2
|
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
|
3
|
Yamada A, Taiji R, Nishimoto Y, Itoh T, Marugami A, Yamauchi S, Minamiguchi K, Yanagawa M, Tomiyama N, Tanaka T. Pictorial Review of Pleural Disease: Multimodality Imaging and Differential Diagnosis. Radiographics 2024; 44:e230079. [PMID: 38547031 DOI: 10.1148/rg.230079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/02/2024]
Abstract
The pleura is a thin, smooth, soft-tissue structure that lines the pleural cavity and separates the lungs from the chest wall, consisting of the visceral and parietal pleurae and physiologic pleural fluid. There is a broad spectrum of normal variations and abnormalities in the pleura, including pneumothorax, pleural effusion, and pleural thickening. Pneumothorax is associated with pulmonary diseases and is caused by iatrogenic or traumatic factors. Chest radiography and US help detect pneumothorax with various signs, and CT can also help assess the causes. Pleural effusion occurs in a wide spectrum of diseases, such as heart failure, cirrhosis, asbestos-related diseases, infections, chylothorax, and malignancies. Chest US allows detection of a small pleural effusion and evaluation of echogenicity or septa in pleural effusion. Pleural thickening may manifest as unilateral or bilateral and as focal, multifocal, or diffuse. Various diseases can demonstrate pleural thickening, such as asbestos-related diseases, neoplasms, and systemic diseases. CT, MRI, and fluorodeoxyglucose (FDG) PET/CT can help differentiate between benign and malignant lesions. Knowledge of these features can aid radiologists in suggesting diagnoses and recommending further examinations with other imaging modalities. The authors provide a comprehensive review of the clinical and multimodality imaging findings of pleural diseases and their differential diagnoses. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.
Collapse
Affiliation(s)
- Aya Yamada
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Ryosuke Taiji
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Yuko Nishimoto
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Takahiro Itoh
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Aki Marugami
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Satoshi Yamauchi
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Kiyoyuki Minamiguchi
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Masahiro Yanagawa
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Noriyuki Tomiyama
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| | - Toshihiro Tanaka
- From the Department of Diagnostic and Interventional Radiology, Nara Medical University, 840 Shijo-cho, Kashihara-city, Nara 634-8522, Japan (A.Y., R.T., T.I., A.M., S.Y., K.M., T.T.); Department of Radiology, Nara Prefecture General Medical Center, Nara, Japan (Y.N.); Division of Diagnostic Imaging, Department of Interventional Radiology, University of Texas MD Anderson Cancer Center, Houston, Tex (K.M.); and Department of Radiology, Osaka University Graduate School of Medicine, Osaka, Japan (M.Y., N.T.)
| |
Collapse
|
6
|
Pinto E, Penha D, Hochhegger B, Monaghan C, Marchiori E, Taborda-Barata L, Irion K. Incidental chest findings on coronary CT angiography: a pictorial essay and management proposal. JORNAL BRASILEIRO DE PNEUMOLOGIA : PUBLICACAO OFICIAL DA SOCIEDADE BRASILEIRA DE PNEUMOLOGIA E TISILOGIA 2022; 48:e20220015. [PMID: 35584528 PMCID: PMC9064655 DOI: 10.36416/1806-3756/e20220015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/18/2022] [Accepted: 03/07/2022] [Indexed: 11/17/2022]
Abstract
Many health systems have been using coronary CT angiography (CCTA) as a first-line examination for ischaemic heart disease patients in various countries. The rising number of CCTA examinations has led to a significant increase in the number of reported incidental extracardiac findings, mainly in the chest. Pulmonary nodules are the most common incidental findings on CCTA scans, as there is a substantial overlap of risk factors between the population seeking to exclude ischaemic heart disease and those at risk of developing lung cancer (i.e., advanced age and smoking habits). However, most incidental findings are clinically insignificant and actively pursuing them could be cost-prohibitive and submit the patient to unnecessary and potentially harmful examinations. Furthermore, there is little consensus regarding when to report or actively exclude these findings and how to manage them, that is, when to trigger an alert or to immediately refer the patient to a pulmonologist, a thoracic surgeon or a multidisciplinary team. This pictorial essay discusses the current literature on this topic and is illustrated with a review of CCTA scans. We also propose a checklist organised by organ and system, recommending actions to raise awareness of pulmonologists, thoracic surgeons, cardiologists and radiologists regarding the most significant and actionable incidental findings on CCTA scans.
Collapse
Affiliation(s)
- Erique Pinto
- . Faculdade de Ciências da Saúde, Universidade da Beira Interior, Covilhã, Portugal
| | - Diana Penha
- . Faculdade de Ciências da Saúde, Universidade da Beira Interior, Covilhã, Portugal.,. Imaging Department, Liverpool Heart and Chest Hospital NHS Foundation Trust, Liverpool, United Kingdom
| | - Bruno Hochhegger
- . Pontifícia Universidade Católica do Rio Grande do Sul, Porto Alegre (RS) Brasil
| | - Colin Monaghan
- . Imaging Department, Liverpool Heart and Chest Hospital NHS Foundation Trust, Liverpool, United Kingdom
| | - Edson Marchiori
- . Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro (RJ) Brasil.,. Faculdade de Medicina, Universidade Federal Fluminense, Niterói (RJ) Brasil
| | - Luís Taborda-Barata
- . Faculdade de Ciências da Saúde, Universidade da Beira Interior, Covilhã, Portugal
| | - Klaus Irion
- . Imaging Department, Liverpool Heart and Chest Hospital NHS Foundation Trust, Liverpool, United Kingdom
| |
Collapse
|
8
|
Schreuder A, Prokop M, Scholten ET, Mets OM, Chung K, Mohamed Hoesein FAA, Jacobs C, Schaefer-Prokop CM. CT-Detected Subsolid Nodules: A Predictor of Lung Cancer Development at Another Location? Cancers (Basel) 2021; 13:cancers13112812. [PMID: 34200018 PMCID: PMC8200192 DOI: 10.3390/cancers13112812] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2021] [Revised: 05/31/2021] [Accepted: 06/01/2021] [Indexed: 11/16/2022] Open
Abstract
The purpose of this case-cohort study was to investigate whether the frequency and computed tomography (CT) features of pulmonary nodules posed a risk for the future development of lung cancer (LC) at a different location. Patients scanned between 2004 and 2012 at two Dutch academic hospitals were cross-linked with the Dutch Cancer Registry. All patients who were diagnosed with LC by 2014 and a random selection of LC-free patients were considered. LC patients who were determined to be LC-free at the time of the scan and all LC-free patients with an adequate scan were included. The nodule count and types (solid, part-solid, ground-glass, and perifissural) were recorded per scan. Age, sex, and other CT measures were included to control for confounding factors. The cohort included 163 LC patients and 1178 LC-free patients. Cox regression revealed that the number of ground-glass nodules and part-solid nodules present were positively correlated to future LC risk. The area under the receiver operating curve of parsimonious models with and without nodule type information were 0.827 and 0.802, respectively. The presence of subsolid nodules in a clinical setting may be a risk factor for future LC development in another pulmonary location in a dose-dependent manner. Replication of the results in screening cohorts is required for maximum utility of these findings.
Collapse
Affiliation(s)
- Anton Schreuder
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
- Correspondence:
| | - Mathias Prokop
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
| | - Ernst T. Scholten
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
| | - Onno M. Mets
- Department of Radiology and Nuclear Medicine, Academic Medical Center, 1105 AZ Amsterdam, The Netherlands;
| | - Kaman Chung
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
- Department of Radiology, Meander Medisch Centrum, 3813 TZ Amersfoort, The Netherlands
| | | | - Colin Jacobs
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
| | - Cornelia M. Schaefer-Prokop
- Department of Medical Imaging, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands; (M.P.); (E.T.S.); (K.C.); (C.J.); (C.M.S.-P.)
- Department of Radiology, Meander Medisch Centrum, 3813 TZ Amersfoort, The Netherlands
| |
Collapse
|