1
|
Sourlos N, Pelgrim G, Wisselink HJ, Yang X, de Jonge G, Rook M, Prokop M, Sidorenkov G, van Tuinen M, Vliegenthart R, van Ooijen PMA. Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT. Eur Radiol Exp 2024; 8:63. [PMID: 38764066 PMCID: PMC11102890 DOI: 10.1186/s41747-024-00459-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 03/18/2024] [Indexed: 05/21/2024] Open
Abstract
BACKGROUND Emphysema influences the appearance of lung tissue in computed tomography (CT). We evaluated whether this affects lung nodule detection by artificial intelligence (AI) and human readers (HR). METHODS Individuals were selected from the "Lifelines" cohort who had undergone low-dose chest CT. Nodules in individuals without emphysema were matched to similar-sized nodules in individuals with at least moderate emphysema. AI results for nodular findings of 30-100 mm3 and 101-300 mm3 were compared to those of HR; two expert radiologists blindly reviewed discrepancies. Sensitivity and false positives (FPs)/scan were compared for emphysema and non-emphysema groups. RESULTS Thirty-nine participants with and 82 without emphysema were included (n = 121, aged 61 ± 8 years (mean ± standard deviation), 58/121 males (47.9%)). AI and HR detected 196 and 206 nodular findings, respectively, yielding 109 concordant nodules and 184 discrepancies, including 118 true nodules. For AI, sensitivity was 0.68 (95% confidence interval 0.57-0.77) in emphysema versus 0.71 (0.62-0.78) in non-emphysema, with FPs/scan 0.51 and 0.22, respectively (p = 0.028). For HR, sensitivity was 0.76 (0.65-0.84) and 0.80 (0.72-0.86), with FPs/scan of 0.15 and 0.27 (p = 0.230). Overall sensitivity was slightly higher for HR than for AI, but this difference disappeared after the exclusion of benign lymph nodes. FPs/scan were higher for AI in emphysema than in non-emphysema (p = 0.028), while FPs/scan for HR were higher than AI for 30-100 mm3 nodules in non-emphysema (p = 0.009). CONCLUSIONS AI resulted in more FPs/scan in emphysema compared to non-emphysema, a difference not observed for HR. RELEVANCE STATEMENT In the creation of a benchmark dataset to validate AI software for lung nodule detection, the inclusion of emphysema cases is important due to the additional number of FPs. KEY POINTS • The sensitivity of nodule detection by AI was similar in emphysema and non-emphysema. • AI had more FPs/scan in emphysema compared to non-emphysema. • Sensitivity and FPs/scan by the human reader were comparable for emphysema and non-emphysema. • Emphysema and non-emphysema representation in benchmark dataset is important for validating AI.
Collapse
Affiliation(s)
- Nikos Sourlos
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
| | - GertJan Pelgrim
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
- Department of Oral Surgery of the Medical Spectrum Twente (MST), Enschede, 7500KA, The Netherlands
| | - Hendrik Joost Wisselink
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
- DataScience Center in Health (DASH), University Medical Center Groningen, Groningen, 9713GZ, The Netherlands
| | - Xiaofei Yang
- Department of Epidemiology, University Medical Center Groningen, Groningen, 9713GZ, The Netherlands
| | - Gonda de Jonge
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
| | - Mieneke Rook
- Department of Radiology, Martini Hospital, Groningen, 9728NT, The Netherlands
| | - Mathias Prokop
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
| | - Grigory Sidorenkov
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
- Department of Epidemiology, University Medical Center Groningen, Groningen, 9713GZ, The Netherlands
| | - Marcel van Tuinen
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
| | - Rozemarijn Vliegenthart
- Department of Radiology, University Medical Center of Groningen, Groningen, 9713GZ, The Netherlands
- DataScience Center in Health (DASH), University Medical Center Groningen, Groningen, 9713GZ, The Netherlands
| | - Peter M A van Ooijen
- DataScience Center in Health (DASH), University Medical Center Groningen, Groningen, 9713GZ, The Netherlands.
- Department of Radiation Oncology, University Medical Center Groningen, Groningen, 9713GZ, The Netherlands.
| |
Collapse
|
2
|
Henschke C, Huber R, Jiang L, Yang D, Cavic M, Schmidt H, Kazerooni E, Zulueta JJ, Sales Dos Santos R, Ventura L. Perspective on Management of Low-Dose Computed Tomography Findings on Low-Dose Computed Tomography Examinations for Lung Cancer Screening. From the International Association for the Study of Lung Cancer Early Detection and Screening Committee. J Thorac Oncol 2024; 19:565-580. [PMID: 37979778 DOI: 10.1016/j.jtho.2023.11.013] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Revised: 10/24/2023] [Accepted: 11/13/2023] [Indexed: 11/20/2023]
Abstract
Lung cancer screening using low-dose computed tomography (LDCT) carefully implemented has been found to reduce deaths from lung cancer. Optimal management starts with selection of eligibility criteria, counseling of screenees, smoking cessation, selection of the regimen of screening which specifies the imaging protocol, and workup of LDCT findings. Coordination of clinical, radiologic, and interventional teams and ultimately treatment of diagnosed lung cancers under screening determine the benefit of LDCT screening. Ethical considerations of who should be eligible for LDCT screening programs are important to provide the benefit to as many people at risk of lung cancer as possible. Unanticipated diseases identified on LDCT may offer important benefits through early detection of leading global causes of death, such as cardiovascular diseases and chronic obstructive pulmonary disease, as the latter may result from conditions such as emphysema and bronchiectasis, which can be identified early on LDCT. This report identifies the key components of the regimen of LDCT screening for lung cancer which include the need for a management system to provide data for continuous updating of the regimen and provides quality assurance assessment of actual screenings. Multidisciplinary clinical management is needed to maximize the benefit of early detection, diagnosis, and treatment of lung cancer. Different regimens have been evolving throughout the world as the resources and needs may be different, for countries with limited resources. Sharing of results, further knowledge, and incorporation of technologic advances will continue to accelerate worldwide improvements in the diagnostic and treatment approaches.
Collapse
Affiliation(s)
- Claudia Henschke
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York.
| | - Rudolf Huber
- Division of Respiratory Medicine and Thoracic Oncology, Department of Medicine, University of Munich - Campus Innenstadt, Ziemssenstrabe, Munich, Germany
| | - Long Jiang
- Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China
| | - Dawei Yang
- Department of Pulmonary Medicine and Critical Care, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Milena Cavic
- Department of Experimental Oncology, Institute of Oncology and Radiology of Serbia, Belgrade, Serbia
| | - Heidi Schmidt
- Department of Medical Imaging, Toronto General Hospital, Toronto, Canada
| | - Ella Kazerooni
- Division of Cardiothoracic Radiology and Internal Medicine, University of Michigan Medical School, Frankel Cardiovascular Center, Ann Arbor, Michigan
| | - Javier J Zulueta
- Department of Medicine, Mount Sinai Morningside, New York, New York
| | - Ricardo Sales Dos Santos
- Department of Minimally Invasive Thoracic and Robotic Surgery, Albert Einstein Israeli Hospital, Sao Paulo, Brazil
| | - Luigi Ventura
- Department of Medicine and Surgery, University Hospital of Parma, Parma, Italy
| |
Collapse
|
3
|
Antonicelli A, Muriana P, Favaro G, Mangiameli G, Lanza E, Profili M, Bianchi F, Fina E, Ferrante G, Ghislandi S, Pistillo D, Finocchiaro G, Condorelli G, Lembo R, Novellis P, Dieci E, De Santis S, Veronesi G. The Smokers Health Multiple ACtions (SMAC-1) Trial: Study Design and Results of the Baseline Round. Cancers (Basel) 2024; 16:417. [PMID: 38254906 PMCID: PMC10814085 DOI: 10.3390/cancers16020417] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Revised: 01/13/2024] [Accepted: 01/15/2024] [Indexed: 01/24/2024] Open
Abstract
BACKGROUND Lung cancer screening with low-dose helical computed tomography (LDCT) reduces mortality in high-risk subjects. Cigarette smoking is linked to up to 90% of lung cancer deaths. Even more so, it is a key risk factor for many other cancers and cardiovascular and pulmonary diseases. The Smokers health Multiple ACtions (SMAC-1) trial aimed to demonstrate the feasibility and effectiveness of an integrated program based on the early detection of smoking-related thoraco-cardiovascular diseases in high-risk subjects, combined with primary prevention. A new multi-component screening design was utilized to strengthen the framework on conventional lung cancer screening programs. We report here the study design and the results from our baseline round, focusing on oncological findings. METHODS High-risk subjects were defined as being >55 years of age and active smokers or formers who had quit within 15 years (>30 pack/y). A PLCOm2012 threshold >2% was chosen. Subject outreach was streamlined through media campaign and general practitioners' engagement. Eligible subjects, upon written informed consent, underwent a psychology consultation, blood sample collection, self-evaluation questionnaire, spirometry, and LDCT scan. Blood samples were analyzed for pentraxin-3 protein levels, interleukins, microRNA, and circulating tumor cells. Cardiovascular risk assessment and coronary artery calcium (CAC) scoring were performed. Direct and indirect costs were analyzed focusing on the incremental cost-effectiveness ratio per quality-adjusted life years gained in different scenarios. Personalized screening time-intervals were determined using the "Maisonneuve risk re-calculation model", and a threshold <0.6% was chosen for the biennial round. RESULTS In total, 3228 subjects were willing to be enrolled. Out of 1654 eligible subjects, 1112 participated. The mean age was 64 years (M/F 62/38%), with a mean PLCOm2012 of 5.6%. Former and active smokers represented 23% and 77% of the subjects, respectively. At least one nodule was identified in 348 subjects. LDCTs showed no clinically significant findings in 762 subjects (69%); thus, they were referred for annual/biennial LDCTs based on the Maisonneuve risk (mean value = 0.44%). Lung nodule active surveillance was indicated for 122 subjects (11%). Forty-four subjects with baseline suspicious nodules underwent a PET-FDG and twenty-seven a CT-guided lung biopsy. Finally, a total of 32 cancers were diagnosed, of which 30 were lung cancers (2.7%) and 2 were extrapulmonary cancers (malignant pleural mesothelioma and thymoma). Finally, 25 subjects underwent lung surgery (2.25%). Importantly, there were zero false positives and two false negatives with CT-guided biopsy, of which the patients were operated on with no stage shift. The final pathology included lung adenocarcinomas (69%), squamous cell carcinomas (10%), and others (21%). Pathological staging showed 14 stage I (47%) and 16 stage II-IV (53%) cancers. CONCLUSIONS LDCTs continue to confirm their efficacy in safely detecting early-stage lung cancer in high-risk subjects, with a negligible risk of false-positive results. Re-calculating the risk of developing lung cancer after baseline LDCTs with the Maisonneuve model allows us to optimize time intervals to subsequent screening. The Smokers health Multiple ACtions (SMAC-1) trial offers solid support for policy assessments by policymakers. We trust that this will help in developing guidelines for the large-scale implementation of lung cancer screening, paving the way for better outcomes for lung cancer patients.
Collapse
Affiliation(s)
- Alberto Antonicelli
- Faculty of Medicine and Surgery, School of Thoracic Surgery, Università Vita-Salute San Raffaele, 20132 Milan, Italy; (A.A.); (G.V.)
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| | - Piergiorgio Muriana
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| | - Giovanni Favaro
- Department of Anesthesia and Intensive Care, IRCCS Istituto Oncologico Veneto (IOV), 35128 Padua, Italy;
| | - Giuseppe Mangiameli
- Division of Thoracic Surgery, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy; (G.M.); (E.F.)
- Department of Biomedical Sciences, Humanitas University, 20072 Pieve Emanuele, Italy; (E.L.); (G.F.); (G.C.)
| | - Ezio Lanza
- Department of Biomedical Sciences, Humanitas University, 20072 Pieve Emanuele, Italy; (E.L.); (G.F.); (G.C.)
- Department of Interventional Radiology, IRCCS Humanitas Clinical and Research Center, 20089 Rozzano, Italy;
| | - Manuel Profili
- Department of Interventional Radiology, IRCCS Humanitas Clinical and Research Center, 20089 Rozzano, Italy;
| | - Fabrizio Bianchi
- Unit of Cancer Biomarkers, Fondazione IRCCS Casa Sollievo della Sofferenza, 71013 San Giovanni Rotondo, Italy;
| | - Emanuela Fina
- Division of Thoracic Surgery, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy; (G.M.); (E.F.)
| | - Giuseppe Ferrante
- Department of Biomedical Sciences, Humanitas University, 20072 Pieve Emanuele, Italy; (E.L.); (G.F.); (G.C.)
- Cardio Center, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy
| | - Simone Ghislandi
- CERGAS and Department of Social and Political Sciences, Bocconi University, 20136 Milan, Italy;
| | - Daniela Pistillo
- Center for Biological Resources, Humanitas Cancer Center, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy;
| | - Giovanna Finocchiaro
- Department of Medical Oncology, Humanitas Cancer Center, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy;
| | - Gianluigi Condorelli
- Department of Biomedical Sciences, Humanitas University, 20072 Pieve Emanuele, Italy; (E.L.); (G.F.); (G.C.)
- Cardio Center, IRCCS Humanitas Research Hospital, 20089 Rozzano, Italy
| | - Rosalba Lembo
- Department of Anesthesia and Intensive Care, Section of Biostatistics, Università Vita-Salute San Raffaele, 20132 Milan, Italy;
| | - Pierluigi Novellis
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| | - Elisa Dieci
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| | - Simona De Santis
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| | - Giulia Veronesi
- Faculty of Medicine and Surgery, School of Thoracic Surgery, Università Vita-Salute San Raffaele, 20132 Milan, Italy; (A.A.); (G.V.)
- Department of Thoracic Surgery, IRCCS Ospedale San Raffaele, 20132 Milan, Italy; (P.N.); (E.D.); (S.D.S.)
| |
Collapse
|
4
|
Gareen IF, Hoffman RM, Tailor TD. Separating Actionable From Incidental Findings-Imperative for Meaningful Clinical Outcomes-Reply. JAMA Intern Med 2023; 183:1176-1177. [PMID: 37639256 DOI: 10.1001/jamainternmed.2023.4067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 08/29/2023]
Affiliation(s)
- Ilana F Gareen
- Department of Epidemiology, Brown University School of Public Health, Providence, Rhode Island
- Center for Statistical Sciences, Brown University School of Public Health, Providence, Rhode Island
| | - Richard M Hoffman
- Holden Comprehensive Cancer Center, Department of Medicine, University of Iowa Carver College of Medicine, University of Iowa, Iowa City
| | - Tina D Tailor
- Division of Cardiothoracic Radiology, Department of Radiology, Duke Health, Durham, North Carolina
| |
Collapse
|
5
|
Patel P, Flores R, Alpert N, Pyenson B, Taioli E. Effect of stage shift and immunotherapy treatment on lung cancer survival outcomes. Eur J Cardiothorac Surg 2023; 64:ezad203. [PMID: 37285318 PMCID: PMC10412408 DOI: 10.1093/ejcts/ezad203] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/19/2023] [Revised: 05/01/2023] [Accepted: 06/06/2023] [Indexed: 06/09/2023] Open
Abstract
OBJECTIVES Non-small-cell lung cancer mortality has declined at a faster rate than incidence due to multiple factors, including changes in smoking behaviour, early detection which shifts diagnosis, and novel therapies. Limited resources require that we quantify the contribution of early detection versus novel therapies in improving lung cancer survival outcomes. METHODS Non-small-cell lung cancer patients from the Surveillance, Epidemiology, and End Results-Medicare data were queried and divided into: (i) stage IV diagnosed in 2015 (n = 3774) and (ii) stage I-III diagnosed in 2010-2012 (n = 15 817). Multivariable Cox-proportional hazards models were performed to assess the independent association of immunotherapy or diagnosis at stage I/II versus III with survival. RESULTS Patients treated with immunotherapy had significantly better survival than those who did not (HRadj: 0.49, 95% confidence interval: 0.43-0.56), as did those diagnosed at stage I/II versus stage III (HRadj: 0.36, 95% confidence interval: 0.35-0.37). Patients on immunotherapy had a 10.7-month longer survival than those who were not. Stage I/II patients had an average survival benefit of 34 months, compared to stage III. If 25%% of stage IV patients not on immunotherapy received it, there would be a gain of 22 292 person-years survival per 100 000 diagnoses. A switch of only 25% from stage III to stage I/II would correspond to 70 833 person-years survival per 100 000 diagnoses. CONCLUSIONS In this cohort study, earlier stage at diagnosis contributed to life expectancy by almost 3 years, while gains from immunotherapy would contribute ½ year of survival. Given the relative affordability of early detection, risk reduction through increased screening should be optimized.
Collapse
Affiliation(s)
- Parth Patel
- Department of Thoracic Surgery, Icahn School of Medicine at Mount Sinai, Mount Sinai Health System, New York, NY, USA
| | - Raja Flores
- Department of Thoracic Surgery, Icahn School of Medicine at Mount Sinai, Mount Sinai Health System, New York, NY, USA
| | - Naomi Alpert
- Institute for Translational Epidemiology and Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Bruce Pyenson
- NYU School of Global Public Health, New York University, New York, NY, USA
- Milliman Inc., New York, NY, USA
| | - Emanuela Taioli
- Department of Thoracic Surgery, Icahn School of Medicine at Mount Sinai, Mount Sinai Health System, New York, NY, USA
- Institute for Translational Epidemiology and Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| |
Collapse
|
6
|
Wisselink HJ, Steerenberg DJD, Rook M, Pelgrim GJ, Heuvelmans MA, van den Berge M, de Bock GH, Vliegenthart R. Predicted versus CT-derived total lung volume in a general population: The ImaLife study. PLoS One 2023; 18:e0287383. [PMID: 37327210 PMCID: PMC10275439 DOI: 10.1371/journal.pone.0287383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Accepted: 06/05/2023] [Indexed: 06/18/2023] Open
Abstract
Predicted lung volumes based on the Global Lung Function Initiative (GLI) model are used in pulmonary disease detection and monitoring. It is unknown how well the predicted lung volume corresponds with computed tomography (CT) derived total lung volume (TLV). The aim of this study was to compare the GLI-2021 model predictions of total lung capacity (TLC) with CT-derived TLV. 151 female and 139 male healthy participants (age 45-65 years) were consecutively selected from a Dutch general population cohort, the Imaging in Lifelines (ImaLife) cohort. In ImaLife, all participants underwent low-dose, inspiratory chest CT. TLV was measured by an automated analysis, and compared to predicted TLC based on the GLI-2021 model. Bland-Altman analysis was performed for analysis of systematic bias and range between limits of agreement. To further mimic the GLI-cohort all analyses were repeated in a subset of never-smokers (51% of the cohort). Mean±SD of TLV was 4.7±0.9 L in women and 6.2±1.2 L in men. TLC overestimated TLV, with systematic bias of 1.0 L in women and 1.6 L in men. Range between limits of agreement was 3.2 L for women and 4.2 L for men, indicating high variability. Performing the analysis with never-smokers yielded similar results. In conclusion, in a healthy cohort, predicted TLC substantially overestimates CT-derived TLV, with low precision and accuracy. In a clinical context where an accurate or precise lung volume is required, measurement of lung volume should be considered.
Collapse
Affiliation(s)
- Hendrik J. Wisselink
- Department of Radiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Danielle J. D. Steerenberg
- Department of Radiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Mieneke Rook
- Department of Radiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
- Department of Radiology, Martini Hospital, Groningen, The Netherlands
| | - Gert-Jan Pelgrim
- Department of Radiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Marjolein A. Heuvelmans
- Department of Pulmonology, Medisch Spectrum Twente, Enschede, The Netherlands
- Department of Epidemiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Maarten van den Berge
- Department of Pulmonology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Geertruida H. de Bock
- Department of Epidemiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Rozemarijn Vliegenthart
- Department of Radiology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
- DataScience in Health, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| |
Collapse
|
7
|
Kheradmand F, Zhang Y, Corry DB. Contribution of adaptive immunity to human COPD and experimental models of emphysema. Physiol Rev 2023; 103:1059-1093. [PMID: 36201635 PMCID: PMC9886356 DOI: 10.1152/physrev.00036.2021] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2021] [Revised: 09/15/2022] [Accepted: 09/20/2022] [Indexed: 02/01/2023] Open
Abstract
The pathophysiology of chronic obstructive pulmonary disease (COPD) and the undisputed role of innate immune cells in this condition have dominated the field in the basic research arena for many years. Recently, however, compelling data suggesting that adaptive immune cells may also contribute to the progressive nature of lung destruction associated with COPD in smokers have gained considerable attention. The histopathological changes in the lungs of smokers can be limited to the large or small airways, but alveolar loss leading to emphysema, which occurs in some individuals, remains its most significant and irreversible outcome. Critically, however, the question of why emphysema progresses in a subset of former smokers remained a mystery for many years. The recognition of activated and organized tertiary T- and B-lymphoid aggregates in emphysematous lungs provided the first clue that adaptive immune cells may play a crucial role in COPD pathophysiology. Based on these findings from human translational studies, experimental animal models of emphysema were used to determine the mechanisms through which smoke exposure initiates and orchestrates adaptive autoreactive inflammation in the lungs. These models have revealed that T helper (Th)1 and Th17 subsets promote a positive feedback loop that activates innate immune cells, confirming their role in emphysema pathogenesis. Results from genetic studies and immune-based discoveries have further provided strong evidence for autoimmunity induction in smokers with emphysema. These new findings offer a novel opportunity to explore the mechanisms underlying the inflammatory landscape in the COPD lung and offer insights for development of precision-based treatment to halt lung destruction.
Collapse
Affiliation(s)
- Farrah Kheradmand
- Department of Medicine, Baylor College of Medicine, Houston, Texas
- Department of Pathology and Immunology, Baylor College of Medicine, Houston, Texas
- Biology of Inflammation Center, Baylor College of Medicine, Houston, Texas
- Center for Translational Research on Inflammatory Diseases (CTRID), Michael E. DeBakey Department of Veterans Affairs Medical Center, Houston, Texas
| | - Yun Zhang
- Department of Medicine, Baylor College of Medicine, Houston, Texas
- Department of Pathology and Immunology, Baylor College of Medicine, Houston, Texas
| | - David B Corry
- Department of Medicine, Baylor College of Medicine, Houston, Texas
- Department of Pathology and Immunology, Baylor College of Medicine, Houston, Texas
- Biology of Inflammation Center, Baylor College of Medicine, Houston, Texas
- Center for Translational Research on Inflammatory Diseases (CTRID), Michael E. DeBakey Department of Veterans Affairs Medical Center, Houston, Texas
| |
Collapse
|
8
|
Adams SJ, Stone E, Baldwin DR, Vliegenthart R, Lee P, Fintelmann FJ. Lung cancer screening. Lancet 2023; 401:390-408. [PMID: 36563698 DOI: 10.1016/s0140-6736(22)01694-4] [Citation(s) in RCA: 53] [Impact Index Per Article: 53.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Revised: 07/26/2022] [Accepted: 08/25/2022] [Indexed: 12/24/2022]
Abstract
Randomised controlled trials, including the National Lung Screening Trial (NLST) and the NELSON trial, have shown reduced mortality with lung cancer screening with low-dose CT compared with chest radiography or no screening. Although research has provided clarity on key issues of lung cancer screening, uncertainty remains about aspects that might be critical to optimise clinical effectiveness and cost-effectiveness. This Review brings together current evidence on lung cancer screening, including an overview of clinical trials, considerations regarding the identification of individuals who benefit from lung cancer screening, management of screen-detected findings, smoking cessation interventions, cost-effectiveness, the role of artificial intelligence and biomarkers, and current challenges, solutions, and opportunities surrounding the implementation of lung cancer screening programmes from an international perspective. Further research into risk models for patient selection, personalised screening intervals, novel biomarkers, integrated cardiovascular disease and chronic obstructive pulmonary disease assessments, smoking cessation interventions, and artificial intelligence for lung nodule detection and risk stratification are key opportunities to increase the efficiency of lung cancer screening and ensure equity of access.
Collapse
Affiliation(s)
- Scott J Adams
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.
| | - Emily Stone
- Faculty of Medicine, University of New South Wales and Department of Lung Transplantation and Thoracic Medicine, St Vincent's Hospital, Sydney, NSW, Australia
| | - David R Baldwin
- Respiratory Medicine Unit, David Evans Research Centre, Nottingham University Hospitals NHS Trust, Nottingham, UK
| | | | - Pyng Lee
- Division of Respiratory and Critical Care Medicine, National University Hospital and National University of Singapore, Singapore
| | - Florian J Fintelmann
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA
| |
Collapse
|
9
|
Dyer DS, White C, Conley Thomson C, Gieske MR, Kanne JP, Chiles C, Parker MS, Menchaca M, Wu CC, Kazerooni EA. A Quick Reference Guide for Incidental Findings on Lung Cancer Screening CT Examinations. J Am Coll Radiol 2023; 20:162-172. [PMID: 36509659 DOI: 10.1016/j.jacr.2022.08.009] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2022] [Revised: 08/12/2022] [Accepted: 08/18/2022] [Indexed: 12/14/2022]
Abstract
PURPOSE The US Preventive Services Task Force has recommended lung cancer screening (LCS) with low-dose CT (LDCT) in high-risk individuals since 2013. Because LDCT encompasses the lower neck, chest, and upper abdomen, many incidental findings (IFs) are detected. The authors created a quick reference guide to describe common IFs in LCS to assist LCS program navigators and ordering providers in managing the care continuum in LCS. METHODS The ACR IF white papers were reviewed for findings on LDCT that were age appropriate for LCS. A draft guide was created on the basis of recommendations in the IF white papers, the medical literature, and input from subspecialty content experts. The draft was piloted with LCS program navigators recruited through contacts by the ACR LCS Steering Committee. The navigators completed a survey on overall usefulness, clarity, adequacy of content, and user experience with the guide. RESULTS Seven anatomic regions including 15 discrete organs with 45 management recommendations were identified as relevant to the age of individuals eligible for LCS. The draft was piloted by 49 LCS program navigators from 32 facilities. The guide was rated as useful and clear by 95% of users. No unexpected or adverse experiences were reported in using the guide. On the basis of feedback, relevant sections were reviewed and edited. CONCLUSIONS The ACR Lung Cancer Screening CT Incidental Findings Quick Reference Guide outlines the common IFs in LCS and can serve as an easy-to-use resource for ordering providers and LCS program navigators to help guide management.
Collapse
Affiliation(s)
- Debra S Dyer
- Chair, Department of Radiology, Director, Lung Cancer Screening Program, and Director, Incidental Lung Nodule Program & Lung Nodule Registry, National Jewish Health, Denver, Colorado.
| | - Charles White
- Vice Chair, Clinical Affairs, University of Maryland School of Medicine, Baltimore, Maryland. https://twitter.com/
| | - Carey Conley Thomson
- Chair, Department of Medicine and Director, Multidisciplinary Thoracic Oncology and Lung Cancer Screening Program, Department of Medicine, Mount Auburn Hospital/Beth Israel Lahey Health, Cambridge, Massachusetts; and Harvard Medical School, Boston, Massachusetts
| | - Michael R Gieske
- Director, Lung Cancer Screening Physician, Director, Virtual Health Director, Primary Care East Department, Lead Provider, Ft. Mitchell St. Elizabeth Primary Care, Physician Director, Policy and Government Relations, St Elizabeth Healthcare, Edgewood, Kentucky
| | - Jeffrey P Kanne
- Chief, Thoracic Imaging and Vice Chair, Quality and Safety, Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin. https://twitter.com/
| | - Caroline Chiles
- Director, Lung Cancer Screening Program, Atrium Health Wake Forest Baptist, Winston-Salem, North Carolina. https://twitter.com/
| | - Mark S Parker
- Director, Thoracic Imaging Section and Director, Thoracic Imaging Fellowship Program, Early Detection Lung Screening Program, VCU Health Systems, Richmond, Virginia
| | - Martha Menchaca
- Department of Radiology, University of Illinois at Chicago, Chicago, Illinois
| | - Carol C Wu
- Deputy Chair Ad Interim, Department of Thoracic Imaging, MD Anderson Cancer Center, Houston, Texas. https://twitter.com/
| | - Ella A Kazerooni
- Associate Chief Clinical Officer for Diagnostics and Clinical Information Management, University of Michigan Medical School, Ann Arbor, Michigan. https://twitter.com/
| |
Collapse
|
10
|
Fuhrman J, Yip R, Zhu Y, Jirapatnakul AC, Li F, Henschke CI, Yankelevitz DF, Giger ML. Evaluation of emphysema on thoracic low-dose CTs through attention-based multiple instance deep learning. Sci Rep 2023; 13:1187. [PMID: 36681685 PMCID: PMC9867724 DOI: 10.1038/s41598-023-27549-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2022] [Accepted: 01/04/2023] [Indexed: 01/22/2023] Open
Abstract
In addition to lung cancer, other thoracic abnormalities, such as emphysema, can be visualized within low-dose CT scans that were initially obtained in cancer screening programs, and thus, opportunistic evaluation of these diseases may be highly valuable. However, manual assessment for each scan is tedious and often subjective, thus we have developed an automatic, rapid computer-aided diagnosis system for emphysema using attention-based multiple instance deep learning and 865 LDCTs. In the task of determining if a CT scan presented with emphysema or not, our novel Transfer AMIL approach yielded an area under the ROC curve of 0.94 ± 0.04, which was a statistically significant improvement compared to other methods evaluated in our study following the Delong Test with correction for multiple comparisons. Further, from our novel attention weight curves, we found that the upper lung demonstrated a stronger influence in all scan classes, indicating that the model prioritized upper lobe information. Overall, our novel Transfer AMIL method yielded high performance and provided interpretable information by identifying slices that were most influential to the classification decision, thus demonstrating strong potential for clinical implementation.
Collapse
Affiliation(s)
- Jordan Fuhrman
- Committee on Medical Physics, Department of Radiology, The University of Chicago, 5841 S Maryland Avenue, MC2026, Chicago, 60637, USA.
| | - Rowena Yip
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA
| | - Yeqing Zhu
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA
| | - Artit C Jirapatnakul
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA
| | - Feng Li
- Committee on Medical Physics, Department of Radiology, The University of Chicago, 5841 S Maryland Avenue, MC2026, Chicago, 60637, USA
| | - Claudia I Henschke
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA
| | - David F Yankelevitz
- Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, 10029, USA
| | - Maryellen L Giger
- Committee on Medical Physics, Department of Radiology, The University of Chicago, 5841 S Maryland Avenue, MC2026, Chicago, 60637, USA
| |
Collapse
|
11
|
Elicker BM. Chronic Obstructive Pulmonary Disease and Small Airways Diseases. Semin Respir Crit Care Med 2022; 43:825-838. [PMID: 36252610 DOI: 10.1055/s-0042-1755567] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
The small airways are a common target of injury within the lungs and may be affected by a wide variety of inhaled, systemic, and other disorders. Imaging is critical in the detection and diagnosis of small airways disease since significant injury may occur prior to pulmonary function tests showing abnormalities. The goal of this article is to describe the typical imaging findings and patterns of small airways diseases. An approach which divides the imaging appearances into four categories (tree-in-bud opacities, poorly defined centrilobular nodules, mosaic attenuation, and emphysema) will provide a framework in which to formulate appropriate and focused differential diagnoses.
Collapse
Affiliation(s)
- Brett M Elicker
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, California
| |
Collapse
|
12
|
Metwally EM, Rivera MP, Durham DD, Lane L, Perera P, Lamb D, Henderson LM. Lung Cancer Screening in Individuals With and Without Lung-Related Comorbidities. JAMA Netw Open 2022; 5:e2230146. [PMID: 36066893 PMCID: PMC9449784 DOI: 10.1001/jamanetworkopen.2022.30146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/19/2022] [Accepted: 07/21/2022] [Indexed: 11/30/2022] Open
Abstract
Importance Comorbidities characterize the underlying health status of individuals. In the context of lung cancer screening (LCS), lung-related comorbidities may influence the observed benefits and harms. Objective To compare the characteristics of individuals undergoing LCS, the LCS examination result, the cancer detection rate (CDR), and the false-positive rate (FPR) in those with and without lung-related comorbidities. Design, Setting, and Participants A prospective cohort study was conducted in 5 academic and community screening sites across North Carolina from January 1, 2014, to November 7, 2020. Participants included 611 individuals screened for lung cancer who completed a 1-page health history questionnaire. Exposures Presence of at least 1 self-reported lung-related comorbidity, including chronic obstructive pulmonary disease, chronic bronchitis, emphysema, asthma, bronchiectasis, pulmonary fibrosis, silicosis, asbestosis, sarcoidosis, and tuberculosis. Main Outcomes and Measures The LCS examination result was determined from the radiologist's Lung Imaging Reporting and Data System assessment (negative, 1 or 2; positive, 3 or 4). The age-adjusted CDR and FPR were calculated per 100 LCS examinations, using binary logistic regression. Results Among the 611 individuals screened for lung cancer (308 men [50.4%]; mean [SD] age, 64 [6.2] years), 335 (54.8%) had at least 1 lung-related comorbidity. Individuals with vs without lung-related comorbidities were more likely to be female than male (180 of 335 [53.7%] vs 123 of 276 [44.6%]; P = .02), White vs non-White race (275 of 326 [84.4%] vs 193 of 272 [71.0%]; P < .001), and have high school or less education vs greater than a high school education (108 of 231 [46.7%] vs 64 of 208 [30.8%]; P = .001). There were no significant differences in the proportion of positive LCS examinations in those with vs without a lung-related comorbidity at baseline (37 [16.0%] vs 22 [11.1%]; P = .14) or subsequent (40 [12.3%] vs 23 [10.6%]; P = .54) LCS examination. Comparing individuals with vs without lung-related comorbidities, there was no statistically significant difference in the CDR (1.6 vs 1.9 per 100; P = .73) or FPR (13.0 vs 9.3 per 100; P = .16). Of the 17 individuals with lung cancer, 13 patients (76.5%) were diagnosed with stage I lung cancer. Conclusions and Relevance The findings of this study suggest that individuals with self-reported lung-related comorbidities undergoing LCS were more likely to be female, of White race, and have less education than those without lung-related comorbidity. Although no statistically significant differences in the proportion of positive examinations, CDR, or FPR by self-reported lung comorbidities were noted, additional studies with larger numbers of individuals undergoing screening are needed to understand LCS outcomes in those with lung-related comorbidities.
Collapse
Affiliation(s)
- Eman M. Metwally
- Lineberger Cancer Comprehensive Center, University of North Carolina at Chapel Hill
| | - M. Patricia Rivera
- Division of Pulmonary and Critical Care, University of Rochester Medical Center, Rochester, New York
- Wilmot Cancer Center, University of Rochester Medical Center, Rochester, New York
| | | | - Lindsay Lane
- Department of Radiology, University of North Carolina at Chapel Hill
| | - Pasangi Perera
- Department of Radiology, University of North Carolina at Chapel Hill
| | - Derek Lamb
- Department of Radiology, University of North Carolina at Chapel Hill
| | - Louise M. Henderson
- Lineberger Cancer Comprehensive Center, University of North Carolina at Chapel Hill
- Department of Radiology, University of North Carolina at Chapel Hill
- Department of Epidemiology, University of North Carolina at Chapel Hill
| |
Collapse
|
13
|
Pinsky PF, Lynch DA, Gierada DS. Incidental Findings on Low-Dose CT Scan Lung Cancer Screenings and Deaths From Respiratory Diseases. Chest 2022; 161:1092-1100. [PMID: 34838524 PMCID: PMC9005861 DOI: 10.1016/j.chest.2021.11.015] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2021] [Revised: 11/16/2021] [Accepted: 11/16/2021] [Indexed: 11/28/2022] Open
Abstract
BACKGROUND Incidental respiratory disease-related findings are frequently observed on low-dose CT (LDCT) lung cancer screenings. This study analyzed data from the National Lung Screening Trial (NLST) to assess the relationship between such findings and respiratory disease mortality (RDM), excluding lung cancer. RESEARCH QUESTION Are incidental respiratory findings on LDCT scanning associated with increased RDM? STUDY DESIGN AND METHODS Subjects in the NLST LDCT arm received three annual screens. Trial radiologists noted findings related to possible lung cancer, as well as respiratory-related incidental findings. Demographic characteristics, smoking history, and medical history were captured in a baseline questionnaire. Kaplan-Meier curves were used to assess cumulative RDM. Multivariate proportional hazards models were used to assess risk factors for RDM; in addition to incidental CT scan findings, variables included respiratory disease history (COPD/emphysema, and asthma), smoking history, and demographic factors (age, race, sex, and BMI). RESULTS Of 26,722 subjects in the NLST LDCT arm, 25,002 received the baseline screen and a subsequent LDCT screen. Overall, 59% were male, 26.5% were aged ≥ 65 years at baseline, and 10.6% reported a history of COPD/emphysema. Emphysema on LDCT scanning was reported in 30.7% of subjects at baseline and in 44.2% at any screen. Of those with emphysema on baseline LDCT scanning, 18% reported a history of COPD/emphysema. Median mortality follow-up was 10.3 years. There were 3,639 deaths, and 708 were from respiratory diseases. Among subjects with no history of COPD/emphysema, 10-year cumulative RDM ranged from 3.9% for subjects with emphysema and reticular opacities to 1.1% for those with neither condition; the corresponding range among subjects with a COPD/emphysema history was 17.3% (both) to 3.7% (neither). Emphysema on LDCT imaging was associated with a significantly elevated RDM hazard ratio (2.27; 95% CI, 1.92-2.7) in the multivariate model. Reticular opacities (including honeycombing/fibrosis/scar) also had a significantly elevated hazard ratio (1.39; 95% CI, 1.19-1.62). INTERPRETATION Incidental respiratory disease-related findings observed on NLST LDCT screens were frequent and associated with increased mortality from respiratory diseases.
Collapse
Affiliation(s)
- Paul F Pinsky
- Division of Cancer Prevention, National Cancer Institute, Bethesda, MD.
| | - David A Lynch
- Department of Radiology, National Jewish Health, Denver, CO
| | - David S Gierada
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO
| |
Collapse
|
14
|
Abstract
Background: Lung-RADS category 3 and 4 nodules account for most cancers among screening-detected lung cancers and are considered actionable nodules with management implications. The cancer frequency among such nodules is estimated in the Lung-RADS recommendations and has been investigated primarily using retrospectively assigned Lung-RADS classifications. Objective: To assess the frequency of cancer among lung nodules assigned Lung-RADS category 3 or 4 at lung cancer screening (LCS) in clinical practice and factors that impact the cancer frequency within each category. Methods: This retrospective study was based on review of clinical radiology reports of 9148 consecutive low-dose CT LCS examinations performed in 4798 patients between June 2014 and January 2021 as part of an established LCS program. Unique nodules assigned Lung-RADS category 3 or 4 (4A, 4B, or 4X) that were clinically categorized as benign or malignant by a multidisciplinary conference, considering histologic analysis and follow-up imaging, were selected for further analysis; benign diagnoses based on stability required at least 12 months of follow-up imaging. Indeterminate nodules were excluded. Cancer frequencies were evaluated. Results: Of the 9148 LCS examinations, 857 (9.4%) were assigned Lung-RADS category 3, and 721 (7.9%) were assigned category 4. The final analysis included 1297 unique nodules in 1139 patients (598 men, 541 women; mean age, 66.0±6.3 years). A total of 1108/1297 (85.4%) nodules were deemed benign, and 189/1297 (14.6%) were deemed malignant. Frequencies of malignancy for category 3, 4A, 4B, and 4X nodules were 3.9%, 15.5%, 36.3%, and 76.8%, respectively. A total of 45/46 (97.8%) endobronchial nodules (all category 4A) were deemed benign based on resolution. Cancer frequency was 13.1%, 24.4%, and 13.5% for solid, part-solid, and ground-glass nodules, respectively. Conclusions: When applying Lung-RADS for LCS clinical practice, the frequency of Lung-RADS category 3 and 4 nodules, as well as cancer frequency in these categories, were higher than prevalence and cancer risk estimated for category 3 and 4 nodules in the Lung-RADS recommendations and reported in earlier studies using retrospective category assignments. Nearly all endobronchial category 4A nodules were benign. Clinical Impact: Future Lung-RADS iterations should consider these findings from real-world practice to improve the system's clinical utility.
Collapse
|