1
|
Ozcelik N, Kıvrak M, Kotan A, Selimoğlu İ. Lung cancer detection based on computed tomography image using convolutional neural networks. Technol Health Care 2024; 32:1795-1805. [PMID: 37955065 DOI: 10.3233/thc-230810] [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] [Indexed: 11/14/2023]
Abstract
BACKGROUND Lung cancer is the most common type of cancer, accounting for 12.8% of cancer cases worldwide. As initially non-specific symptoms occur, it is difficult to diagnose in the early stages. OBJECTIVE Image processing techniques developed using machine learning methods have played a crucial role in the development of decision support systems. This study aimed to classify benign and malignant lung lesions with a deep learning approach and convolutional neural networks (CNNs). METHODS The image dataset includes 4459 Computed tomography (CT) scans (benign, 2242; malignant, 2217). The research type was retrospective; the case-control analysis. A method based on GoogLeNet architecture, which is one of the deep learning approaches, was used to make maximum inference on images and minimize manual control. RESULTS The dataset used to develop the CNNs model is included in the training (3567) and testing (892) datasets. The model's highest accuracy rate in the training phase was estimated as 0.98. According to accuracy, sensitivity, specificity, positive predictive value, and negative predictive values of testing data, the highest classification performance ratio was positive predictive value with 0.984. CONCLUSION The deep learning methods are beneficial in the diagnosis and classification of lung cancer through computed tomography images.
Collapse
Affiliation(s)
| | - Mehmet Kıvrak
- Recep Tayyip Erdogan University, Biostatistics and Medical Informatics, Rize, Turkey
| | - Abdurrahman Kotan
- Erzurum Regional Training and Research Hospital, Chest Disease, Erzurum, Turkey
| | - İnci Selimoğlu
- Recep Tayyip Erdogan University, Chest Disease, Rize, Turkey
| |
Collapse
|
2
|
Ng JKM, Cheung W, Li JJX, Chan KP, Yip WH, Tse GM. Detection of early (T1) lung cancers and lepidic adenocarcinomas in sputum and bronchial cytology. Ann Diagn Pathol 2023; 67:152191. [PMID: 37579536 DOI: 10.1016/j.anndiagpath.2023.152191] [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: 06/25/2023] [Revised: 08/08/2023] [Accepted: 08/09/2023] [Indexed: 08/16/2023]
Abstract
BACKGROUND The lung is an extensively epithelialized organ, producing ample exfoliated material for sputum and bronchial cytology. In view of the updates in the World Health Organization classification of early (T1/≤ 3 cm) lung cancer with respect to adenocarcinomas with lepidic pattern, this study retrospectively reviews sputum and bronchial cytology paired with resection-confirmed lung cancers. METHODS A computerized search for all lung resection specimens of carcinomas over a 20-year period was performed. Cytologic diagnoses of corresponding sputum and bronchial cytology were classified into five-tiered categories (C1-insufficient/inadequate, C2-benign, C3-atypia, C4-suspicious and C5-malignant). Reports and slides of the resection specimen were reviewed for reclassification of T1 cancers. RESULTS Totally 472 and 383 sputum and bronchial cytology specimens respectively were included. Sensitivity for T1 lesions on sputum cytology were 10.6 %, 2.1 % and 0.5 % at cutoffs of atypia/C3, suspicious/C4 and malignant/C5 categories, lower than bronchial cytology (35.1 %, 15.5 %, 8.1 %; p < 0.001). T1 lesions correlated with lower detection rates, whereas squamous cell carcinoma histology, larger size and bronchial invasion were associated with increased detection rates in sputum and bronchial cytology (p < 0.050). Detection rates for abrasive bronchial cytology (brushing) were overall higher (p = 0.018- < 0.001), but on subgroup comparison, non-abrasive (aspiration, lavage and washing) cytology demonstrated favorable trends (p = 0.063-0.088) in detecting T1 lesions. Adenocarcinomas with lepidic pattern had lower suspicious/C4 (p = 0.040) or above and malignant/C5 (p = 0.019), but not atypia/C3 or above (p = 0.517) rates. CONCLUSIONS Most adenocarcinomas with lepidic pattern are only diagnosed as atypia/C3 on cytology. With its modest sensitivity, interpretation of negative and indeterminate cytology results mandates caution.
Collapse
Affiliation(s)
- Joanna K M Ng
- Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong
| | - Wing Cheung
- Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong
| | - Joshua J X Li
- Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong.
| | - Ka Pang Chan
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong
| | - Wing Ho Yip
- Department of Medicine and Therapeutics, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong
| | - Gary M Tse
- Department of Anatomical and Cellular Pathology, Prince of Wales Hospital, The Chinese University of Hong Kong, Hong Kong
| |
Collapse
|
3
|
Maisonneuve P, Rampinelli C, Bertolotti R, Misotti A, Lococo F, Casiraghi M, Spaggiari L, Bellomi M, Novellis P, Solinas M, Dieci E, Alloisio M, Fontana L, Persechino B, Iavicoli S, Veronesi G. Low-dose computed tomography screening for lung cancer in people with workplace exposure to asbestos. Lung Cancer 2019; 131:23-30. [PMID: 31027694 DOI: 10.1016/j.lungcan.2019.03.003] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2018] [Revised: 02/15/2019] [Accepted: 03/05/2019] [Indexed: 12/24/2022]
Abstract
OBJECTIVES Smoking is the main risk factor for lung cancer, but environmental and occupational exposure to carcinogens also increase lung cancer risk. We assessed whether extending low-dose computed tomography (LDCT) screening to persons with occupational exposure to asbestos may be an effective way reducing lung cancer mortality. MATERIALS AND METHODS We conducted a nested case-control study within the COSMOS screening program, assessing past asbestos exposure with a questionnaire. LDCT scans of asbestos-exposed participants were reviewed to assess the presence of pulmonary, interstitial and pleural alterations in comparison to matched unexposed controls. We also performed an exhaustive review, with meta-analysis, of the literature on LDCT screening in asbestos-exposed persons. RESULTS Exposure to asbestos, initially self-reported by 9.8% of COSMOS participants, was confirmed in 216 of 544 assessable cases, corresponding to 2.6% of the screened population. LDCT of asbestos-exposed persons had significantly more pleural plaques, diaphragmatic pleural thickening and pleural calcifications, but similar frequency of parenchymal and interstitial alterations to unexposed persons. From 16 papers, including this study, overall lung cancer detection rates at baseline were 0.81% (95% CI 0.50-1.19) in asbestos-exposed persons, 0.94% (95% CI 0.47-1.53) in asbestos-exposed smokers (12 studies), and 0.11% (95% CI 0.00-0.43) in asbestos-exposed non-smokers (9 studies). CONCLUSION Persons occupationally exposed to asbestos should be monitored to gather more information about risks. Although LDCT screening is effective in the early detection lung cancer in asbestos-exposed smokers, our data suggest that screening of asbestos-exposed persons with no additional risk factors for cancer does is not viable due to the low detection rate.
Collapse
Affiliation(s)
- Patrick Maisonneuve
- Division of Epidemiology and Biostatistics, IEO, European Institute of Oncology IRCCS, Milan, Italy.
| | - Cristiano Rampinelli
- Department of Medical Imaging and Radiation Sciences, IEO, European Institute of Oncology IRCSS, Milan, Italy
| | - Raffaella Bertolotti
- Division of Thoracic Surgery, Data Management, IEO, European Institute of Oncology IRCSS, Milan, Italy
| | - Alessandro Misotti
- Dietetics and Clinical Nutrition, Hospital of Melegnano, ASST Melegnano-Martesana, Milan, Italy
| | - Filippo Lococo
- Department of Thoracic Surgery, Azienda Unità Sanitaria Locale - IRCCS di Reggio Emilia, Reggio Emilia, Italy
| | - Monica Casiraghi
- Division of Thoracic Surgery, European Institute of Oncology IRCSS, Milan, Italy
| | - Lorenzo Spaggiari
- Division of Thoracic Surgery, European Institute of Oncology IRCSS, Milan, Italy; Department of Oncology and Hemato-oncology, University of Milan, Milan, Italy
| | - Massimo Bellomi
- Department of Medical Imaging and Radiation Sciences, IEO, European Institute of Oncology IRCSS, Milan, Italy; Department of Oncology and Hemato-oncology, University of Milan, Milan, Italy
| | - Pierluigi Novellis
- Division of Thoracic and General Surgery, Humanitas Clinical and Research Center, Rozzano, Milan, Italy
| | - Michela Solinas
- Division of Thoracic and General Surgery, Humanitas Clinical and Research Center, Rozzano, Milan, Italy
| | - Elisa Dieci
- Division of Thoracic and General Surgery, Humanitas Clinical and Research Center, Rozzano, Milan, Italy
| | - Marco Alloisio
- Division of Thoracic and General Surgery, Humanitas Clinical and Research Center, Rozzano, Milan, Italy; Department of Biomedical Science, Humanitas University, Rozzano, Milan, Italy
| | - Luca Fontana
- Italian National Insurance Institute for Workplace Injuries (INAIL), Department of Occupational and Environmental Medicine, Epidemiology and Hygiene, Rome, Italy
| | - Benedetta Persechino
- Italian National Insurance Institute for Workplace Injuries (INAIL), Department of Occupational and Environmental Medicine, Epidemiology and Hygiene, Rome, Italy
| | - Sergio Iavicoli
- Italian National Insurance Institute for Workplace Injuries (INAIL), Department of Occupational and Environmental Medicine, Epidemiology and Hygiene, Rome, Italy
| | - Giulia Veronesi
- Division of Thoracic and General Surgery, Humanitas Clinical and Research Center, Rozzano, Milan, Italy
| |
Collapse
|
4
|
Blandin Knight S, Crosbie PA, Balata H, Chudziak J, Hussell T, Dive C. Progress and prospects of early detection in lung cancer. Open Biol 2017; 7:170070. [PMID: 28878044 PMCID: PMC5627048 DOI: 10.1098/rsob.170070] [Citation(s) in RCA: 460] [Impact Index Per Article: 65.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2017] [Accepted: 07/27/2017] [Indexed: 12/14/2022] Open
Abstract
Lung cancer is the leading cause of cancer-related death in the world. It is broadly divided into small cell (SCLC, approx. 15% cases) and non-small cell lung cancer (NSCLC, approx. 85% cases). The main histological subtypes of NSCLC are adenocarcinoma and squamous cell carcinoma, with the presence of specific DNA mutations allowing further molecular stratification. If identified at an early stage, surgical resection of NSCLC offers a favourable prognosis, with published case series reporting 5-year survival rates of up to 70% for small, localized tumours (stage I). However, most patients (approx. 75%) have advanced disease at the time of diagnosis (stage III/IV) and despite significant developments in the oncological management of late stage lung cancer over recent years, survival remains poor. In 2014, the UK Office for National Statistics reported that patients diagnosed with distant metastatic disease (stage IV) had a 1-year survival rate of just 15-19% compared with 81-85% for stage I.
Collapse
MESH Headings
- Adenocarcinoma/diagnostic imaging
- Adenocarcinoma/genetics
- Adenocarcinoma/mortality
- Adenocarcinoma/surgery
- Adenocarcinoma of Lung
- Biomarkers, Tumor/blood
- Biomarkers, Tumor/genetics
- Bronchoscopy/methods
- Carcinoma, Non-Small-Cell Lung/diagnostic imaging
- Carcinoma, Non-Small-Cell Lung/genetics
- Carcinoma, Non-Small-Cell Lung/mortality
- Carcinoma, Non-Small-Cell Lung/surgery
- Carcinoma, Squamous Cell/diagnostic imaging
- Carcinoma, Squamous Cell/genetics
- Carcinoma, Squamous Cell/mortality
- Carcinoma, Squamous Cell/surgery
- Circulating Tumor DNA/blood
- Circulating Tumor DNA/genetics
- Early Detection of Cancer/methods
- Humans
- Liquid Biopsy/methods
- Lung Neoplasms/diagnostic imaging
- Lung Neoplasms/genetics
- Lung Neoplasms/mortality
- Lung Neoplasms/surgery
- Neoplasm Staging
- Neoplastic Cells, Circulating/metabolism
- Neoplastic Cells, Circulating/pathology
- Prognosis
- Radiography
- Small Cell Lung Carcinoma/diagnostic imaging
- Small Cell Lung Carcinoma/genetics
- Small Cell Lung Carcinoma/mortality
- Small Cell Lung Carcinoma/surgery
- Survival Analysis
Collapse
Affiliation(s)
- Sean Blandin Knight
- North West Lung Centre, University Hospital South Manchester, Manchester, UK
| | - Phil A Crosbie
- North West Lung Centre, University Hospital South Manchester, Manchester, UK
- Cancer Research UK Lung Cancer Centre of Excellence at Manchester and University College London, UK
| | - Haval Balata
- North West Lung Centre, University Hospital South Manchester, Manchester, UK
| | - Jakub Chudziak
- Clinical and Experimental Pharmacology Group, Cancer Research UK Manchester Institute, University of Manchester, Manchester, UK
| | - Tracy Hussell
- Manchester Collaborative Centre for Inflammation Research, University of Manchester, Manchester, UK
| | - Caroline Dive
- Cancer Research UK Lung Cancer Centre of Excellence at Manchester and University College London, UK
- Clinical and Experimental Pharmacology Group, Cancer Research UK Manchester Institute, University of Manchester, Manchester, UK
| |
Collapse
|
5
|
Weng DY, Chen J, Taslim C, Hsu PC, Marian C, David SP, Loffredo CA, Shields PG. Persistent alterations of gene expression profiling of human peripheral blood mononuclear cells from smokers. Mol Carcinog 2016; 55:1424-37. [PMID: 26294040 PMCID: PMC4860148 DOI: 10.1002/mc.22385] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2015] [Revised: 07/04/2015] [Accepted: 08/03/2015] [Indexed: 01/12/2023]
Abstract
The number of validated biomarkers of tobacco smoke exposure is limited, and none exist for tobacco-related cancer. Additional biomarkers for smoke, effects on cellular systems in vivo are needed to improve early detection of lung cancer, and to assist the Food and Drug Administration in regulating exposures to tobacco products. We assessed the effects of smoking on the gene expression using human cell cultures and blood from a cross-sectional study. We profiled global transcriptional changes in cultured smokers' peripheral blood mononuclear cells (PBMCs) treated with cigarette smoke condensate (CSC) in vitro (n = 7) and from well-characterized smokers' blood (n = 36). ANOVA with adjustment for covariates and Pearson correlation were used for statistical analysis in this study. CSC in vitro altered the expression of 1 178 genes (177 genes with > 1.5-fold-change) at P < 0.05. In vivo, PBMCs of heavy and light smokers differed for 614 genes (29 with > 1.5-fold-change) at P < 0.05 (309 remaining significant after adjustment for age, race, and gender). Forty-one genes were persistently altered both in vitro and in vivo, 22 having the same expression pattern reported for non-small cell lung cancer. Our data provides evidence that persistent alterations of gene expression in vitro and in vivo may relate to carcinogenic effects of cigarette smoke, and the identified genes may serve as potential biomarkers for cancer. The use of an in vitro model to corroborate results from human studies provides a novel way to understand human exposure and effect. © 2015 Wiley Periodicals, Inc.
Collapse
Affiliation(s)
- Daniel Y Weng
- Comprehensive Cancer Center, The Ohio State University, Columbus, Ohio
| | - Jinguo Chen
- Center for Human Immunology, National Institute of Health, Bethesda, Maryland
| | - Cenny Taslim
- Comprehensive Cancer Center, The Ohio State University, Columbus, Ohio
| | - Ping-Ching Hsu
- Comprehensive Cancer Center, The Ohio State University, Columbus, Ohio
| | - Catalin Marian
- Comprehensive Cancer Center, The Ohio State University, Columbus, Ohio
- University of Medicine and Pharmacy, Timisoara, Romania
| | - Sean P David
- Department of Medicine, Stanford University School of Medicine, Stanford, California
| | - Christopher A Loffredo
- Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, District of Columbia
| | - Peter G Shields
- Comprehensive Cancer Center, The Ohio State University, Columbus, Ohio.
| |
Collapse
|
6
|
Hofmann-Preiß K, Rehbock B. [Early recognition of lung cancer in workers occupationally exposed to asbestos]. Radiologe 2016; 56:810-6. [PMID: 27502004 DOI: 10.1007/s00117-016-0151-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
Abstract
Despite the fact that working with asbestos and placing it on the market have been banned in Germany since 1993 according to the Ordinance on Hazardous Substances, asbestos-related diseases of the lungs and pleura are still the leading cause of death in occupational diseases. The maximum industrial usage of asbestos was reached in former West Germany in the late 1970s and in former East Germany the late 1980s. Occupational diseases, mainly mesotheliomas and lung cancer emerging now are thus caused by asbestos exposure which occurred 30-40 years earlier. It is known that the combination of smoking and asbestos exposure results in a superadditive increase in the risk to develop lung cancer. No suitable screening methods for early detection of malignant mesothelioma are currently available and the therapeutic options are still very limited; however, the national lung screening trial (NLST) has shown for the first time that by employing low-dose computed tomography (LDCT) in heavy smokers, lung cancer mortality can be significantly reduced. According to current knowledge the resulting survival benefits far outweigh the potential risks involved in the diagnostic work-up of suspicious lesions. These results in association with the recommendations of international medical societies and organizations were pivotal as the German statutory accident insurance (DGUV) decided to provide LDCT as a special occupational medical examination for workers previously exposed to asbestos and with a particularly high risk for developing lung cancer.
Collapse
Affiliation(s)
- K Hofmann-Preiß
- BDT MVZ Erlangen, Wetterkreuz 21, 91058, Erlangen, Deutschland.
| | - B Rehbock
- Praxis für Diagnostische Radiologie mit pneumologischem Schwerpunkt, Bismarck-Str. 45-47, 10627, Berlin, Deutschland
| |
Collapse
|
7
|
Weissman DN. Role of chest computed tomography in prevention of occupational respiratory disease: review of recent literature. Semin Respir Crit Care Med 2015; 36:433-48. [PMID: 26024350 DOI: 10.1055/s-0035-1547348] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
This review provides an update on literature published over the past 5 years that is relevant to using chest computed tomography (CT) as a tool for preventing occupational respiratory disease. An important area of investigation has been in the use of low-dose CT (LDCT) to screen asbestos-exposed populations for lung cancer. Two recent systematic reviews have reached conclusions in support of screening. Based on the limited evidence that is currently available, the Finnish Institute of Occupational Health has recommended LDCT screening in asbestos-exposed individuals if their personal combination of risk factors yields a risk for lung cancer equal to that needed for entry into the National Lung Screening Trial. It has also recommended further research, such as to document the optimal frequency of screening and the effectiveness of screening. Recent literature continues to support high-resolution CT (HRCT) as being more sensitive than chest radiography in detecting pneumoconiosis. However, there are insufficient data to determine the effectiveness of HRCT screening in improving individual outcomes if used in screening for pneumoconiosis and its routine use for this purpose cannot be recommended. However, if HRCT is used to evaluate populations, recent literature shows that the International Classification of HRCT for Occupational and Environmental Respiratory Diseases provides an important tool for reproducible evaluation and recording of findings. HRCT is an important tool for individual patient management and recent literature has documented that chest HRCT findings are significantly associated with outcomes such as pulmonary function and mortality.
Collapse
Affiliation(s)
- David N Weissman
- Division of Respiratory Disease Studies, National Institute for Occupational Safety and Health, Morgantown, West Virginia
| |
Collapse
|
8
|
Pairon JC, Andujar P, Rinaldo M, Ameille J, Brochard P, Chamming’s S, Clin B, Ferretti G, Gislard A, Laurent F, Luc A, Wild P, Paris C. Asbestos Exposure, Pleural Plaques, and the Risk of Death from Lung Cancer. Am J Respir Crit Care Med 2014; 190:1413-20. [DOI: 10.1164/rccm.201406-1074oc] [Citation(s) in RCA: 47] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
|