Lung CT Images Research Articles

Lung CT Image Segmentation Using Reinforcement Learning

Nowadays, lung disease is a major global problem in the world. Many of the lung diseases are untreatable and reduce the life span of the individual. Initial diagnosis of these diseases can help to completely cure the illness and reduce disease progression. Diagnosis of lung disease is often made based on CT scan images of the lungs. But the diagnosis of lung disease in CT images is a complicated and challenging task. Such a challenge is due to the noise of imaging, the lack of transparency of the image, the intensity of the lighting of some components, and so on. Eliminating these issues makes it easy to diagnose the disease for specialized physicians as well as existing automated diagnostic systems. In this paper, we propose a novel approach for lung CT image segmentation that solves some of these challenges. Also, correct accurate segmentation of these images can help to automatically detect lung diseases. The correct segmentation means a precise determination of the intensity of each area’s brightness, the exact location of the pixels in each area and the preservation of the original image. We employed a reinforcement-based approach for our image segmentation. The proposed method produces the image without noise, and the image components are split with the best accuracy. To evaluate our approach, we manually generated 200 labelled lung CT images. After that, the proposed method, along with two recently published approaches is evaluated against our generated dataset. This comparative evaluation is conducted in two qualitative and quantitative ways. For the qualitative comparison, we employed the consultation of two ultrasound radiologists for evaluating the results of our approach. We also used a similarity measurement to quantitatively evaluate the performance of our proposed segmentation method. In both evaluation approaches, the proposed algorithm provides better performance compared to the other methods. The proposed method provides an accuracy of more than 90% for lung image segmentation, which shows around 5% increase in the accuracy comparing to the state of the art. The high accuracy of this method is due to its fitness to the application.

A Study on Detection of COVID-19 in Lung CT Images Using Transfer Learning With Resnet Pre-Trained Model

A Study on Detection of COVID-19 in Lung CT Images Using Transfer Learning With Resnet Pre-Trained Model

Computer-Aided Diagnosis Research of a Lung Tumor Based on a Deep Convolutional Neural Network and Global Features.

Based on the better generalization ability and the feature learning ability of the deep convolutional neural network, it is very significant to use the DCNN on the computer-aided diagnosis of a lung tumor. Firstly, a deep convolutional neural network was constructed according to the fuzzy characteristics and the complexity of lung CT images. Secondly, the relation between model parameters (iterations, different resolution) and recognition rate is discussed. Thirdly, the effects of different model structures for the identification of a lung tumor were analyzed by changing convolution kernel size, feature dimension, and depth of the network. Fourthly, the different optimization methods on how to influence the DCNN performance were discussed from three aspects containing pooling methods (maximum pooling and mean pooling), activation function (sigmoid and ReLU), and training algorithm (batch gradient descent and gradient descent with momentum). Finally, the experimental results verified the feasibility of DCNN used on computer-aided diagnosis of lung tumors, and it can achieve a good recognition rate when selecting the appropriate model parameters and model structure and using the method of gradient descent with momentum.

Semi-Supervised Ensemble Classifier with Improved Sparrow Search Algorithm and Its Application in Pulmonary Nodule Detection

The Adaptive Boosting (AdaBoost) classifier is a widely used ensemble learning framework, and it can get good classification results on general datasets. However, it is challenging to apply the AdaBoost classifier directly to pulmonary nodule detection of labeled and unlabeled lung CT images since there are still some drawbacks to ensemble learning method. Therefore, to solve the labeled and unlabeled data classification problem, the semi-supervised AdaBoost classifier using an improved sparrow search algorithm (AdaBoost-ISSA-S4VM) was established. Firstly, AdaBoost classifier is used to construct a strong semi-supervised classifier using several weak classifiers S4VM (AdaBoost-S4VM). Next, in order to solve the accuracy problem of AdaBoost-S4VM, sparrow search algorithm (SSA) is introduced in the AdaBoost classifier and S4VM. Then, sine cosine algorithm and new labor cooperation structure are adopted to increase the global optimal solution and convergence performance of sparrow search algorithm, respectively. Furthermore, based on the improved sparrow search algorithm and adaptive boosting classifier, the AdaBoost-S4VM classifier is improved. Finally, the effective improved AdaBoost-ISSA-S4VM classification model was developed for actual pulmonary nodule detection based on the publicly available LIDC-IDRI database. The experimental results have proved that the established AdaBoost-ISSA-S4VM classification model has good performance on labeled and unlabeled lung CT images.

Motion correction for routine X-ray lung CT imaging

A novel motion correction algorithm for X-ray lung CT imaging has been developed recently. It was designed to perform for routine chest or thorax CT scans without gating, namely axial or helical scans with pitch around 1.0. The algorithm makes use of two conjugate partial angle reconstruction images for motion estimation via non-rigid registration which is followed by a motion compensated reconstruction. Differently from other conventional approaches, no segmentation is adopted in motion estimation. This makes motion estimation of various fine lung structures possible. The aim of this study is to explore the performance of the proposed method in correcting the lung motion artifacts which arise even under routine CT scans with breath-hold. The artifacts are known to mimic various lung diseases, so it is of great interest to address the problem. For that purpose, a moving phantom experiment and clinical study (seven cases) were conducted. We selected the entropy and positivity as figure of merits to compare the reconstructed images before and after the motion correction. Results of both phantom and clinical studies showed a statistically significant improvement by the proposed method, namely up to 53.6% (p < 0.05) and up to 35.5% (p < 0.05) improvement by means of the positivity measure, respectively. Images of the proposed method show significantly reduced motion artifacts of various lung structures such as lung parenchyma, pulmonary vessels, and airways which are prominent in FBP images. Results of two exemplary cases also showed great potential of the proposed method in correcting motion artifacts of the aorta which is known to mimic aortic dissection. Compared to other approaches, the proposed method provides an excellent performance and a fully automatic workflow. In addition, it has a great potential to handle motions in wide range of organs such as lung structures and the aorta. We expect that this would pave a way toward innovations in chest and thorax CT imaging.

COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet

BackgroundCurrently, there is an urgent need for efficient tools to assess the diagnosis of COVID-19 patients. In this paper, we present feasible solutions for detecting and labeling infected tissues on CT lung images of such patients. Two structurally-different deep learning techniques, SegNet and U-NET, are investigated for semantically segmenting infected tissue regions in CT lung images.MethodsWe propose to use two known deep learning networks, SegNet and U-NET, for image tissue classification. SegNet is characterized as a scene segmentation network and U-NET as a medical segmentation tool. Both networks were exploited as binary segmentors to discriminate between infected and healthy lung tissue, also as multi-class segmentors to learn the infection type on the lung. Each network is trained using seventy-two data images, validated on ten images, and tested against the left eighteen images. Several statistical scores are calculated for the results and tabulated accordingly.ResultsThe results show the superior ability of SegNet in classifying infected/non-infected tissues compared to the other methods (with 0.95 mean accuracy), while the U-NET shows better results as a multi-class segmentor (with 0.91 mean accuracy).ConclusionSemantically segmenting CT scan images of COVID-19 patients is a crucial goal because it would not only assist in disease diagnosis, also help in quantifying the severity of the illness, and hence, prioritize the population treatment accordingly. We propose computer-based techniques that prove to be reliable as detectors for infected tissue in lung CT scans. The availability of such a method in today’s pandemic would help automate, prioritize, fasten, and broaden the treatment of COVID-19 patients globally.

Determining Average Linear Dimension and Volume of Korean Lungs for Lung Phantom Construction.

The purpose of this study was to determine the average size and volume of lungs and to simulate the morphology of internal organs for the development of a Korean adult lung phantom. The body-size data of 2,195 males and 2,293 females aged between 20 and 60 y were included to calculate the average physical dimensions. Two hundred datasets of computed tomography corresponding to the average physique range were collected to measure the average linear dimensions (the length of x, y, and z-axis) of lungs. One set of lung CT images was finally obtained and converted to three-dimensional (3D) format. To confirm the validity of the new lung model, physical lung phantoms were constructed using International Commission on Radiation Units and Measurements (ICRU) density and similar density to what was obtained from the human CT image and then compared with the Lawrence Livermore National Laboratory (LLNL) phantom. The mean size of the chest width and thickness was 31.8 ± 2.8 and 21.4 ± 1.9 cm for males and 28.0 ± 1.6 cm and 19.4 ± 2.0 cm for females, respectively. The standard deviation of the lung dimension in this group was ± 3.0 cm in length, ± 0.8 cm in width, and ± 2.27 cm in depth. The two modified lung phantoms showed highly accurate geometry and linear attenuation coefficient vs. those of the LLNL phantom. The difference in CT number was ± 2% HU for the LLNL phantom and ± 4% HU for the human CT image based on a CT examination conducted using the chest CT protocol. Moreover, both lungs weighed 734 g to 1,246 g, within the range of the reference value of the ICRU report. These results demonstrate that a new lung model based on average linear dimension measurement in a group with average physique simulated the features and physical properties of real human lungs and facilitated further studies for phantom construction.

Three-Dimensional Quantitative Analysis of Chronic Obstructive Pulmonary Lesions on CT Images

In this paper, the three-dimensional segmentation of pulmonary honeycomb lesions and the function of image biomarkers are integrated into a quantitative analysis module of the lung, and integrated into the PACS image diagnosis workstation for the quantitative analysis of doctors. It is difficult to segment honeycomb lesions in lung CT images because of its diffuse and blurred edges, but it has good texture characteristics. Based on this feature, this paper converts honeycomb lesions into a texture classification problem. Firstly, the lung parenchyma is extracted by automatic threshold segmentation and region growing method, and then the lung parenchyma is divided into several small regions according to the texture by watershed method. Then, according to the texture characteristics of each small area, the trained support vector machine is used to classify. Finally, the correlation between gray level and spatial position of slice data is used to correct the classification results, so as to reduce false positive areas. In order to expand the study of imaging biomarkers of chronic lung diseases to more extensive major diseases, a sample database was established for a wide range of multiple lesions. Through feature extraction and feature analysis of multiple lesions in database, potential feature differences can be excavated, which lays a solid foundation for further study of image biomarkers of multiple lesions.

Design of an Online Detection System for COVID-19 based on Attention Mechanism

Corona Virus Disease 2019 (COVID-19) is an acute respiratory infection caused by the 2019 novel coronavirus infection that was discovered in some hospitals in Wuhan, China in December 2019. From a global perspective, COVID-19 epidemic is still in a pandemic period. Every country is taking timely preventive measures. Therefore, it is necessary to use Artificial Intelligence (AI) identification to assist radiologists in diagnosing COVID-19. This paper proposes a network model of dynamic self-attention machine for pneumonia images. The model adopts DPN92 and GCNet. It implements CR images and CT image classification of COVID-19. A COVID-19 detection system based on dynamic auto-attention machine is designed. The lung CT or CR images that meet the design requirements will be uploaded through the browser, and the background server will analyze and process the lung images, and finally output the detection category of the lung images.

Nodule segmentation of lung CT image for medical applications

Lung cancer increases number of deaths worldwide. This motivates the detection of Cancer in the early stages. In order to detect cancer in the various stages segmentation of initial lung portion and in turn, nodules is primary and very important step in diagnosing the cancer using Computer Vision (CV) and Machine Learning (ML) techniques. This paper contributes to the CV based cancer diagnosed system. This paper proposes cuckoo search optimization technique to optimize the initial segmentation of the lung portion, and then Active Contour (AC) technique has been applied to segment the nodules from the segmented lung image. In order to fine turn the post- processing after the nodule segmentation operation, Markov Random Field (MRF) technique has been applied. The results of the experimentation of the proposed method of lung and nodule segmentation have been reported in the results and discussion section.

Lung ultrasound and computed tomography to monitor COVID-19 pneumonia in critically ill patients: a two-center prospective cohort study

BackgroundLung ultrasound can adequately monitor disease severity in pneumonia and acute respiratory distress syndrome. We hypothesize lung ultrasound can adequately monitor COVID-19 pneumonia in critically ill patients.MethodsAdult patients with COVID-19 pneumonia admitted to the intensive care unit of two academic hospitals who underwent a 12-zone lung ultrasound and a chest CT examination were included. Baseline characteristics, and outcomes including composite endpoint death or ICU stay > 30 days were recorded. Lung ultrasound and CT images were quantified as a lung ultrasound score involvement index (LUSI) and CT severity involvement index (CTSI). Primary outcome was the correlation, agreement, and concordance between LUSI and CTSI. Secondary outcome was the association of LUSI and CTSI with the composite endpoints.ResultsWe included 55 ultrasound examinations in 34 patients, which were 88% were male, with a mean age of 63 years and mean P/F ratio of 151. The correlation between LUSI and CTSI was strong (r = 0.795), with an overall 15% bias, and limits of agreement ranging − 40 to 9.7. Concordance between changes in sequentially measured LUSI and CTSI was 81%. In the univariate model, high involvement on LUSI and CTSI were associated with a composite endpoint. In the multivariate model, LUSI was the only remaining independent predictor.ConclusionsLung ultrasound can be used as an alternative for chest CT in monitoring COVID-19 pneumonia in critically ill patients as it can quantify pulmonary involvement, register changes over the course of the disease, and predict death or ICU stay > 30 days.Trial registration: NTR, NL8584. Registered 01 May 2020—retrospectively registered, https://www.trialregister.nl/trial/8584

ResBCDU-Net: A Deep Learning Framework for Lung CT Image Segmentation.

Lung CT image segmentation is a key process in many applications such as lung cancer detection. It is considered a challenging problem due to existing similar image densities in the pulmonary structures, different types of scanners, and scanning protocols. Most of the current semi-automatic segmentation methods rely on human factors therefore it might suffer from lack of accuracy. Another shortcoming of these methods is their high false-positive rate. In recent years, several approaches, based on a deep learning framework, have been effectively applied in medical image segmentation. Among existing deep neural networks, the U-Net has provided great success in this field. In this paper, we propose a deep neural network architecture to perform an automatic lung CT image segmentation process. In the proposed method, several extensive preprocessing techniques are applied to raw CT images. Then, ground truths corresponding to these images are extracted via some morphological operations and manual reforms. Finally, all the prepared images with the corresponding ground truth are fed into a modified U-Net in which the encoder is replaced with a pre-trained ResNet-34 network (referred to as Res BCDU-Net). In the architecture, we employ BConvLSTM (Bidirectional Convolutional Long Short-term Memory)as an advanced integrator module instead of simple traditional concatenators. This is to merge the extracted feature maps of the corresponding contracting path into the previous expansion of the up-convolutional layer. Finally, a densely connected convolutional layer is utilized for the contracting path. The results of our extensive experiments on lung CT images (LIDC-IDRI database) confirm the effectiveness of the proposed method where a dice coefficient index of 97.31% is achieved.

Mobile lung cancer early warning based on Windows Azure cloud computing

In view of the repeated investment in the current medical lung cancer early warning system, 'information island' and the low rate of lung cancer early warning, this paper proposes a mobile lung cancer early warning system based on Windows Azure cloud computing with the application requirements of medical information system. The system is applied to the smart phones of Windows system, and the Windows Azure Microsoft cloud platform is accessed through wireless network, using SQL Azure to store medical data (such as lung CT image, ECG curve and high-resolution colour ultrasound image), embed the medical lung cancer early warning model based on deep learning in the cloud computing platform to process and analyse the patient's medical data, and realise the real-time synchronous update of doctors, patients and cloud platform data. The accuracy of lung cancer early-warning system on LIDC-IDRI is high, and the detection results are uploaded to doctors and patients' smart phones in real time. The results show that the mobile lung cancer early warning system based on Windows Azure cloud computing not only effectively integrates medical resources, but also provides patients with medical services and consultation at home, which integrates the advantages of all aspects and adapts to the development of the times.

Auto-Diagnosis of COVID-19 Using Lung CT Images With Semi-Supervised Shallow Learning Network

In the current world pandemic situation, the contagious Novel Coronavirus Disease 2019 (COVID-19) has raised a real threat to human lives owing to infection on lung cells and human respiratory systems. It is a daunting task for the researchers to find suitable infection patterns on lung CT images for automated diagnosis of COVID-19. A novel integrated semi-supervised shallow neural network framework comprising a Parallel Quantum-Inspired Self-supervised Network (PQIS-Net) for automatic segmentation of lung CT images followed by Fully Connected (FC) layers, is proposed in this article. The proposed PQIS-Net model is aimed at providing fully automated segmentation of lung CT slices without incorporating pre-trained convolutional neural network based models. A parallel trinity of layered structure of quantum bits are interconnected using an N-connected second order neighborhood-based topology in the suggested PQIS-Net architecture for segmentation of lung CT slices with wide variations of local intensities. A random patch-based classification on PQIS-Net segmented slices is incorporated at the classification layers of the suggested semi-supervised shallow neural network framework. Intensive experiments have been conducted using three publicly available data sets, one for purely segmentation task and the other two for classification (COVID-19 diagnosis). The experimental outcome on segmentation of CT slices using self-supervised PQIS-Net and the diagnosis efficiency (Accuracy, Precision and AUC) of the integrated semi-supervised shallow framework is found to be promising. The proposed model is also found to be superior than the best state-of-the-art techniques and pre-trained convolutional neural network-based models, specially in COVID-19 and Mycoplasma Pneumonia (MP) screening.

Mobile lung cancer early warning based on Windows Azure cloud computing

In view of the repeated investment in the current medical lung cancer early warning system, 'information island' and the low rate of lung cancer early warning, this paper proposes a mobile lung cancer early warning system based on Windows Azure cloud computing with the application requirements of medical information system. The system is applied to the smart phones of Windows system, and the Windows Azure Microsoft cloud platform is accessed through wireless network, using SQL Azure to store medical data (such as lung CT image, ECG curve and high-resolution colour ultrasound image), embed the medical lung cancer early warning model based on deep learning in the cloud computing platform to process and analyse the patient's medical data, and realise the real-time synchronous update of doctors, patients and cloud platform data. The accuracy of lung cancer early-warning system on LIDC-IDRI is high, and the detection results are uploaded to doctors and patients' smart phones in real time. The results show that the mobile lung cancer early warning system based on Windows Azure cloud computing not only effectively integrates medical resources, but also provides patients with medical services and consultation at home, which integrates the advantages of all aspects and adapts to the development of the times.

Positron Emission Tomography/Computed Tomography Alert Finding in an Esophageal Cancer Patient

Emergency pathologies often accompany malignancies. We herein report a case of pulmonary abscess in a patient with esophageal cancer which was depicted during the F-18-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) staging study. The patient's history of recent dilatation of the cancer stenosis in adjunct to the previous CT lung imaging, which was normal, made evident the diagnosis of the pulmonary abscess due to the perforation of the esophageal neoplasm. This life-threatening condition was promptly referred and successfully managed.

Clinical and CT Manifestations of 56 COVID-19 Patients

Objective: To analyze the clinical manifestations and lung CT findings of patients infected with the 2019 coronavirus disease (COVID-19). Methods: The clinical manifestations and lung CT image data of 56 confirmed COVID-19 patients were retrospectively analyzed. These data were collected in the Fourth People’s Hospital of Huai’an from January 23-February 13, 2020. All 56 patients were confirmed cases with positive nucleic acid test. Results: The main clinical manifestations of 56 patients were fever, cough, sputum, and some patients were accompanied by headache, sore throat, nasal congestion and runny nose, fatigue, muscle aches and other symptoms. 42 patients had the symptoms of moderate or low fever, with an average body temperature of 38.0 ±0.7 °C, and 41 patients had the symptoms of dry cough. Of 56 patients with chest CT examination, 50 cases showed ground glass opacity (GGO) in the lungs, 38 cases showed varying degrees of consolidation in the GGO, 49 cases showed the vascular enhancement sign (VES) in the lung lesions, 28 cases showed the pavement stone sign, and 17 cases had the lungs of fiber stripes. Only 1 of the 56 patients had a little pleural effusion, and there was no mediastinal lymphadenopathy. The frequency of ground glass opacity and vascular enhancement sign was the highest, however, there were no significant differences among the three groups in the early stage, progression stage and recovery stage. In the early stage, the occurrence rate of pavement stone signs and air bronchi signs were significantly lower than that of the progression stage and recovery stage. The occurrence rate of fiber stripes was the highest in the recovery period, which was obviously higher than that in the first and second stages. Conclusion: Combined with epidemiological history and clinical symptoms, chest CT abnormalities and routine blood examination can be used as an important reference before nucleic acid detection so as to screen the risky population, which is helpful for early clinical treatment.

A Case of Pulmonary Cryptococcosis with Normal Immune Function

<i>Objective</i> Pulmonary cryptococcosis (PC) is a pulmonary fungal disease caused by Cryptococcus neoformans infection, the clinical manifestations are pneumonia or pulmonary nodules, or acute respiratory distress syndrome (ARDS) in severe cases. But its clinical manifestations lack specificity, so it is often misdiagnosed or missed in recent years. Pulmonary cryptococcosis is common in patients with human immunodeficiency virus (HIV) and non-HIV-associated immunosuppression, it has been found that pulmonary cryptococcosis is also common in people with sound immune function. The purpose of this paper is to report the diagnosis and treatment process of a patient with pulmonary cryptococcosis in our hospital, so as to provide reference for the diagnosis and treatment of the disease and reduce the misdiagnosis rate and missed diagnosis rate of the disease. <i>Methods</i> The diagnosis and treatment process of a case of pulmonary cryptococcosis in our hospital were reviewed. <i>Results</i> Combined with the patient's lung CT Imaging manifestations, and environmental exposure history and immune status, pulmonary cryptococcosis was considered. After empirical anti-cryptococcosis treatment, the patient's symptoms improved, and pulmonary nodules disappeared according to lung CT review. <i>Conclusion</i> Clinicians should identify the imaging characteristics of patients with cryptococcus pneumonicum and combine them with their environmental exposure history and immune status to avoid missed diagnosis and delayed disease.

Risk factors analysisi for COVID‑19 in the elderly

Objective: To analyze the clinical characteristics and prognosis of the coronavirus disease 2019 (COVID‑19) in the elderly(aged 60 or above), and to explore the high risk factors of severe disease progression for early identification and prevention. Methods: Novel coronavirus pneumonia patients aged 60 or above diagnosed in Hubei Veterans Hospital from January 20 to February 29 in year 2020 were collected. According to the degrees of disease, the patients were divided into mild and severe groups, and their clinical features, laboratory examination, chest CT features, treatment, and outcome were compared. Results: A total of 108 patients were included, including 69 in mild group and 39 in severe group. The average age of the severe group was higher than that of the mild group ( P <0.001). The clinical symptoms of fever, expectoration, dyspnea, fatigue and diarrhea in the severe group were severer and more common than those in the mild group (all P <0.001). The proportion of hypertension ( P <0.05), respiratory system diseases (such as chronic bronchitis and COPD) ( P <0.05), and hypoproteinemia ( P <0.001) combined with COVID⁃19 were higher in severe groupthe severe group. Leukocyte count (WBC), neutrophil count (NEUT), CRP and SAA in the severe group were significantly higher ( P <0.05), while lymphocyte count (LY) and eosinophil count (EOS) were lower than those in the mild group ( P <0.05). Lung CT images showed that patients in the severe group had more bilateral lung involvements and pleural effusion than those in the mild group ( P <0.05). Among the 108 cases, 96 (88.9%) were cured and improved, 12 (11.1%) died. Conclusion: Age, basic comorbidities, decreasing in lymphocytes and acidophilic granulocytes, and multiple bacterial infections are risk factors for severe COVID‑19. Hypoalbuminemia may be a potential and independent adverse prognostic indicator for the elderly COVID‑19. Symptoms of dyspnea and diarrhea, bilateral lung involvements, the pleural effusion are high risk signs for the elderly COVID‑19 patients progressing to severe. These findings are valuable for the early recognition, early diagnosis and treatment for COVID⁃19. © 2021, Editorial Board of Medical Journal of Wuhan University. All right reserved.

Radiomics Based Bayesian Inversion Method for Prediction of Cancer and Pathological Stage.

Objective: To develop a Bayesian inversion framework on longitudinal chest CT scans which can perform efficient multi-class classification of lung cancer. Methods: While the unavailability of large number of training medical images impedes the performance of lung cancer classifiers, the purpose built deep networks have not performed well in multi-class classification. The presented framework employs particle filtering approach to address the non-linear behaviour of radiomic features towards benign and cancerous (stages I, II, III, IV) nodules and performs efficient multi-class classification (benign, early stage cancer, advanced stage cancer) in terms of posterior probability function. A joint likelihood function incorporating diagnostic radiomic features is formulated which can compute likelihood of cancer and its pathological stage. The proposed research study also investigates and validates diagnostic features to discriminate accurately between early stage (I, II) and advanced stage (III, IV) cancer. Results: The proposed stochastic framework achieved 86% accuracy on the benchmark database which is better than the other prominent cancer detection methods. Conclusion: The presented classification framework can aid radiologists in accurate interpretation of lung CT images at an early stage and can lead to timely medical treatment of cancer patients.