Intelligent classification of lung malignancies using deep learning techniques

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Priyanka Yadlapalli ◽  
D. Bhavana ◽  
Suryanarayana Gunnam
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Ct Scan ◽  
Transfer Learning ◽  
Confusion Matrix ◽  
Chest Ct ◽  
Lung Nodules ◽  
Content Type ◽  
Chest Ct Scan

PurposeComputed tomography (CT) scan can provide valuable information in the diagnosis of lung diseases. To detect the location of the cancerous lung nodules, this work uses novel deep learning methods. The majority of the early investigations used CT, magnetic resonance and mammography imaging. Using appropriate procedures, the professional doctor in this sector analyses these images to discover and diagnose the various degrees of lung cancer. All of the methods used to discover and detect cancer illnesses are time-consuming, expensive and stressful for the patients. To address all of these issues, appropriate deep learning approaches for analyzing these medical images, which included CT scan images, were utilized.Design/methodology/approachRadiologists currently employ chest CT scans to detect lung cancer at an early stage. In certain situations, radiologists' perception plays a critical role in identifying lung melanoma which is incorrectly detected. Deep learning is a new, capable and influential approach for predicting medical images. In this paper, the authors employed deep transfer learning algorithms for intelligent classification of lung nodules. Convolutional neural networks (VGG16, VGG19, MobileNet and DenseNet169) are used to constrain the input and output layers of a chest CT scan image dataset.FindingsThe collection includes normal chest CT scan pictures as well as images from two kinds of lung cancer, squamous and adenocarcinoma impacted chest CT scan images. According to the confusion matrix results, the VGG16 transfer learning technique has the highest accuracy in lung cancer classification with 91.28% accuracy, followed by VGG19 with 89.39%, MobileNet with 85.60% and DenseNet169 with 83.71% accuracy, which is analyzed using Google Collaborator.Originality/valueThe proposed approach using VGG16 maximizes the classification accuracy when compared to VGG19, MobileNet and DenseNet169. The results are validated by computing the confusion matrix for each network type.

Transfer Learning-Based Detection of Covid-19 Using Chest CT Scan Images

2021 ◽  
pp. 393-402
Author(s):  
Aryaman Chand ◽  
Khushi Chandani ◽  
Monika Arora
Keyword(s):  
Ct Scan ◽  
Transfer Learning ◽  
Chest Ct ◽  
Chest Ct Scan

Postoperative follow-up of lung cancer: Randomized trial comparing two follow-up programs in completely resected non-small cell lung cancer (IFCT-0302).

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. TPS7111-TPS7111
Author(s):  
Virginie Westeel ◽  
Fabrice Barlesi ◽  
Jean Domas ◽  
Philippe Girard ◽  
Pascal Foucher ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Physical Examination ◽  
Ct Scan ◽  
Fiberoptic Bronchoscopy ◽  
Chest Ct ◽  
Small Cell Lung ◽  
X Ray ◽  
Chest X Ray ◽  
Chest Ct Scan

TPS7111 Background: There are no robust data published on the follow-up after surgery for non-small cell lung cancer (NSCLC). Current international guidelines are informed by expert opinion. Most of them recommend regular follow-up with clinic visit and thoracic imaging, either chest X-ray of Chest CT-scan. The IFCT-0302 trial addresses the question whether a surveillance program with chest CT-scan and fiberoptic bronchoscopy can improve survival compared to a follow-up only based on physical examination and chest x-ray. There is no such trial ongoing over the world. Methods: The IFCT-0302 trial is a multicenter open-label controlled randomized phase III trial. The objective of the trial is to compare two follow-up programs after surgery for stage I-IIIa NSCLC. The primary endpoint is overall survival. Patients are randomly assigned to arm 1, minimal follow-up, including physical examination and chest x-ray; or arm 2, a follow-up consisting of physical examination and chest x-ray plus chest CT scan and fiberoptic bronchoscopy (optional for adenocarcinomas). In both arms, follow-up procedures are performed every 6 months during the first two postoperative years, and every year between the third and the fifth years. The main eligibility criteria include: completely resected stage I-IIIA (6th UICC TNM classification) or T4 (in case of nodules in the same lobe as the tumor) N0 M0 NSCLC, surgery within the previous 8 weeks. Patients who have received and/or who will receive pre/post-operative chemotherapy and/or radiotherapy are eligible. Statistical considerations: 1,744 patients is required. Accrual status: 1,568 patients from 119 French centers had been included. The end of accrual can be expected for September 2012. Ancillary study: Blood samples are collected in 1000 patients for genomic high density SNP micro-array analysis. This collection will contribute to the French genome wide association study (gwas) of lung cancer gene susceptibility, and the genetic factors predictive of survival and lung cancer recurrence will be analyzed.

scholarly journals Coronary Artery Calsification on Chest CT Scan as Coronary Heart Disease Predictor in Lung Cancer Patients

2021 ◽  
Vol 41 (2) ◽  
pp. 94-101
Author(s):  
Luths Maharina ◽  
Yusup Subagio Sutanto ◽  
Widiastuti Widiastuti ◽  
Sulistyani Kusumaningrum ◽  
Adam Prabata ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Coronary Heart Disease ◽  
Heart Disease ◽  
Coronary Artery ◽  
Ct Scan ◽  
Cancer Patients ◽  
Chest Ct ◽  
Lung Cancer Patients ◽  
Chest Ct Scan

scholarly journals A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray images

2021 ◽  
pp. 105014
Author(s):  
Khabir Uddin Ahamed ◽  
Manowarul Islam ◽  
Ashraf Uddin ◽  
Arnisha Akhter ◽  
Bikash Kumar Paul ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ct Scan ◽  
Chest Ct ◽  
Learning Approach ◽  
X Ray ◽  
Chest Ct Scan

COVID-19 image transmission using convolutional neural networks based algorithms for medical applications

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gangadhar Ch ◽  
Nama Ajay Nagendra ◽  
Syed Mutahar Aaqib ◽  
C.M. Sulaikha ◽  
Shaheena Kv ◽  
...  
Keyword(s):  
Neural Networks ◽  
Information Systems ◽  
Ct Scan ◽  
Health Information ◽  
Convolutional Neural Networks ◽  
Health Information Systems ◽  
Ct Images ◽  
Chest Ct ◽  
Content Type ◽  
Chest Ct Scan

Purpose COVID-19 would have a far-reaching impact on the international health-care industry and the patients. For COVID-19, there is a need for unique screening tests to reliably and rapidly determine who is infected. Medical COVID images protection is critical when data pertaining to computer images are being transmitted through public networks in health information systems. Design/methodology/approach Medical images such as computed tomography (CT) play key role in the diagnosis of COVID-19 patients. Neural networks-based methods are designed to detect COVID patients using chest CT scan images. And CT images are transmitted securely in health information systems. Findings The authors hereby examine neural networks-based COVID diagnosis methods using chest CT scan images and secure transmission of CT images for health information systems. For screening patients infected with COVID-19, a new approach using convolutional neural networks is proposed, and its output is simulated. Originality/value The required patient’s chest CT scan images have been taken from online databases such as GitHub. The experiments show that neural networks-based methods are effective in the diagnosis of COVID-19 patients using chest CT scan images.

Deep learning based affective computing

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Saurabh Kumar
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Transfer Learning ◽  
Affective Computing ◽  
Machine Learning Algorithms ◽  
Human Beings ◽  
Learning Models ◽  
Text And Image ◽  
Content Type

PurposeDecision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the emotional states of people. However, the representation and classification of emotions is a very challenging task. The study used customized methods of deep learning models to aid in the accurate classification of emotions and sentiments.Design/methodology/approachThe present study presents affective computing model using both text and image data. The text-based affective computing was conducted on four standard datasets using three deep learning customized models, namely LSTM, GRU and CNN. The study used four variants of deep learning including the LSTM model, LSTM model with GloVe embeddings, Bi-directional LSTM model and LSTM model with attention layer.FindingsThe result suggests that the proposed method outperforms the earlier methods. For image-based affective computing, the data was extracted from Instagram, and Facial emotion recognition was carried out using three deep learning models, namely CNN, transfer learning with VGG-19 model and transfer learning with ResNet-18 model. The results suggest that the proposed methods for both text and image can be used for affective computing and aid in decision-making.Originality/valueThe study used deep learning for affective computing. Earlier studies have used machine learning algorithms for affective computing. However, the present study uses deep learning for affective computing.

scholarly journals ResCovNet: A Deep Learning-Based Architecture For COVID-19 Detection From Chest CT Scan Images

2020 ◽  
Author(s):  
Ankan Ghosh Dastider ◽  
Mohseu Rashid Subah ◽  
Farhan Sadik ◽  
Tanvir Mahmud ◽  
Shaikh Anowarul Fattah
Keyword(s):  
Deep Learning ◽  
Ct Scan ◽  
Chest Ct ◽  
Chest Ct Scan
Sign in / Sign up

Export Citation Format

Share Document