Machine Learning Based Lung Cancer Disease Prediction System (original) (raw)
Related papers
Lung Cancer Detection Using Region Based Convolutional Neural Network (R-CNN
Lung Cancer is a risky disease that causes human to death at primary age and it is an unrestrained cell growth in tissues on the lung. The effective identification of the lung nodule importantly leads to the chance of lung cancer risk assessment. Finding the precise locations of lung nodules are a dangerous and complicated task. Nowadays, Image processing methods are commonly used in several medical areas for improvement of image for former detection and treatment stages. Medical image segmentation is a critical step in evolving Computer-Aided Diagnosis (CAD), which supports the physician to admit an suitable procedure about the clinical case. The goal of segmentation is to alter interpretation of the image and do it easy to examine. Precise lung segmentation from Computed Tomography (CT) is a hard task due to the uneven shape and countless ambiguity in lung edges with the background. Here, we proposed a new identification model for Lung Cancer Nodule using Region based semantic segmentation algorithm: R-CNN (Regions with CNN feature). Our proposed approach follows effective image processing methods as step by step procedure as Preprocessing, Gray-scale conversion, Image Enhancement, Image Segmentation, Feature extraction and Cancer Nodule detection. For this research, LUNA16 dataset is used, which has 3D image of lungs which is deposited in around 180 2D image slices according to their image number. The dataset is composed from Kaggle repository. Our proposed method produced enhanced result on all the tested images compared with the results of earlier research works.
Lung Cancer Detection using Fusion, CNN and YOLO in MATLAB
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2023
Lung Cancer is one of the major causes of deaths in India. Various data analytics and classification approaches have been used to diagnose and find lung cancer in numerous cases. Lung Cancer can only be cured by early tumour diagnosis because the basis of the diseases is yet unknown, making prevention impossible. In order to classify the existence of lung cancer/tumour in a CT picture and PET image, a lung cancer detection method using image processing and deep learning is applied. Using Fusion technique, we first obtain CT scans, then PET images of the same patient, then combine both images into one. The classification carried out using image feature extraction. As a result, the combined CT and PET scan images of the patient are classified as normal or abnormal. The tumour component of the abnormal photos is the focus of the detecting process. Using YOLO and CNN, an effective strategy to identify lung cancer and its phases is one that also seeks to produce more precise results.
Prediction of Lung Cancer Using Convolutional Neural Network (CNN)
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Early prediction of lung nodules is right now the one of the most effective approaches to treat lung diseases. Accordingly, computer-aided diagnosis (CAD) of lung nodules has received a lot of attention over the previous decade., whose objective is to productively identify, portion lung nodules and arrange them as whether they are generous or harmful. Powerful recognition of such nodules stays a test because of their intervention fit as a fiddle, size and surface. This paper aims to classify and community malignant development in the lung using CNN algorithm. This paper proposes a technique that uses a Convolutionary Neural Network (CNN) to order tumors that are identified as dangerous or amiable in lung disease screening thought tomography filters. CNNs have remarkable features, such as taking into account spatial invariance at different part extraction. As a progressively mechanized methodology, the CNN technique uses picture information as input information and can be straightforwardly classified as yield. The machine will detect the image of the lung knob participant in characteristics with various targets and dimensions when observing the disruption in the standard representation of the pneumonic knob due to its radiological complexity and fluctuation of sizes and shapes, thereby doing the constructive side of the classification function and enhancing the precision of classification steps
YOLOv8-Based Lung Nodule Detection: A Novel Hybrid Deep Learning Model Proposal
IRJET, 2023
Small oval or circular masses identified in the lungs are known as lung nodules. When these nodules are smaller than 3 cm, they are often considered less concerning; however, over time, they may increase in size, potentially leading to more serious consequences. Early detection of these nodules and timely preventive measures are crucial to impede their progression to malignancy. Conventional diagnostic methods like computerized tomography (CT) and radiographic imaging techniques are utilized for this purpose. Nevertheless, these approaches can either subject patients to excessive radiation or prove inadequate in detecting small nodules. As a result, various deep learning-based image processing techniques are being explored for lung nodule detection. In this study, a novel deep-learning model is proposed for the automated real- time detection of lung nodules. The proposed model exhibits a remarkable accuracy of 92.3% in nodule detection, along with a sensitivity of 88.5% and a mean average precision (mAP) of 53.5%. The model is built using the YOLOv8 architecture, with the YOLOv8m configuration yielding the best results. Additionally, graphical comparisons with existing studies in the literature demonstrate the effectiveness of the training model
Lung cancer detection using Convolutional Neural Network (CNN)
International Journal of Advance Research, Ideas and Innovations in Technology, 2019
Lung cancer is a dangerous disease that taking human life rapidly worldwide. The death of the people is increasing exponentially because of lung cancer. In order to reduce the disease and save a human's life, the automated system is needed. The purpose of the lung cancer detection system is able to detect and provide reliable information to doctors and clinicians from the medical image. To minimize this problem, many systems have been proposed by using different image processing techniques, machine learning, and deep learning techniques. A computed tomography (CT) imaging modality is an efficient technique for medical screening used for lung cancer detection and diagnosis. Physician and radiologist use the CT scan images to analyze, interpret and diagnose the lung cancer from lung tissues. However, in most cases, obtaining an accurate diagnosis result without using the extra medical tool known as a computer- Aid detection and Diagnosis (CAD) system is tedious work for many physicians. To obtain an accurate result from computer-aided diagnosis system lung segmentation methods are basic once. So in this project, we have used different lung segmentation and nodules segmentation methods. Our work has consisted of preprocessing, and lung segmentation by using thresholding, and also used the U-net model for detection of the candidate nodules of the patient’s lung CT scan and classification methodology. We have used a convolutional neural network and designed a 3D CNN model that has a 0.77% accuracy performance.
Lung carcinoma detection at premature stage using deep learning techniques
AGRIVOLTAICS2021 CONFERENCE: Connecting Agrivoltaics Worldwide
Lung cancer is one of the commonest diseases globally and accounts for more deaths from lung cancer than other ones. We did an exact review of the distributed things on the study of disease transmission, conclusion, and treatment of lung cancer and as the dispersion of lung cancer is rapidly going on, it reaches the epidemic range or peak level. Besides, it has beaten the earlier commonest outline of cancer and is presently the commonest harm in men and women. Different modalities for early recognition through screening are being researched and it is observed that the majority of the patients have died due to late detection of this disease so recognition at the premature stage, as well as accurate detection of a lung nodule, is very much necessary so the most challenging thing is to develop a robust method for nodule detection that is why the main objective of this paper is early detection, minimizing the false rate, as well as improving accuracy. In the paper, a new model is proposed based on deep-learning for the pinpointing of region precisely, as we know there is a huge advancement in Deep convolutional neural networks in pre-processing, we adopted Three-dimensional Convolutional Neural Network) for the prognosis of lung cancer from the CT images of the long-sufferer. As one knows about the convolution neural network, it makes things easier to extract significant data by processing the images of the dataset. Gradient-weighted class activation mapping strategies can convey the information by visualization for precise judgment in lung knot by point-up the adversely affected area.
Lung Cancer Detection using Image Processing and CNN
2021
Cancer is known to be one of the most dangerous health problems in the world and among it, lung cancer is known to be the most serious cancer with the smallest survival rate. The lung cancer risk population is also very high as compared to other deadly diseases, for example, cardiovascular diseases. Therefore, early detection of lung cancer is a must for survival. Nowadays, a lot of research has been done using Convolutional Neural Networks in the medical field. Image classification is one of the methods to detect cancer at early stages. First, the datasets for CT scans are accessed from Kaggle. Images are refined with the pre-processing method. The image dataset will be trained on two different models namely~ Manual CNN and AlexNet. Further, the model producing the highest accuracy will be chosen and the processed images will be used to predict whether the CT scan image is malignant (cancerous), benign (non-cancerous) or normal. Keywords― Lung Cancer Classification, Image Data Augm...
IRJET- An Approach for Lung Cancer Detection using Deep Learning
IRJET, 2020
Lung malignant growth is a perilous sickness that taking human life quickly around the world. The passing of the individuals is expanding exponentially on account of lung malignant growth. So as to lessen the illness and spare a human's life, the mechanized framework is required. The motivation behind the lung malignant growth identification framework can identify and give dependable data to specialists and clinicians from the clinical picture. To limit this issue, numerous frameworks have been proposed by utilizing diverse picture preparing methods, AI, and profound learning strategies. A registered tomography (CT) imaging methodology is a proficient procedure for clinical screening utilized for lung disease location and analysis. Doctor and radiologist utilize the CT examine pictures to investigate, decipher and analyze the lung malignant growth from lung tissues. Be that as it may, much of the time, getting an exact determination result without utilizing the additional clinical device known as a PC Aid identification and Diagnosis (CAD) framework is monotonous work for some doctors. To get a precise outcome from PC supported analysis framework lung disease identification techniques are essential once. Machine learning algorithms such as support vector machines are often used to detect and classify tumors. But they are regularly restricted by the presumptions we make when we characterize highlights. This outcomes in decreased affectability. Nonetheless, profound learning could be perfect arrangement in light of the fact that these calculations can take in highlights from crude picture information. One test in actualizing these calculations is the shortage of named clinical picture information. While this is a confinement for all uses of profound learning, it is all the more so for clinical picture information in view of patient classification concerns. In this exploration we manufacture a convolutional neural system, train it, and have it distinguish lung cancer of the patient's lung CT scan and classification methodology. We have used a convolutional neural network and designed a 3D CNN model that has a 0.97% accuracy performance. Our model has a precision with 87.31 %, recall with 74.46 % and specificity with 97.68 %.
Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
IEEE Access, 2021
Early pulmonary nodule detection is very important in lung cancer diagnosis and screening. Most state-of-the-art lung nodule detection models are based on Faster Region-based Convolutional Neural Network (Faster R-CNN) due to its superior performance. However, this object detection approach faces difficulties with the variety of nodule sizes in training datasets. In this paper, we propose a novel Computer-Aided Detection (CAD) system based on Faster R-CNN model with adaptive anchor box for lung nodule detection. Our method employs ground-truth nodule sizes in the training dataset to generate adaptive anchor box sizes of Faster R-CNN. Learned anchors are used as hyper-parameter to boost Faster R-CNN's detection performance. A residual convolutional neural network is proposed to reduce false positives from Faster R-CNN's output. Our method is trained and tested on the largest publicly available LUNA16 dataset. Experiments show that our proposed system achieves a high sensitivity of 95.64% at 1.72 false positives per scan, and a Competition Performance Metric (CPM) score of 88.2%, which outperforms other recent stateof-the-art detection methods. The false positive reduction network achieves a sensitivity of 93.8%, specificity of 97.6% and accuracy of 95.7%. An additional evaluation on a completely independent SPIE-AAPM dataset demonstrates the generalization of our proposed model with 89.3% sensitivity.
The current paper is aimed at examining the use of machine learning approaches for lung cancer detection and classification using medical imaging data. In order to create the model, we collected a comprehensive dataset of 2400 images of lung cancer at different stages and healthy pictures. These data were preprocessed, and several approaches to the feature extraction were considered, namely Histogram of Oriented Gradients , and Local Binary Patterns. In addition, we attempted to use deep learning representations to determine their usefulness in this case. Moreover, these features were used for four ML models, namely Convolutional Neural Network , ResNet-18, , and VGG-19, to determine the most suitable one. To evaluate the general performance of these models, all the characteristic points were taken into account, such as the precision, recall, F1 score, accuracy, and confusion matrices. The results of the primary analysis indicate that the accuracy of our proposed model was the highest, 96.86%. The other places were taken by other deep learning architectures, which also demonstrate high level performance. In general, we may conclude that the findings show it is possible to use ML algorithms to improve the quality of clinical decisions and make the process of lung cancer detection and classification more accurate. At the same time, we were able to provide a comprehensive evaluation of all these results and the thorough analysis of the general performance of each model. This may serve as the basis for the subsequent improvements and changes that would allow enhancing the general quality of diagnostics and training more advanced models.