MA20.10 Lung Cancer Prediction Using Deep Learning Software: Validation on Independent Multi-Centre Data

Peschl, Heiko; Han, Daiwei; Ooijen, Peter M. A. van; Oudkerk, Matthijs; Dorrius, Monique D.; Rook, Mieneke; Vliegenthart, R.; Heusse, C. P.; Batora, N.; Kauczor, Hans‐Ulrich; Silva, C. Da; Stackelberg, Oyunbileg von; Rubtsov, R. V.; Wielpütz, Mark O.; Ather, Sarim; Tsakok, Maria; Arteta, Carlos; Pickup, Lyndsey C.; Hussain, Shaista; Hickes, William; Novotný, P.; Santos, Clayton André Maia dos; Fay, E.; Declerck, Jérôme; Potesi, V.; Kadir, Timor; Gleeson, Fergus

doi:10.1016/j.jtho.2018.08.489

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network has nil layers that are fully linked. In Table 1, you'll find more network settings [15] [24] [22].…”

Section: Page 529mentioning

confidence: 99%

Lung Cancer Segmentation and Classification Using Integration of Convolutional Neural Network & Unet Network Over CT Images: A Deep Learning Approach

Mathews

2022

IJMTS

View full text Add to dashboard Cite

Purpose: Cellular breakdown in the lungs screening is a cycle that is utilized to recognize the presence of cancer in the lungs in any case. Mostly it occurs among the elderly, especially smokers. Lung infections are lung-affecting illnesses that impede the respiratory mechanism. Cellulose breakdown in the lungs is one of the top causes of mortality in people all over the globe. Early recognition can improve endurance chances. As the world is revolutionizing with so many emerging technologies and one of the most popular technology is Deep Learning (DL) which has shown tremendous development in medical fields. So this paper brings an effective deep learning framework for lung cancer detection. Objective: To develop a CAD system for efficient lung cancer detection from CT images using a combination of CNN and UNET. For improving accuracy in the proposed system a better feature extraction and feature selection techniques is incorporate, i.e., by using autoencoder and selection based on Kernal function for effective boostings. Methodology: For this deep learning framework, the following are the stages. (a) Data Collection from the popular repository IQ-OTHNCCD lung cancer dataset which contains CT images of a total of 1198 from 110 CT slice cases, (b) Preprocessing CT images with an alpha-trimmed mean filter and CLAHE for improved enhancement, (c) Segmentation using CNN for segmenting the cancer regions) with the use of an autoencoder, extracting characteristics like area, perimeter, centroid, and mean intensity) feature selection using kernel function and finally f) classification using UNet network. Findings/Result: In terms of accuracy, sensitivity, specificity, recall, precision, F1-score, detection rate, TPR, FPR, and computation time, experiments are carried out on a range of cutting-edge models, and our suggested model surpasses them all (accuracy:0.95, sensitivity:0.97, specificity:0.98, detection rate:0.94). Originality: This paper is incorporating 2 neural networks over main stages such as segmentation and classification which eventually improves the quality of the model higher and also these are performed over real-time public medical records which shows the novelty of the model. Paper type: Methodology paper

show abstract

“…The network has nil layers that are fully linked. In Table 1, you'll find more network settings [15] [24] [22].…”

Section: Page 529mentioning

confidence: 99%

Lung Cancer Segmentation and Classification Using Integration of Convolutional Neural Network & Unet Network Over CT Images: A Deep Learning Approach

Mathews

2022

IJMTS

View full text Add to dashboard Cite

show abstract

“…The kernel mapping provides a unifying framework for the majority of the model architectures that are commonly used. When the number of images used in the testing process increases, the accuracy of image enhancement must improve [8][9][10].…”

Section: Survey Of the Workmentioning

confidence: 99%

A Novel Classification With Deep Convolutional Neural Networks on Pulmonary Nodule

Mathews¹,

K²

2022

JES

View full text Add to dashboard Cite

Medical images are an important part of a patient’s health record, and they need data manipulation, processing, and handling by computers. As a result, medical data is a type of bigdata, and its analysis has become complex. Because manual disease diagnosis takes longer and produces less accurate results, it may result in incorrect treatment. Three DCNN architectures have been exploited and evaluated for tumor detection and classification. The sample image for the experimentation is chosen from Lung Image Database Consortium (LIDC) with Image Database Resource Initiative (IDRI) and Kaggle dataset which consists of normal and abnormal image. The experimental results of proposed DCNN classifier achieved best accuracy than the GoogleNet, AlexNet, Artificial neural network and support vector machine.

show abstract

“…We developed a CNN trained for the task of Lung Cancer Prediction (LCP-CNN), using the National Lung Sceening Trial (NLST) data, and configured it to specifically identify benign nodules, enabling them to be "ruled out"of unnecessary follow-up with a high degree of certainty. [5] Recently, validating this LCP-CNN on a retrospective UK dataset it was shown that the LCP-CNN outperformed the Brock University model for lung nodule risk categorization [6]. A second study showed that using the LCP-CNN, nodules could be classified into low (5% malignancy treshold) and high-risk (65 % malignancy treshold) categories, with improved accuracy compared to traditional risk prediction models [7].…”

Section: Introductionmentioning

confidence: 97%

Lung cancer prediction by Deep Learning to identify benign lung nodules

et al. 2021

View full text Add to dashboard Cite

Introduction: Deep Learning has been proposed as promising tool to classify malignant nodules. Our aim was to retrospectively validate our Lung Cancer Prediction Convolutional Neural Network (LCP-CNN), which was trained on US screening data, on an independent dataset of indeterminate nodules in an European multicentre trial, to rule out benign nodules maintaining a high lung cancer sensitivity. Methods: The LCP-CNN has been trained to generate a malignancy score for each nodule using CT data from the U.S. National Lung Screening Trial (NLST), and validated on CT scans containing 2106 nodules (205 lung cancers) detected in patients from from the Early Lung Cancer Diagnosis Using Artificial Intelligence and Big Data (LUCINDA) study, recruited from three tertiary referral centers in the UK, Germany and Netherlands. We pre-defined a benign nodule rule-out test, to identify benign nodules whilst maintaining a high sensitivity, by calculating thresholds on the malignancy score that achieve at least 99 % sensitivity on the NLST data. Overall performance per validation site was evaluated using Area-Under-the-ROC-Curve analysis (AUC). Results: The overall AUC across the European centers was 94.5 % (95 %CI 92.6-96.1). With a high sensitivity of 99.0 %, malignancy could be ruled out in 22.1 % of the nodules, enabling 18.5 % of the patients to avoid followup scans. The two false-negative results both represented small typical carcinoids.

show abstract

MA20.10 Lung Cancer Prediction Using Deep Learning Software: Validation on Independent Multi-Centre Data

Cited by 5 publications

References 0 publications

Lung Cancer Segmentation and Classification Using Integration of Convolutional Neural Network & Unet Network Over CT Images: A Deep Learning Approach

Lung Cancer Segmentation and Classification Using Integration of Convolutional Neural Network & Unet Network Over CT Images: A Deep Learning Approach

A Novel Classification With Deep Convolutional Neural Networks on Pulmonary Nodule

Lung cancer prediction by Deep Learning to identify benign lung nodules

Contact Info

Product

Resources

About