Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 49
Filter
1.
Respirology ; 27(10): 818-833, 2022 10.
Article in English | MEDLINE | ID: covidwho-1997207

ABSTRACT

In recent years, pulmonary imaging has seen enormous progress, with the introduction, validation and implementation of new hardware and software. There is a general trend from mere visual evaluation of radiological images to quantification of abnormalities and biomarkers, and assessment of 'non visual' markers that contribute to establishing diagnosis or prognosis. Important catalysts to these developments in thoracic imaging include new indications (like computed tomography [CT] lung cancer screening) and the COVID-19 pandemic. This review focuses on developments in CT, radiomics, artificial intelligence (AI) and x-ray velocimetry for imaging of the lungs. Recent developments in CT include the potential for ultra-low-dose CT imaging for lung nodules, and the advent of a new generation of CT systems based on photon-counting detector technology. Radiomics has demonstrated potential towards predictive and prognostic tasks particularly in lung cancer, previously not achievable by visual inspection by radiologists, exploiting high dimensional patterns (mostly texture related) on medical imaging data. Deep learning technology has revolutionized the field of AI and as a result, performance of AI algorithms is approaching human performance for an increasing number of specific tasks. X-ray velocimetry integrates x-ray (fluoroscopic) imaging with unique image processing to produce quantitative four dimensional measurement of lung tissue motion, and accurate calculations of lung ventilation.


Subject(s)
COVID-19 , Lung Neoplasms , Artificial Intelligence , COVID-19/diagnostic imaging , Early Detection of Cancer/methods , Humans , Lung Neoplasms/diagnostic imaging , Pandemics , Rheology , Tomography, X-Ray Computed/methods , X-Rays
2.
Health Expect ; 25(4): 1776-1788, 2022 08.
Article in English | MEDLINE | ID: covidwho-1961583

ABSTRACT

BACKGROUND: Many countries are introducing low-dose computed tomography screening programmes for people at high risk of lung cancer. Effective communication strategies that convey risks and benefits, including unfamiliar concepts and outcome probabilities based on population risk, are critical to achieving informed choice and mitigating inequalities in uptake. METHODS: This study investigated the acceptability of an aspect of NHS England's communication strategy in the form of a leaflet that was used to invite and inform eligible adults about the Targeted Lung Health Check (TLHC) programme. Acceptability was assessed in terms of how individuals engaged with, comprehended and responded to the leaflet. Semi-structured, 'think aloud' interviews were conducted remotely with 40 UK screening-naïve current and former smokers (aged 55-73). The verbatim transcripts were analysed thematically using a coding framework based on the Dual Process Theory of cognition. RESULTS: The leaflet helped participants understand the principles and procedures of screening and fostered cautiously favourable intentions. Three themes captured the main results of the data analysis: (1) Response-participants experienced anxiety about screening results and further investigations, but the involvement of specialist healthcare professionals was reassuring; (2) Engagement-participants were rapidly drawn to information about lung cancer prevalence, and benefits of screening, but deliberated slowly about early diagnosis, risks of screening and less familiar symptoms of lung cancer; (3) Comprehension-participants understood the main principles of the TLHC programme, but some were confused by its rationale and eligibility criteria. Radiation risks, abnormal screening results and numerical probabilities of screening outcomes were hard to understand. CONCLUSION: The TLHC information leaflet appeared to be acceptable to the target population. There is scope to improve aspects of comprehension and engagement in ways that would support informed choice as a distributed process in lung cancer screening. PATIENT OR PUBLIC CONTRIBUTION: The insight and perspectives of patient representatives directly informed and improved the design and conduct of this study.


Subject(s)
Early Detection of Cancer , Health Communication , Health Literacy , Lung Neoplasms , National Health Programs , Pamphlets , Adult , Comprehension , Early Detection of Cancer/methods , England , Health Communication/methods , Humans , Lung , Lung Neoplasms/diagnosis , Lung Neoplasms/diagnostic imaging , Mass Screening , National Health Programs/standards , State Medicine
3.
Comput Math Methods Med ; 2022: 9422902, 2022.
Article in English | MEDLINE | ID: covidwho-1950460

ABSTRACT

Objective: Molecular targeted drug therapy and chemotherapy are the main treatments for advanced non-small-cell lung cancer, and the combination of both has advantages in prolonging patients' progression-free survival and overall survival. This study investigated the effects of bevacizumab combined with chemotherapy under nursing intervention on CT, cytokeratin 19 fragment antigen 21-1 (CYFRA21-1), and gastrin-releasing peptide precursor (ProGRP) and prognosis of lung cancer patients. Methods: 102 patients with non-small-cell lung cancer admitted to our hospital from January 2018 to May 2019 were divided into observation group and control group, with 51 cases each. The control group was treated with basic chemotherapy, and the observation group was treated with bevacizumab in combination with the control group, and both groups used nursing interventions. The clinical effects, CYFRA21-1 and ProGRP levels, baseline data, CT parameters, 24-month cumulative survival, and the effects of CYFRA21-1 and ProGRP on long-term survival and lung function were compared. Results: The disease control rate of the observation group was 94.12%, which was significantly higher than that of the control group (76.47%); after 7 d, 30 d, 60 d, and 90 d of treatment, the levels of CYFRA21-1 and ProGRP were statistically downregulated. The difference in lymph node metastasis, lesion diameter, plain Eff-Z, venous stage, and arterial stage normalized iodine concentrations (NIC) was statistically significant; the survival rate at 24 months in the observation group was 74.51% (38/51); the cumulative survival rate at 24 months in the control group was 52.94% (27/51), and the difference was statistically significant (X 2 = 4.980, P = 0.026). The cumulative survival rate at 24 months was significantly lower in patients with high expression of CYFRA21-1 and ProGRP compared with those with low expression of CYFRA21-1 and ProGRP. After treatment, in the observation group, the forceful spirometry (FVC), forceful expiratory volume in one second (FEV1), and FEV1/FVC levels were significantly different from those before treatment and were significantly different from those in the control group. Conclusion: Bevacizumab in combination with standard chemotherapy regimens with nursing interventions could benefit patients with advanced non-small-cell lung cancer and had a good prospect of application.


Subject(s)
Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Antigens, Neoplasm , Bevacizumab/therapeutic use , Biomarkers, Tumor , Carcinoma, Non-Small-Cell Lung/diagnostic imaging , Carcinoma, Non-Small-Cell Lung/drug therapy , Humans , Keratin-19 , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/drug therapy , Lung Neoplasms/pathology , Peptide Fragments , Prognosis , Protein Precursors , Recombinant Proteins , Tomography, X-Ray Computed
5.
Med Image Anal ; 80: 102491, 2022 08.
Article in English | MEDLINE | ID: covidwho-1867483

ABSTRACT

Segmentation of lung pathology in Computed Tomography (CT) images is of great importance for lung disease screening. However, the presence of different types of lung pathologies with a wide range of heterogeneities in size, shape, location, and texture, on one side, and their visual similarity with respect to surrounding tissues, on the other side, make it challenging to perform reliable automatic lesion segmentation. To leverage segmentation performance, we propose a deep learning framework comprising a Normal Appearance Autoencoder (NAA) model to learn the distribution of healthy lung regions and reconstruct pathology-free images from the corresponding pathological inputs by replacing the pathological regions with the characteristics of healthy tissues. Detected regions that represent prior information regarding the shape and location of pathologies are then integrated into a segmentation network to guide the attention of the model into more meaningful delineations. The proposed pipeline was tested on three types of lung pathologies, including pulmonary nodules, Non-Small Cell Lung Cancer (NSCLC), and Covid-19 lesion on five comprehensive datasets. The results show the superiority of the proposed prior model, which outperformed the baseline segmentation models in all the cases with significant margins. On average, adding the prior model improved the Dice coefficient for the segmentation of lung nodules by 0.038, NSCLCs by 0.101, and Covid-19 lesions by 0.041. We conclude that the proposed NAA model produces reliable prior knowledge regarding the lung pathologies, and integrating such knowledge into a prior segmentation network leads to more accurate delineations.


Subject(s)
COVID-19 , Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , COVID-19/diagnostic imaging , Humans , Image Processing, Computer-Assisted/methods , Lung/diagnostic imaging , Lung Neoplasms/diagnostic imaging , Tomography, X-Ray Computed
6.
Clin Radiol ; 77(8): e620-e627, 2022 08.
Article in English | MEDLINE | ID: covidwho-1867031

ABSTRACT

AIM: To develop a multi-task learning (MTL) V-Net for pulmonary lobar segmentation on computed tomography (CT) and application to diseased lungs. MATERIALS AND METHODS: The described methodology utilises tracheobronchial tree information to enhance segmentation accuracy through the algorithm's spatial familiarity to define lobar extent more accurately. The method undertakes parallel segmentation of lobes and auxiliary tissues simultaneously by employing MTL in conjunction with V-Net-attention, a popular convolutional neural network in the imaging realm. Its performance was validated by an external dataset of patients with four distinct lung conditions: severe lung cancer, COVID-19 pneumonitis, collapsed lungs, and chronic obstructive pulmonary disease (COPD), even though the training data included none of these cases. RESULTS: The following Dice scores were achieved on a per-segment basis: normal lungs 0.97, COPD 0.94, lung cancer 0.94, COVID-19 pneumonitis 0.94, and collapsed lung 0.92, all at p<0.05. CONCLUSION: Despite severe abnormalities, the model provided good performance at segmenting lobes, demonstrating the benefit of tissue learning. The proposed model is poised for adoption in the clinical setting as a robust tool for radiologists and researchers to define the lobar distribution of lung diseases and aid in disease treatment planning.


Subject(s)
COVID-19 , Lung Neoplasms , Pulmonary Disease, Chronic Obstructive , COVID-19/diagnostic imaging , Humans , Image Processing, Computer-Assisted/methods , Lung/diagnostic imaging , Lung Neoplasms/diagnostic imaging , Pulmonary Disease, Chronic Obstructive/diagnostic imaging , Tomography, X-Ray Computed/methods
7.
Respirology ; 27(9): 776-785, 2022 09.
Article in English | MEDLINE | ID: covidwho-1846281

ABSTRACT

The US Preventive Task Force (USPSTF) has updated screening criteria by expanding age range and reducing smoking history required for eligibility; the International Lung Screen Trial (ILST) data have shown that PLCOM2012 performs better for eligibility than USPSTF criteria. Screening adherence is low (4%-6% of potential eligible candidates in the United States) and depends upon multiple system and patient/candidate-related factors. Smoking cessation in lung cancer improves survival (past prospective trial data, updated meta-analysis data); smoking cessation is an essential component of lung cancer screening. Circulating biomarkers are emerging to optimize screening and early diagnosis. COVID-19 continues to affect lung cancer treatment and screening through delays and disruptions; specific operational challenges need to be met. Over 70% of suspected malignant lesions develop in the periphery of the lungs. Bronchoscopic navigational techniques have been steadily improving to allow greater accuracy with target lesion approximation and therefore diagnostic yield. Fibre-based imaging techniques provide real-time microscopic tumour visualization, with potential diagnostic benefits. With significant advances in peripheral lung cancer localization, bronchoscopically delivered ablative therapies are an emerging field in limited stage primary and oligometastatic disease. In advanced stage lung cancer, small-volume samples acquired through bronchoscopic techniques yield material of sufficient quantity and quality to support clinically relevant biomarker assessment.


Subject(s)
COVID-19 , Lung Neoplasms , Multiple Pulmonary Nodules , COVID-19/epidemiology , Early Detection of Cancer/methods , Humans , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/pathology , Prospective Studies
8.
J Pathol ; 257(4): 413-429, 2022 07.
Article in English | MEDLINE | ID: covidwho-1844201

ABSTRACT

Lung diseases carry a significant burden of morbidity and mortality worldwide. The advent of digital pathology (DP) and an increase in computational power have led to the development of artificial intelligence (AI)-based tools that can assist pathologists and pulmonologists in improving clinical workflow and patient management. While previous works have explored the advances in computational approaches for breast, prostate, and head and neck cancers, there has been a growing interest in applying these technologies to lung diseases as well. The application of AI tools on radiology images for better characterization of indeterminate lung nodules, fibrotic lung disease, and lung cancer risk stratification has been well documented. In this article, we discuss methodologies used to build AI tools in lung DP, describing the various hand-crafted and deep learning-based unsupervised feature approaches. Next, we review AI tools across a wide spectrum of lung diseases including cancer, tuberculosis, idiopathic pulmonary fibrosis, and COVID-19. We discuss the utility of novel imaging biomarkers for different types of clinical problems including quantification of biomarkers like PD-L1, lung disease diagnosis, risk stratification, and prediction of response to treatments such as immune checkpoint inhibitors. We also look briefly at some emerging applications of AI tools in lung DP such as multimodal data analysis, 3D pathology, and transplant rejection. Lastly, we discuss the future of DP-based AI tools, describing the challenges with regulatory approval, developing reimbursement models, planning clinical deployment, and addressing AI biases. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.


Subject(s)
COVID-19 , Lung Neoplasms , Artificial Intelligence , Humans , Lung/diagnostic imaging , Lung Neoplasms/diagnostic imaging , Pathologists
9.
Clin Imaging ; 86: 83-88, 2022 Jun.
Article in English | MEDLINE | ID: covidwho-1803771

ABSTRACT

PURPOSE: To assess radiology representation, multimedia content, and multilingual content of United States lung cancer screening (LCS) program websites. MATERIALS AND METHODS: We identified the websites of US LCS programs with the Google internet search engine using the search terms lung cancer screening, low-dose CT screening, and lung screening. We used a standardized checklist to assess and collect specific content, including information regarding LCS staff composition and references to radiologists and radiology. We also tabulated types and frequencies of included multimedia and multilingual content and patient narratives. RESULTS: We analyzed 257 unique websites. Of these, only 48% (124 of 257) referred to radiologists or radiology in text, images, or videos. Radiologists were featured in images or videos on only 14% (36 of 257) of websites. Radiologists were most frequently acknowledged for their roles in reading or interpreting imaging studies (35% [90 of 574]). Regarding multimedia content, only 36% (92 of 257) of websites had 1 image, 27% (70 of 257) included 2 or more images, and 26% (68 of 257) of websites included one or more videos. Only 3% (7 of 257) of websites included information in a language other than English. Patient narratives were found on only 15% (39 of 257) of websites. CONCLUSIONS: The field of Radiology is mentioned in text, images, or videos by less than half of LCS program websites. Most websites make only minimal use of multimedia content such as images, videos, and patient narratives. Few websites provide LCS information in languages other than English, potentially limiting accessibility to diverse populations.


Subject(s)
Lung Neoplasms , Radiology , Early Detection of Cancer , Humans , Internet , Lung Neoplasms/diagnostic imaging , Multimedia , Search Engine , United States
10.
Zhongguo Fei Ai Za Zhi ; 25(3): 147-155, 2022 Mar 20.
Article in Chinese | MEDLINE | ID: covidwho-1780097

ABSTRACT

BACKGROUND: At present, the research progress of targeted therapy for epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK) gene mutations in lung adenocarcinoma is very rapid, which brings new hope for the treatment of advanced lung adenocarcinoma patients. However, the specific imaging and pathological features of EGFR and ALK gene mutations in adenocarcinoma are still controversial. This study will further explore the correlation between EGFR, ALK gene mutations and imaging and pathological features in invasive lung adenocarcinoma. METHODS: A total of 525 patients with lung adenocarcinoma who underwent surgery in our center from January 2018 to December 2019 were included. According to the results of postoperative gene detection, the patients were divided into EGFR gene mutation group, ALK gene mutation group and wild group, and the EGFR gene mutation group was divided into exon 19 and exon 21 subtypes. The pathological features of the mutation group and wild group, such as histological subtype, lymph node metastasis, visceral pleural invasion (VPI) and imaging features such as tumor diameter, consolidation tumor ratio (CTR), lobulation sign, spiculation sign, pleural retraction sign, air bronchus sign and vacuole sign were analyzed by univariate analysis and multivariate Logistic regression analysis to explore whether the gene mutation group had specific manifestations. RESULTS: EGFR gene mutation group was common in women (OR=2.041, P=0.001), with more pleural traction sign (OR=1.506, P=0.042), and had little correlation with lymph node metastasis and VPI (P>0.05). Among them, exon 21 subtype was more common in older (OR=1.022, P=0.036), women (OR=2.010, P=0.007), and was associated with larger tumor diameter (OR=1.360, P=0.039) and pleural traction sign (OR=1.754, P=0.029). Exon 19 subtype was common in women (OR=2.230, P=0.009), with a high proportion of solid components (OR=1.589, P=0.047) and more lobulation sign (OR=2.762, P=0.026). ALK gene mutations were likely to occur in younger patients (OR=2.950, P=0.045), with somking history (OR=1.070, P=0.002), and there were more micropapillary components (OR=4.184, P=0.019) and VPI (OR=2.986, P=0.034) in pathology. CONCLUSIONS: The EGFR and ALK genes mutated adenocarcinomas have specific imaging and clinicopathological features, and the mutations in exon 19 or exon 21 subtype have different imaging features, which is of great significance in guiding the clinical diagnosis and treatment of pulmonary nodules.


Subject(s)
Adenocarcinoma of Lung , Anaplastic Lymphoma Kinase , Lung Neoplasms , Adenocarcinoma of Lung/diagnostic imaging , Adenocarcinoma of Lung/genetics , Aged , Anaplastic Lymphoma Kinase/genetics , ErbB Receptors/genetics , Female , Genes, erbB-1 , Humans , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/genetics , Lung Neoplasms/pathology , Mutation , Tomography, X-Ray Computed/methods
11.
Comput Math Methods Med ; 2022: 3722703, 2022.
Article in English | MEDLINE | ID: covidwho-1765182

ABSTRACT

Objective: To investigate the clinical efficacy of digital subtraction angiography- (DSA-) guided bronchial arterial chemoembolization (BACE) in patients with primary bronchial lung cancer. Methods: A total of 178 patients with primary intermediate and advanced bronchial lung cancer admitted to our hospital from February 2019 to March 2020 were selected as the subjects, and they were divided into control group (84 cases) and observation group (94 cases) according to the different chemotherapy regimens adopted by the patients. The control group was treated with traditional perfusion chemotherapy, and the observation group was treated with DSA-guided BACE interventional therapy, treated for 4 cycles, and followed up until the end of June 2021. The short-term clinical efficacy, hemoptysis remission, and incidence of adverse reactions were compared between the two groups. The mortality and recurrence rates between the two groups from treatment to the end of follow-up were counted, and the quality of life after treatment and 1 year after treatment were compared. Results: The short-term remission rate (73.40% vs. 58.33%), disease control rate (93.62% vs. 84.52%), hemoptysis remission rate (75.00% vs. 41.51%), the quality of life after chemotherapy cycle (90.86 ± 2.55 vs. 78.04 ± 2.21), and the quality of life after 1 year of follow-up (85.68 ± 2.23 vs. 70.27 ± 1.72) in the observation group were significantly higher than those in the control group, and the difference was statistically significant (P < 0.05). The incidence of adverse reactions (9.57% vs. 20.24%), mortality (10.64% vs. 21.43%), and recurrence rate (11.70% vs. 27.38%) during the follow-up period in the observation group were significantly lower than those in control group, and the differences were statistically significant (P < 0.05). Conclusion: DSA-guided BACE interventional therapy for patients with primary middle-advanced bronchial lung cancer has significant efficacy, which can not only reduce the mortality and recurrence rate of patients but also improve the quality of life of patients, with fewer adverse reactions and high safety, which is worthy of promotion.


Subject(s)
Lung Neoplasms , Quality of Life , Bronchi , Humans , Lung , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/therapy , Treatment Outcome
12.
Technol Cancer Res Treat ; 21: 15330338221085375, 2022.
Article in English | MEDLINE | ID: covidwho-1745537

ABSTRACT

Introduction: Chest computed tomography (CT) is important for the early screening of lung diseases and clinical diagnosis, particularly during the COVID-19 pandemic. We propose a method for classifying peripheral lung cancer and focal pneumonia on chest CT images and undertake 5 window settings to study the effect on the artificial intelligence processing results. Methods: A retrospective collection of CT images from 357 patients with peripheral lung cancer having solitary solid nodule or focal pneumonia with a solitary consolidation was applied. We segmented and aligned the lung parenchyma based on some morphological methods and cropped this region of the lung parenchyma with the minimum 3D bounding box. Using these 3D cropped volumes of all cases, we designed a 3D neural network to classify them into 2 categories. We also compared the classification results of the 3 physicians with different experience levels on the same dataset. Results: We conducted experiments using 5 window settings. After cropping and alignment based on an automatic preprocessing procedure, our neural network achieved an average classification accuracy of 91.596% under a 5-fold cross-validation in the full window, in which the area under the curve (AUC) was 0.946. The classification accuracy and AUC value were 90.48% and 0.957 for the junior physician, 94.96% and 0.989 for the intermediate physician, and 96.92% and 0.980 for the senior physician, respectively. After removing the error prediction, the accuracy improved significantly, reaching 98.79% in the self-defined window2. Conclusion: Using the proposed neural network, in separating peripheral lung cancer and focal pneumonia in chest CT data, we achieved an accuracy competitive to that of a junior physician. Through a data ablation study, the proposed 3D CNN can achieve a slightly higher accuracy compared with senior physicians in the same subset. The self-defined window2 was the best for data training and evaluation.


Subject(s)
COVID-19 , Lung Neoplasms , Artificial Intelligence , COVID-19/diagnostic imaging , Humans , Lung Neoplasms/diagnostic imaging , Neural Networks, Computer , Pandemics , Retrospective Studies , Tomography, X-Ray Computed/methods
13.
J Immunother Cancer ; 10(3)2022 03.
Article in English | MEDLINE | ID: covidwho-1731296

ABSTRACT

Vaccination against COVID-19 is critical for immuno-compromised individuals, including patients with cancer. Systemic reactogenicity, a manifestation of the innate immune response to vaccines, occurs in up to 69% of patients following vaccination with RNA-based COVID-19 vaccines. Tumor regression can occur following an intense immune-inflammatory response and novel strategies to treat cancer rely on manipulating the host immune system. Here, we report spontaneous regression of metastatic salivary gland myoepithelial carcinoma in a patient who experienced grade 3 systemic reactogenicity, following vaccination with the mRNA-1273 COVID-19 vaccine. Histological and immunophenotypic inspection of the postvaccination lung biopsy specimens showed a massive inflammatory infiltrate with scant embedded tumor clusters (<5%). Highly multiplexed imaging mass cytometry showed that the postvaccination lung metastasis samples had remarkable immune cell infiltration, including CD4+ T cells, CD8+ T cells, natural killer cells, B cells, and dendritic cells, which contrasted with very low levels of these cells in the prevaccination primary tumor and lung metastasis samples. CT scans obtained 3, 6, and 9 months after the second vaccine dose demonstrated persistent tumor shrinkage (50%, 67%, and 73% reduction, respectively), suggesting that vaccination stimulated anticancer immunity. Insight: This case suggests that the mRNA-1273 COVID-19 vaccine stimulated anticancer immunity and tumor regression.


Subject(s)
2019-nCoV Vaccine mRNA-1273 , Immunity, Innate , Immunogenicity, Vaccine , Lung Neoplasms/immunology , Myoepithelioma/immunology , Parotid Neoplasms/surgery , B-Lymphocytes , CD4-Positive T-Lymphocytes , CD8-Positive T-Lymphocytes , Female , Humans , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/secondary , Middle Aged , Myoepithelioma/diagnostic imaging , Myoepithelioma/secondary , Parotid Neoplasms/pathology
15.
Health Expect ; 25(1): 408-418, 2022 02.
Article in English | MEDLINE | ID: covidwho-1691570

ABSTRACT

BACKGROUND: Patient engagement in research agenda setting is increasingly being seen as a strategy to improve the responsiveness of healthcare to patient priorities. Implementation of low-dose computed tomography (LDCT) screening for lung cancer is suboptimal, suggesting that research is needed. OBJECTIVES: This study aimed to describe an approach by which a Veteran patient group worked with other stakeholders to develop a research agenda for LDCT screening and to describe the research questions that they prioritized. METHODS: We worked with Veterans organizations to identify 12 Veterans or family members at risk for or having experience with lung cancer to form a Patient Advisory Council (PAC). The PAC met repeatedly from June 2018 to December 2020, both independently and jointly, with stakeholders representing clinicians, health administrators and researchers to identify relevant research topics. The PAC prioritized these topics and then identified questions within these areas where research was needed using an iterative process. Finally, they ranked the importance of obtaining answers to these questions. RESULTS: PAC members valued the co-learning generated by interactions with stakeholders, but emphasized the importance of facilitation to avoid stakeholders dominating the discussion. The PAC prioritized three broad research areas-(1) the impact of insurance on uptake of LDCT; (2) how best to inform Veterans about LDCT; and (3) follow-up and impact of screening results. Using these areas as guides, PAC members identified 20 specific questions, ranking as most important (1) innovative outreach methods, (2) the impact of screening on psychological health, and (3) the impact of outsourcing scans from VA to non-VA providers on completion of recommended follow-up of screening results. The latter two were not identified as high priority by the stakeholder group. CONCLUSIONS: We present an approach that facilitates co-learning between Veteran patients and providers, researchers and health system administrators to increase patient confidence in their ability to contribute important information to a research agenda. The research questions prioritized by the Veterans who participated in this project illustrate that for this new screening technology, patients are concerned about the practical details of implementation (e.g., follow-up) and the technology's impact on quality of life. PATIENT OR PUBLIC CONTRIBUTION: Veterans and Veteran advocates contributed to our research team throughout the entire research process, including conceiving and co-authoring this manuscript.


Subject(s)
Lung Neoplasms , Veterans , Early Detection of Cancer , Humans , Lung Neoplasms/diagnostic imaging , Quality of Life , Research
16.
Tomography ; 8(1): 513-528, 2022 02 11.
Article in English | MEDLINE | ID: covidwho-1687047

ABSTRACT

The COVID-19 pneumonia pandemic represents the most severe health emergency of the 21st century and has been monopolizing health systems' economic and human resources world-wide. Cancer patients have been suffering from the health systems' COVID-19 priority management with evidence of late diagnosis leading to patients' poor prognosis and late medical treatment. The radiologist plays a pivotal role as CT represents a non-invasive radiological technique which may help to identify possible overlap and differential diagnosis between COVID-19 pneumonia and lung cancer, which represents the most frequent cancer histology in COVID-19 patients. Our aims are: to present the main CT features of COVID-19 pneumonia; to provide the main differential diagnosis with lung cancer, chemotherapy-, immunotherapy-, and radiotherapy-induced lung disease; and to suggest practical tips and key radiological elements to identify possible overlap between COVID-19 pneumonia and lung cancer. Despite similarities or overlapping findings, the combination of clinics and some specific radiological findings, which are also identified by comparison with previous and follow-up CT scans, may guide differential diagnosis. It is crucial to search for typical COVID-19 pneumonia phase progression and typical radiological features on HRTC. The evidence of atypical findings such as lymphadenopathies and mediastinal and vessel invasion, as well as the absence of response to therapy, should arouse the suspicion of lung cancer and require contrast administration. Ground-glass areas and/or consolidations bound to radiotherapy fields or pneumonitis arising during and after oncological therapy should always arouse the suspicion of radiation-induced lung disease and chemo/immunotherapy-induced lung disease. The radiological elements we suggest for COVID-19 and lung cancer differential diagnosis may be used to develop AI protocols to guarantee an early and proper diagnosis and treatment to improve patients' quality of life and life expectancy.


Subject(s)
COVID-19 , Lung Neoplasms , Pneumonia , COVID-19/diagnostic imaging , Diagnosis, Differential , Humans , Lung Neoplasms/diagnostic imaging , Quality of Life , SARS-CoV-2
17.
Tuberk Toraks ; 69(4): 499-509, 2021 Dec.
Article in English | MEDLINE | ID: covidwho-1594579

ABSTRACT

INTRODUCTION: One of the patient groups adversely affected during the COVID19 pandemic is those suffering with cancer. The aim of this study was to evaluate the clinical characteristics and outcomes of lung cancer (LC) patients with COVID-19. MATERIALS AND METHODS: Three thousand seven-hundred and fifty hospitalized patients with a presumptive diagnosis of COVID-19 in a tertiary referral hospital between March 2020-February 2021 were retrospectively evaluated. Among them, 36 hospitalized COVID-19 patients with a history of primary LC were included in the study. Univariate and multivariate analyses were carried out to assess the risk factors associated with severe disease. RESULT: Of the 36 patients included in the study, 28 (77%) were males and 8 (23%) were females. Median age was 67 years (min-max: 53-81 years). Six patients (17%) had a diagnosis of small cell LC, whereas 30 patients (83%) had a diagnosis of non-small cell LC. The most common symptoms were fever (n= 28, 77%), coughing and myalgia (n= 21, 58%) and dyspnea (n= 18, 50%). The most common radiological finding was ground glass opacity (GGO) (n= 30), of which 13 was bilateral and 17 was unilateral in distribution. Nearly 30% (n= 11) of LC patients with COVID-19 developed severe disease, 5% (n= 2) of the 36 patients were admitted to intensive care unit and all of these patients eventually expired. LC patients with COVID-19 and patchy consolidation on computed tomography of thorax (Th CT) on admission had a higher risk of developing severe disease in univariate (HR 2.41, 95%CI: 1.4- 4.4, p= 0.04) and multivariate Cox regression analysis (HR 0.48, 95%CI: 0.24-0.97, p= 0.03). CONCLUSIONS: Clinical characteristics, laboratory and radiographic findings were similar in LC patients with COVID-19 when compared with the general population, LC patients have a higher mortality rate than the general population, with a 5% mortality rate in our series. Our findings suggest that LC may be a risk factor associated with the prognosis of COVID-19 patients.


Subject(s)
COVID-19 , Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Aged , Female , Humans , Lung , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/epidemiology , Male , Retrospective Studies , SARS-CoV-2
18.
Med Phys ; 49(1): 420-431, 2022 Jan.
Article in English | MEDLINE | ID: covidwho-1544357

ABSTRACT

PURPOSE: Motion-mask segmentation from thoracic computed tomography (CT) images is the process of extracting the region that encompasses lungs and viscera, where large displacements occur during breathing. It has been shown to help image registration between different respiratory phases. This registration step is, for example, useful for radiotherapy planning or calculating local lung ventilation. Knowing the location of motion discontinuity, that is, sliding motion near the pleura, allows a better control of the registration preventing unrealistic estimates. Nevertheless, existing methods for motion-mask segmentation are not robust enough to be used in clinical routine. This article shows that it is feasible to overcome this lack of robustness by using a lightweight deep-learning approach usable on a standard computer, and this even without data augmentation or advanced model design. METHODS: A convolutional neural-network architecture with three 2D U-nets for the three main orientations (sagittal, coronal, axial) was proposed. Predictions generated by the three U-nets were combined by majority voting to provide a single 3D segmentation of the motion mask. The networks were trained on a database of nonsmall cell lung cancer 4D CT images of 43 patients. Training and evaluation were done with a K-fold cross-validation strategy. Evaluation was based on a visual grading by two experts according to the appropriateness of the segmented motion mask for the registration task, and on a comparison with motion masks obtained by a baseline method using level sets. A second database (76 CT images of patients with early-stage COVID-19), unseen during training, was used to assess the generalizability of the trained neural network. RESULTS: The proposed approach outperformed the baseline method in terms of quality and robustness: the success rate increased from 53 % to 79 % without producing any failure. It also achieved a speed-up factor of 60 with GPU, or 17 with CPU. The memory footprint was low: less than 5 GB GPU RAM for training and less than 1 GB GPU RAM for inference. When evaluated on a dataset with images differing by several characteristics (CT device, pathology, and field of view), the proposed method improved the success rate from 53 % to 83 % . CONCLUSION: With 5-s processing time on a mid-range GPU and success rates around 80 % , the proposed approach seems fast and robust enough to be routinely used in clinical practice. The success rate can be further improved by incorporating more diversity in training data via data augmentation and additional annotated images from different scanners and diseases. The code and trained model are publicly available.


Subject(s)
COVID-19 , Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Four-Dimensional Computed Tomography , Humans , Image Processing, Computer-Assisted , Lung Neoplasms/diagnostic imaging , Lung Neoplasms/radiotherapy , SARS-CoV-2
20.
Med Phys ; 48(12): 7913-7929, 2021 Dec.
Article in English | MEDLINE | ID: covidwho-1516790

ABSTRACT

PURPOSE: Feature maps created from deep convolutional neural networks (DCNNs) have been widely used for visual explanation of DCNN-based classification tasks. However, many clinical applications such as benign-malignant classification of lung nodules normally require quantitative and objective interpretability, rather than just visualization. In this paper, we propose a novel interpretable multi-task attention learning network named IMAL-Net for early invasive adenocarcinoma screening in chest computed tomography images, which takes advantage of segmentation prior to assist interpretable classification. METHODS: Two sub-ResNets are firstly integrated together via a prior-attention mechanism for simultaneous nodule segmentation and invasiveness classification. Then, numerous radiomic features from the segmentation results are concatenated with high-level semantic features from the classification subnetwork by FC layers to achieve superior performance. Meanwhile, an end-to-end feature selection mechanism (named FSM) is designed to quantify crucial radiomic features greatly affecting the prediction of each sample, and thus it can provide clinically applicable interpretability to the prediction result. RESULTS: Nodule samples from a total of 1626 patients were collected from two grade-A hospitals for large-scale verification. Five-fold cross validation demonstrated that the proposed IMAL-Net can achieve an AUC score of 93.8% ± 1.1% and a recall score of 93.8% ± 2.8% for identification of invasive lung adenocarcinoma. CONCLUSIONS: It can be concluded that fusing semantic features and radiomic features can achieve obvious improvements in the invasiveness classification task. Moreover, by learning more fine-grained semantic features and highlighting the most important radiomics features, the proposed attention and FSM mechanisms not only can further improve the performance but also can be used for both visual explanations and objective analysis of the classification results.


Subject(s)
Adenocarcinoma of Lung , Adenocarcinoma , Lung Neoplasms , Adenocarcinoma/diagnostic imaging , Adenocarcinoma of Lung/diagnostic imaging , Humans , Lung Neoplasms/diagnostic imaging , Neural Networks, Computer , Tomography, X-Ray Computed
SELECTION OF CITATIONS
SEARCH DETAIL