Assistive AI in Lung Cancer Screening: A Retrospective Multinational Study in the United States and Japan.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the impact of an artificial intelligence (AI) assistant for lung cancer screening (LCS) on multinational clinical workflows. Materials and Methods An AI assistant for LCS was evaluated on two retrospective randomized multireader multicase studies, where 627 (141 cancer positive) low-dose chest CT cases were each read twice (with and without AI assistance) by experienced thoracic radiologists (6 US-based or 6 Japan-based), resulting in a total of 7,524 interpretations. Positive cases were defined as those within two years before a pathology-confirmed lung cancer diagnosis. Negative cases were defined as those without any subsequent cancer diagnosis for at least two years and were enriched for a spectrum of diverse nodules. The studies measured the readers' level of suspicion (LoS, on a 0-100 scale), country-specific screening system scoring categories, and management recommendations. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) for LoS and sensitivity and specificity of recall recommendations. Results With AI assistance, the radiologists' AUC increased by 0.023 (0.70 to 0.72, P = .02) for the US study and by 0.023 (0.93 to 0.96, P = .18) for the Japan study. Scoring system specificity for actionable findings increased 5.5% (57%-63%, P < .001) for the US study and 6.7% (23%-30%, P < .001) for the Japan study. There was no evidence of a difference in corresponding sensitivity between unassisted and AI-assisted reads for the US (67.3%-67.5%, P = .88) and Japan (98%-100%, P > .99) studies. Corresponding standalone AI AUC system performance was 0.75 95% CI [0.70-0.81] and 0.88 95%CI [0.78-0.97] for the US and Japan-based datasets, respectively. Conclusion The concurrent AI interface improved LCS specificity in both US and Japan-based reader studies, meriting further study in additional international screening environments. ©RSNA, 2024.

Fleischner Society: Glossary of Terms for Thoracic Imaging.

Members of the Fleischner Society have compiled a glossary of terms for thoracic imaging that replaces previous glossaries published in 1984, 1996, and 2008, respectively. The impetus to update the previous version arose from multiple considerations. These include an awareness that new terms and concepts have emerged, others have become obsolete, and the usage of some terms has either changed or become inconsistent to a degree that warranted a new definition. This latest glossary is focused on terms of clinical importance and on those whose meaning may be perceived as vague or ambiguous. As with previous versions, the aim of the present glossary is to establish standardization of terminology for thoracic radiology and, thereby, to facilitate communications between radiologists and clinicians. Moreover, the present glossary aims to contribute to a more stringent use of terminology, increasingly required for structured reporting and accurate searches in large databases. Compared with the previous version, the number of images (chest radiography and CT) in the current version has substantially increased. The authors hope that this will enhance its educational and practical value. All definitions and images are hyperlinked throughout the text. Click on each figure callout to view corresponding image. © RSNA, 2024 Supplemental material is available for this article. See also the editorials by Bhalla and Powell in this issue.

Current Imaging of Idiopathic Pulmonary Fibrosis.

The major role of imaging (CT) in usual interstitial pneumonia (UIP)/idiopathic pulmonary fibrosis (IPF) is in the initial diagnosis. We propose several modifications to existing guidelines to help improve the accuracy of this diagnosis and to enhance interobserver agreement. CT detects the common complications and associations that occur with UIP/IPF including acute exacerbation, lung cancer, and dendriform pulmonary ossification and is useful in informing prognosis based on baseline fibrosis severity. Serial CT imaging is a topic of great interest; it may identify disease progression before FVC decline or clinical change.

Shades of Gray: Subsolid Nodule Considerations and Management.

Subsolid nodules are common on chest CT imaging and may be either benign or malignant. Their varied features and broad differential diagnoses present management challenges. Although subsolid nodules often represent lung adenocarcinomas, other possibilities are common and influence management. Practice guidelines exist for subsolid nodule management for both incidentally and screening-detected nodules, incorporating patient and nodule characteristics. This review highlights the similarities and differences among these algorithms, with the intent of providing a resource for comparison and aid in choosing management options.

Management of Lung Nodules and Lung Cancer Screening During the COVID-19 Pandemic: CHEST Expert Panel Report.

BACKGROUND: The risks from potential exposure to coronavirus disease 2019 (COVID-19), and resource reallocation that has occurred to combat the pandemic, have altered the balance of benefits and harms that informed current (pre-COVID-19) guideline recommendations for lung cancer screening and lung nodule evaluation. Consensus statements were developed to guide clinicians managing lung cancer screening programs and patients with lung nodules during the COVID-19 pandemic. METHODS: An expert panel of 24 members, including pulmonologists (n = 17), thoracic radiologists (n = 5), and thoracic surgeons (n = 2), was formed. The panel was provided with an overview of current evidence, summarized by recent guidelines related to lung cancer screening and lung nodule evaluation. The panel was convened by video teleconference to discuss and then vote on statements related to 12 common clinical scenarios. A predefined threshold of 70% of panel members voting agree or strongly agree was used to determine if there was a consensus for each statement. Items that may influence decisions were listed as notes to be considered for each scenario. RESULTS: Twelve statements related to baseline and annual lung cancer screening (n = 2), surveillance of a previously detected lung nodule (n = 5), evaluation of intermediate and high-risk lung nodules (n = 4), and management of clinical stage I non-small-cell lung cancer (n = 1) were developed and modified. All 12 statements were confirmed as consensus statements according to the voting results. The consensus statements provide guidance about situations in which it was believed to be appropriate to delay screening, defer surveillance imaging of lung nodules, and minimize nonurgent interventions during the evaluation of lung nodules and stage I non-small-cell lung cancer. CONCLUSIONS: There was consensus that during the COVID-19 pandemic, it is appropriate to defer enrollment in lung cancer screening and modify the evaluation of lung nodules due to the added risks from potential exposure and the need for resource reallocation. There are multiple local, regional, and patient-related factors that should be considered when applying these statements to individual patient care.

Management of Lung Nodules and Lung Cancer Screening During the COVID-19 Pandemic: CHEST Expert Panel Report.

BACKGROUND: The risks from potential exposure to coronavirus disease 2019 (COVID-19), and resource reallocation that has occurred to combat the pandemic, have altered the balance of benefits and harms that informed current (pre-COVID-19) guideline recommendations for lung cancer screening and lung nodule evaluation. Consensus statements were developed to guide clinicians managing lung cancer screening programs and patients with lung nodules during the COVID-19 pandemic. METHODS: An expert panel of 24 members, including pulmonologists (n = 17), thoracic radiologists (n = 5), and thoracic surgeons (n = 2), was formed. The panel was provided with an overview of current evidence, summarized by recent guidelines related to lung cancer screening and lung nodule evaluation. The panel was convened by video teleconference to discuss and then vote on statements related to 12 common clinical scenarios. A predefined threshold of 70% of panel members voting agree or strongly agree was used to determine if there was a consensus for each statement. Items that may influence decisions were listed as notes to be considered for each scenario. RESULTS: Twelve statements related to baseline and annual lung cancer screening (n = 2), surveillance of a previously detected lung nodule (n = 5), evaluation of intermediate and high-risk lung nodules (n = 4), and management of clinical stage I non-small cell lung cancer (n = 1) were developed and modified. All 12 statements were confirmed as consensus statements according to the voting results. The consensus statements provide guidance about situations in which it was believed to be appropriate to delay screening, defer surveillance imaging of lung nodules, and minimize nonurgent interventions during the evaluation of lung nodules and stage I non-small cell lung cancer. CONCLUSIONS: There was consensus that during the COVID-19 pandemic, it is appropriate to defer enrollment in lung cancer screening and modify the evaluation of lung nodules due to the added risks from potential exposure and the need for resource reallocation. There are multiple local, regional, and patient-related factors that should be considered when applying these statements to individual patient care.

Lung Hyperlucency: A Clinical-Radiologic Algorithmic Approach to Diagnosis.

Areas of diminished lung density are frequently identified both on routine chest radiographs and chest CT examinations. Colloquially referred to as hyperlucent foci of lung, a broad range of underlying pathophysiologic mechanisms and differential diagnoses account for these changes. Despite this, the spectrum of etiologies can be categorized into underlying parenchymal, airway, and vascular-related entities. The purpose of this review is to provide a practical diagnostic algorithmic approach to pulmonary hyperlucencies incorporating clinical history and characteristic imaging patterns to narrow the differential.

An Algorithmic Approach to the Interpretation of Diffuse Lung Disease on Chest CT Imaging: A Theory of Almost Everything.

We propose an algorithmic approach to the interpretation of diffuse lung disease on high-resolution CT. Following an initial review of pertinent lung anatomy, the following steps are included. Step 1: a preliminary review of available chest radiographs, including the "scanogram" obtained at the time of the CT examination. Step 2: a review of optimal methods of data acquisition and reconstruction, emphasizing the need for contiguous high-resolution images throughout the entire thorax. Step 3: initial uninterrupted scrolling of contiguous high-resolution images throughout the chest to establish the quality of examination as well as an overview of the presence and extent of disease. Step 4: determination of one of three predominant categories - primarily reticular disease, nodular disease, or diseases associated with diffuse alteration in lung density. Based on this determination, one of the three following Steps are followed: Step 5: evaluation of cases primarily involving diffuse lung reticulation; Step 6: evaluation of cases primarily resulting in diffuse lung nodules; and Step 7: evaluation of cases with diffuse alterations in lung density including those with diffusely diminished lung density vs those with heterogenous or diffusely increased lung density, respectively. It is anticipated that this algorithmic approach will substantially enhance initial interpretations of a wide range of pulmonary disease.

Management of Lung Nodules and Lung Cancer Screening During the COVID-19 Pandemic: CHEST Expert Panel Report.

Background: The risks from potential exposure to coronavirus disease 2019 (COVID-19), and resource reallocation that has occurred to combat the pandemic, have altered the balance of benefits and harms that informed current (pre-COVID-19) guideline recommendations for lung cancer screening and lung nodule evaluation. Consensus statements were developed to guide clinicians managing lung cancer screening programs and patients with lung nodules during the COVID-19 pandemic. Materials and Methods: An expert panel of 24 members, including pulmonologists (n = 17), thoracic radiologists (n = 5), and thoracic surgeons (n = 2), was formed. The panel was provided with an overview of current evidence, summarized by recent guidelines related to lung cancer screening and lung nodule evaluation. The panel was convened by video teleconference to discuss and then vote on statements related to 12 common clinical scenarios. A predefined threshold of 70% of panel members voting agree or strongly agree was used to determine if there was a consensus for each statement. Items that may influence decisions were listed as notes to be considered for each scenario. Results: Twelve statements related to baseline and annual lung cancer screening (n = 2), surveillance of a previously detected lung nodule (n = 5), evaluation of intermediate and high-risk lung nodules (n = 4), and management of clinical stage I non-small cell lung cancer (n = 1) were developed and modified. All 12 statements were confirmed as consensus statements according to the voting results. The consensus statements provide guidance about situations in which it was believed to be appropriate to delay screening, defer surveillance imaging of lung nodules, and minimize nonurgent interventions during the evaluation of lung nodules and stage I non-small cell lung cancer. Conclusion: There was consensus that during the COVID-19 pandemic, it is appropriate to defer enrollment in lung cancer screening and modify the evaluation of lung nodules due to the added risks from potential exposure and the need for resource reallocation. There are multiple local, regional, and patient-related factors that should be considered when applying these statements to individual patient care.© 2020 RSNA; The American College of Chest Physicians, published by Elsevier Inc; and The American College of Radiology, published by Elsevier Inc.

Author Correction: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Approach to Peribronchovascular Disease on CT.

Diseases that are predominantly peribronchovascular in distribution on computed tomography by definition involve the bronchi, adjacent vasculature, and associated lymphatics involving the central or axial lung interstitium. An understanding of diseases that can present with focal peribronchovascular findings is useful for establishing diagnoses and guiding patient management. This review will cover clinical and imaging features that may assist in differentiating amongst the various causes of primarily peribronchovascular disease.

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20-43% and is now included in US screening guidelines1-6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7-10. We propose a deep learning algorithm that uses a patient's current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.

Managing Incidental Findings on Thoracic CT: Mediastinal and Cardiovascular Findings. A White Paper of the ACR Incidental Findings Committee.

The ACR Incidental Findings Committee presents recommendations for managing incidentally detected mediastinal and cardiovascular findings found on CT. The Chest Subcommittee was composed of thoracic radiologists who developed the provided guidance. These recommendations represent a combination of current published evidence and expert opinion and were finalized by informal iterative consensus. The recommendations address the most commonly encountered mediastinal and cardiovascular incidental findings and are not intended to be a comprehensive review of all incidental findings associated with these compartments. Our goal is to improve the quality of care by providing guidance on how to manage incidentally detected thoracic findings.

Lepidic Predominant Pulmonary Lesions (LPL): CT-based Distinction From More Invasive Adenocarcinomas Using 3D Volumetric Density and First-order CT Texture Analysis.

RATIONALE AND OBJECTIVES: This study aimed to differentiate pathologically defined lepidic predominant lesions (LPL) from more invasive adenocarcinomas (INV) using three-dimensional (3D) volumetric density and first-order texture histogram analysis of surgically excised stage 1 lung adenocarcinomas. MATERIALS AND METHODS: This retrospective study was institutional review board approved and Health Insurance Portability and Accountability Act compliant. Sixty-four cases of pathologically proven stage 1 lung adenocarcinoma surgically resected between September 2006 and October 2015, including LPL (n = 43) and INV (n = 21), were evaluated using high-resolution computed tomography. Quantitative measurements included nodule volume, percent solid volume (% solid), and first-order texture histogram analysis including skewness, kurtosis, entropy, and mean nodule attenuation within each histogram quartile. Binomial logistic regression models were used to identify the best set of parameters distinguishing LPL from INV. RESULTS: Univariate analysis of 3D volumetric density and histogram features was statistically significant between LPL and INV groups (P < .05). Accuracy of a binomial logistic model to discriminate LPL from INV based on size and % solid was 85.9%. With optimized probability cutoff, the model achieves 81% sensitivity, 76.7% specificity, and area under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.821-0.973). An additional model based on size and mean nodule attenuation of the third quartile (Hu_Q3) of the histogram achieved similar accuracy of 81.3% and area under the receiver operating characteristic curve of 0.877 (95% confidence interval, 0.790-0.964). CONCLUSIONS: Both 3D volumetric density and first-order texture analysis of stage 1 lung adenocarcinoma allow differentiation of LPL from more invasive adenocarcinoma with overall accuracy of 85.9%-81.3%, based on multivariate analyses of either size and % solid or size and Hu_Q3, respectively.

Recommendations for Measuring Pulmonary Nodules at CT: A Statement from the Fleischner Society.

These recommendations for measuring pulmonary nodules at computed tomography (CT) are a statement from the Fleischner Society and, as such, incorporate the opinions of a multidisciplinary international group of thoracic radiologists, pulmonologists, surgeons, pathologists, and other specialists. The recommendations address nodule size measurements at CT, which is a topic of importance, given that all available guidelines for nodule management are essentially based on nodule size or changes thereof. The recommendations are organized according to practical questions that commonly arise when nodules are measured in routine clinical practice and are, together with their answers, summarized in a table. The recommendations include technical requirements for accurate nodule measurement, directions on how to accurately measure the size of nodules at the workstation, and directions on how to report nodule size and changes in size. The recommendations are designed to provide practical advice based on the available evidence from the literature; however, areas of uncertainty are also discussed, and topics needing future research are highlighted. © RSNA, 2017 Online supplemental material is available for this article.

Coronary artery calcification is common on nongated chest computed tomography imaging.

BACKGROUND: Coronary artery calcification as assessed by computed tomography (CT) is a validated predictor of cardiovascular risk, whether identified on a dedicated cardiac study or on a routine non-gated chest CT. The prevalence of incidentally detected coronary artery calcification on non-gated chest CT imaging and consistency of reporting have not been well characterized. HYPOTHESIS: Coronary calcification is present on chest CT in some patients not taking statin therapy and may be under-reported. METHODS: Non-gated chest CT images dated 1/1/2012 to 1/1/2013 were retrospectively reviewed. Demographics and medical history were obtained from charts. Patients with known history of coronary revascularization and/or pacemaker/defibrillator were excluded. Two independent readers with cardiac CT expertise evaluated images for the presence and anatomical distribution of any coronary calcification, blinded to all clinical information including CT reports. Original clinical CT reports were subsequently reviewed. RESULTS: Coronary calcification was identified in 204/304 (68%) chest CTs. Patients with calcification were older and had more hyperlipidemia, smoking history, and known coronary artery disease. Of patients with calcification, 43% were on aspirin and 62% were on statin medication at the time of CT. Coronary calcification was identified in 69% of reports when present. CONCLUSIONS: A high prevalence of coronary calcification was found in non-gated chest CT scans performed for non-cardiac indications. In one-third, coronary calcification was not mentioned in the clinical report when actually present. In this population of patients with cardiac risk factors, standard reporting of the presence of coronary calcification may provide an opportunity for risk factor modification.