample T-Test value (p<0.005) with G-power estimate of 0.8. Conclusion: The Decision tree approach outperforms the KNN classifier in lung cancer CT scan image categorization. [ABSTRACT FROM AUTHOR]

The aim of this research is to use the Decision Tree classifier to identify lung cancer in scanned pictures and compare its performance to that of the Support Vector Machine classifier. Methods and materials The lung cancer database contains information on 60 samples (patients). Clincalc's sample G power has two groups, with alpha (0.05), power (80%), and enrollment ratio (n1 = 30) for group 1 and (n2 = 30) for group 2. Decision Tree outperforms standard SVM classifiers in terms of accuracy, with a 95.13 percent success rate. According to the results of this study, the decision tree method is more accurate than the Support Vector Machine classifier. [ABSTRACT FROM AUTHOR]

One of the main causes of death in the world is caused by cancer. And one of them is Lung Cancer. According to World Health Organization, in 2014 the death rate caused by lung cancer in Indonesia was 21.8% in men and 9.1% in women with 30,865 cases of death caused by lung cancer each year in men and women. Many studies have been carried out on computational lung cancer. One of them is by implementing machine learning in detecting lung cancer. However, there are obstacles, namely the imbalance in the amount of data between patients and non-patients. So it takes an approach to overcome this imbalance. One of these methods is ADASYN which is then combined with the Random Forest classification algorithm. In this study, we will compare the results of the classification model performance in Random Forest before and after the ADASYN sampling method was used in the training process. The results of this study showed an increase in the performance of the Random Forest classification model with an AUC value of 0.859 after the ADASYN sampling method was carried out with an error rate of 4.9%. [ABSTRACT FROM AUTHOR]

Lung cancer is one of the most common causes of death according to WHO in 2020. One of the ways to detect lung cancer is through X-rays. Because the examination is generally carried out manually through the naked eye of experts, it is advisable to have an alternative to detect the disease as early as possible so that the patient can get the right treatment. This study aims to detect the presence of lung cancer from chest x-ray images with the application of deep learning, namely Convolutional Neural Network (CNN). In this study, the authors used 90 cancer images and 90 normal images. The research design stage consisted of pre-processing on x-ray images and identification using CNN. The research obtained an accuracy rate of 87%. [ABSTRACT FROM AUTHOR]

Lung cancer is one of the most prevalent cancers in the world and is responsible for most cancer-related fatalities. The present methods for identifying lung cancer, such as CT scans and biopsies, have drawbacks, such as being expensive, intrusive, and exposing patients to radiation. Convolutional neural networks (CNN), deep learning, and other machine learning approaches have recently demonstrated promising outcomes in medical image analysis, including lung cancer identification. The openly accessible Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) used a dataset of 1,010 lung nodules. The nodules in the dataset were both benign and malignant, and they were different sizes and shapes. The photos were preprocessed by being uniformly resized to 32x32 pixels and normalizing the pixel values to be between 0 and 1. The database was separated into a data-training set (80%) and a data-validating set (20%) at random. We built a CNN model with three convolutional layers, each followed by a max-pooling layer and a dropout layer to prevent overfitting. With a batch size of 32 and a learning rate of 0.001, the Adam optimizer was trained to perform model training. The model's sensitivity, specificity, and overall precision on the validation set were 96.6%, 94.7%, and 95.8%, respectively. To assess the accuracy of our CNN model, we compared it to the performance of four radiologists with varying levels of experience in the diagnosis of lung cancer.In terms of sensitivity, our CNN model outscored all four radiologists while matching their specificity levels. AUC of 0.98, showing great diagnostic accuracy, was reached by our CNN model according to a receiver operating characteristic (ROC) analysis we also carried out. Our research shows the promise of CNN models for precise and effective lung cancer nodule detection on CT scans. CNN models can help radiologists identify lung nodules with high accuracy, lowering the possibility of patients being ignored or misdiagnosed. Future research might examine the potential use of Deep networks in clinical decision-making and lung disease detection initiatives. [ABSTRACT FROM AUTHOR]

In this research work, an Efficient Segmentation and Classification (ESC) system for Lung Cancer Diagnosis (LCD) is developed. It consists of three main modules; Fusion of Different Lung Imaging Modalities (FDLIM) module, Segmentation of Lung Nodules (SLN) module and Classification of Lung Nodules (CLN) module. In the FDLIM module, two different imaging modalities Computed Tomography (CT) and Positron Emission Tomography (PET) lung images are fused. The lung nodules are detected in the SLN module and then in the CLN module they are classified into normal or abnormal. In the SLN module, the lung nodules are segmented from the fused images obtained from the aforementioned three fusion approaches. To the low frequency components of DTWT sub-bands are set zero before reconstruct the image by the inverse DTWT. Then, the fuzzy C-means clustering algorithm is employed to cluster the regions and post-processing is applied to detect the exact location of lung nodules. The performance metrics used to evaluate the SLN and CLN module are sensitivity, specificity and accuracy. The SLN module gives maximum average sensitivity of 97.92% with specificity of 97.84% while using the fused image obtained from the DTWT-CNN approach. It is observed that the CLN module that uses the fused image from the DTWT-CNN approach provides a higher sensitivity of 98% and specificity of 100%. It is noted that the performance of fusion approach in the frequency domain (WEFL and DTWT-CNN) is higher than spatial domain fusion approach (SSMR). The proposed system yields the overall accuracy of 99%. This research work mainly focused to reduce the diagnosis error through CAD. [ABSTRACT FROM AUTHOR]

Cellular breakdown in the lungs is a perilous and dangerous illness. Initially, it goes unnoticed and progresses, yet it risks life on the other side. Cellular breakdown in the lungs can be easily identified from CT scan images. Computer-assisted analysis in CT scans aids doctors in accurately identifying cancerous cells. The primary objective of this study is to evaluate various computational strategies, thoroughly examine the most effective existing techniques, identify their limitations and challenges, and ultimately propose new models that build upon the current best model. The approach used involved categorizing and ranking strategies for locating lung cancer cells based on detection accuracy. The method was assessed incrementally, revealing common constraints and shortcomings. Some methods are less precise, while others achieve higher accuracy using support vector machine algorithms; however, they fall short of 100 percent accuracy. Consequently, our research aims to enhance accuracy by up to 99.99 percent. [ABSTRACT FROM AUTHOR]

Lung cancer accounts for the majority of the deaths across the world. It's not only the smoking but there are numerous reasons for the occurrence of lung cancer. The 5-year survival rate for lung cancer is 56 % for the cases in which the disease is still present within the lungs. The recent advance in drug design has made Gefitinib, a popular drug utilized for the treatment of NSCLC. Gefitinib was permitted by US FDA Department in the year of 2003. Moreover available reports suggest that there is resistance for the action of gefitinib treatment because of changes in the PI3K/AKT signaling pathway. In this present work, insilico studies were performed with the assistance of Pubchem database to find the potent inhibitor against the lung cancer EGFR mutation. Computational tools such as molinspiration cheminformatics and OSIRIS property explorer were employed to check the efficacy of the screened drug molecules. Further, the data reduction of the molecules was carried out utilizing Patchdock software. Our research clearly indicates that CID: 5329022 which is an anilinoquinazoline derivative could be a potential drug molecule to overcome gefitinib resistance associated with NSCLC. [ABSTRACT FROM AUTHOR]

High-Z ion doped hydroxyapatite, including zirconium doped hydroxyapatite has prospects as drug candidates for x-ray induced dynamic therapy (XDT) in cancer therapy. Its nanosized combined with doped ion could assist ion doped hydroxyapatite accumulates in cancer cell compared to non doped hydroxyapatite. However the mechanism of ion doped hydroxyapatite internalization in cancer cell is currentle unknown. In this study, internalization of scandium-46 (46Sc) labeled zirconium doped hydroxyapatite (HApZr) and 46Sc non doped hydroxyapatite (HAp) in A549 lung cancer cell line was carried out to understand the effect of zirconium doping into HAp. Docking study was carried out to compared HApZr and HAp binding energy to several receptor proteins related to internalization including receptor tyrosine kinase of ERBB2 and PI3K/AKT protein kinase B. HApZr was internalized higher in lung cancer compared to HAp. Docking study revealed that binding energy of HApZr with ERBB2 and PI3K protein was lower compared to HAp. ERBB2 and PI3K protein are overexpressed in cancer cell thus could be a key for cancer survival pathway. Lower binding energy of HApZr stimulates higher uptake of HApZr in cancer cell compared to HAp as obtained in internalization study. These findings have important implications for further development of HApZr or other ion doped hydroxyapatite as potential agent for x-ray induced therapy of cancer. [ABSTRACT FROM AUTHOR]

Aim: Deep learning plays a vital role in image classification due to its effective and accurate results in classification, prediction, and recognition. The main objective of the study is to detect lung cancer using a low dose computed tomography lung image dataset with deep neural network techniques(Deep CNN and CNN). Materials and Methods: Two groups used in this study are Deep Convolutional Neural Network and Convolutional Neural Network with 5l5 lung images for each sample. Binary Classification is performed for Benign and Malignant lung cancer images using a Deep Convolutional neural network algorithm(N=l0) and Convolutional neural network algorithm(N=l0). Results and Discussion: The accuracy of lung cancer detection using a Deep convolutional neural network is 95% and the Convolutional neural network is 84% with a significance of p=0.03l. Attained significant accuracy ratio (p<0.05 independent sample T-test) in SPSS statistical analysis as well. Conclusion: The proposed Deep Convolutional neural network algorithm seems to be significantly better in predicting lung cancer with more accuracy than a convolutional neural network. [ABSTRACT FROM AUTHOR]

Aim: In medical images removal of noise is a challenging task. Lung cancer is one of the health care problems which need to be detected in an effective manner. The main aim of the study is to evaluate the peak signal-to-noise ratio parameters of lung CT images using Gabor filtering compared with Fast Fourier Transformation (FFT) technique. Materials and methods: Gabor filter is used for texture analysis and also analyzes the weather there is any other specific frequency content in CT image in specific region around a point or region of analysis. A total of 178 images are analysed for performance evaluation of gabor filter. Statistical analysis is carried out for the samples with a G Power of 0.8. Results: Images are evaluated for 10%,50%,90% of noise density. Values of PSNR (37%) and MSE (29%) for Gabor filters are found to be high compared to FFT filters. Conclusion: Performances of the filters applied on CT pictures were evaluated by image quality assessment like Mean-Squared Error (MSE) and Peak Signal/Noise ratio (PSNR). The experimental study shows that the Gabor filter performance is better in comparison to FFT filters in removing noises in CT imaging of carcinoma by having low MSE values and high PSNR values. [ABSTRACT FROM AUTHOR]

Computed Tomography (CT) is far and wide utilized to make a diagnosis and access thoracic diseases. The enhanced resolution of CT examination has resulted in a considerable investigation of statistics for analysis. Computerizing the scrutiny of such facts is consequently necessitate and fashioned a hastily emergent research region in medical imaging. The finding of thoracic diseases by means of image processing directs to a pre-processing step identified as "Lung segmentation" which portrays a wide range of techniques starts with simple Thresholding and numerous image processing elements are incorporated to progress segmentation, precision and heftiness. In image processing, techniques like image pre-processing, segmentation and feature extraction have been thrashed out in detail. This paper suggestions investigation of literature on computer examination of the lungs in CT scans and statements the Preprocessing ideas, segmentation of a choice of pulmonary arrangements, and Feature Extraction intended at recognition and categorization of chest abnormalities. As well as, research developments and disputes are recognized and instructions for further examinations are discussed. [ABSTRACT FROM AUTHOR]

Lung cancer has frequently surfaced as among the most lethal diseases that humanity has ever known. Early tumor identification is crucial in saving. X-rays and MRI scans may not be as successful as computed tomography (CT) scanning of the lungs in determining the presence of cancer. This study's key goals are to identify cancerous lung nodules from the provided inputs lung images and categorize lung cancer according to severity. This study applies cutting-edge machine learning techniques (SVM) to locate the Normal, Benign and Malignant lung cancer by training and extracting aspects of the CT images. SVM deep learning approaches offers the advantage of being able to handle random batches of data with large dimensionality. With each characteristic as input, the SVM's efficiency is tracked. The extracted findings reveal the superior performance of the SVM technique to predict the malignant CT images with high accuracy value reach to 100 %. The proposed technique to predict and identification of malignant CT images based on SVM machine learning considered as promising strategy to detect and categorize lung cancer in early phases. [ABSTRACT FROM AUTHOR]

Lung cancer is almost always caused by unchecked cell proliferation, and men and women are hit equally hard by it. As a consequence, it's tough to breathe both in and out. The most major causes of lung cancer in the globe are active smoking and passive exposure to secondhand smoke. Lung cancer mortality is rising in both young and elderly people when compared to other malignancies. A high mortality rate persists despite modern medical facilities that allow for precise diagnosis and efficient treatment. As a consequence, action must be taken as soon as possible to allow for an earlier and more precise diagnosis. Machine learning has had a major impact on the health industry because to its great computing capacity for early illness prediction and reliable data processing. We used a variety of machine learning methods to sort existing data on lung cancer into benign and malignant UCI machine learning repositories. The input data are first converted to binary before being categorized into cancerous and non-cancerous situations using the commonly used Weka programme. An accuracy rate of 81.25 percent in the comparative method shows that the suggested RBF classification is a successful technique for the classification of lung cancer data for classification purposes. [ABSTRACT FROM AUTHOR]

The world leading fatal disease is lung cancer, with an annual rate of approximately 1.8 million. Lung cancer is a condition in which aberrant cells divide and grow rapidly, culminating in a malignancy. Lung cancer cannot be prevented; however, its threat may be reduced. Therefore, early investigation of lung cancer is absolutely vital. The diagnosis of lung cancer is expensive and long-lasting with various examinations like x-rays and different diagnostic imaging strategies. As a result, finding novel ways of early and precise lung cancer identification is critical for effective therapy. This increases the demand for supervised learning methods in clinical diagnostics of lung cancer using medical datasets making the diagnosis system efficient. In this approach, the investigation aims at assessing the classification performance of several predictors inside the assessment to improve the efficiency of diagnosing lung cancer via distinct signs by evaluating the previous performance of various methods. The paper methodology includes selecting the input data, preprocessing, segmenting the data, feature selection, extraction, and selecting the optimal supervised learning approach like SVM (Support Vector Machine), ANN (Artificial Neural Network), NB (Naïve Bayes), KNN (K-Nearest Neighbor) etc. As a result, a comparative analysis has been performed on the lung cancer dataset. In the final outcome, Support Vector Machine is performing the best result with a comparison of other learning techniques. [ABSTRACT FROM AUTHOR]

The main aim is to measure and compare the accuracy of lung cancer prediction using the VGG19 and Inception V3 model. The performance was analysed on 989 CT images with 80% (G power). The dataset related to this work is collected from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases (IQ-OTH/NCCD). Convolution Neural Network (CNN) based Inception V3 and VGG19 methods used for prediction of lung cancer. The statistical analysis was done using the SPSS tool. Using G power (80%) the sample size of the two groups is 1978 (989×2) CT scan images. The proposed model CNN Inceptionv3 produced improved accuracy of 0.8634±0.05468 than the CNN-VGG19 with the significance value of 0.0145. It would be prudent that the proposed CNN-Inception V3 model produced high accuracy (%) compared with CNN-VGG-19 model. [ABSTRACT FROM AUTHOR]

Lung cancer becomes one of the serious diseases that lead to life threatening problems in the recent year. Regardless of age and healthy lifestyle the disease occur in any age depends on the health records and behavioral habits since it is a life threatening disease treating the lung cancer in early stages become mandatory. Early lung cancer are predictable bycategorizing the scanned images as tumor or nodule in the initial screening itself. In the proposed work early prediction of lung cancer is done using artificial intelligence models that consist of iterative training phase. The proposed model utilizes Luna 16 dataset. The problem behind the early prediction of lung tumor using CT images found in identifying the smaller pixels that resilient around the tumor area. In case of tumor or nodule prediction the problem occurs at their decision-making scenario whether the segmented area is tumor or nodule. These resilient pixels are corrected at the segmentation process itself. The proposed to study focused on working out the segmentation part and the classification path using artificial intelligence model called DeepStamp Boost Model (DSBM) is utilized. [ABSTRACT FROM AUTHOR]

Radon and its decay products constitute a potential environmental health hazard, and their measurement is therefore important. Indoor radon measurements were carried out in 20 dwellings at Madina in the La Nkwantanang Municipality, Greater Accra Region, during the dry season in Ghana in November 2019. The indoor radon concentrations ranged from 37.61±6.13 Bq/m3 to 334.30±18.28 Bq/m3. The mean indoor radon concentration was 151.51±14.71 Bq/m3, which exceeds the World Health Organization action level of 100 Bq/m3 and within the International Commission on Radiological Protection (ICRP) reference level of 100 Bq/m3 - 300 Bq/m3. The annual effective dose ranged from 0.939 ± 0.02 mSv/yr to 8.35±2.88 mSv/yr, with an average of 3.78±0.37mSv/yr. Given that radon is the second leading cause of lung cancer, it is necessary to increase the public's awareness about the gas and take action to reduce its levels in homes. [ABSTRACT FROM AUTHOR]

The objective of the study is to detect the Lungs Cancer positive patient with the help of Chest Diagnostic image dataset by using machine learning based on Genetic Artificial Neural Network Algorithm. To achieve accuracy a novel augmented dataset classification is used. Accuracy and Loss of Lungs Cancer detection are Performed from kaggel library. Dataset of 2400 chest image dataset with total sample size 30. The two groups Genetic Artificial Neural Network (N = 15) and Multilayer Perceptron(N = 15). The study proved that Genetic Artificial Neural Network achieved better accuracy as 99.66% which is higher, compared to Multilayer Perceptron accuracy as 99.13%. Finally, the Genetic Artificial Neural Network appears significantly better than Multilayer Perceptron. The statistical analysis shows significant differences between the sample groups. The two algorithmGenetic Artificial Neural Network and Multilayer Perceptron are statistically satisfied with the independent sample T-test value p = 0.001 (p < 0.005) with confidence level of 95%. Study shows, Genetic Artificial Neural Network seems better (Std. Error Mean = 1.96525) than Multilayer Perceptron (Std. Error Mean = 6.13974). [ABSTRACT FROM AUTHOR]

This study compares the Novel Deep Convolutional Neural Network algorithm with the Genetic Algorithm in an effort to detect lung cancer more accurately. Two organizations are involved in the proposed study to detect lung cancer. The Deep CNN method was in Group 1, while the Genetic Algorithm was in Group 2. A sample size calculation was made. It was determined that 40 samples altogether, with 20 samples each group, were collected. The predictive accuracy of the upgraded Deep CNN algorithm and the Genetic Algorithm were compared. With a p value of 0.047 (p0.05), CNN's accuracy (93.4%) greatly outperformed the Genetic Algorithm's (64.47%). The information was gathered from a number of sources for use in lung cancer prediction systems. The enhanced Deep CNN algorithm was used to improve accuracy. [ABSTRACT FROM AUTHOR]

Cancer is a disease with a high mortality rate. Cancer is developed when the cell does not undergo a cell division process, the presence of uncontrolled cell growth turns to tumor cells and spread to various other organ systems. Early detection of such cancer improves the chances of favourable outcomes. Despite the fact that the early prognosis of cancer has made considerable improvement. Lung cancer is the second leading cancer worldwide. The identification of lung cancer and lung nodule segmentation is a crucial preliminary step. The Deep Learning network works best for medical image automation. Deep learning models and computer vision applications are expanding rapidly in the modern era. This paper includes Computed Tomography (CT) images to segment challenging lung nodules. The modified U Net introduced in this paper performs the segmentation of lung nodules. The dataset is obtained from the Radiology Department at Chennai Rajiv Gandhi General Government Hospital. The ResNodNet outproduces the segmented nodule, the model combines Respath and U Net to facilitate the categorization of multi-featured data that has been proposed as ResNodNet. The classification results produced by the suggested method are accurate at 98.6%. [ABSTRACT FROM AUTHOR]

Truthful examination and detection of lung nodules are very crucial for prevention of lung cancer deaths. Radiologists have to spend their huge time for diagnosis of lung nodules from computed tomography (CT) images. Moreover, there is a high possibility of false positive or false negative results even after detecting lung nodule candidates. So, an effective computer aided detection (CADe) tool that can detect and classify lung nodules in lung CT images may be of immense help in this aspect and so researchers throughout the globe have been working on it. We too have been engaged in this field with an objective of developing efficient and novel CADe systems. This paper describes our developed 2D convolution neural network (2D CNN) model for classification of lung CT images into 2 important classes viz. benign & malignant. In our study, we have used 206 lung CT images in DICOM format collected from LIDC-IDRI open source database. Total 9 layers viz. input layer, convolution layer, ReLU Layer, convolution layer, ReLU layer, fully connected layer, fully connected layer, softmax layer and classification layer respectively have been used in the model. Experimental result of our model has achieved satisfying result with 63.64 % accuracy at initial learning rate: 0.01; validation frequency: 50; max epoch: 30 and mini batch size: 128. [ABSTRACT FROM AUTHOR]

Lung cancer has become a serious problem in the world. One way to classify lung cancer is to use machine learning. The problems in this study are how to apply support vector machine (SVM) as a classifier and artificial bee colony rate of change (ABC-ROC) as a feature selection method in the case of lung cancer classification; how to compare the accuracy values and the running time between SVM without reduce or select the features first, SVM with artificial bee colony (ABC) feature selection, and SVM with ABC-ROC feature selection in the case of lung cancer classification. This study aims to classify lung cancer using SVM with feature selection based on ABC-ROC algorithm. In this study, three types of classification were carried out, namely classification using Support Vector Machine (SVM) without feature reduction or feature selection, classification using SVM and ABC as feature selection method, and classification using SVM and ABC-ROC as feature selection. This study uses two datasets from the Kent Ridge Biomedical Dataset, namely Michigan lung cancer data consisting of 96 samples with 7129 features (genes) and Ontario lung cancer data consisting of 39 samples with 2880 features. Cancer is classified into two classes, namely cancer and non-cancerous. Hopefully, the results of this study to be useful for the community in classifying cancer, especially lung cancer, more accurate and faster. Furthermore, the results of this study could be useful to determining the genes that influence lung cancer. [ABSTRACT FROM AUTHOR]

Lung cancer is the most common cancer that kills many people across the world. Many computer-assisted algorithms are used for the analysis of this cancer. In this research, Random Forest and Support Vector Machine (SVM) algorithms are used to predict Lung Cancer. K-NN Algorithm is used for pre-processing the dataset and then, the existing algorithms such as Random Forest and SVM are applied in the dataset for diagnosing the lung cancer in the patients and a newly proposed algorithm, Optimized RF Algorithm combines the characteristics of Random Forest and SVM is used in this research. When compared with the Random Forest algorithm and Support Vector Machine, the results show that the Optimized RF Algorithm (Optimized-RF) gives better performance than the existing algorithms. [ABSTRACT FROM AUTHOR]

Diagnosis of cancer at an early stage helps to save human life. Among the most promising cancer diagnosis technologies, an electronic nose (e-nose) serves as a simple and cost-effective tool for the detection of lung cancer biomarkers in exhaled breath. The surface acoustic wave (SAW) is one of the viable e-nose technologies, which provides features like high sensitivity, small size, less expensive, and can detect a wide range of Volatile Organic Compounds (VOCs) present in the exhaled breath. The SAW propagation is confined to the surface and its amplitude reduces with respect to the depth of penetration. The SAW sensor can be produced easily on a piezoelectric substrate using interdigitated electrodes. Due to the interaction between the VOCs and the sensing layer on top of the piezoelectric material, the resonance frequency of SAW gets modulated. Thus, the shift in the resonance frequency of the SAW reflects the proportionate concentration of VOCs present in the human breath. In this paper, we propose the simulation and design techniques of the SAW sensor using the Finite Element Method (FEM). The proposed SAW sensor model comprises Aluminium Nitride (AlN) as a piezoelectric layer. Over which, the Poly-Iso-Butylene (PIB) layer is simulated and acts as a sensing material for cancer-related VOCs (biomarkers). The sensitivity analysis exhibits that the higher molar-mass VOCs like propyl-benzene, nonane, ethylbenzene, octane, and methyl-cyclopentane have better sensitivity compared to the other VOCs. This has been confirmed by the high resonance frequency shift due to the mass loading effect. [ABSTRACT FROM AUTHOR]

Detection of lung cancer has great clinical importance and increases the chance for patient survival. One of the most effective technologies to automatically detecting lung cancer with an accuracy of diagnosis, robustness, and detection speed is the computer-aided diagnosis (CAD). For this cause, lung cancer detection based on CAD techniques has been suggested and investigated in many research studies. The aim of this paper is to provide an overview of the relevant literature on lung cancer detection based on CAD techniques and a number of associated challenges. Authors believe that automatic CAD techniques will be the promising value to help doctors and radiologists to detect and diagnose lung cancer with high accuracy, robustness, efficiency and speed. [ABSTRACT FROM AUTHOR]

Recent advancements in deep learning have made it easier to identify and classify lung disorders in medical imaging. As a result, there are several works in the literature on the diagnosis of lung disorders using deep learning. The deep learning research for detecting lung illnesses in medical imaging is presented in this section. Only few research publications on deep learning for detecting lung disorders has been published in the recent five years. Early detection of coronavirus disease in 2019 (COVID-19) is crucial to control the pandemic. COVID-19 is spreading rapidly around the world. The use of computed tomography (CT) images enables rapid and accurate detection of COVID-19. The deep learning techniques of the proposed method are based on a Hadoop Distributed Deep Convolutional Neural Network (HdiDConvNNet) address the problem statement for early detection of lung diagnose. The purpose of our research is to use various distributed deep learning algorithms to distinguish CT scan images with COVID-19 and non-COVID 19. Clinicians can use automated COVID-19 diagnostics using CT scan images as a fast and efficient way to detect COVID - 19. Precision and Recall are both important factor for this research work, hence the results are analyzed in terms of F1-Score. The confusion matrix and results for the F1-Score, Precision, Recall, and overall Accuracy are also presented to provide a complete analysis of the Model performance. The proposed methods have had a significant impact in the country as a warning to society. Therefore, the existence of such a hypothesis for innovative research will significantly reduce the incidence of lung cancer deaths affected by Covid-19 and will be considered for prior public advice. [ABSTRACT FROM AUTHOR]

Radiotherapy helps kill cancer cells in patients. In the radiotherapy process, radiation quality assurance is needed to maintain consistency and safety in administering doses to the target. The implementation of radiotherapy in patients requires planning made by medical physicists. In this study, radiotherapy treatment planning was carried out using the 3D Slicer-SlicerRT in the case of lung cancer with the diagnosis of stage II squamous cell carcinoma, male sex and consisted of 1 nodule. Patient data is obtained from The Cancer Imaging Archive, NSCLC-Radiomics. The method in this study began with processing patient data with a total fraction recipe of 60 Gy/30 and 63 Gy/30. The variations given are combination gantry angles of 0°,45°,90°,135°,180°, and 225°, with the number of beams being 4, 5, and 6. Furthermore, the value of the homogeneity index, tissue density, and electron density was evaluated. Dosage planning is limited to 95−107% of the dosage determined based on the ICRU 50. This study obtained the results of tissue density and electron density relatively by the reference standards for each organ. The treatment planning results are by the total standard and have the best homogeneity index of 0.25449 for five beams. [ABSTRACT FROM AUTHOR]

Radiation dose is the basis used to optimize lung cancer treatment, requiring the right and accurate amount. One of the steps used in optimizing treatment is radiotherapy treatment planning, which aims to maximize the dose targeted at tumor cells and minimize the dose to healthy organs. This study aims to evaluate the fulfillment of total dose standards for healthy organs and the homogeneity of dose distribution using the 3D slicer-Slicer RT software. The method used in this study used two CT data and RT-Structures of NSCLC-Radiomics with a diagnosis of stage IIIB squamous cell carcinoma from The Cancer Imaging Archive (TCIA), the exact location of cancer, and only one nodule. Network density values are calculated using segment statistics on 3D Slicer based on CT-DICOM information. Meanwhile, the treatment plan was built using 3D Slicer-SlicerRT with a 60 Gy/30 fraction dose. The treatment design uses four planes, and optimization combines the gantry angle and beams weight. The results showed that the treatment planning system using 3D Slicer-SlicerRT met the total dose standard for healthy organs and had a homogeneity index for the first and second patient was 0.004 and 0.009, respectively. [ABSTRACT FROM AUTHOR]

In computer vision applications, edges of the objects in the image are determined as one of the prime stages. Among various types of Edge Detection (ED) techniques we have, Canny Edge Detector (CED) provides better results. In this paper a new architecture for CED has been introduced and is called Dual port Block Random Access Memory (DBRAM). In this method a hardware analysis is done and performance parameters such as LUT, flip flop, slices and frequency by FPGA Virtex 6 are carried out. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has made substantial progress in healthcare during the previous two decades. During this time, researchers discovered the true causes of a number of ailments, established new diagnostic tools, and produced novel remedies. Despite these breakthroughs, diseases like cancer continue to haunt us because we are still susceptible to them. Cancer is the second leading cause of death in the world, killing one out of every ten individuals. Colon and lung cancer are two of the most serious and lethal diseases that individuals worldwide confront, and they have become a major medical concern. On the other hand, early identification of the disease considerably increases the odds of survival. This study employs the EfficientNetB7 Transfer Learning (TL) technique to develop a classification model that incorporates histopathology images to distinguish between five types of lung and colon tissues (two benign and three malignant). Furthermore, using histogram photos from the Kaggle collection, a mechanism for predicting lung and colon cancer has been developed. Precision, recall, and f1score, on the other hand, are used to assess the model#x2019;s performance. The EfficientNetB7 model attained a significant accuracy of 98 percent, according to the results. This model will aid medical experts in developing an effective and appropriate approach for detecting various types of lung and colon cancers. [ABSTRACT FROM AUTHOR]

Lung cancer is the leading cause of male cancer mortality and the second most common cancer for women following breast cancer. Lung cancer is also considered the most common among occupational-related cancers. One common risk factor is exposure to particulate matter, especially PM2.5 (particles with aerodynamic diameter ≤ 2.5 µm). The study aims to perform a critical review, explore, and robust summary of the relationships between exposure to particulate matter and lung cancer mortality in global workers. A comprehensive search was carried out in the bibliographic databases or Medical Subject Headings, including Science Direct, PubMed, and Medline. The search was applied to the articles that were published between 2010 and 2020. The only study provided Hazard ratio estimation further analyzed in the quantitative analysis. With strict literature search and screening processes, it yielded 45 articles eligible with the abstract assessment. Six studies were eligible for the full-text requirement, and three were analyzed in the meta-analysis. Five prospective cohort study and one case-control study was employed in the meta-regression. The main composition of exposure is a PM2.5 derived from silica and mix substances. Workplace settings vary from construction, Electric Arc Furnace (EAC), hospital, metal mines, and pottery factories. Fixed and random effect models and meta-regression are used to obtain pooled estimates of Hazard Ratio (HR), and P-value functions are used to demonstrate the consistency of results. Forest plot analysis reported I2 = 96%, HR = 1.78 [1.74, 1.83], p-value = 0.001. It indicated that the studies are considered homogeneous, and there is supporting evidence that there is an association between particulate matter exposure and lung cancer mortality. The exposure of particulate matter in the workplace (Silica, metal, and combined substances) may be the main factor for the mortality of workers, both male and female. [ABSTRACT FROM AUTHOR]

The impact of tobacco smoke on human wellbeing is a significant issue around the world. The tobacco epidemic drives deaths in excess of 8 million individuals per year around the globe. Tobacco Smoking being the reason of many health disorder like lung infection and atherosclerosis. Tobacco smoking one of danger factor for the turn of events of chronic obstructive pulmonary disease, damages the peripheral air ways and obliteration of lung parenchyma and emphysema. Lungs are the leading section of the respiratory tract and most affected by the tobacco smoking. Cigarette smoke contain nicotine, carbon monoxide, tar, anabasine, nornicotine and other toxic chemicals and they are carcinogenic in nature. The consumption of tobacco carcinogens evaluating life risk, common carcinogens are aldehydes and other organic compounds like benzene and butadiene. Nicotine is the reason why individuals keep on smoking, regardless of the notable antagonistic impacts on health. Nicotine behaves as both an energizer and a depressant to the central nervous system. List of carcinogens have been identified i.e., aromatic amines, polycyclic aromatic hydrocarbons and N-nitrosamines. The goal of this review is to present the impacts of smoking on smokers. [ABSTRACT FROM AUTHOR]

The main aim of this work is to calculate the accuracy in early prediction of lung cancer using CT images.: The dataset of 989 lung images has been taken from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases with 80% of G-power. The proposed method contains image preprocessing, augmentation and features extraction of images using Convolution Neural Network (CNN) based VGG16 and VGG19 models. Based on training (80%), validation (18%) and testing (2%) of the dataset in python software the accuracy and precision is calculated. A comparative analysis is made between two algorithms using SPSS software. Results : The proposed model CNN-VGG19 produced improved accuracy of 0.9599±0.0217 than VGG 16 with the significance value of <0.05It would be prudent that the proposed CNN-VGG-19 model produced high accuracy (%) results compared with CNN-VGG16 model. [ABSTRACT FROM AUTHOR]

Although cancer is a broad term, it is an important problem that causes a high rate of death. It indicates disease that occurs when cellular changes cause cells to grow and divide uncontrollably. Cancerous cells can form tumors, damage the immune system, and cause other aberrations that prevent the body from functioning properly. In particular, lung cancer is the type of cancer with the highest death rate in the last five years. The important thing in lung cancer is early diagnosis and diagnosis to ensure the survival of patients. In this study, a model that automatically detects lung cancer has been developed in order to detect lung cancer early and take the necessary precautions at the first stage of the disease. The aim of our study is to diagnose the presence of lung cancer cells based on attributes and information from human symptoms. In our study, a dataset consisting of 26 features and 3 classes determining lung cancer as low, medium and high was used. Some preprocessing and transformations have been done to make the data more suitable for predictive analysis. The first 26 features were used as the inputs of the model. The lung cancer feature was used as the predicted output based on the input features. The values of the attributes are normalized. In the first stage, data preprocessing was carried out with various data mining techniques in order to process the data more easily and increase the performance. In the proposed model, feedforward backpropagation Artificial Neural Network model was used to detect the presence of lung cancer in the body of the person. Unlike other studies, the factors that cause lung cancer by producing our own neural network have been determined. When the results obtained are compared with the studies in the literature, it has been observed that it gives very successful results. [ABSTRACT FROM AUTHOR]

Use of gene expression data from microarrays can be used to identify and treat a variety of diseases. There are duplicated high-dimensional feature genes in the microarray gene expression data, as well as smaller training and test samples. Lung cancer strikes the elderly the worst. Only a small fraction of persons diagnosed with lung cancer are under the age of 45. When a person is discovered, they are typically over the age of 70. Lung cancer is the most common kind of cancer. This study aims to find the best classifier for Lung cancer gene data to identify normal and abnormal patterns. The statistical characteristics of precision, accuracy, GDR, recall, and f-measure were used to compare the performance of the four classifiers. Extracted information is categorized using PCA, Detrend FA, EM, and Detrend FA with EM classifiers. PCA and Detrend FA. When using the EM Classifier, Detrend FA beats the competition, achieving an accuracy of 93.36% and a GDR of 84.68%. [ABSTRACT FROM AUTHOR]

Lung cancer is deadly cancer same as colon cancer, both of them can grow simultaneously. Most researchers conduct research to detect one disease on one single body organ. So, in this study, we proposed a computer-aided diagnosing system using the Convolutional Neural Network (CNN) to detect lung and colon cancer tissues on the LC25000 dataset. The LC25000 dataset contains 25000 histopathological color image samples of colon and lung tissues which indicated cancer (adenocarcinoma) or not. In this study, we used three pre-trained CNN models, which are ShuffleNet V2, GoogLeNet, and ResNet18 also one simple customized CNN model. From the evaluation metrics tables given in this study, the highest accuracy to classify lung cancer was gained by ResNet18 with 98.82% accuracy but the shortest training time gained by ShuffleNet V2 with 1749.5 seconds. ShuffleNet V2 was the best model used to classify colon data, it gives 99.87% accuracy with the fastest training times 1202.3 seconds. The customized CNN model proposed by us get 93.02% accuracy to classify lung cancer and 88.26% accuracy for colon cancer. The proposed CNN model also gained the shortest training time which was better than GoogLeNet and ResNet18. [ABSTRACT FROM AUTHOR]

In most nations, lung cancer (LC) is the main cause to mortality cases occurring due to tumors to males and females. Lung nodules (masses) are recognized through digital technologies support precise diagnosis using medical imaging techniques such as CT-scan, X-rays and MRI. As the nodules are normally connected to the blood vessels, identification of lung nodules is a difficult task. Several studies illustrate that diagnosing or detecting such cases earlier is regarded the best successful method to counter this disease. Many systems have been developed that automatically identify lung tumors by using magnetic resonance spectroscopy and pattern recognition methods. Despite the encouraging consistency of the classification, none of these schemes have set their course in clinical practice, which also concerns the lack of clarity concerning the process of taking decisions. In this paper, we present a systematic mapping study on lung tumors recognition. After four sorting methods, we obtained 375 relevant studies in total. After applying four filters manually, 48 papers as primary studies related to the main topic are selected as listed in Appendix (A). The selected papers classified them with respect to several facets. The results provide an overview of the existing relevant studies in reported in the literature, highlight focus areas and research gaps. [ABSTRACT FROM AUTHOR]

Copyright of International Science, Culture & Sports Congress is the property of International Science Culture & Sports Association (UBIKS) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)