Assessing the Accuracy of a Deep Learning Method to Risk Stratify Indeterminate Pulmonary Nodules

Published on Jul 15, 2020in American Journal of Respiratory and Critical Care Medicine17.452
· DOI :10.1164/RCCM.201903-0505OC
Pierre P. Massion65
Estimated H-index: 65
(Vandy: Vanderbilt University),
Sanja L. Antic4
Estimated H-index: 4
(Vandy: Vanderbilt University)
+ 17 AuthorsFergus V. Gleeson58
Estimated H-index: 58
(University of Oxford)
Sources
Abstract
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...
Download
📖 Papers frequently viewed together
5,552 Citations
12 Authors (Ziyu Bai, ..., Zhuo Zhang)
2 Citations
6 Citations
References45
Newest
#1Rebecca L. Siegel (ACS: American Cancer Society)H-Index: 67
#2Kimberly D. Miller (ACS: American Cancer Society)H-Index: 28
Last. Ahmedin Jemal (ACS: American Cancer Society)H-Index: 139
view all 3 authors...
Each year, the American Cancer Society estimates the numbers of new cancer cases and deaths that will occur in the United States and compiles the most recent data on population-based cancer occurrence. Incidence data (through 2016) were collected by the Surveillance, Epidemiology, and End Results Program; the National Program of Cancer Registries; and the North American Association of Central Cancer Registries. Mortality data (through 2017) were collected by the National Center for Health Statis...
6,326 CitationsSource
#1Peng Huang (Johns Hopkins University)H-Index: 103
#2Cheng Ting Lin (Johns Hopkins University)H-Index: 13
Last. Stephen Lam (UBC: University of British Columbia)H-Index: 86
view all 20 authors...
Summary Background Current lung cancer screening guidelines use either mean diameter, volume, or density of the largest lung nodule on the previous CT scan or appearance of a new nodule to ascertain the timing of the next CT scan. We aimed to develop an accurate screening protocol by estimating the 3-year lung cancer risk after two screening CT scans using deep learning of radiologists' CT readings and other universally available clinical information. Methods A deep learning algorithm (referred ...
30 CitationsSource
#1Diego Ardila (Google)H-Index: 3
#2Atilla P. Kiraly (Google)H-Index: 6
Last. Shravya Shetty (Google)H-Index: 8
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...
487 CitationsSource
#1Arjun Nair (UCLH: University College London Hospitals NHS Foundation Trust)H-Index: 20
#2Emily C. Bartlett (University of Cambridge)H-Index: 4
Last. Sujal R. Desai (University of Cambridge)H-Index: 42
view all 16 authors...
Radiological evaluation of incidentally detected lung nodules on computed tomography (CT) influences management. We assessed international radiological variation in 1) pulmonary nodule characterisation; 2) hypothetical guideline-derived management; and 3) radiologists' management recommendations.107 radiologists from 25 countries evaluated 69 CT-detected nodules, recording: 1) first-choice composition (solid, part-solid or ground-glass, with percentage confidence); 2) morphological features; 3) ...
10 CitationsSource
#1Rahul Paul (USF: University of South Florida)H-Index: 9
#2Lawrence O. Hall (USF: University of South Florida)H-Index: 60
Last. Robert J. GilliesH-Index: 106
view all 5 authors...
Lung cancer is the leading cause of cancer-related deaths globally, which makes early detection and diagnosis a high priority. Computed tomography (CT) is the method of choice for early detection and diagnosis of lung cancer. Radiomics features extracted from CT-detected lung nodules provide a good platform for early detection, diagnosis, and prognosis. In particular when using low dose CT for lung cancer screening, effective use of radiomics can yield a precise non-invasive approach to nodule t...
22 CitationsSource
#1Peng Huang (JHUSOM: Johns Hopkins University School of Medicine)H-Index: 33
#1Peng HuangH-Index: 31
Last. Stephen Lam (UBC: University of British Columbia)H-Index: 86
view all 17 authors...
Computer-aided diagnosis significantly reduces the low-dose CT screening false-positive rate and increases the positive predictive value of lung nodule evaluation.
75 CitationsSource
#1Rahul Paul (USF: University of South Florida)H-Index: 9
#2Samuel H. Hawkins (USF: University of South Florida)H-Index: 8
Last. Dmitry B. Goldgof (USF: University of South Florida)H-Index: 61
view all 6 authors...
Lung cancer has a high incidence and mortality rate. Early detection and diagnosis of lung cancers is best achieved with low-dose computed tomography (CT). Classical radiomics features extracted from lung CT images have been shown as able to predict cancer incidence and prognosis. With the advancement of deep learning and convolutional neural networks (CNNs), deep features can be identified to analyze lung CTs for prognosis prediction and diagnosis. Due to a limited number of available images in...
37 CitationsSource
#1Amelia W. Maiga (VUMC: Vanderbilt University Medical Center)H-Index: 6
#2Stephen A. Deppen (VUMC: Vanderbilt University Medical Center)H-Index: 18
Last. Eric L. Grogan (VUMC: Vanderbilt University Medical Center)H-Index: 21
view all 9 authors...
Importance Clinical guidelines recommend that clinicians estimate the probability of malignancy for patients with indeterminate pulmonary nodules (IPNs) larger than 8 mm. Adherence to these guidelines is unknown. Objectives To determine whether clinicians document the probability of malignancy in high-risk IPNs and to compare these quantitative or qualitative predictions with the validated Mayo Clinic Model. Design, Setting, and Participants Single-institution, retrospective cohort study of pati...
5 CitationsSource
#1Guixia Kang (Beijing University of Posts and Telecommunications)H-Index: 5
#1Kang Guixia (Beijing University of Posts and Telecommunications)
Last. Zhang Ningbo (Beijing University of Posts and Telecommunications)H-Index: 1
view all 4 authors...
The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All network...
78 CitationsSource
#1Viswam S. Nair (USF: University of South Florida)H-Index: 17
#2Vandana Sundaram (Stanford University)H-Index: 25
Last. Michael K. Gould (KP: Kaiser Permanente)H-Index: 67
view all 4 authors...
16 CitationsSource
Cited By20
Newest
#1Riqiang Gao (Vandy: Vanderbilt University)H-Index: 4
Last. Bennett A. LandmanH-Index: 41
view all 9 authors...
Image Quality Assessment (IQA) is important for scientific inquiry, especially in medical imaging and machine learning. Potential data quality issues can be exacerbated when human-based workflows use limited views of the data that may obscure digital artifacts. In practice, multiple factors such as network issues, accelerated acquisitions, motion artifacts, and imaging protocol design can impede the interpretation of image collections. The medical image processing community has developed a wide ...
#1Daiwei Han (UMCG: University Medical Center Groningen)H-Index: 3
#2Marjolein A Heuvelmans (UMCG: University Medical Center Groningen)H-Index: 17
Last. Rozemarijn Vliegenthart (UMCG: University Medical Center Groningen)H-Index: 37
view all 13 authors...
To evaluate the performance of a novel convolutional neural network (CNN) for the classification of typical perifissural nodules (PFN). Chest CT data from two centers in the UK and The Netherlands (1668 unique nodules, 1260 individuals) were collected. Pulmonary nodules were classified into subtypes, including “typical PFNs” on-site, and were reviewed by a central clinician. The dataset was divided into a training/cross-validation set of 1557 nodules (1103 individuals) and a test set of 196 nodu...
Source
Source
#2Arnaud Arindra Adiyoso Setio (Siemens)H-Index: 12
Last. Colin JacobsH-Index: 24
view all 10 authors...
Background Accurate estimation of the malignancy risk of pulmonary nodules at chest CT is crucial for optimizing management in lung cancer screening. Purpose To develop and validate a deep learning (DL) algorithm for malignancy risk estimation of pulmonary nodules detected at screening CT. Materials and Methods In this retrospective study, the DL algorithm was developed with 16 077 nodules (1249 malignant) collected -between 2002 and 2004 from the National Lung Screening Trial. External validati...
1 CitationsSource
#1Rafael Paez (VUMC: Vanderbilt University Medical Center)
#2M. Kammer (VUMC: Vanderbilt University Medical Center)
Last. Pierre P. MassionH-Index: 65
view all 3 authors...
Purpose of review Lung cancer remains the leading cause of cancer-related death in the United States, with poor overall 5-year survival. Early detection and diagnosis are key to survival as demonstrated in lung cancer screening trials. However, with increasing implementation of screening guidelines and use of computed tomography, there has been a sharp rise in the incidence of indeterminate pulmonary nodules (IPNs). Risk stratification of IPNs, particularly those in the intermediate-risk categor...
Source
#1Fabien Maldonado (VUMC: Vanderbilt University Medical Center)H-Index: 35
#2Cyril Varghese (Mayo Clinic)H-Index: 3
Last. Tobias Peikert (Mayo Clinic)H-Index: 31
view all 13 authors...
Introduction Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pre-test probability of malignancy is relatively straightforward, those with intermediate pre-test probability commonly require advanced imaging or biopsy. Noninvasive risk stratification tool...
3 CitationsSource
#1Wenhui Lv (Southern Medical University)H-Index: 1
#1Wenhui Lv (Southern Medical University)H-Index: 1
Last. Guangming Lu (Southern Medical University)H-Index: 55
view all 25 authors...
Abstract Purpose To propose a practical strategy for the clinical application of deep learning algorithm, i.e., Hierarchical-Ordered Network-ORiented Strategy (HONORS), and a new approach to pulmonary nodule classification in various clinical scenarios, i.e., Filter-Guided Pyramid NETwork (FGP-NET). Materials and Methods We developed and validated FGP-NET on a collection of 2106 pulmonary nodules on computed tomography images which combined screened and clinically detected nodules, and performed...
Source
#1Barbara J. KennerH-Index: 5
#2Suresh T. Chari (University of Texas MD Anderson Cancer Center)H-Index: 103
Last. Brian M. Wolpin (Harvard University)H-Index: 64
view all 34 authors...
ABSTRACT Despite considerable research efforts, pancreatic cancer is associated with a dire prognosis and a 5-year survival rate of only 10%. Early symptoms of the disease are mostly nonspecific. The premise of improved survival through early detection is that more individuals will benefit from potentially curative treatment. Artificial intelligence (AI) methodology has emerged as a successful tool for risk stratification and identification in general health care. In response to the maturity of ...
Source
#1Susan Fernandes (Edin.: University of Edinburgh)
#2Gareth O. S. Williams (Edin.: University of Edinburgh)H-Index: 5
Last. Kevin Dhaliwal (Edin.: University of Edinburgh)H-Index: 24
view all 10 authors...
Solitary pulmonary nodules (SPNs) are a clinical challenge, given there is no single clinical sign or radiological feature that definitively identifies a benign from a malignant SPN. The early detection of lung cancer has a huge impact on survival outcome. Consequently, there is great interest in the prompt diagnosis, and treatment of malignant SPNs. Current diagnostic pathways involve endobronchial/transthoracic tissue biopsies or radiological surveillance, which can be associated with suboptim...
Source
#1Daniel AjonaH-Index: 20
#2Ana Remírez (CIMA: Chartered Institute of Management Accountants)H-Index: 5
Last. Ruben PioH-Index: 47
view all 15 authors...
ABSTRACT Lung cancer screening detects early-stage cancers, but also a large number of benign nodules. Molecular markers can help in the lung cancer screening process by refining inclusion criteria or guiding the management of indeterminate pulmonary nodules. In this study, we developed a diagnostic model based on the quantification in plasma of complement-derived fragment C4c, cytokeratin fragment 21.1 (CYFRA 21-1) and C-reactive protein (CRP). The model was first validated in two independent c...
1 CitationsSource