Indeterminate Lung Nodules Research Articles

B-242 Improved Patient Satisfaction With Novel Capillary Blood Collection Devices as an Alternative to Venipuncture for Applications in Clinical Proteomic Assays

Abstract Background Two new clinical diagnostic tests are available that aid in the identification of lung nodules as likely malignant or likely benign. One test is an ELISA that measures the levels of seven autoantibodies to tumor-associated antigens that aids in the identification of patients with likely malignant lung nodules who may benefit from timely intervention. The other is an LC-MS/MS-based (MRM) test that measures the ratio of two proteins (LG3BP and C163A) combined with several clinical and radiological factors to aid in the identification of patients with likely benign lung nodules who may benefit from additional CT surveillance. Since commercialization, we have found that test access may be improved by providing alternatives to traditional venipuncture. Therefore, we conducted evaluation studies with two novel non-fingerstick capillary blood collection devices. These devices puncture the skin by utilizing either microneedles (Device A) or a lancet (Device B) for capillary blood collection. Methods Blood specimens were collected from consented donors using one of the two capillary blood collection devices and by venipuncture into K2EDTA blood collection tubes. Feedback was also solicited from the healthcare professionals and donors via a standard questionnaire. The whole blood specimens were shipped to the testing laboratory where the samples were processed according to the respective clinical assay workflows. Feasibility testing for the ELISA-based assay was conducted with both devices using normal healthy donor specimens (105 donors for Device A and 43 for Device B). Clinical evaluation was executed utilizing only Device B (77 donors with lung cancer and 13 with an indeterminate lung nodule). Feasibility testing for the LC-MS/MS-based assay was conducted with both devices using healthy donor specimens (103 donors for Device A and 41 for Device B), while clinical evaluation utilized only Device B (80 donors with lung cancer and 30 with an indeterminate lung nodule). Results Both capillary blood collection devices revealed good correlations to venous blood draws for the ELISA-based test during feasibility. The two devices also showed good correlations for the LC-MS/MS-based test, with the results from Device A requiring a correction factor. Due to technical and operational challenges throughout feasibility, Device B became the preferred device to be evaluated for the clinical study. Good correlations for both diagnostic tests were observed from the clinical study. During clinical evaluation, healthcare professionals and donors were asked to rate the ease-of-use, pain, and speed of collection when using Device B. Most healthcare professionals (108/126) rated the device as easy to use. Ninety-five percent of the donors reported minimal pain while the remainder reported moderate pain. Ninety-one percent of the donors felt that the time required to collect blood using Device B was acceptable. Sixty percent of the donors preferred the capillary collection device (Device B), 17% preferred venipuncture, while 23% reported no preference for blood collection. Conclusions The novel capillary blood collection devices demonstrated high correlations for two clinical diagnostic tests. Feedback collected from healthcare professionals and donors revealed that the majority preferred the capillary blood collection device as compared to traditional venipuncture for blood collection.

Limited Additional Value of a Chest CT in Whole-Body Staging with PET-MRI: A Retrospective Cohort Study.

Hybrid PET-MRI systems are being used more frequently. One of the drawbacks of PET-MRI imaging is its inferiority in detecting lung nodules, so it is often combined with a computed tomography (CT) of the chest. However, chest CT often detects additional, indeterminate lung nodules. The objective of this study was to assess the sensitivity of detecting metastatic versus indeterminate nodules with PET-MRI compared to chest CT. A total of 328 patients were included. All patients had a PET/MRI whole-body scan for (re)staging of cancer combined with an unenhanced chest CT performed at our center between 2014 and 2020. Patients had at least a two-year follow-up. Six percent of the patients had lung metastases at initial staging. The sensitivity and specificity of PET-MRI for detecting lung metastases were 85% and 100%, respectively. The incidence of indeterminate lung nodules on chest CT was 30%. The sensitivity of PET-MRI to detect indeterminate lung nodules was poor (23.0%). The average size of the indeterminate lung nodules detected on PET-MRI was 7 ± 4 mm, and the missed indeterminate nodules on PET-MRI were 4 ± 1 mm (p < 0.001). The detection of metastatic lung nodules is fairly good with PET-MRI, whereas the sensitivity of PET-MRI for detecting indeterminate lung nodules is size-dependent. This may be an advantage, limiting unnecessary follow-up of small, indeterminate lung nodules while adequately detecting metastases.

The Role of Biomarkers in Lung Cancer Screening.

Lung Cancer Screening (LCS) is an evolving field with variations in its implementation in various countries. There are only scarce data from National LCS programs. We aim to provide an up-to-date overview of the current evidence regarding the use of biomarkers in LCS. A multidisciplinary Task Force experts' panel collaborated and conducted a systematic literature search, followed by screening, review and synthesis of available evidence. Biomarkers in LCS could be used to improve risk stratification in high-risk participants, improve clarification regarding indeterminate lung nodules and avoid overdiagnosis in suspicious lung findings. Currently, there seem to be promising biomarkers (blood/serum/breath) that have been studied in various trials; however, there is still a lack of solid evidence in clinical validation that would pave the way for their integration into LCS programs. Biomarkers are the next logical step in improving the LCS pathway and its efficiency by playing an adjuvant role in a minimally invasive way. National LCS programs and pilot studies should integrate biomarkers to validate their accuracy in real-life LCS participants.

LDCT image biomarkers that matter most for the deep learning classification of indeterminate pulmonary nodules.

Continued improvement in deep learning methodologies has increased the rate at which deep neural networks are being evaluated for medical applications, including diagnosis of lung cancer. However, there has been limited exploration of the underlying radiological characteristics that the network relies on to identify lung cancer in computed tomography (CT) images. In this study, we used a combination of image masking and saliency activation maps to systematically explore the contributions of both parenchymal and tumor regions in a CT image to the classification of indeterminate lung nodules. We selected individuals from the National Lung Screening Trial (NLST) with solid pulmonary nodules 4-20 mm in diameter. Segmentation masks were used to generate three distinct datasets; 1) an Original Dataset containing the complete low-dose CT scans from the NLST, 2) a Parenchyma-Only Dataset in which the tumor regions were covered by a mask, and 3) a Tumor-Only Dataset in which only the tumor regions were included. The Original Dataset significantly outperformed the Parenchyma-Only Dataset and the Tumor-Only Dataset with an AUC of 80.80 ± 3.77% compared to 76.39 ± 3.16% and 78.11 ± 4.32%, respectively. Gradient-weighted class activation mapping (Grad-CAM) of the Original Dataset showed increased attention was being given to the nodule and the tumor-parenchyma boundary when nodules were classified as malignant. This pattern of attention remained unchanged in the case of the Parenchyma-Only Dataset. Nodule size and first-order statistical features of the nodules were significantly different with the average malignant and benign nodule maximum 3d diameter being 23mm and 12mm, respectively. We conclude that network performance is linked to textural features of nodules such as kurtosis, entropy and intensity, as well as morphological features such as sphericity and diameter. Furthermore, textural features are more positively associated with malignancy than morphological features.

Abstract 6090: Integration of innate and adaptive immune signatures for early detection of cancer

Abstract Up to 50% of cancer patients are diagnosed at a late stage with tumors that are often unresectable, leading to intensive treatments and a preventable loss of life. Whilst multiple assays have been developed to tackle the issue of disease mortality, these approaches have serious limitations. For example, circulating tumor DNA (ctDNA) preferentially detects hard-to-treat tumors and micrometastatic disease, with limited sensitivity and specificity for early-stage malignancy, underscoring an urgent need for novel early detection strategies. Substantial evidence exists to demonstrate that signals related to innate (e.g. pro-inflammatory cytokines) and adaptive (e.g. antibodies and T cell receptors [TCRs]) immune engagement arise early in the development of cancer. The immune system therefore offers potential as an exquisitely sensitive and highly specific intrinsic early detection system for cancer. Here we propose the development of a pan-cancer novel early detection assay, using peripheral blood to measure three key cancer-specific components of the anti-tumor immune response: i) T cell receptor (TCR) sequences, ii) antibody signatures, iii) cytokine markers. Our preliminary data demonstrates that an age and smoking-matched cohort of lung cancer patients can be distinguished from healthy donors using TCR sequencing data processed through a published machine learning approach (p&amp;lt;0.01). In support of this, a pilot study on a custom peptide microarray comprised of lung cancer associated antigens and recurrent neoantigens demonstrated that lung cancer patient samples show significantly higher antibody intensities than healthy donors. Thirdly, using data from a prospective cohort study, we have demonstrated that inflammatory markers can be leveraged to predict future cancer diagnosis, and identified key protein markers for future work. These data provide proof-of-principle for the use of these analytes as a tool for early detection. We are actively curating a unique cohort of samples for this work from a prospective study, Nodule Immunophenotyping Biomarker for Lung Cancer Early Diagnosis (NIMBLE) (NCT05432739), which recruits patients with indeterminate lung nodules that may represent early cancers (&amp;gt;280 patients to date). This malignancy has high mortality rates and a significant need for early detection strategies. Through this, we aim to understand the early immunobiological response to cancer and leverage this information to design a novel multi-parametric immunopredictor assay for early detection of cancer. Citation Format: Evelyn Fitzsimons, Alexander Coulton, Hongchang Fu, Marcellus Augustine, Richard Lee, James Reading, Kevin Litchfield. Integration of innate and adaptive immune signatures for early detection of cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6090.

Abstract 6104: EDRN Lung Team Project 2 validation of molecular biomarkers for the early detection of lung cancer in the setting of indeterminate pulmonary nodules

Abstract Background: The goal of the Early Detection Research Network (EDRN) Lung Team Project #2 (LTP-2) is to establish a cohort (n= 300) of high-risk people with indeterminate pulmonary nodules (6mm-30mm) to clinically validate the diagnostic accuracy of existing molecular and imaging biomarkers discovered and analytically validated through the EDRN program. These biomarkers comprise signals measured in serum (glycan or cytokine), plasma (protein, miRNA, RNA, or methylated circulating tumor DNA), airway epithelial cells (RNA or DNA), nasal brush cells (RNA or DNA), and/or chest CT images. Methods: Eligible participants had an indeterminate nodule discovered incidentally or through low-dose CT screening within 14 months prior to enrollment and were aged 45-90 years, with 20 pack-years or more cigarette smoking history, free of lung cancer, and willing to provide blood, nasal brushing, and optionally bronchoscopic brush biopsy specimens. Baseline medical and demographic data were collected from each subject. Baseline and years 1 and 2 follow-up CT images were obtained. Each specimen at each respective site was labeled with a 2-D barcode provided by the DMCC and specimen information was entered into the Validation Study Information Management System (VSIMS) developed by the EDRN Data Management and Coordinating Center (DMCC). Aliquots of blinded specimens from selected cases and controls will be dispensed to each EDRN site for biomarker analysis. Analysis plan: Primary endpoint: The positive diagnostic likelihood ratio (DLR+) will be used to measure biomarker performance within values of DLR+ &amp;gt;= 2 or DLR- &amp;lt;= 0.5, a range considered clinically useful for any patients with indeterminate lung nodules. The sample size calculation targeted &amp;gt;80% power to test the null hypotheses that a) a positive biomarker does not alter risk across a range of specificities, and b) a negative biomarker does not alter risk across a range of sensitivities. The EDRN Data Management and Coordinating Center (DMCC) will unblind and complete analysis and report results. Exploratory endpoint: The diagnostic accuracy of combined biomarkers will be calculated using a logistic regression model with flexible functional forms. Results and Discussion: More than 300 subjects were enrolled into the LTP2 cohort including a sufficient number of cases and controls (cohort size n&amp;gt;300) to reach power according to calculated estimates. Chest CT images were collected and are in the process of transfer to a central database. Plasma specimens have been distributed to test sites. RNA and DNA extraction from NBC and AEC is in process and based on results thus far the specimen quality and quantity is more than sufficient from the number of subjects needed to reach power for the primary endpoint and to conduct the planned exploratory analyses. Citation Format: James C. Willey, Eric L. Grogan, Stephen A. Deppen, James G. Herman, Michael N. Kammer, Matthew B. Schabath, Lynn Sorbara, Harvey I. Pass, Jun-Chieh J. Tsay, Ziding Feng, Avrum Spira, Erin L. Crawford, Jackie Dahlgren, Steven M. Dubinett, Kimberly R. Rieger-Christ, Marc E. Lenburg. EDRN Lung Team Project 2 validation of molecular biomarkers for the early detection of lung cancer in the setting of indeterminate pulmonary nodules [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6104.

Navigational Bronchoscopy vs CT Scan-Guided Transthoracic Needle Biopsy for the Diagnosis of Indeterminate Lung Nodules: Protocol and Rationale for the Navigation Endoscopy to Reach Indeterminate Lung Nodules vs Transthoracic Needle Aspiration, a Randomized Controlled Study Multicenter Randomized Trial

Navigational Bronchoscopy vs CT Scan-Guided Transthoracic Needle Biopsy for the Diagnosis of Indeterminate Lung Nodules: Protocol and Rationale for the Navigation Endoscopy to Reach Indeterminate Lung Nodules vs Transthoracic Needle Aspiration, a Randomized Controlled Study Multicenter Randomized Trial

The impact of pre-operative indeterminate lung nodules in the surgical management of pancreatic ductal adenocarcinoma

The impact of pre-operative indeterminate lung nodules in the surgical management of pancreatic ductal adenocarcinoma

MA11.03 First in Human Prospective Validation of Intraoperative Artificial Intelligence Guided Diagnosis of Indeterminate Lung Nodules

MA11.03 First in Human Prospective Validation of Intraoperative Artificial Intelligence Guided Diagnosis of Indeterminate Lung Nodules

Radiomics Model for Predicting Pulmonary Metastasis in Sarcoma Patients

The lung is the most common site of metastasis in localized extremity soft tissue sarcomas (STS). Indeterminant lung nodules leads to challenges for both patients and providers. As such, accuracy in the diagnosis of pulmonary metastasis (PM) is important for clinical decision making. The purpose of this is study is to develop and evaluate a CT-based radiomic model to predict PM in sarcoma patients with indeterminate pulmonary nodules. Fifty-seven stage I-III sarcoma patients with indeterminate lung nodules on unenhanced CT that were approved for this study by our institution's internal review board (IRB). Twenty-two developed and categorized as PM and 35 without PM. A total number of 322 indeterminate nodules were investigated, where 165 & 157 nodules were from patients with and without PM, respectively. A total of 96 radiomic features (RF) (including first order statistics, 2d shape features, gray level co-occurrence, gray level size zone, gray level run length, neighboring gray tone difference & gray level dependence matrices) were taken from unenhanced CT images of each patient. We included 2D shape features since the size and shape of indeterminate lung nodules may have some correlation with PM. Spearman correlation were used to rule out redundant features (r2>0.9). T-test statistics was used to determine feature with significant differences that can differentiate responders with and without PM. Support Vector Machine (SVM) model was fitted to combinations of groups of 2-3 radiomic features. The AUC of the ROC curve was used to evaluate the model performance. Pointwise confidence intervals (CI) for AUC were calculated using 100 bootstrap replicates. Four features were found significant after Spearman correlation and T-test statistical testing: 1. Maximum (MAX); 2. Minor Axis Length (MAL); 3. Gray Level Non-uniformity (GLNU); and 4. Interquartile Range (IR). The best performing 2-feature radiomic SVM model had an AUC of 0.69 (95% CI 0.61,0.74) for the MAX and GLNU features. The best performing 3-feature radiomic SVM model had an AUC of 0.74 (95% CI 0.70,0.80) for the MAX, MAL and IR features. CT-based radiomics model has the potential to be used to predict PM in sarcoma patients presenting with indeterminate lung nodules. Additional research will focus on investigating derived parameters for existing RF, such as the ratio of the max RF to mean RF, to see if they improve the predictive performance of the model, as well as testing the models on external patient cohort. These radiomic models could be useful tools in guiding PM screening and providing a patient specific monitoring of sarcoma patients.

Size measurement of lung nodules on CT: which diameter is most stable to inter-observer variability?

Indeterminate lung nodules detected on CT are common findings in the clinical practice, and the correct assessment of their size is critical for patient evaluation and management. We compared the stability of three definitions of nodule diameter (Feret's mean diameter, Martin's mean diameter and area-equivalent diameter) to inter-observer variability on a population of 336 solid nodules from 207 subjects. We found that inter-observer agreement was highest with Martin's mean diameter (intra-class correlation coefficient = 0.977, 95% Confidence interval = 0.977–0.978), followed by area-equivalent diameter (0.972, 0.971–0.973) and Feret's mean diameter (0.965, 0.964–0.966). The differences were statistically significant. In conclusion, although all the three diameter definitions achieved very good inter-observer agreement (ICC > 0.96), Martin's mean diameter was significantly better than the others. Future guidelines may consider adopting Martin's mean diameter as an alternative to the currently used Feret's (caliper) diameter for assessing the size of lung nodules on CT.

The Scan, the Needle, or the Knife? National Trends in Diagnosing Stage I Lung Cancer.

Indeterminate lung nodules have been increasingly discovered since the expansion of lung cancer screening programs. The diagnostic approach for suspicious nodules varies based on institutional resources and preferences. The aim of this study is to analyze factors associated with diagnostic modalities used for early-stage non-small cell lung cancer (NSCLC). The National Cancer Database was queried for all patients with stage I NSCLC from 2004 to 2015. Four diagnostic modalities were identified, including clinical radiography alone (CRA), bronchial cytology (BC), procedural biopsy (PB), and surgical biopsy (SB). A multivariable multinomial logistic regression was used to assess associations of patient demographics, cancer characteristics, and facility characteristics with these modalities. Of 250,614 patients, 4,233 (1.7%) had CRA, 5,226 (2.1%) had BC, 147,621 (59.9%) had PB, and 93,534 (37.3%) had SB. Older patients were more likely to receive CRA (adjusted odds ratio [ORadj] = 5.3) and less likely to receive SB (ORadj = 0.73). Black patients were less likely to receive SB (ORadj = 0.83) and more likely to receive BC (ORadj = 1.31). Private insurance was associated with SB (ORadj = 1.11), whereas Medicaid was associated with BC (ORadj = 1.21). Patients more than 50 miles from the facility were more likely to undergo SB (ORadj = 1.25 vs PB; ORadj = 1.30 vs CRA; ORadj = 1.38 vs BC). Patients receiving SB had shorter days from diagnosis to treatment (23.0 vs 53.5 to 64.7 for other modalities, P < 0.001). Diagnostic SB to confirm early-stage NSCLC was associated with younger age, greater travel distance, and shorter time to treatment in comparison with other modalities. Black race and non-private insurance were less likely to be associated with SB.

Form Factors as Potential Imaging Biomarkers to Differentiate Benign vs. Malignant Lung Lesions on CT Scans.

Indeterminate lung nodules detected on CT scans are common findings in clinical practice. Their correct assessment is critical, as early diagnosis of malignancy is crucial to maximise the treatment outcome. In this work, we evaluated the role of form factors as imaging biomarkers to differentiate benign vs. malignant lung lesions on CT scans. We tested a total of three conventional imaging features, six form factors, and two shape features for significant differences between benign and malignant lung lesions on CT scans. The study population consisted of 192 lung nodules from two independent datasets, containing 109 (38 benign, 71 malignant) and 83 (42 benign, 41 malignant) lung lesions, respectively. The standard of reference was either histological evaluation or stability on radiological followup. The statistical significance was determined via the Mann–Whitney U nonparametric test, and the ability of the form factors to discriminate a benign vs. a malignant lesion was assessed through multivariate prediction models based on Support Vector Machines. The univariate analysis returned four form factors (Angelidakis compactness and flatness, Kong flatness, and maximum projection sphericity) that were significantly different between the benign and malignant group in both datasets. In particular, we found that the benign lesions were on average flatter than the malignant ones; conversely, the malignant ones were on average more compact (isotropic) than the benign ones. The multivariate prediction models showed that adding form factors to conventional imaging features improved the prediction accuracy by up to 14.5 pp. We conclude that form factors evaluated on lung nodules on CT scans can improve the differential diagnosis between benign and malignant lesions.

The state of the art for artificial intelligence in lung digital pathology.

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

Video-assisted thoracoscopic (VATS) era in surgical treatment of spontaneous pneumothorax

Background: VATS is now regarded by many surgeons to be the gold standard in the surgical management of a variety of thoracic conditions, such as spontaneous pneumothorax (SP), pleural diseases, and indeterminate lung nodules. Aim and objectives: to describe different VATS techniques in patients with spontaneous pneumothorax.Summary: Several clinical management issues remain unanswered. Firstly, the duration of prolonged air leak that warrants VATS remain controversial. Current recommendations range from five days by BTS to three days advocated by our institute with more than a decade of experience with VATS for SP. Furthermore, whether VATS should be offered to all patients with low general anesthetic risk presenting with first episode of SP is unclear. Furthermore, the evolution of surgical techniques to allow ipsilateral thoracoscopic approach to treat contralateral bullous lesion may redefine the indications for CT scan in SP. Technically, the debate will continue among the surgeons on the type of VATS procedure that will minimize pneumothorax recurrence. Most surgeons will agree that some form of bullectomy (endoscopic staple or suturing) is mandatory. However, the nature of pleurodesis (mechanical, chemical, or both) that follow is often at the discretion of the individual clinician.

Association between Low-Dose Computed Tomography Results and 1-Year Smoking Cessation in a Residential Smoking Cessation Program.

The COVID-19 pandemic is a global health threat. Smoking and smoking-related lung diseases are risk factors for severe COVID-19 infection. This study investigated whether low-dose computed tomography (LDCT) scan results affected the success of 1-year smoking cessation. The Gyeonggi Southern Smoking Support Center performed the residential smoking cessation program from January to December 2018. During the program, LDCT was performed on 292 participants; 6 months later, follow-up via telephone or visit was conducted. Among the 179 participants who succeeded in smoking cessation for 6 months, telephone follow-up was conducted to determine whether there was a 12-month continuous smoking cessation. In order to evaluate the association between LDCT results and 12-month continuous abstinence rate (CAR), logistic regression was used to estimate the odds ratio (OR) and 95% confidence interval (CI). The CARs at 6 and 12 months were 61.3% and 31.5%, respectively. Indeterminate or suspicious malignant lung nodules were associated with a higher 12-month CAR (OR, 3.02; 95% CI, 1.15–7.98), whereas psychiatric history was associated with a lower 12-month CAR (OR, 0.06; 95% CI, 0.03–0.15). These results suggest that abnormal lung screening results may encourage smokers to quit smoking.

Comparison Between Magnetic Resonance Imaging and Computed Tomography in the Detection and Volumetric Assessment of Lung Nodules: A Prospective Study.

Rationale and ObjectivesComputed tomography (CT) lung nodule assessment is routinely performed and appears very promising for lung cancer screening. However, the radiation exposure through time remains a concern. With the overall goal of an optimal management of indeterminate lung nodules, the objective of this prospective study was therefore to evaluate the potential of optimized ultra-short echo time (UTE) MRI for lung nodule detection and volumetric assessment.Materials and MethodsEight (54.9 ± 13.2 years) patients with at least 1 non-calcified nodule ≥4 mm were included. UTE under high-frequency non-invasive ventilation (UTE-HF-NIV) and in free-breathing at tidal volume (UTE-FB) were investigated along with volumetric interpolated breath-hold examination at full inspiration (VIBE-BH). Three experienced readers assessed the detection rate of nodules ≥4 mm and ≥6 mm, and reported their location, 2D-measurements and solid/subsolid nature. Volumes were measured by two experienced readers. Subsequently, two readers assessed the detection and volume measurements of lung nodules ≥4mm in gold-standard CT images with soft and lung kernel reconstructions. Volumetry was performed with lesion management software (Carestream, Rochester, New York, USA).ResultsUTE-HF-NIV provided the highest detection rate for nodules ≥4 mm (n = 66) and ≥6 mm (n = 32) (35 and 50%, respectively). No dependencies were found between nodule detection and their location in the lung with UTE-HF-NIV (p > 0.4), such a dependency was observed for two readers with VIBE-BH (p = 0.002 and 0.03). Dependencies between the nodule's detection and their size were noticed among readers and techniques (p < 0.02). When comparing nodule volume measurements, an excellent concordance was observed between CT and UTE-HF-NIV, with an overestimation of 13.2% by UTE-HF-NIV, <25%-threshold used for nodule's growth, conversely to VIBE-BH that overestimated the nodule volume by 28.8%.ConclusionUTE-HF-NIV is not ready to replace low-dose CT for lung nodule detection, but could be used for follow-up studies, alternating with CT, based on its volumetric accuracy.

Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Centre.

Importance: The stratification of indeterminate lung nodules is a growing problem, but the burden of lung nodules on healthcare services is not well-described. Manual service evaluation and research cohort curation can be time-consuming and potentially improved by automation.Objective: To automate lung nodule identification in a tertiary cancer centre.Methods: This retrospective cohort study used Electronic Healthcare Records to identify CT reports generated between 31st October 2011 and 24th July 2020. A structured query language/natural language processing tool was developed to classify reports according to lung nodule status. Performance was externally validated. Sentences were used to train machine-learning classifiers to predict concerning nodule features in 2,000 patients.Results: 14,586 patients with lung nodules were identified. The cancer types most commonly associated with lung nodules were lung (39%), neuro-endocrine (38%), skin (35%), colorectal (33%) and sarcoma (33%). Lung nodule patients had a greater proportion of metastatic diagnoses (45 vs. 23%, p < 0.001), a higher mean post-baseline scan number (6.56 vs. 1.93, p < 0.001), and a shorter mean scan interval (4.1 vs. 5.9 months, p < 0.001) than those without nodules. Inter-observer agreement for sentence classification was 0.94 internally and 0.98 externally. Sensitivity and specificity for nodule identification were 93 and 99% internally, and 100 and 100% at external validation, respectively. A linear-support vector machine model predicted concerning sentence features with 94% accuracy.Conclusion: We have developed and validated an accurate tool for automated lung nodule identification that is valuable for service evaluation and research data acquisition.

P09.02 A Clinical Evaluation Algorithm to Define Clinical Utility of Lung Nodule Diagnosis in a Multi-Collaborator Setting Using Real World Data

New biomarkers for the diagnosis of indeterminate lung nodules (IPN) suspicious for lung cancer are being developed regularly. Clinically useful new diagnostic tests for IPN requires improvement in post-test risk classification to reduce subsequent testing or time to diagnosis. Therefore, measuring the activity to a diagnosis is needed. In a collaboration between Lahey Hospital and Medical Center (LHMC), representing a large screening only population, Vanderbilt University Medical Center (VUMC), a tertiary referral center with incidental and screening discovered nodules, and OneFlorida Clinical Research Consortium, a statewide network with incidental nodules, we defined an algorithm to combine real world data (RWD) from electronic health records (EHR) to measure the clinical activity necessary to diagnose an IPN.

Lung Metastases Versus Second Primary Lung Cancers in Patients with Primary Urothelial Carcinoma of the Bladder: A National Population-Based Assessment.

The work-up and diagnosis of indeterminate lung nodules at time of bladder cancer diagnosis may delay or change treatment. To quantify the incidence of synchronous and metachronous lung cancers in adults with bladder cancer and compare these rates to the incidence of bladder cancer metastases in the lung. We retrospectively analyzed all adults diagnosed with bladder cancer in the Surveillance, Epidemiology and End Results (SEER) registry (2010- 2015) and identified second primary lung cancers defined as being either synchronous (diagnosed within 6 months of bladder cancer diagnosis) or metachronous (more than 6 months following index bladder cancer diagnosis). The risk of second primary lung cancers were reported as a standardized incidence ratio (SIR) reflecting observed and expected case ratios. A total of 88,335 patients diagnosed with bladder cancer were included. Among adults with NMIBC (n = 66,071) and MIBC (n = 18,879), 0.3% and 3.9% had bladder cancer metastatic to the lungs at diagnosis. Synchronous second primary lung cancers were diagnosed in 0.4% and 0.7% of patients with NMIBC and MIBC, respectively. Compared to the general population, the SIR for synchronous lung cancers among adults with NMIBC was 2.5 (95% CI 2.3- 2.9) and was 4.7 (95% CI 4.0- 5.6) for adults with MIBC. Bladder cancer metastatic to the lung is more common in adults with MIBC compared to NMIBC. There are similar frequencies of synchronous second primary lung cancers regardless of initial bladder cancer stage.