Prevalence and variables associated with solitary pulmonary nodules in a routine clinic-based population: a cross-sectional study

Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification

The accuracy of predictive models for solitary pulmonary nodule (SPN) diagnosis can be greatly increased by incorporating repeat imaging and medical context, such as electronic health records (EHRs). However, clinically routine modalities such as imaging and diagnostic codes can be asynchronous and irregularly sampled over different time scales which are obstacles to longitudinal multimodal learning. In this work, we propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from routinely collected EHRs for SPN classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans. Our classifier is pretrained on 2,668 scans from a public dataset and 1,149 subjects with longitudinal chest CTs, billing codes, medications, and laboratory tests from EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs revealed a significant AUC improvement over a longitudinal multimodal baseline (0.824 vs 0.752 AUC), as well as improvements over a single cross-section multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741 AUC). This work demonstrates significant advantages with a novel approach for co-learning longitudinal imaging and non-imaging phenotypes with transformers. Code available at https://github.com/MASILab/lmsignatures.

Detection of circulating rare cells benefitted the diagnosis of malignant solitary pulmonary nodules

INTRODUCTION

Solitary pulmonary nodules (SPNs) are challenging in differentiating between benignancy and malignancy. Therefore, more effective non-invasive biomarkers are urgently needed. The purpose of this investigation was to examine whether circulating rare cells (CRCs) could facilitate the differentiation between benign and malignant SPNs as well as its sensitivity and specificity.

METHODS

164 patients diagnosed with SPNs, 24 healthy volunteers, and 25 patients diagnosed with advanced-stage lung cancer were included. CT/PET-CT images, serum tumor markers, and biopsy results were collected. The CRCs were examined using subtraction enrichment and immunostaining-fluorescence in situ hybridization (SE-iFISH) and their relationship with malignant or benign SPNs was analyzed.

RESULTS

The total CRC numbers from patients with malignant SPNs diagnosed by biopsy were significantly greater compared to those with benign SPNs (P < 0.0001), but not significantly different from patients with advanced lung cancer (P > 0.05). The total CRCs, with a cut-off value of 21.5 units, showed 67.6% sensitivity and 73.3% specificity [area under curve (AUC) 95% CI, 0.778 (0.666-0.889)] in discriminating benign and malignant SPNs and the triploid CRCs exhibited a high positive likelihood ratio of 8.4, which suggested that CRCs appeared to have a distinct advantage in discriminating benign and malignant SPNs compared to CT/PET-CT images and serum tumor markers and could be a potential screening indicator for lung cancer in the high-risk population.

CONCLUSIONS

SE-iFISH could effectively detect CRCs including circulating tumor cells (CTCs) and circulating tumor-derived endothelial cells (CTECs) and the detection of CRCs could benefit the differentiation of patients with benign and malignant SPNs.

Differences in the clinical management of women and men after detection of a solitary pulmonary nodule in clinical practice

OBJECTIVES

To explore differences in the clinical management of men and women in the 5 years after detecting a solitary pulmonary nodule (SPN) by chest radiograph or CT in routine clinical practice.

METHODS

We followed up 545 men and 347 women with an SPN detected by chest radiograph or CT in a retrospective cohort of 25,422 individuals undergoing routine thoracic imaging in 2010-2011. We compared the frequency of each management strategy (no further test, immediate intervention or follow up) according to sex by means of chi-squared. We estimated the relative risk of women versus men of having been followed up instead of an immediate intervention using multivariate logistic regression. We compared by sex the time between detection of the nodule and lung cancer diagnosis, the time between diagnosis and death by means of Mann-Whitney U test and the cumulative effective dose of radiation in each management strategy by means of t test.

RESULTS

Women were more likely than men to have follow-up rather than immediate intervention (aRR = 1.8, CI 1.3-2.7, p = 0.002), particularly in those who underwent CT (aRR = 4.2, CI 1.9-9.3, p < 0.001). The median time between SPN detection and lung cancer diagnosis was higher in women (4.2 months, interquartile range (IQR) 5.1) than in men (1.5 months, IQR 16.2). The mean cumulative effective dose was 21.3 mSv, 19.4 mSv in men and 23.9mv in women (p = 0.023).

CONCLUSIONS

Our results could reflect decisions based on a greater suspicion of lung cancer in men. The incidental detection of SPNs is increasing, and it is necessary to establish clear strategies aimed to reduce variability in their management according to patient's sex.

KEY POINTS

• After incidental finding of SPN, women were less likely to receive an immediate intervention. • Accumulative radiation was higher in women than in men. • Our results could reflect decisions based on a greater suspicion of lung cancer in men.

How to avoid describing your radiological research study incorrectly

Abstract

This review identifies and examines terms used to describe a radiological research “study” or “trial”. A taxonomy of clinical research descriptions is explained with reference to medical imaging examples. Because many descriptive terms have precise methodological implications, it is important that these terms are understood by readers and used correctly by researchers, so that the reader is not misled.

Key Points

• Multiple different terms are being used to describe radiological research “studies” and “trials”, and many of these terms have precise methodological implications.

• Radiological researchers sometimes use titles that describe their research incorrectly. This can mislead the reader as to what was actually done.

• It is important that readers and researchers understand the correct taxonomy of clinical research and that researchers adopt the correct description for their work.

Assessment of Fluorodeoxyglucose F18-Labeled Positron Emission Tomography for Diagnosis of High-Risk Lung Nodules

Importance

Clinicians rely heavily on fluorodeoxyglucose F18-labeled positron emission tomography (FDG-PET) imaging to evaluate lung nodules suspicious for cancer. We evaluated the performance of FDG-PET for the diagnosis of malignancy in differing populations with varying cancer prevalence.

Objective

To determine the performance of FDG-PET/computed tomography (CT) in diagnosing lung malignancy across different populations with varying cancer prevalence.

Design, Setting, and Participants

Multicenter retrospective cohort study at 6 academic medical centers and 1 Veterans Affairs facility that comprised a total of 1188 patients with known or suspected lung cancer from 7 different cohorts from 2005 to 2015.

Exposures

18F fluorodeoxyglucose PET/CT imaging.

Main Outcome and Measures

Final diagnosis of cancer or benign disease was determined by pathological tissue diagnosis or at least 18 months of stable radiographic follow-up.

Results

Most patients were male smokers older than 60 years. Overall cancer prevalence was 81% (range by cohort, 50%-95%). The median nodule size was 22 mm (interquartile range, 15-33 mm). Positron emission tomography/CT sensitivity and specificity were 90.1% (95% CI, 88.1%-91.9%) and 39.8% (95% CI, 33.4%-46.5%), respectively. False-positive PET scans occurred in 136 of 1188 patients. Positive predictive value and negative predictive value were 86.4% (95% CI, 84.2%-88.5%) and 48.7% (95% CI, 41.3%-56.1%), respectively. On logistic regression, larger nodule size and higher population cancer prevalence were both significantly associated with PET accuracy (odds ratio, 1.027; 95% CI, 1.015-1.040 and odds ratio, 1.030; 95% CI, 1.021-1.040, respectively). As the Mayo Clinic model-predicted probability of cancer increased, the sensitivity and positive predictive value of PET/CT imaging increased, whereas the specificity and negative predictive value dropped.

Conclusions and Relevance

High false-positive rates were observed across a range of cancer prevalence. Normal PET/CT scans were not found to be reliable indicators of the absence of disease in patients with a high probability of lung cancer. In this population, aggressive tissue acquisition should be prioritized using a comprehensive lung nodule program that emphasizes advanced tissue acquisition techniques such as CT-guided fine-needle aspiration, navigational bronchoscopy, and endobronchial ultrasonography.

Communication About the Probability of Cancer in Indeterminate Pulmonary Nodules

Importance

Clinical guidelines recommend that clinicians estimate the probability of malignancy for patients with indeterminate pulmonary nodules (IPNs) larger than 8 mm. Adherence to these guidelines is unknown.

Objectives

To determine whether clinicians document the probability of malignancy in high-risk IPNs and to compare these quantitative or qualitative predictions with the validated Mayo Clinic Model.

Design, Setting, and Participants

Single-institution, retrospective cohort study of patients from a tertiary care Department of Veterans Affairs hospital from January 1, 2003, through December 31, 2015. Cohort 1 included 291 veterans undergoing surgical resection of known or suspected lung cancer from January 1, 2003, through December 31, 2015. Cohort 2 included a random sample of 239 veterans undergoing inpatient or outpatient pulmonary evaluation of IPNs at the hospital from January 1, 2003, through December 31, 2012.

Exposures

Clinician documentation of the quantitative or qualitative probability of malignancy.

Main Outcomes and Measures

Documentation from pulmonary and/or thoracic surgery clinicians as well as information from multidisciplinary tumor board presentations was reviewed. Any documented quantitative or qualitative predictions of malignancy were extracted and summarized using descriptive statistics. Clinicians' predictions were compared with risk estimates from the Mayo Clinic Model.

Results

Of 291 patients in cohort 1, 282 (96.9%) were men; mean (SD) age was 64.6 (9.0) years. Of 239 patients in cohort 2, 233 (97.5%) were men; mean (SD) age was 65.5 (10.8) years. Cancer prevalence was 258 of 291 cases (88.7%) in cohort 1 and 110 of 225 patients with a definitive diagnosis (48.9%) in cohort 2. Only 13 patients (4.5%) in cohort 1 and 3 (1.3%) in cohort 2 had a documented quantitative prediction of malignancy prior to tissue diagnosis. Of the remaining patients, 217 of 278 (78.1%) in cohort 1 and 149 of 236 (63.1%) in cohort 2 had qualitative statements of cancer risk. In cohort 2, 23 of 79 patients (29.1%) without any documented malignancy risk statements had a final diagnosis of cancer. Qualitative risk statements were distributed among 32 broad categories. The most frequently used statements aligned well with Mayo Clinic Model predictions for cohort 1 compared with cohort 2. The median Mayo Clinic Model-predicted probability of cancer was 68.7% (range, 2.4%-100.0%). Qualitative risk statements roughly aligned with Mayo predictions.

Conclusions and Relevance

Clinicians rarely provide quantitative documentation of cancer probability for high-risk IPNs, even among patients drawn from a broad range of cancer probabilities. Qualitative statements of cancer risk in current practice are imprecise and highly variable. A standard scale that correlates with predicted cancer risk for IPNs should be used to communicate with patients and other clinicians.

The determinants of lung cancer after detecting a solitary pulmonary nodule are different in men and women, for both chest radiograph and CT

Objectives

To determine the factors associated with lung cancer diagnosis and mortality after detecting a solitary pulmonary nodule (SPN) in routine clinical practice, in men and in women for both chest radiograph and CT.

Materials and methods

A 5-year follow-up of a retrospective cohort of of 25,422 (12,594 men, 12,827 women) patients aged ≥35 years referred for chest radiograph or CT in two hospitals in Spain (2010–2011). SPN were detected in 893 (546 men, 347 women) patients. We estimated the cumulative incidence of lung cancer at 5-years, the association of patient and nodule characteristics with SPN malignancy using Poisson logistic regression, stratifying by sex and type of imaging test. We calculated lung cancer specific mortality rate by sex and SPN detection and hazard rates by cox regression.

Results

133 (14.9%) out of 893 patients with an SPN and 505 (2.06%) of the 24,529 patients without SPN were diagnosed with lung cancer. Median diameter of SPN in women who developed cancer was larger than in men. Men who had a chest radiograph were more likely to develop a lung cancer if the nodule was in the upper-lobes, which was not the case for women. In patients with an SPN, smoking increased the risk of lung cancer among men (chest radiograph: RR = 11.3, 95%CI 1.5–83.3; CT: RR = 7.5, 95%CI 2.2, 26.0) but smoking was not significantly associated with lung cancer diagnosis or mortality among women with an SPN. The relative risk of lung cancer diagnosis in women with SPN versus those without was much higher compared to men (13.7; 95%CI 9.2, 20.4 versus 6.2; 95%CI 4.9,7.9).

Conclusion

The factors associated with SPN malignancy and 5-year lung cancer mortality were different among men and women, especially regarding smoking history and SPN characteristics, where we observed a relatively high rate of lung cancer diagnosis among female non-smokers.

Oblique views of chest radiography from a designed rotation angle recommendation increase the contrast ratio between obscured lesions and surrounding structures

Background

Chest radiography (CXR) is the main tool used to detect pulmonary nodules. Lateral views of CXR are less effective and the aim of our study was to develop a rotation angle recommendation model to obtain the best oblique CXR with significantly increased contrast between lesions and surrounding normal structures in order to enhance the detection rate for potential obscured lesions on traditional posterior and anterior (PA) CXR.

Methods

A total of 140 subjects receiving low‐dose lung computed tomography (CT) screening were enrolled from the health check‐up database. An additional 14 cases with lung lesions on chest CT were included. Demography was also reviewed. Gross, left and right cardiothoracic ratios (CTR) were measured. All CT images were transformed to CXR to detect the best rotation angles and produce different views of CXR. Contrast ratio was calculated in the transformed CXR from CT with lesions. Comparison of contrast ratio among oblique, posterior‐anterior and lateral views was performed.

Results

CXR shows smaller gross CTR and left CTR but larger heart width and thoracic width in men than in women. Correlation evaluation displays gross CTR, heart width and left CTR are positively correlated with age only for the women group. The most important factor for the best rotation angle is right CTR for left rotation angle and left CTR for right rotation angle. The contrast ratio of the lesion to surrounding structures is significantly better on the oblique views in the designed angles than that on the traditional views.

Conclusion

CXR oblique views in the assigned angle from the 10‐degree rotation angle recommendation are able to enhance contrast ratio between the possible obscured lesions and surrounding structures on CXR.

[Combined use of thin-section CT and 18F-FDG PET/CT for characterization of solitary pulmonary nodules]

OBJECTIVE

To investigate whether fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) combined with thin-section CT improves the diagnostic performance for solitary pulmonary nodules (SPNs).

METHODS

A total of 267 patients underwent examinations with 18F-FDG PET/CT and thin-section CT for evaluating the SPNs with undetermined nature, which was further confirmed by pathological examination or clinical follow-up. The performance of two diagnostic criteria based on findings in PET/CT alone (Criterion 1) and in PET/CT combined with thin-section CT (Criterion 2) were compared.

RESULTS

Thin-section CT provided greater diagnostic information for SPNs in 84.2% of the patients. Compared with Criterion 1, the diagnosis based on Criterion 2 significantly increased the diagnostic sensitivity (80.4% vs 91%, P&lt;0.01) and accuracy (76.4% vs 87.2%, P<0.01) for lung cancer. The lesion size and the CT features including lobulation, air bronchogram, and feeding vessel, but not SUV_max, were all helpful for characterizing non-solid SPNs. Thin-section CT rectified diagnostic errors in 50% (20/40) of the cancerous lesions, which had been diagnosed as benign by PET due to their low metabolism. For non-solid SPNs, Criterion 2 showed a significantly higher diagnostic sensitivity than Criterion 1 (90.0% vs 40.0%, P=0.000) but their diagnostic specificity were comparable (75.2% vs 58.3%, P=0.667). For solid nodules, the use of thin-section CT resulted in no significant improvement in the diagnostic performance (P>0.05).

CONCLUSION

The combination of PET/CT and thin-section CT creates a synergistic effect for the characterization of SPNs, especially non-solid nodules.

The additional value of the lateral chest radiograph for the detection of small pulmonary nodules-a ROC analysis

OBJECTIVE

For the past 30 years, many authors have described different advantages of the use of the additional lateral chest radiograph. However, some radiologic departments gave up performing the lateral view recently. A potential reason for this might be a lack of evidence for any diagnostic benefit of the additional lateral view of the thorax in recent studies. The objective of this study was to evaluate the diagnostic benefit of the additional lateral view for the detection of small pulmonary nodules compared with CT examinations as a gold standard.

METHOD

The patient population consisted of 45 patients with SPN and 45 patients without SPN. Four radiologists with varying experience in the assessment of thoracic imaging first examined the sole posteroanterior (PA) projection. After a few days, they were instructed to examine the PA and the additional lateral view. A receiver-operating characteristic analysis was accomplished to compare the documented results.

RESULTS

The mean Az value of the sole PA view was 0.75 and 0.77 by the combination of PA and additional lateral view. So, there was no significant difference between the detectable Az values (Δ = 0.02; p = 0.384). With a cut-off value of >3, the additional view even reduced the sensitivity by averaging to 5.6%. The decrease of sensitivity by using the additional view was most detectable within the group of more experienced radiologists.

CONCLUSION

The additional lateral view of the chest provides no diagnostic benefit in the detection of small pulmonary nodules in comparison with the sole PA projection. Nevertheless, the results of the present study must not be understood as a general evaluation of the benefits of the lateral radiograph per se, because we did not examine other relevant issues (i.e. cardiac failure, lung parenchyma diseases or abnormalities in hilar anatomy). Advances in knowledge: Our study demonstrates a lack of evidence for any diagnostic benefit of the additional lateral view of the thorax in detecting SPN.

The Fate of Patients with Solitary Pulmonary Nodules: Clinical Management and Radiation Exposure Associated

Background

The appropriate management of the large number of lung nodules detected during the course of routine medical care presents a challenge. We aimed to evaluate the usual clinical practice in solitary pulmonary nodule (SPN) management and associated radiation exposure.

Methods

We examined 893 radiology reports of consecutive patients undergoing chest computed tomography (CT) and radiography at two public hospitals in Spain. Information on diagnostic procedures from SPN detection and lung cancer diagnosis was collected prospectively for 18 months.

Results

More than 20% of patients with SPN detected on either chest radiograph (19.8%) or CT (26.1%) underwent no additional interventions and none developed lung cancer (100% negative predictive value). 346 (72.0%) patients with SPN detected on chest radiograph and 254 (61.5%) patients with SPN detected on CT had additional diagnostic tests and were not diagnosed with lung cancer. In patients undergoing follow-up imaging for SPNs detected on CT median number of additional imaging tests was 3.5 and the mean cumulative effective dose was 24.4 mSv; for those detected on chest radiograph the median number of additional imaging tests was 2.8 and the mean cumulative effective dose was 10.3 mSv.

Conclusions

Patients who did not have additional interventions were not diagnosed of lung cancer. There was an excessive amount of interventions in a high percentage of patients presenting SPN, which was associated with an excess of radiation exposure.

Thoracic Malignancies and Pulmonary Nodules in Patients under Evaluation for Transcatheter Aortic Valve Implantation (TAVI): Incidence, Follow Up and Possible Impact on Treatment Decision

BACKGROUND

Transcatheter aortic valve implantation (TAVI) has become the treatment of choice in patients with severe aortic valve stenosis who are not eligible for operative replacement and an alternative for those with high surgical risk. Due to high age and smoking history in a high proportion of TAVI patients, suspicious findings are frequently observed in pre-procedural chest computer tomography (CCT).

METHODS

CCT scans of 484 consecutive patients undergoing TAVI were evaluated for incidentally discovered solitary pulmonary nodules (SPN).

RESULTS

In the entire study population, SPN ≥ 5 mm were found in 87 patients (18%). These patients were compared to 150 patients who were incidentally collected from the 397 patients without SPN or with SPN < 5 mm (control group). After a median follow-up of 455 days, lung cancer was diagnosed in only two patients. Neither SPN ≥ 5 mm (p = 0.579) nor SPN > 8 mm (p = 0.328) were significant predictors of overall survival.

CONCLUSIONS

Despite the high prevalence of SPNs in this single center TAVI cohort lung cancer incidence at midterm follow-up seems to be low. Thus, aggressive diagnostic approaches for incidentally discovered SPN during TAVI evaluation should not delay the treatment of aortic stenosis. Unless advanced thoracic malignancy is obvious, the well documented reduction of morbidity and mortality by TAVI outweighs potentially harmful delays regarding further diagnostics. Standard guideline-approved procedure for SPN can be safely performed after TAVI.

When and how should patients with multiple endocrine neoplasia type 1 be screened for thymic and bronchial carcinoid tumours?

Patients with multiple endocrine neoplasia type 1 (MEN1) are commonly evaluated for clinical manifestations of this syndrome with the rationale that early diagnosis and adequate treatment will result in improved survival and quality of life. Thymic and bronchial carcinoid tumours are uncommon but important manifestations of MEN1. Current practice guidelines recommend evaluation with computed tomography or magnetic resonance imaging scan of the chest every 1-2 years to detect these neoplasms. However, the certainty that patients will be better off (increased survival or quality of life) as a result of this case detection strategy is based on evidence at moderate-high risk of bias that yields only imprecise results of indirect relevance to these patients. In order to improve the care that patients with MEN1 receive, co-ordinated efforts from different stakeholders are required so that large, prospective, multicentre studies evaluating patient important outcomes are carried out.

Significance of pulmonary nodules in multi-detector computed tomography scan of noncancerous patients

Background:

Computed tomography (CT) scan is one the most useful devices in chest imaging. CT scan can be used in mediastinal abnormality, lungs, and pleural evaluations. According to the high prevalence and different causes of pulmonary nodules, we designed this study to evaluate the prevalence and the types of pulmonary nodules in noncancerous patients who underwent chest multi-detector CT (MDCT) scan.

Materials and Methods:

This was a cross-sectional study which was in our hospital to evaluate the prevalence of pulmonary nodules in noncancerous patients who underwent MDCT. A checklist was used for data collection containing number, location, size, and shape of pulmonary nodules if present in CT scan, and we also included patient's age and history of smoking. We analyzed the data with Statistical Program for Social Sciences software (version 18).

Results:

In this study, 115 patients (40%) had a pulmonary nodule. The mean number of a total nodule in each patient was 0.8 ± 0.07. Mean number of intra-parenchymal, sub pleural, and perivascular nodules were 0.34 ± 0.04, 0.31 ± 0.04, and 0.14 ± 0.02, respectively. The mean number of calcified nodules was 0.13 ± 0.02. There was no significant correlation between age and nodule characteristics (P > 0.05).

Conclusion:

The prevalence of pulmonary nodules was quite frequent in MDCT scan of noncancerous cases. So, it should not be overvalued in noncancerous cases.

Using Clinical Risk Models for Lung Nodule Classification

Evaluation and diagnosis of indeterminate pulmonary nodules is a significant and increasing burden on our health care system. The advent of lung cancer screening with low-dose computed tomography only exacerbates this problem, and more surgeons will be evaluating smaller and screening discovered nodules. Multiple calculators exist that can help the clinician diagnose lung cancer at the bedside. The Prostate, Lung, Colorectal and Ovarian Cancer (PLCO) model helps to determine who needs lung cancer screening, and the McWilliams and Mayo models help to guide the primary care clinician or pulmonologist with diagnosis by estimating the probability of cancer in patients with indeterminate pulmonary nodules. The Thoracic Research Evaluation And Treatment (TREAT) model assists surgeons to determine who needs a surgical biopsy among patients referred for suspicious lesions. Additional work is needed to develop decision support tools that will facilitate the use of these models in clinical practice, to complement the clinician's judgment and enhance shared decision making with the patient at the bedside.