Performance of AI to exclude normal chest radiographs to reduce radiologists' workload.

INTRODUCTION: This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest radiographs and its potential to reduce radiologist workload. METHODS: Retrospective analysis included consecutive chest radiographs from two medical centers between Oct 1, 2016 and Oct 14, 2016. Exclusions comprised follow-up exams within the inclusion period, bedside radiographs, incomplete images, imported radiographs, and pediatric radiographs. Three chest radiologists categorized findings into normal, clinically irrelevant, clinically relevant, urgent, and critical. A commercial AI system processed all radiographs, scoring 10 chest abnormalities on a 0-100 confidence scale. AI system performance was evaluated using the area under the ROC curve (AUC), assessing the detection of normal radiographs. Sensitivity was calculated for the default and a conservative operating point. the detection of negative predictive value (NPV) for urgent and critical findings, as well as the potential workload reduction, was calculated. RESULTS: A total of 2603 radiographs were acquired in 2141 unique patients. Post-exclusion, 1670 radiographs were analyzed. Categories included 479 normal, 332 clinically irrelevant, 339 clinically relevant, 501 urgent, and 19 critical findings. The AI system achieved an AUC of 0.92. Sensitivity for normal radiographs was 92% at default and 53% at the conservative operating point. At the conservative operating point, NPV was 98% for urgent and critical findings, and could result in a 15% workload reduction. CONCLUSION: A commercially available AI system effectively identifies normal chest radiographs and holds the potential to lessen radiologists' workload by omitting half of the normal exams from reporting. CLINICAL RELEVANCE STATEMENT: The AI system is able to detect half of all normal chest radiographs at a clinically acceptable operating point, thereby potentially reducing the workload for the radiologists by 15%. KEY POINTS: The AI system reached an AUC of 0.92 for the detection of normal chest radiographs. Fifty-three percent of normal chest radiographs were identified with a NPV of 98% for urgent findings. AI can reduce the workload of chest radiography reporting by 15%.

Enhancing a deep learning model for pulmonary nodule malignancy risk estimation in chest CT with uncertainty estimation.

OBJECTIVE: To investigate the effect of uncertainty estimation on the performance of a Deep Learning (DL) algorithm for estimating malignancy risk of pulmonary nodules. METHODS AND MATERIALS: In this retrospective study, we integrated an uncertainty estimation method into a previously developed DL algorithm for nodule malignancy risk estimation. Uncertainty thresholds were developed using CT data from the Danish Lung Cancer Screening Trial (DLCST), containing 883 nodules (65 malignant) collected between 2004 and 2010. We used thresholds on the 90th and 95th percentiles of the uncertainty score distribution to categorize nodules into certain and uncertain groups. External validation was performed on clinical CT data from a tertiary academic center containing 374 nodules (207 malignant) collected between 2004 and 2012. DL performance was measured using area under the ROC curve (AUC) for the full set of nodules, for the certain cases and for the uncertain cases. Additionally, nodule characteristics were compared to identify trends for inducing uncertainty. RESULTS: The DL algorithm performed significantly worse in the uncertain group compared to the certain group of DLCST (AUC 0.62 (95% CI: 0.49, 0.76) vs 0.93 (95% CI: 0.88, 0.97); p < .001) and the clinical dataset (AUC 0.62 (95% CI: 0.50, 0.73) vs 0.90 (95% CI: 0.86, 0.94); p < .001). The uncertain group included larger benign nodules as well as more part-solid and non-solid nodules than the certain group. CONCLUSION: The integrated uncertainty estimation showed excellent performance for identifying uncertain cases in which the DL-based nodule malignancy risk estimation algorithm had significantly worse performance. CLINICAL RELEVANCE STATEMENT: Deep Learning algorithms often lack the ability to gauge and communicate uncertainty. For safe clinical implementation, uncertainty estimation is of pivotal importance to identify cases where the deep learning algorithm harbors doubt in its prediction. KEY POINTS: • Deep learning (DL) algorithms often lack uncertainty estimation, which potentially reduce the risk of errors and improve safety during clinical adoption of the DL algorithm. • Uncertainty estimation identifies pulmonary nodules in which the discriminative performance of the DL algorithm is significantly worse. • Uncertainty estimation can further enhance the benefits of the DL algorithm and improve its safety and trustworthiness.

Ferumoxtran-10-enhanced MRI for pre-operative metastatic lymph node detection in pancreatic, duodenal, or periampullary adenocarcinoma.

OBJECTIVES: To assess 3-Tesla (3-T) ultra-small superparamagnetic iron oxide (USPIO)-enhanced MRI in detecting lymph node (LN) metastases for resectable adenocarcinomas of the pancreas, duodenum, or periampullary region in a node-to-node validation against histopathology. METHODS: Twenty-seven consecutive patients with a resectable pancreatic, duodenal, or periampullary adenocarcinoma were enrolled in this prospective single expert centre study. Ferumoxtran-10-enhanced 3-T MRI was performed pre-surgery. LNs found on MRI were scored for suspicion of metastasis by two expert radiologists using a dedicated scoring system. Node-to-node matching from in vivo MRI to histopathology was performed using a post-operative ex vivo 7-T MRI of the resection specimen. Sensitivity and specificity were calculated using crosstabs. RESULTS: Eighteen out of 27 patients (median age 65 years, 11 men) were included in the final analysis (pre-surgery withdrawal n = 4, not resected because of unexpected metastases peroperatively n = 2, and excluded because of inadequate contrast-agent uptake n = 3). On MRI 453 LNs with a median size of 4.0 mm were detected, of which 58 (13%) were classified as suspicious. At histopathology 385 LNs with a median size of 5.0 mm were found, of which 45 (12%) were metastatic. For 55 LNs node-to-node matching was possible. Analysis of these 55 matched LNs, resulted in a sensitivity and specificity of 83% (95% CI: 36-100%) and 92% (95% CI: 80-98%), respectively. CONCLUSION: USPIO-enhanced MRI is a promising technique to preoperatively detect and localise LN metastases in patients with pancreatic, duodenal, or periampullary adenocarcinoma. CLINICAL RELEVANCE STATEMENT: Detection of (distant) LN metastases with USPIO-enhanced MRI could be used to determine a personalised treatment strategy that could involve neoadjuvant or palliative chemotherapy, guided resection of distant LNs, or targeted radiotherapy. REGISTRATION: The study was registered on clinicaltrials.gov NCT04311047. https://clinicaltrials.gov/ct2/show/NCT04311047?term=lymph+node&cond=Pancreatic+Cancer&cntry=NL&draw=2&rank=1 . KEY POINTS: LN metastases of pancreatic, duodenal, or periampullary adenocarcinoma cannot be reliably detected with current imaging. This technique detected LN metastases with a sensitivity and specificity of 83% and 92%, respectively. MRI with ferumoxtran-10 is a promising technique to improve preoperative staging in these cancers.

Reduced Lung-Cancer Mortality with Volume CT Screening in a Randomized Trial.

BACKGROUND: There are limited data from randomized trials regarding whether volume-based, low-dose computed tomographic (CT) screening can reduce lung-cancer mortality among male former and current smokers. METHODS: A total of 13,195 men (primary analysis) and 2594 women (subgroup analyses) between the ages of 50 and 74 were randomly assigned to undergo CT screening at T0 (baseline), year 1, year 3, and year 5.5 or no screening. We obtained data on cancer diagnosis and the date and cause of death through linkages with national registries in the Netherlands and Belgium, and a review committee confirmed lung cancer as the cause of death when possible. A minimum follow-up of 10 years until December 31, 2015, was completed for all participants. RESULTS: Among men, the average adherence to CT screening was 90.0%. On average, 9.2% of the screened participants underwent at least one additional CT scan (initially indeterminate). The overall referral rate for suspicious nodules was 2.1%. At 10 years of follow-up, the incidence of lung cancer was 5.58 cases per 1000 person-years in the screening group and 4.91 cases per 1000 person-years in the control group; lung-cancer mortality was 2.50 deaths per 1000 person-years and 3.30 deaths per 1000 person-years, respectively. The cumulative rate ratio for death from lung cancer at 10 years was 0.76 (95% confidence interval [CI], 0.61 to 0.94; P = 0.01) in the screening group as compared with the control group, similar to the values at years 8 and 9. Among women, the rate ratio was 0.67 (95% CI, 0.38 to 1.14) at 10 years of follow-up, with values of 0.41 to 0.52 in years 7 through 9. CONCLUSIONS: In this trial involving high-risk persons, lung-cancer mortality was significantly lower among those who underwent volume CT screening than among those who underwent no screening. There were low rates of follow-up procedures for results suggestive of lung cancer. (Funded by the Netherlands Organization of Health Research and Development and others; NELSON Netherlands Trial Register number, NL580.).

Impact of time-to-treatment on survival for advanced non-small cell lung cancer patients in the Netherlands: a nationwide observational cohort study.

BACKGROUND: The assumption that more rapid treatment improves survival of advanced non-small cell lung cancer (NSCLC) has not yet been proven. We studied the relation between time-to-treatment and survival in advanced stage NSCLC patients in a large multicentric nationwide retrospective cohort. Additionally, we identified factors associated with delay. METHOD: We selected 10 306 patients, diagnosed and treated between 2014 and 2019 for clinical stage III and IV NSCLC, from the Netherlands Cancer Registry that includes nationwide data from 109 Dutch hospitals. Associations between survival and time-to-treatment were tested with Cox proportional hazard regression analyses. Time-to-treatment was adjusted for multiple covariates including diagnostic procedures and type of therapy. Factors associated with delay were identified by multilevel logistic regression. RESULTS: Risk of death significantly decreased with longer time-to-treatment for stage III patients receiving only radiotherapy (adjusted HR, aHR >21 days: 0.59 (95% CI 0.48 to 0.73)) or any type of systemic therapy (aHR >49 days: 0.72 (95% CI 0.56 to 0.91)) and stage IV patients receiving chemotherapy and/or immunotherapy (aHR >21 days: 0.81 (95% CI 0.73 to 0.88)). No significant association was found for stage III patients treated with chemoradiotherapy and stage IV patients treated with targeted therapy. More complex diagnostic procedures often delay treatment. CONCLUSION: Although in general it is important to start treatment as early as possible, our study finds no evidence that a more rapid start of treatment improves outcomes in advanced stage NSCLC patients. The benefit of urgent treatment is probably confounded by unmeasured patient and tumour characteristics and, clinical urgency dictating timelines of treatment. Time-to-treatment and its impact should be continuously evaluated as therapeutic strategies continue to evolve and improve.

Prior CT Improves Deep Learning for Malignancy Risk Estimation of Screening-detected Pulmonary Nodules.

Background Prior chest CT provides valuable temporal information (eg, changes in nodule size or appearance) to accurately estimate malignancy risk. Purpose To develop a deep learning (DL) algorithm that uses a current and prior low-dose CT examination to estimate 3-year malignancy risk of pulmonary nodules. Materials and Methods In this retrospective study, the algorithm was trained using National Lung Screening Trial data (collected from 2002 to 2004), wherein patients were imaged at most 2 years apart, and evaluated with two external test sets from the Danish Lung Cancer Screening Trial (DLCST) and the Multicentric Italian Lung Detection Trial (MILD), collected in 2004-2010 and 2005-2014, respectively. Performance was evaluated using area under the receiver operating characteristic curve (AUC) on cancer-enriched subsets with size-matched benign nodules imaged 1 and 2 years apart from DLCST and MILD, respectively. The algorithm was compared with a validated DL algorithm that only processed a single CT examination and the Pan-Canadian Early Lung Cancer Detection Study (PanCan) model. Results The training set included 10 508 nodules (422 malignant) in 4902 trial participants (mean age, 64 years ± 5 [SD]; 2778 men). The size-matched external test sets included 129 nodules (43 malignant) and 126 nodules (42 malignant). The algorithm achieved AUCs of 0.91 (95% CI: 0.85, 0.97) and 0.94 (95% CI: 0.89, 0.98). It significantly outperformed the DL algorithm that only processed a single CT examination (AUC, 0.85 [95% CI: 0.78, 0.92; P = .002]; and AUC, 0.89 [95% CI: 0.84, 0.95; P = .01]) and the PanCan model (AUC, 0.64 [95% CI: 0.53, 0.74; P < .001]; and AUC, 0.63 [95% CI: 0.52, 0.74; P < .001]). Conclusion A DL algorithm using current and prior low-dose CT examinations was more effective at estimating 3-year malignancy risk of pulmonary nodules than established models that only use a single CT examination. Clinical trial registration nos. NCT00047385, NCT00496977, NCT02837809 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Horst and Nishino in this issue.

ERS/ESTS/ESTRO/ESR/ESTI/EFOMP statement on management of incidental findings from low dose CT screening for lung cancer.

BACKGROUND: Screening for lung cancer with low radiation dose computed tomography has a strong evidence base, is being introduced in several European countries and is recommended as a new targeted cancer screening programme. The imperative now is to ensure that implementation follows an evidence-based process that will ensure clinical and cost effectiveness. This European Respiratory Society (ERS) task force was formed to provide an expert consensus for the management of incidental findings which can be adapted and followed during implementation. METHODS: A multi-European society collaborative group was convened. 23 topics were identified, primarily from an ERS statement on lung cancer screening, and a systematic review of the literature was conducted according to ERS standards. Initial review of abstracts was completed and full text was provided to members of the group for each topic. Sections were edited and the final document approved by all members and the ERS Science Council. RESULTS: Nine topics considered most important and frequent were reviewed as standalone topics (interstitial lung abnormalities, emphysema, bronchiectasis, consolidation, coronary calcification, aortic valve disease, mediastinal mass, mediastinal lymph nodes and thyroid abnormalities). Other topics considered of lower importance or infrequent were grouped into generic categories, suitable for general statements. CONCLUSIONS: This European collaborative group has produced an incidental findings statement that can be followed during lung cancer screening. It will ensure that an evidence-based approach is used for reporting and managing incidental findings, which will mean that harms are minimised and any programme is as cost-effective as possible.

Trends in the incidence of pulmonary nodules in chest computed tomography: 10-year results from two Dutch hospitals.

OBJECTIVE: To study trends in the incidence of reported pulmonary nodules and stage I lung cancer in chest CT. METHODS: We analyzed the trends in the incidence of detected pulmonary nodules and stage I lung cancer in chest CT scans in the period between 2008 and 2019. Imaging metadata and radiology reports from all chest CT studies were collected from two large Dutch hospitals. A natural language processing algorithm was developed to identify studies with any reported pulmonary nodule. RESULTS: Between 2008 and 2019, a total of 74,803 patients underwent 166,688 chest CT examinations at both hospitals combined. During this period, the annual number of chest CT scans increased from 9955 scans in 6845 patients in 2008 to 20,476 scans in 13,286 patients in 2019. The proportion of patients in whom nodules (old or new) were reported increased from 38% (2595/6845) in 2008 to 50% (6654/13,286) in 2019. The proportion of patients in whom significant new nodules (≥ 5 mm) were reported increased from 9% (608/6954) in 2010 to 17% (1660/9883) in 2017. The number of patients with new nodules and corresponding stage I lung cancer diagnosis tripled and their proportion doubled, from 0.4% (26/6954) in 2010 to 0.8% (78/9883) in 2017. CONCLUSION: The identification of incidental pulmonary nodules in chest CT has steadily increased over the past decade and has been accompanied by more stage I lung cancer diagnoses. CLINICAL RELEVANCE STATEMENT: These findings stress the importance of identifying and efficiently managing incidental pulmonary nodules in routine clinical practice. KEY POINTS: • The number of patients who underwent chest CT examinations substantially increased over the past decade, as did the number of patients in whom pulmonary nodules were identified. • The increased use of chest CT and more frequently identified pulmonary nodules were associated with more stage I lung cancer diagnoses.

Influence of device-assisted suction against resistance (Mueller maneuver) on image quality in CTPA for suspected lung embolism.

OBJECTIVES: To investigate the effect of a device-assisted suction against resistance Mueller maneuver (MM) on transient interruption of contrast (TIC) in the aorta and pulmonary trunk (PT) on computed tomography pulmonary angiogram (CTPA). METHODS: In this prospective single-center study, 150 patients with suspected pulmonary artery embolism were assigned randomly with two different breathing maneuvers (Mueller maneuver (MM) or standard end-inspiratory breath-hold command (SBC)) during routine CTPA. The MM was performed using a patented prototype (Contrast Booster™) which allows both the patient by means of visual feedback and the medical staff in the CT scanning room to monitor whether the patient is sucking sufficiently or not. Mean Hounsfield attenuation in descending aorta and PT was measured and compared. RESULTS: Overall, patients with MM showed an attenuation of 338.24 HU in the pulmonary trunk, compared to 313.71 HU in SBC (p = 0.157). In the aorta, the values for MM were lower compared to SBC (134.42 HU vs. 177.83 HU, p = 0.001). The TP-aortic ratio was significantly higher in the MM group at 3.86 compared to the SBC group at 2.26, p = 0.001. TIC phenomenon was absent in the MM group, whereas it was present in 9 patients (12.3%) in the SBC group (p = 0.005). Overall contrast was better on all levels for MM (p < 0.001). The presence of breathing artifacts was higher in the MM group (48.1% vs. 30.1%, p = 0.038), without clinical consequence. CONCLUSIONS: Performing the MM with the application of the prototype is an effective way of preventing the TIC phenomenon during i.v. contrast-enhanced CTPA scanning compared to the standard end-inspiratory breathing command. CLINICAL RELEVANCE: Compared to standard end-inspiratory breathing command, the device-assisted Mueller maneuver (MM) improves contrast enhancement and prevents the transient interruption of contrast (TIC) phenomenon in CTPA. Therefore, it may offer optimized diagnostic workup and timely treatment for patients with pulmonary embolism. KEY POINTS: • Transient interruption of contrast (TIC) may impair image quality in CTPA. • Mueller Maneuver using a device prototype could lower the rate of TIC. • Device application in clinical routine may increase diagnostic accuracy.

Abdominopelvic CT Image Quality: Evaluation of Thin (0.5-mm) Slices Using Deep Learning Reconstruction.

BACKGROUND. Because thick-section images (typically 3-5 mm) have low image noise, radiologists typically use them to perform clinical interpretation, although they may additionally refer to thin-section images (typically 0.5-0.625 mm) for problem solving. Deep learning reconstruction (DLR) can yield thin-section images with low noise. OBJECTIVE. The purpose of this study is to compare abdominopelvic CT image quality between thin-section DLR images and thin- and thick-section hybrid iterative reconstruction (HIR) images. METHODS. This retrospective study included 50 patients (31 men and 19 women; median age, 64 years) who underwent abdominopelvic CT between June 15, 2020, and July 29, 2020. Images were reconstructed at 0.5-mm section using DLR and at 0.5-mm and 3.0-mm sections using HIR. Five radiologists independently performed pairwise comparisons (0.5-mm DLR and either 0.5-mm or 3.0-mm HIR) and recorded the preferred image for subjective image quality measures (scale, -2 to 2). The pooled scores of readers were compared with a score of 0 (denoting no preference). Image noise was quantified using the SD of ROIs on regions of homogeneous liver. RESULTS. For comparison of 0.5-mm DLR images and 0.5-mm HIR images, the median pooled score was 2 (indicating a definite preference for DLR) for noise and overall image quality and 1 (denoting a slight preference for DLR) for sharpness and natural appearance. For comparison of 0.5-mm DLR and 3.0-mm HIR, the median pooled score was 1 for the four previously mentioned measures. These assessments were all significantly different (p < .001) from 0. For artifacts, the median pooled score for both comparisons was 0, which was not significant for comparison with 3.0-mm HIR (p = .03) but was significant for comparison with 0.5-mm HIR (p < .001) due to imbalance in scores of 1 (n = 28) and -1 (slight preference for HIR, n = 1). Noise for 0.5-mm DLR was lower by mean differences of 12.8 HU compared with 0.5-mm HIR and 4.4 HU compared with 3.0-mm HIR (both p < .001). CONCLUSION. Thin-section DLR improves subjective image quality and reduces image noise compared with currently used thin- and thick-section HIR, without causing additional artifacts. CLINICAL IMPACT. Although further diagnostic performance studies are warranted, the findings suggest the possibility of replacing current use of both thin- and thick-section HIR with the use of thin-section DLR only during clinical interpretations.

Multi-source data approach for personalized outcome prediction in lung cancer screening: update from the NELSON trial.

Trials show that low-dose computed tomography (CT) lung cancer screening in long-term (ex-)smokers reduces lung cancer mortality. However, many individuals were exposed to unnecessary diagnostic procedures. This project aims to improve the efficiency of lung cancer screening by identifying high-risk participants, and improving risk discrimination for nodules. This study is an extension of the Dutch-Belgian Randomized Lung Cancer Screening Trial, with a focus on personalized outcome prediction (NELSON-POP). New data will be added on genetics, air pollution, malignancy risk for lung nodules, and CT biomarkers beyond lung nodules (emphysema, coronary calcification, bone density, vertebral height and body composition). The roles of polygenic risk scores and air pollution in screen-detected lung cancer diagnosis and survival will be established. The association between the AI-based nodule malignancy score and lung cancer will be evaluated at baseline and incident screening rounds. The association of chest CT imaging biomarkers with outcomes will be established. Based on these results, multisource prediction models for pre-screening and post-baseline-screening participant selection and nodule management will be developed. The new models will be externally validated. We hypothesize that we can identify 15-20% participants with low-risk of lung cancer or short life expectancy and thus prevent ~140,000 Dutch individuals from being screened unnecessarily. We hypothesize that our models will improve the specificity of nodule management by 10% without loss of sensitivity as compared to assessment of nodule size/growth alone, and reduce unnecessary work-up by 40-50%.

A Bayesian estimation method for cerebral blood flow measurement by area-detector CT perfusion imaging.

PURPOSE: Bayesian estimation with advanced noise reduction (BEANR) in CT perfusion (CTP) could deliver more reliable cerebral blood flow (CBF) measurements than the commonly used reformulated singular value decomposition (rSVD). We compared the efficacy of CBF measurement by CTP using BEANR and rSVD, evaluating both relative to N-isopropyl-p-[(123) I]- iodoamphetamine (123I-IMP) single-photon emission computed tomography (SPECT) as a reference standard, in patients with cerebrovascular disease. METHODS: Thirty-one patients with suspected cerebrovascular disease underwent both CTP on a 320 detector-row CT system and SPECT. We applied rSVD and BEANR in the ischemic and contralateral regions to create CBF maps and calculate CBF ratios from the ischemic side to the healthy contralateral side (CBF index). The analysis involved comparing the CBF index between CTP methods and SPECT using Pearson's correlation and limits of agreement determined with Bland-Altman analyses, before comparing the mean difference in the CBF index between each CTP method and SPECT using the Wilcoxon matched pairs signed-rank test. RESULTS: The CBF indices of BEANR and 123I-IMP SPECT were significantly and positively correlated (r = 0.55, p < 0.0001), but there was no significant correlation between the rSVD method and SPECT (r = 0.15, p > 0.05). BEANR produced smaller limits of agreement for CBF than rSVD. The mean difference in the CBF index between BEANR and SPECT differed significantly from that between rSVD and SPECT (p < 0.001). CONCLUSIONS: BEANR has a better potential utility for CBF measurement in CTP than rSVD compared to SPECT in patients with cerebrovascular disease.

Scan-based competing death risk model for re-evaluating lung cancer computed tomography screening eligibility.

BACKGROUND: A baseline computed tomography (CT) scan for lung cancer (LC) screening may reveal information indicating that certain LC screening participants can be screened less, and instead require dedicated early cardiac and respiratory clinical input. We aimed to develop and validate competing death (CD) risk models using CT information to identify participants with a low LC risk and a high CD risk. METHODS: Participant demographics and quantitative CT measures of LC, cardiovascular disease and chronic obstructive pulmonary disease were considered for deriving a logistic regression model for predicting 5-year CD risk using a sample from the National Lung Screening Trial (n=15 000). Multicentric Italian Lung Detection data were used to perform external validation (n=2287). RESULTS: Our final CD model outperformed an external pre-scan model (CD Risk Assessment Tool) in both the derivation (area under the curve (AUC) 0.744 (95% CI 0.727-0.761) and 0.677 (95% CI 0.658-0.695), respectively) and validation cohorts (AUC 0.744 (95% CI 0.652-0.835) and 0.725 (95% CI 0.633-0.816), respectively). By also taking LC incidence risk into consideration, we suggested a risk threshold where a subgroup (6258/23 096 (27%)) was identified with a number needed to screen to detect one LC of 216 (versus 23 in the remainder of the cohort) and ratio of 5.41 CDs per LC case (versus 0.88). The respective values in the validation cohort subgroup (774/2287 (34%)) were 129 (versus 29) and 1.67 (versus 0.43). CONCLUSIONS: Evaluating both LC and CD risks post-scan may improve the efficiency of LC screening and facilitate the initiation of multidisciplinary trajectories among certain participants.

Comprehensive Health Assessment 3 Months After Recovery From Acute Coronavirus Disease 2019 (COVID-19).

BACKGROUND: Long-term health sequelae of coronavirus disease 2019 (COVID-19) may be multiple but have thus far not been systematically studied. METHODS: All patients discharged after COVID-19 from the Radboud University Medical Center, Nijmegen, the Netherlands, were consecutively invited to a multidisciplinary outpatient facility. Also, nonadmitted patients with mild disease but with symptoms persisting >6 weeks could be referred by general practitioners. Patients underwent a standardized assessment including measurements of lung function, chest computed tomography (CT)/X-ray, 6-minute walking test, body composition, and questionnaires on mental, cognitive, health status, and quality of life (QoL). RESULTS: 124 patients (59 ±â€…14 years, 60% male) were included: 27 with mild, 51 with moderate, 26 with severe, and 20 with critical disease. Lung diffusion capacity was below the lower limit of normal in 42% of discharged patients. 99% of discharged patients had reduced ground-glass opacification on repeat CT imaging, and normal chest X-rays were found in 93% of patients with mild disease. Residual pulmonary parenchymal abnormalities were present in 91% of discharged patients and correlated with reduced lung diffusion capacity. Twenty-two percent had low exercise capacity, 19% low fat-free mass index, and problems in mental and/or cognitive function were found in 36% of patients. Health status was generally poor, particularly in the domains functional impairment (64%), fatigue (69%), and QoL (72%). CONCLUSIONS: This comprehensive health assessment revealed severe problems in several health domains in a substantial number of ex-COVID-19 patients. Longer follow-up studies are warranted to elucidate natural trajectories and to find predictors of complicated long-term trajectories of recovery.

Deep Learning for Malignancy Risk Estimation of Pulmonary Nodules Detected at Low-Dose Screening CT.

Background Accurate estimation of the malignancy risk of pulmonary nodules at chest CT is crucial for optimizing management in lung cancer screening. Purpose To develop and validate a deep learning (DL) algorithm for malignancy risk estimation of pulmonary nodules detected at screening CT. Materials and Methods In this retrospective study, the DL algorithm was developed with 16 077 nodules (1249 malignant) collected -between 2002 and 2004 from the National Lung Screening Trial. External validation was performed in the following three -cohorts -collected between 2004 and 2010 from the Danish Lung Cancer Screening Trial: a full cohort containing all 883 nodules (65 -malignant) and two cancer-enriched cohorts with size matching (175 nodules, 59 malignant) and without size matching (177 -nodules, 59 malignant) of benign nodules selected at random. Algorithm performance was measured by using the area under the receiver operating characteristic curve (AUC) and compared with that of the Pan-Canadian Early Detection of Lung Cancer (PanCan) model in the full cohort and a group of 11 clinicians composed of four thoracic radiologists, five radiology residents, and two pulmonologists in the cancer-enriched cohorts. Results The DL algorithm significantly outperformed the PanCan model in the full cohort (AUC, 0.93 [95% CI: 0.89, 0.96] vs 0.90 [95% CI: 0.86, 0.93]; P = .046). The algorithm performed comparably to thoracic radiologists in cancer-enriched cohorts with both random benign nodules (AUC, 0.96 [95% CI: 0.93, 0.99] vs 0.90 [95% CI: 0.81, 0.98]; P = .11) and size-matched benign nodules (AUC, 0.86 [95% CI: 0.80, 0.91] vs 0.82 [95% CI: 0.74, 0.89]; P = .26). Conclusion The deep learning algorithm showed excellent performance, comparable to thoracic radiologists, for malignancy risk estimation of pulmonary nodules detected at screening CT. This algorithm has the potential to provide reliable and reproducible malignancy risk scores for clinicians, which may help optimize management in lung cancer screening. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Tammemägi in this issue.

Chest CT in the Emergency Department for Diagnosis of COVID-19 Pneumonia: Dutch Experience.

Background Clinicians need to rapidly and reliably diagnose coronavirus disease 2019 (COVID-19) for proper risk stratification, isolation strategies, and treatment decisions. Purpose To assess the real-life performance of radiologist emergency department chest CT interpretation for diagnosing COVID-19 during the acute phase of the pandemic, using the COVID-19 Reporting and Data System (CO-RADS). Materials and Methods This retrospective multicenter study included consecutive patients who presented to emergency departments in six medical centers between March and April 2020 with moderate to severe upper respiratory symptoms suspicious for COVID-19. As part of clinical practice, chest CT scans were obtained for primary work-up and scored using the five-point CO-RADS scheme for suspicion of COVID-19. CT was compared with severe acute respiratory syndrome coronavirus 2 reverse-transcription polymerase chain reaction (RT-PCR) assay and a clinical reference standard established by a multidisciplinary group of clinicians based on RT-PCR, COVID-19 contact history, oxygen therapy, timing of RT-PCR testing, and likely alternative diagnosis. Performance of CT was estimated using area under the receiver operating characteristic curve (AUC) analysis and diagnostic odds ratios against both reference standards. Subgroup analysis was performed on the basis of symptom duration grouped presentations of less than 48 hours, 48 hours through 7 days, and more than 7 days. Results A total of 1070 patients (median age, 66 years; interquartile range, 54-75 years; 626 men) were included, of whom 536 (50%) had a positive RT-PCR result and 137 (13%) of whom were considered to have a possible or probable COVID-19 diagnosis based on the clinical reference standard. Chest CT yielded an AUC of 0.87 (95% CI: 0.84, 0.89) compared with RT-PCR and 0.87 (95% CI: 0.85, 0.89) compared with the clinical reference standard. A CO-RADS score of 4 or greater yielded an odds ratio of 25.9 (95% CI: 18.7, 35.9) for a COVID-19 diagnosis with RT-PCR and an odds ratio of 30.6 (95% CI: 21.1, 44.4) with the clinical reference standard. For symptom duration of less than 48 hours, the AUC fell to 0.71 (95% CI: 0.62, 0.80; P < .001). Conclusion Chest CT analysis using the coronavirus disease 2019 (COVID-19) Reporting and Data System enables rapid and reliable diagnosis of COVID-19, particularly when symptom duration is greater than 48 hours. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Elicker in this issue.

Automated Assessment of COVID-19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence.

Background The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients with chest infections suspected to be caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the COVID-19 Reporting and Data System (CO-RADS) and CT severity scoring systems. Materials and Methods The CO-RADS AI system consists of three deep-learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19, and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who underwent a nonenhanced chest CT examination because of clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic analysis, linearly weighted κ values, and classification accuracy. Results A total of 105 patients (mean age, 62 years ± 16 [standard deviation]; 61 men) and 262 patients (mean age, 64 years ± 16; 154 men) were evaluated in the internal and external test sets, respectively. The system discriminated between patients with COVID-19 and those without COVID-19, with areas under the receiver operating characteristic curve of 0.95 (95% CI: 0.91, 0.98) and 0.88 (95% CI: 0.84, 0.93), for the internal and external test sets, respectively. Agreement with the eight human observers was moderate to substantial, with mean linearly weighted κ values of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion With high diagnostic performance, the CO-RADS AI system correctly identified patients with COVID-19 using chest CT scans and assigned standardized CO-RADS and CT severity scores that demonstrated good agreement with findings from eight independent observers and generalized well to external data. © RSNA, 2020 Supplemental material is available for this article.

Combining pulmonary and cardiac computed tomography biomarkers for disease-specific risk modelling in lung cancer screening.

OBJECTIVES: Combined assessment of cardiovascular disease (CVD), COPD and lung cancer may improve the effectiveness of lung cancer screening in smokers. The aims were to derive and assess risk models for predicting lung cancer incidence, CVD mortality and COPD mortality by combining quantitative computed tomography (CT) measures from each disease, and to quantify the added predictive benefit of self-reported patient characteristics given the availability of a CT scan. METHODS: A survey model (patient characteristics only), CT model (CT information only) and final model (all variables) were derived for each outcome using parsimonious Cox regression on a sample from the National Lung Screening Trial (n=15 000). Validation was performed using Multicentric Italian Lung Detection data (n=2287). Time-dependent measures of model discrimination and calibration are reported. RESULTS: Age, mean lung density, emphysema score, bronchial wall thickness and aorta calcium volume are variables that contributed to all final models. Nodule features were crucial for lung cancer incidence predictions but did not contribute to CVD and COPD mortality prediction. In the derivation cohort, the lung cancer incidence CT model had a 5-year area under the receiver operating characteristic curve of 82.5% (95% CI 80.9-84.0%), significantly inferior to that of the final model (84.0%, 82.6-85.5%). However, the addition of patient characteristics did not improve the lung cancer incidence model performance in the validation cohort (CT model 80.1%, 74.2-86.0%; final model 79.9%, 73.9-85.8%). Similarly, the final CVD mortality model outperformed the other two models in the derivation cohort (survey model 74.9%, 72.7-77.1%; CT model 76.3%, 74.1-78.5%; final model 79.1%, 77.0-81.2%), but not the validation cohort (survey model 74.8%, 62.2-87.5%; CT model 72.1%, 61.1-83.2%; final model 72.2%, 60.4-84.0%). Combining patient characteristics and CT measures provided the largest increase in accuracy for the COPD mortality final model (92.3%, 90.1-94.5%) compared to either other model individually (survey model 87.5%, 84.3-90.6%; CT model 87.9%, 84.8-91.0%), but no external validation was performed due to a very low event frequency. CONCLUSIONS: CT measures of CVD and COPD provides small but reproducible improvements to nodule-based lung cancer risk prediction accuracy from 3 years onwards. Self-reported patient characteristics may not be of added predictive value when CT information is available.

Deep learning-based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms.

OBJECTIVES: To evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT). METHODS: Cerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests. RESULTS: For all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively. CONCLUSIONS: With a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times. KEY POINTS: • Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction. • Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction. • Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time.

Lung cancer screening by nodule volume in Lung-RADS v1.1: negative baseline CT yields potential for increased screening interval.

OBJECTIVES: The 2019 Lung CT Screening Reporting & Data System version 1.1 (Lung-RADS v1.1) introduced volumetric categories for nodule management. The aims of this study were to report the distribution of Lung-RADS v1.1 volumetric categories and to analyse lung cancer (LC) outcomes within 3 years for exploring personalized algorithm for lung cancer screening (LCS). METHODS: Subjects from the Multicentric Italian Lung Detection (MILD) trial were retrospectively selected by National Lung Screening Trial (NLST) criteria. Baseline characteristics included selected pre-test metrics and nodule characterization according to the volume-based categories of Lung-RADS v1.1. Nodule volume was obtained by segmentation with dedicated semi-automatic software. Primary outcome was diagnosis of LC, tested by univariate and multivariable models. Secondary outcome was stage of LC. Increased interval algorithms were simulated for testing rate of delayed diagnosis (RDD) and reduction of low-dose computed tomography (LDCT) burden. RESULTS: In 1248 NLST-eligible subjects, LC frequency was 1.2% at 1 year, 1.8% at 2 years and 2.6% at 3 years. Nodule volume in Lung-RADS v1.1 was a strong predictor of LC: positive LDCT showed an odds ratio (OR) of 75.60 at 1 year (p < 0.0001), and indeterminate LDCT showed an OR of 9.16 at 2 years (p = 0.0068) and an OR of 6.35 at 3 years (p = 0.0042). In the first 2 years after negative LDCT, 100% of resected LC was stage I. The simulations of low-frequency screening showed a RDD of 13.6-21.9% and a potential reduction of LDCT burden of 25.5-41%. CONCLUSIONS: Nodule volume by semi-automatic software allowed stratification of LC risk across Lung-RADS v1.1 categories. Personalized screening algorithm by increased interval seems feasible in 80% of NLST eligible. KEY POINTS: • Using semi-automatic segmentation of nodule volume, Lung-RADS v1.1 selected 10.8% of subjects with positive CT and 96.87 relative risk of lung cancer at 1 year, compared to negative CT. • Negative low-dose CT by Lung-RADS v1.1 was found in 80.6% of NLST eligible and yielded 40 times lower relative risk of lung cancer at 2 years, compared to positive low-dose CT; annual screening could be preference sensitive in this group. • Semi-automatic segmentation of nodule volume and increased screening interval by volumetric Lung-RADS v1.1 could retrospectively suggest a 25.5-41% reduction of LDCT burden, at the cost of 13.6-21.9% rate of delayed diagnosis.