Lung cancer prediction by Deep Learning to identify benign lung nodules.

Published on Jan 31, 2021in Lung Cancer5.705
· DOI :10.1016/J.LUNGCAN.2021.01.027
Marjolein A Heuvelmans20
Estimated H-index: 20
(UMCG: University Medical Center Groningen),
Peter M. A. van Ooijen23
Estimated H-index: 23
(UMCG: University Medical Center Groningen)
+ 17 AuthorsHeiko Peschl3
Estimated H-index: 3
(University of Oxford)
Sources
Abstract
Abstract 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 centres 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 centres 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 follow-up scans. The two false-negative results both represented small typical carcinoids. Conclusion The LCP-CNN, trained on participants with lung nodules from the US NLST dataset, showed excellent performance on identification of benign lung nodules in a multi-center external dataset, ruling out malignancy with high accuracy in about one fifth of the patients with 5-15 mm nodules.
References9
Newest
#1Pierre P. Massion (Veterans Health Administration)H-Index: 67
#2Sanja L. Antic (Vandy: Vanderbilt University)H-Index: 5
Last. Timor KadirH-Index: 24
view all 20 authors...
Rationale: The management indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unne...
Source
Background Estimation of the risk of malignancy in pulmonary nodules detected by CT is central in clinical management. The use of artificial intelligence (AI) offers an opportunity to improve risk prediction. Here we compare the performance of an AI algorithm, the lung cancer prediction convolutional neural network (LCP-CNN), with that of the Brock University model, recommended in UK guidelines. Methods A dataset of incidentally detected pulmonary nodules measuring 5–15 mm was collected retrospe...
Source
#1Diego Ardila (Google)H-Index: 3
#2Atilla Peter Kiraly (Google)H-Index: 18
Last. Shravya Shetty (Google)H-Index: 9
view all 12 authors...
With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20–43% and is now included in US screening guidelines1–6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7–10. We propose a deep learning algorithm that uses a patient’s current and prior computed tomography volumes to predict the ri...
Source
#1Heiko Peschl (University of Oxford)H-Index: 3
#2Daiwei HanH-Index: 6
Last. Hans-Ulrich Kauczor (Heidelberg University)H-Index: 75
view all 27 authors...
Source
Background Neuroendocrine tumours (nets) are classified by site of origin, with lung being the second most common primary site after the gastrointestinal tract. Lung nets are rare and heterogeneous, with varied pathologic and clinical features. Typical and atypical carcinoid tumours are low-grade lung nets which, compared with the more common high-grade nets, are associated with a more favourable prognosis. Still, optimal treatment strategies are lacking. Methods This review concentrates on clas...
Source
#1Matthijs Oudkerk (UMCG: University Medical Center Groningen)H-Index: 94
#2Anand DevarajH-Index: 33
Last. John K. Field (University of Liverpool)H-Index: 88
view all 22 authors...
Summary Lung cancer screening with low-dose CT can save lives. This European Union (EU) position statement presents the available evidence and the major issues that need to be addressed to ensure the successful implementation of low-dose CT lung cancer screening in Europe. This statement identified specific actions required by the European lung cancer screening community to adopt before the implementation of low-dose CT lung cancer screening. This position statement recommends the following acti...
Source
#1Francesco Ciompi (Radboud University Nijmegen)H-Index: 26
#2Kaman Chung (Radboud University Nijmegen)H-Index: 10
Last. Bram van Ginneken (Radboud University Nijmegen)H-Index: 84
view all 13 authors...
The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevan...
Source
#1Heber MacMahon (U of C: University of Chicago)H-Index: 78
#2David P. Naidich (NYU: New York University)H-Index: 81
Last. Alexander A. Bankier (Harvard University)H-Index: 56
view all 15 authors...
The minimum threshold size for routine follow-up has been increased, and recommended follow-up intervals are now given as a range rather than as a precise time period to give radiologists, clinicians, and patients greater discretion to accommodate individual risk factors and preferences.
Source
#1Nanda Horeweg (Erasmus University Medical Center)H-Index: 14
#2Joost van Rosmalen (Erasmus University Medical Center)H-Index: 10
Last. Matthijs Oudkerk (UMCG: University Medical Center Groningen)H-Index: 94
view all 17 authors...
Summary Background The main challenge in CT screening for lung cancer is the high prevalence of pulmonary nodules and the relatively low incidence of lung cancer. Management protocols use thresholds for nodule size and growth rate to determine which nodules require additional diagnostic procedures, but these should be based on individuals' probabilities of developing lung cancer. In this prespecified analysis, using data from the NELSON CT screening trial, we aimed to quantify how nodule diamete...
Source
Cited By4
Newest
Source
Source
#1Adil Masood (Jamia Millia Islamia)H-Index: 2
#2Kafeel Ahmad (Jamia Millia Islamia)H-Index: 15
Abstract null null Accurate air quality forecasting is critical for systematic pollution control as well as public health and wellness. Most of the traditional forecasting techniques have shown inconsistent predictive accuracy due to the non-linear, dynamic and complex nature of air pollutants. In the past few years, artificial intelligence (AI)-based methods have become the most powerful and forward-looking approaches for air pollution forecasting because of their specific features such as orga...
Source
#1Nagifa Ilma ProggaH-Index: 1
#2Noortaz Rezoana (University of Chittagong)H-Index: 1
Last. Karl AnderssonH-Index: 20
view all 5 authors...
Snakes are curved, limbless, warm blooded reptiles of the phylum serpents. Any characteristics, including head form, body shape, physical appearance, texture of skin and eye structure, might be use ...
Source
#1Takuma Usuzaki (Takeda Pharmaceutical Company)
#2Kengo Takahashi (Tohoku University)H-Index: 1
Last. Kazuhiro Majima (Takeda Pharmaceutical Company)H-Index: 6
view all 7 authors...
Source
#1Umberto G. RossiH-Index: 16
#2Giovanni A. Rossi (Istituto Giannina Gaslini)H-Index: 47
Source
#1Ying ChenH-Index: 5
#2Yerong WangH-Index: 2
view all 6 authors...
Lung nodule classification plays an important role in diagnosis of lung cancer which is essential to patients’ survival. However, because the number of lung CT images in current dataset is relatively small and the ratio of nodule samples to non-nodule samples is usually very different, this makes the training of neural networks difficult and poor performance of neural networks. Hence, LDNNET is proposed, which adopts Dense-Block, batch normalization (BN) and dropout to cope with these problems. ...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.