Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value
Jordan Chamberlin,Madison Kocher,Jeffrey Waltz,Madalyn Snoddy,Natalie Stringer,Joseph Stephenson,Pooyan Sahbaee,Puneet Sharma,Saikiran Rapaka,U. Joseph Schoepf,Andres F. Abadia,Jonathan Sperl,Phillip Hoelzer,Megan Mercer,Nayana Somayaji,Gilberto J. Aquino,Jeremy R. Burt +16 more
Reads0
Chats0
TLDR
In this article, the performance of an AI convolutional neural network (CNN) prototype (AI-RAD Companion, Siemens Healthineers) that automatically detects pulmonary nodules and quantifies coronary artery calcium volume (CACV) on low-dose chest CT (LDCT) was compared to expert radiologists.Abstract:
Artificial intelligence (AI) in diagnostic radiology is undergoing rapid development. Its potential utility to improve diagnostic performance for cardiopulmonary events is widely recognized, but the accuracy and precision have yet to be demonstrated in the context of current screening modalities. Here, we present findings on the performance of an AI convolutional neural network (CNN) prototype (AI-RAD Companion, Siemens Healthineers) that automatically detects pulmonary nodules and quantifies coronary artery calcium volume (CACV) on low-dose chest CT (LDCT), and compare results to expert radiologists. We also correlate AI findings with adverse cardiopulmonary outcomes in a retrospective cohort of 117 patients who underwent LDCT. A total of 117 patients were enrolled in this study. Two CNNs were used to identify lung nodules and CACV on LDCT scans. All subjects were used for lung nodule analysis, and 96 subjects met the criteria for coronary artery calcium volume analysis. Interobserver concordance was measured using ICC and Cohen’s kappa. Multivariate logistic regression and partial least squares regression were used for outcomes analysis. Agreement of the AI findings with experts was excellent (CACV ICC = 0.904, lung nodules Cohen’s kappa = 0.846) with high sensitivity and specificity (CACV: sensitivity = .929, specificity = .960; lung nodules: sensitivity = 1, specificity = 0.708). The AI findings improved the prediction of major cardiopulmonary outcomes at 1-year follow-up including major adverse cardiac events and lung cancer (AUCMACE = 0.911, AUCLung Cancer = 0.942). We conclude the AI prototype rapidly and accurately identifies significant risk factors for cardiopulmonary disease on standard screening low-dose chest CT. This information can be used to improve diagnostic ability, facilitate intervention, improve morbidity and mortality, and decrease healthcare costs. There is also potential application in countries with limited numbers of cardiothoracic radiologists.read more
Citations
More filters
Journal ArticleDOI
AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging:: Towards Radiophenomics.
TL;DR: In this paper, the authors present a review of AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks.
Journal ArticleDOI
AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging
TL;DR: In this paper , the authors present a review of AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks.
Journal ArticleDOI
Radiation-Induced Lung Injury-Current Perspectives and Management.
Mandeep Singh Rahi,Jay Parekh,Prachi Pednekar,Gaurav Parmar,Soniya Abraham,Samar Nasir,Rajamurugan Subramaniyam,Gini Priyadharshini Jeyashanmugaraja,Kulothungan Gunasekaran +8 more
TL;DR: Radiotherapy plays an important role in the treatment of localized primary malignancies involving the chest wall or intrathoracic malignancy, and secondary effects of radiotherapy on the lung result in radiation-induced lung disease.
Journal ArticleDOI
The Future of Lung Cancer Screening: Current Challenges and Research Priorities
TL;DR: In this paper , the authors summarize the evidence that has accumulated to guide optimisation of lung cancer screening, discuss the remaining open questions about the best approach and identify potential barriers to successful implementation.
Journal ArticleDOI
Artificial intelligence in lung cancer diagnosis and prognosis:current application and future perspective.
TL;DR: In this article , a review summarizes various types of AI algorithm applications in lung cancer, including natural language processing (NLP), machine learning and deep learning, and reinforcement learning, in addition, they provide evidence regarding the application of AI for lung cancer diagnostic and clinical prognosis.
References
More filters
PatentDOI
Automatic Liver Segmentation Using Adversarial Image-to-Image Network
TL;DR: In this paper, a method and apparatus for automated liver segmentation in a 3D medical image of a patient is disclosed, where the 3D computed tomography (CT) volume is input to a trained deep image-to-image network.
Journal ArticleDOI
Estimating overdiagnosis in low-dose computed tomography screening for lung cancer: a cohort study.
Giulia Veronesi,Patrick Maisonneuve,Massimo Bellomi,Cristiano Rampinelli,Iara Durli,Raffaella Bertolotti,Lorenzo Spaggiari +6 more
TL;DR: In this paper, the authors assess the volume doubling time (VDT) for screening-detected lung cancer as an indicator of overdiagnosis and estimate the VDT for new cancer from 1 measurement (a diameter of 2 mm assumed the previous year).
Journal ArticleDOI
ACR-STR practice parameter for the performance and reporting of lung cancer screening thoracic computed tomography (CT): 2014 (Resolution 4)
Ella A. Kazerooni,John H. M. Austin,William C. Black,Debra S. Dyer,Todd R. Hazelton,Ann N. Leung,Michael F. McNitt-Gray,Reginald F. Munden,Sudhakar Pipavath +8 more
TL;DR: The American College of Radiology will periodically define new practice parameters and technical standards for radiologic practice to help advance the science of radiology and to improve the quality of service to patients throughout the United States.
Journal ArticleDOI
Automatic Coronary Calcium Scoring in Low-Dose Chest Computed Tomography
TL;DR: Calcium scoring can be performed automatically in low-dose, noncontrast enhanced, non-ECG-synchronized chest CT in screening of heavy smokers to identify subjects who might benefit from preventive treatment.
Journal ArticleDOI
Highly accurate model for prediction of lung nodule malignancy with CT scans.
Jason Causey,Jason Causey,Junyu Zhang,Shiqian Ma,Bo Jiang,Jake Qualls,Jake Qualls,David G. Politte,Fred W. Prior,Shuzhong Zhang,Xiuzhen Huang,Xiuzhen Huang +11 more
TL;DR: NoduleX as mentioned in this paper is a systematic approach to predict lung nodule malignancy from CT data, based on deep learning convolutional neural networks (CNN) for lung cancer diagnosis.
Related Papers (5)
Assessment of Plasma Proteomics Biomarker’s Ability to Distinguish Benign From Malignant Lung Nodules: Results of the PANOPTIC (Pulmonary Nodule Plasma Proteomic Classifier) Trial
Gerard A. Silvestri,Nichole T. Tanner,Nichole T. Tanner,Paul Kearney,Anil Vachani,Pierre P. Massion,Alexander Porter,Steven C. Springmeyer,Kenneth C. Fang,David E. Midthun,Peter J. Mazzone,G.A. Silvestri,L. Leake,P. Mazzone,M. Beukemann,D. Midthun,P. McCarthy,B. Sigal,T. Deluca,F. Laberge,B. Fortin,M. Balaan,B. Dimitt,A. Pierre,F. Allison,L. Yarmus,K. Oakjones-Burgess,N. Tanner,N. Tanner,N. Ettinger,T. Setchfield,David K. Madtes,J. Hubbard,W. McConnell,K. Robinson,A. Lackey,L. Jacques,E. Kuo,V. Markland-Gentles,P. Massion,A. Muterspaug,J. Leach,K. Rothe,William N. Rom,Harvey I. Pass,A. Sorenson,A. Chesnutt,A. Georgeson,A. Balekian,J. Fisher,R. Murali,A. Overton,N. Desai,A. Levesque,W. Krimsky,S. King,Anil Vachani,K. Maletteri,K. Mileham,L. Carter,G. Hong,J. Ma,K. Voelker,H. Barrentine,R. Aronson,M. Henderson,J. Lamberti,C. Krawiecki,A. Case,L. Wilkins,J.M. Ayers,K. Fangmann,J. Landis,L. DeSouza,Z. Hammoud,D. Kah,J. Sanchez,L. Murdoch +77 more