1
|
Affiliation(s)
- Theresa C McLoud
- From the Department of Radiology, Harvard Medical School, Massachusetts General Hospital, 55 Fruit St, MZ-FND 216, Boston, MA 02114-2696 (T.C.M.); and Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic Florida, Jacksonville, Fla (B.P.L.)
| | - Brent P Little
- From the Department of Radiology, Harvard Medical School, Massachusetts General Hospital, 55 Fruit St, MZ-FND 216, Boston, MA 02114-2696 (T.C.M.); and Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic Florida, Jacksonville, Fla (B.P.L.)
| |
Collapse
|
2
|
Martin SS, Kolaneci D, Wichmann JL, Lenga L, Leithner D, Vogl TJ, Jacobi V. Development and evaluation of a computer-based decision support system for diffuse lung diseases at high-resolution computed tomography. Acta Radiol 2022; 63:328-335. [PMID: 33657848 DOI: 10.1177/0284185121995799] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND High-resolution computed tomography (HRCT) is essential in narrowing the possible differential diagnoses of diffuse and interstitial lung diseases. PURPOSE To investigate the value of a novel computer-based decision support system (CDSS) for facilitating diagnosis of diffuse lung diseases at HRCT. MATERIAL AND METHODS A CDSS was developed that includes about 100 different illustrations of the most common HRCT signs and patterns and describes the corresponding pathologies in detail. The logical set-up of the software facilitates a structured evaluation. By selecting one or more CT patterns, the program generates a ranked list of the most likely differential diagnoses. Three independent and blinded radiology residents initially evaluated 40 cases with different lung diseases alone; after at least 12 weeks, observers re-evaluated all cases using the CDSS. RESULTS In 40 patients, a total of 113 HRCT patterns were evaluated. The percentage of correctly classified patterns was higher with CDSS (96.8%) compared to assessment without CDSS (90.3%; P < 0.01). Moreover, the percentage of correct diagnosis (81.7% vs. 64.2%) and differential diagnoses (89.2% vs. 38.3%) were superior with CDSS compared to evaluation without CDSS (both P < 0.01). CONCLUSION Addition of a CDSS using a structured approach providing explanations of typical HRCT patterns and graphical illustrations significantly improved the performance of trainees in characterizing and correctly identifying diffuse lung diseases.
Collapse
Affiliation(s)
- Simon S Martin
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Delina Kolaneci
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Julian L Wichmann
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Lukas Lenga
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Doris Leithner
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Thomas J Vogl
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Volkmar Jacobi
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| |
Collapse
|
3
|
Evaluation of a Novel Content-Based Image Retrieval System for the Differentiation of Interstitial Lung Diseases in CT Examinations. Diagnostics (Basel) 2021; 11:diagnostics11112114. [PMID: 34829461 PMCID: PMC8624384 DOI: 10.3390/diagnostics11112114] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 11/05/2021] [Accepted: 11/11/2021] [Indexed: 11/17/2022] Open
Abstract
To evaluate the reader's diagnostic performance against the ground truth with and without the help of a novel content-based image retrieval system (CBIR) that retrieves images with similar CT patterns from a database of 79 different interstitial lung diseases. We evaluated three novice readers' and three resident physicians' (with at least three years of experience) diagnostic performance evaluating 50 different CTs featuring 10 different patterns (e.g., honeycombing, tree-in bud, ground glass, bronchiectasis, etc.) and 24 different diseases (sarcoidosis, UIP, NSIP, Aspergillosis, COVID-19 pneumonia etc.). The participants read the cases first without assistance (and without feedback regarding correctness), and with a 2-month interval in a random order with the assistance of the novel CBIR. To invoke the CBIR, a ROI is placed into the pathologic pattern by the reader and the system retrieves diseases with similar patterns. To further narrow the differential diagnosis, the readers can consult an integrated textbook and have the possibility of selecting high-level semantic features representing clinical information (chronic, infectious, smoking status, etc.). We analyzed readers' accuracy without and with CBIR assistance and further tested the hypothesis that the CBIR would help to improve diagnostic performance utilizing Wilcoxon signed rank test. The novice readers demonstrated an unassisted accuracy of 18/28/44%, and an assisted accuracy of 84/82/90%, respectively. The resident physicians demonstrated an unassisted accuracy of 56/56/70%, and an assisted accuracy of 94/90/96%, respectively. For each reader, as well as overall, Sign test demonstrated statistically significant (p < 0.01) difference between the unassisted and the assisted reads. For students and physicians, Chi²-test and Mann-Whitney-U test demonstrated statistically significant (p < 0.01) difference for unassisted reads and statistically insignificant (p > 0.01) difference for assisted reads. The evaluated CBIR relying on pattern analysis and featuring the option to filter the results of the CBIR by predominant characteristics of the diseases via selecting high-level semantic features helped to drastically improve novices' and resident physicians' accuracy in diagnosing interstitial lung diseases in CT.
Collapse
|
4
|
Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks. J Digit Imaging 2021; 32:1019-1026. [PMID: 31396776 DOI: 10.1007/s10278-019-00254-8] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1-2-mm slices, 5-10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18 mm, and 25.47 ± 13.63 mm, respectively. Our deep-learning method showed significantly better segmentation performance (p < 0.001), and its segmentation accuracies for volumetric CT were similar to those for HRCT. We have developed an accurate and robust U-Net-based DILD lung segmentation method that can be used for patients scanned with different clinical protocols, including HRCT and volumetric CT.
Collapse
|
5
|
Wang H, Yang YY, Pan Y, Han P, Li ZX, Huang HG, Zhu SZ. Detecting thoracic diseases via representation learning with adaptive sampling. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2019.06.113] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
6
|
Jeny F, Brillet PY, Kim YW, Freynet O, Nunes H, Valeyre D. The place of high-resolution computed tomography imaging in the investigation of interstitial lung disease. Expert Rev Respir Med 2018; 13:79-94. [PMID: 30517828 DOI: 10.1080/17476348.2019.1556639] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023]
Abstract
INTRODUCTION High-resolution computed tomography (HRCT) has revolutionized the diagnosis, prognosis and in some cases the prediction of therapeutic response in interstitial lung disease (ILD). HRCT represents an essential second step to a patient's clinical history, before considering any other investigation, including lung biopsy. Areas covered: This review describes the current place of HRCT in the diagnosis, prognosis and monitoring of ILD. It also lists some perspectives for the near future. Expert commentary: Since the 1980s, HRCT and its interpretation have improved, the diagnosis value of patterns, and the integration of bio-clinical elements to HRCT have been better standardized. The interobserver agreement has been investigated, allowing a better use of some limits in the interpretation of various signs. It not only takes into account one particular predominant sign, but the combination of patterns and the distribution of findings. Thanks to HRCT, the range of diagnoses and their probability are more accurately identified. The contribution of HRCT has been optimized during the multidisciplinary discussion that a difficult diagnosis calls for. HRCT quantification of the extent of diffuse lung disease becomes possible and is linked to prognosis. In the future, artificial intelligence may significantly modify the practice of radiology.
Collapse
Affiliation(s)
- Florence Jeny
- a Université Paris 13, EA2363 "Hypoxie & Poumon" , Sorbonne-Paris-Cité , Bobigny, France.,b Service de pneumologie , hôpital Avicenne , Bobigny , France
| | - Pierre-Yves Brillet
- b Service de pneumologie , hôpital Avicenne , Bobigny , France.,c Service de radiologie , hôpital Avicenne , Bobigny , France
| | - Young-Wouk Kim
- c Service de radiologie , hôpital Avicenne , Bobigny , France
| | - Olivia Freynet
- b Service de pneumologie , hôpital Avicenne , Bobigny , France
| | - Hilario Nunes
- a Université Paris 13, EA2363 "Hypoxie & Poumon" , Sorbonne-Paris-Cité , Bobigny, France.,b Service de pneumologie , hôpital Avicenne , Bobigny , France
| | - Dominique Valeyre
- a Université Paris 13, EA2363 "Hypoxie & Poumon" , Sorbonne-Paris-Cité , Bobigny, France.,b Service de pneumologie , hôpital Avicenne , Bobigny , France
| |
Collapse
|
7
|
Feng DY, Zhou YQ, Xing YF, Li CF, Lv Q, Dong J, Qin J, Guo YF, Jiang N, Huang C, Hu HT, Guo XH, Chen J, Yin LH, Zhang TT, Li X. Selection of glucocorticoid-sensitive patients in interstitial lung disease secondary to connective tissue diseases population by radiomics. Ther Clin Risk Manag 2018; 14:1975-1986. [PMID: 30349276 PMCID: PMC6188005 DOI: 10.2147/tcrm.s181043] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
Purpose The effect of glucocorticoid(s) on connective tissue disease (CTD)-related interstitial lung disease (ILD) is controversial. This multicenter study aimed to identify glucocorticoid-sensitive patients using a radiomics approach. Methods A total of 416 CTD-ILD patients who began glucocorticoid treatment at the discretion of the attending physician, with or without cyclophosphamide, were included in this study. High doses were defined as pulsed intravenous methylprednisolone, an initial dose of 1 mg/kg/day of prednisolone or 0.8 mg/kg/day of methylprednisolone. Low doses were defined as those less than high doses. Radiomics features were manually extracted from primary lung lesions delineated on computed tomography images, and selected by variance, univariate feature selection, and least absolute shrinkage and selection operator regression model. The prediction models were developed using data from 309 patients from two centers and externally validated in 107 patients from four other hospitals. Results Treatment response in the training and validation groups was 38.5% and 36.4%, respectively. Eleven radiomics features were selected from 1,029 features with predictive value. Random forest models built for radiomics features to predict treatment response yielded a sensitivity of 0.897. The calibration curve of a nomogram demonstrated good agreement between prediction and observation. Decision curve analysis indicated that glucocorticoid was beneficial if the predicted response rate was 50%–60% for an individual. High doses of glucocorticoids and cyclophosphamide yielded superior efficacy. Conclusion Radiomics-based predictive models reliably identified glucocorticoid-sensitive CTD-ILD patients. Short-term, high-dose glucocorticoid with cyclophosphamide yielded promising results as a potential therapy.
Collapse
Affiliation(s)
- Ding-Yun Feng
- Department of Respiration, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China,
| | - Yu-Qi Zhou
- Department of Respiration, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China,
| | - Yan-Fang Xing
- Department of Nephrology, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou 510150, People's Republic of China
| | - Chuang-Feng Li
- Department of Radiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Qing Lv
- Department of Rheumatology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Jie Dong
- Department of Radiotherapy, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Jie Qin
- Department of Radiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Yue-Fei Guo
- Department of Radiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Nan Jiang
- Department of Hepatic Surgery, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China
| | - Chencui Huang
- The Associated Laboratory for AI, Cross-strait TsingHua Research Institute and Huiying Medical Technology, Dongsheng Science and Technology Park, HaiDian District, Beijing 100192, People's Republic of China
| | - Hai-Tao Hu
- Department of Surgery, ChanCheng District Center Hospital, Foshan 528000, People's Republic of China
| | - Xing-Hua Guo
- Department of Rheumatology, The LingNan Hospital of Sun Yat-sen University, Guangzhou 510000, People's Republic of China
| | - Jie Chen
- Department of Oncology, HengYang City Center Hospital, Hengyang 421001, People's Republic of China
| | - Liang-Hong Yin
- Department of Nephrology, The First Affiliated Hospital of JINAN University, Guangzhou 510630, People's Republic of China
| | - Tian-Tuo Zhang
- Department of Respiration, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China,
| | - Xing Li
- Department of Medical Oncology and Guangdong Key Laboratory of Liver Disease, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, People's Republic of China,
| |
Collapse
|
8
|
Brooks LRK, Mias GI. Streptococcus pneumoniae's Virulence and Host Immunity: Aging, Diagnostics, and Prevention. Front Immunol 2018; 9:1366. [PMID: 29988379 PMCID: PMC6023974 DOI: 10.3389/fimmu.2018.01366] [Citation(s) in RCA: 124] [Impact Index Per Article: 20.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2018] [Accepted: 06/01/2018] [Indexed: 12/14/2022] Open
Abstract
Streptococcus pneumoniae is an infectious pathogen responsible for millions of deaths worldwide. Diseases caused by this bacterium are classified as pneumococcal diseases. This pathogen colonizes the nasopharynx of its host asymptomatically, but overtime can migrate to sterile tissues and organs and cause infections. Pneumonia is currently the most common pneumococcal disease. Pneumococcal pneumonia is a global health concern and vastly affects children under the age of five as well as the elderly and individuals with pre-existing health conditions. S. pneumoniae has a large selection of virulence factors that promote adherence, invasion of host tissues, and allows it to escape host immune defenses. A clear understanding of S. pneumoniae's virulence factors, host immune responses, and examining the current techniques available for diagnosis, treatment, and disease prevention will allow for better regulation of the pathogen and its diseases. In terms of disease prevention, other considerations must include the effects of age on responses to vaccines and vaccine efficacy. Ongoing work aims to improve on current vaccination paradigms by including the use of serotype-independent vaccines, such as protein and whole cell vaccines. Extending our knowledge of the biology of, and associated host immune response to S. pneumoniae is paramount for our improvement of pneumococcal disease diagnosis, treatment, and improvement of patient outlook.
Collapse
Affiliation(s)
- Lavida R. K. Brooks
- Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI, United States
- Institute for Quantitative Health Science & Engineering, Michigan State University, East Lansing, MI, United States
| | - George I. Mias
- Institute for Quantitative Health Science & Engineering, Michigan State University, East Lansing, MI, United States
- Biochemistry and Molecular Biology, Michigan State University, East Lansing, MI, United States
| |
Collapse
|
9
|
Souza R. Momentum. J Bras Pneumol 2017; 43:327-328. [PMID: 29160377 PMCID: PMC5790649 DOI: 10.1590/s1806-37562017000500001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Affiliation(s)
- Rogério Souza
- . Disciplina de Pneumologia, Instituto do Coração, Hospital das Clínicas, Faculdade de Medicina, Universidade de São Paulo, São Paulo (SP) Brasil.,. Editor-Chefe do JBP - Jornal Brasileiro de Pneumologia, Brasília (DF) Brasil
| |
Collapse
|