scholarly journals “ EARLY PREDICTION OF LUNG CANCER DETECTION USING EXTENDED CONVOLUTIONAL NEURAL NETWORKS”

2021 ◽  
Vol 58 (1) ◽  
pp. 5614-5624
Author(s):  
Dr. Asadi Srinivasulu, Dr. Umesh Neelakantan, Tarkeshwar Barua
Keyword(s):  
Lung Cancer ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Cancer Detection ◽  
Computational Cost ◽  
Malignant Growth ◽  
Huge Number ◽  
Threat Level ◽  
Precision Time ◽  
Lung Cancer Detection

Lung disease is one of the significant reasons for malignancy related passing because of its forceful nature and postponed discoveries at cutting edge stages. Early discovery of disease would encourage in sparing a huge number of lives over the globe consistently. Lung malignant growth discovery at beginning time has gotten significant and furthermore simple with picture handling and profound learning systems. Lung Cancer side effects are persistent cough, chest torment that deteriorates with profound breathing, roughness, unexplained loss of hunger and weight, coughing up blood or rust-shaded mucus, brevity of breath, bronchitis, pneumonia or different diseases that continue repeating. Lung quiet Computer Tomography (CT) check pictures are utilized to identify and arrange the lung knobs and to recognize the threat level of that knob. Extended Convolutional Neural Networks (ECNN) work achieved relative examination with parameters like precision, time intricacy and elite, lessens computational cost, and works with modest quantity of preparing information is superior to the current framework. consumers.

scholarly journals A hybrid model based on convolutional neural networks and fuzzy kernel K-medoids for lung cancer detection

2021 ◽  
Vol 24 (1) ◽  
pp. 126
Author(s):  
Glori Stephani Saragih ◽  
Zuherman Rustam ◽  
Jane Eva Aurelia
Keyword(s):  
Lung Cancer ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Hybrid Model ◽  
Cancer Detection ◽  
High Performance ◽  
Correct Diagnosis ◽  
Computational Time ◽  
Model Based ◽  
Lung Cancer Detection

Lung cancer is the deadliest cancer worldwide. Correct diagnosis of lung cancer is one of the main tasks that is challenging tasks, so the patient can be treated as soon as possible. In this research, we proposed a hybrid model based on convolutional neural networks (CNN) and fuzzy kernel k-medoids (FKKM) for lung cancer detection, where the magnetic resonance imaging (MRI) images are transmitted to CNN, and then the output is used as new input for FKKM. The dataset used in this research consist of MRI images taken from someone who had lung cancer with the treatment of anti programmed cell death-1 (anti-PD1) immunotherapy in 2016 that obtained from the cancer imaging archive. The proposed method obtained accuracy, sensitivity, precision, specificity, and F1-score 100% by using radial basis function (RBF) kernel with sigma of {10<sub>­</sub>­<sup>-8</sup>, 10<sub>­</sub>­<sup>-4</sup>, 10<sub>­</sub>­<sup>-3</sup>, 5x10<sub>­</sub>­<sup>-2</sup>, 10<sub>­</sub>­<sup>-1</sup>, 1, 10­­<sup>4</sup>} in 20-fold cross-validation. The computational time is only taking less than 10 seconds to forward dataset to CNN and 3.85 ± 0.6 seconds in FKKM model. So, the proposed method is more efficient in time and has a high performance for detecting lung cancer from MRI images.

scholarly journals Lung Cancer Detection using CT SCAN Images

2021 ◽  
pp. 611-633
Author(s):  
Dr. M. V. Karthikeyan ◽  
Aravindh. S ◽  
P. Laxman Guru Vignesh
Keyword(s):  
Lung Cancer ◽  
Cancer Detection ◽  
Imaging Modality ◽  
Lung Nodule ◽  
Computational Cost ◽  
Pulmonary Nodules ◽  
Detection Performance ◽  
Lung Segmentation ◽  
Wide Range ◽  
Lung Cancer Detection

Detection of pulmonary nodules has a crucial effect on the diagnosis of lung cancer, but the detection is a nontrivial task, not only because the appearance of pulmonary nodules varies in a wide range, but also because nodule densities have low contrast against adjacent vessel segments and other lung tissues. Computed tomography (CT) has been shown as the most popular imaging modality for nodule detection, because it has the ability to provide reliable image textures for the detection of small nodules. The development of lung nodule CADe systems using CT imaging modality has made good progress over the past decade. Generally, such CADe systems consist of three stages: 1) image pre-processing, 2) initial nodule candidates (INCs) identification, and 3) false positive (FP) reduction of the INCs with preservation of the true positives (TPs). In the pre-processing stage, the system aims to largely reduce the search space to the lungs, where a segmentation of the lungs from the entire chest volume is usually required. Because of the high image contrast between lung fields and the surrounding body tissue, image intensity-based simple thresholding is effective, and is currently the most commonly used technique for lung segmentation. This paper proposes an adaptive solution to mitigate the difficulty of thresholding-based method in lung segmentation. Sufficient detection power for nodule candidates is inevitably accompanied by many (obvious) FPs. A rule-based filtering operation is often employed to cheaply and drastically reduce the number of obvious FPs, so that their influence on the computationally more expensive learning process can be eliminated. In general, FP reduction using machine learning has been extensively studied in the literature. Compared with unsupervised learning that aims to find hidden structures in unlabelled data, supervised learning, which aims to infer a function from labelled training data, is more frequently used to design a CADe system. Compared with the existing approaches, the morphology based lung cancer detection can be an alternative with either comparable detection performance and less computational cost, or comparable cost and better detection performance.

scholarly journals A Deep Analysis of Google Net and Alex Net for Lung Cancer Detection

2019 ◽  
Vol 9 (2) ◽  
pp. 395-399
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Neural Networks ◽  
Cancer Detection ◽  
Research Work ◽  
Imaging Diagnosis ◽  
Layered Architecture ◽  
Initial Learning ◽  
In The Beginning ◽  
Lung Cancer Detection

Lung cancer is the major cancer that cannot be disregarded intentionally and causes deceased with late healthcare. Now, Computed Tomography(CT) scan allows the doctors to recognize the lung cancer in the beginning of the stage. Majority of cases are tends to be failed in diagnosis of determining the lung cancer eventhough the doctors are experienced, they failed to detect the cancer. Deep learning is the important technique that can be applicable in medical imaging diagnosis. In this paper, the implementation of Convolutional Neural Networks such as GoogleNet (Inception) and AlexNet are analyzed for the lung cancer detection. The cancer images from LIDC-IDRI dataset is used for this research work. The Preprocessed cancer images are trained using GoogleNet and AlexNet to determine the cancer affected part of the lungs. The identification of lung cancer by using GoogLeNet and AlexNet are used for training the network, and image classification. These networks are provided with layered architecture for classification. We have found that AlexNet and GoogLeNet provides the comparable results by including parameters like time, initial learning rate and accuracy

Lung Cancer Detection Using Deep Convolutional Neural Network

2021 ◽  
Vol 11 (4) ◽  
pp. 13-20
Author(s):  
Syed Farhan Hyder Abidi ◽  
Sumukhi T. ◽  
Vinod Kumar H. ◽  
Santhosh B.
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Lung Cancer ◽  
Early Detection ◽  
Convolutional Neural Network ◽  
Cancer Detection ◽  
Neural System ◽  
Malignant Growth ◽  
The World ◽  
Lung Cancer Detection

Lung malignant growth is one of the most threatening ailments affecting most of the nations in the world, and detection in earlier stages has been a challenge. Early detection can help in saving many lives. This paper shows a methodology that uses a convolutional neural network (CNN) in machine learning for the detection of tumours in the lung. The specificity of the model is desirable and dependable and increasingly productive in contrast to the accuracy shown by conventional neural system frameworks.

Sign in / Sign up

Export Citation Format

Share Document