Low-dose Lung Cancer Screening Research Articles

Auto-machine learning for opportunistic thyroid nodule detection in lung cancer screening chest CT.

e13639 Background: Automated Machine Learning (Auto-ML) in medical imaging is a process that allows non-experts to utilize machine learning techniques, opening the door for non-coder physician-driven exploitation of the technology. Auto-ML was applied for opportunistic detection of thyroid nodules in the context of low-dose lung cancer screening chest CT, facilitated by an innovative platform integration. By leveraging scans originally intended for lung cancer screening, suspicious appearing asymptomatic thyroid nodules can also be screened for where technically feasible. Methods: CT scans from the National Lung Screening Trial (NLST) dataset were utilized. This dataset contains low-dose chest CT examinations initially used for lung cancer screening. Annotation was carried out within a no-code web-based platform, Gesund.ai. A board-certified diagnostic radiologist annotated 100 CT examinations. A case was labeled "suspicious" if it presented a thyroid nodule of 1 cm or greater in diameter, while cases with no such nodules were deemed "not suspicious." The Auto-ML feature was then engaged within the software platform for parameter adjustments to refine the model without the need for manual coding. This phase was characterized by an iterative exploration of model performance, facilitated by the platform’s robust validation tools. Results: Upon training and validation, the Auto-ML model, cultivated from 100 annotated cases and assessed against a separate set of 130 cases, demonstrated a discernment accuracy of 0.51 in identifying "suspicious" thyroid nodules with a sensitivity and precision of 0.51 and 0.62 respectively. The AUC for this class stands at 0.69, indicating a moderate ability to distinguish between the presence and absence of thyroid nodules. This metric, while foundational, offers insight into the model's potential efficacy in real-world diagnostic scenarios, reflecting the initial capabilities of the platform's Auto-ML integration in enhancing diagnostic processes. Conclusions: The findings from this study highlight the potential of Auto-ML in revolutionizing opportunistic screening for thyroid nodules via lung cancer CT. The initial accuracy rate underscores the necessity for further refinement and validation of the model, but also demonstrates the promising potential of Auto-ML. Institutional Auto-ML would include extraction of appropriate studies through the no-code software platform integrated directly within the PACS framework. This process would ensure data immobility and foster a secure environment for dataset creation. Annotation would be carried out by multiple physician imagers within the same facility, enhancing the data’s accuracy and comprehensiveness specific for the institution’s patient population. This exploration highlights the strategic role of Auto-ML in advancing cancer patient care through innovative technological integration.

Coronary Artery Calcification on Low-Dose Lung Cancer Screening CT in South Korea: Visual and Artificial Intelligence-Based Assessment and Association With Cardiovascular Events.

BACKGROUND. Coronary artery calcification (CAC) on lung cancer screening low-dose chest CT (LDCT) is a cardiovascular risk marker. South Korea was the first Asian country to initiate a national LDCT lung cancer screening program, although CAC-related outcomes are poorly explored. OBJECTIVE. The purpose of this article is to evaluate CAC prevalence and severity using visual analysis and artificial intelligence (AI) methods and to characterize CAC's association with major adverse cardiovascular events (MACEs) in patients undergoing LDCT in Korea's national lung cancer screening program. METHODS. This retrospective study included 1002 patients (mean age, 62.4 ± 5.4 [SD] years; 994 men, eight women) who underwent LDCT at two Korean medical centers between April 2017 and May 2023 as part of Korea's national lung cancer screening program. Two radiologists independently assessed CAC presence and severity using visual analysis, consulting a third radiologist to resolve differences. Two AI software applications were also used to assess CAC presence and severity. MACE occurrences were identified by EMR review. RESULTS. Interreader agreement for CAC presence and severity, expressed as kappa, was 0.793 and 0.671, respectively. CAC prevalence was 53.4% by consensus visual assessment, 60.1% by AI software I, and 56.6% by AI software II. CAC severity was mild, moderate, and severe by consensus visual analysis in 28.0%, 10.3%, and 15.1%; by AI software I in 39.9%, 14.0%, and 6.2%; and by AI software II in 34.9%, 14.3%, and 7.3%. MACEs occurred in 36 of 625 (5.6%) patients with follow-up after LDCT (median, 1108 days). MACE incidence in patients with no, mild, moderate, and severe CAC for consensus visual analysis was 1.1%, 5.0%, 2.9%, and 8.6%, respectively (p < .001); for AI software I, it was 1.3%, 3.0%, 7.9%, and 11.3% (p < .001); and for AI software II, it was 1.2%, 3.4%, 7.7%, and 9.6% (p < .001). CONCLUSION. For Korea's national lung cancer screening program, MACE occurrence increased significantly with increasing CAC severity, whether assessed by visual analysis or AI software. The study is limited by the large sex imbalance for Korea's national lung cancer screening program. CLINICAL IMPACT. The findings provide reference data for health care practitioners engaged in developing and overseeing national lung cancer screening programs, highlighting the importance of routine CAC evaluation.

Deep learning analysis of epicardial adipose tissue to predict cardiovascular risk in heavy smokers

BackgroundHeavy smokers are at increased risk for cardiovascular disease and may benefit from individualized risk quantification using routine lung cancer screening chest computed tomography. We investigated the prognostic value of deep learning-based automated epicardial adipose tissue quantification and compared it to established cardiovascular risk factors and coronary artery calcium.MethodsWe investigated the prognostic value of automated epicardial adipose tissue quantification in heavy smokers enrolled in the National Lung Screening Trial and followed for 12.3 (11.9–12.8) years. The epicardial adipose tissue was segmented and quantified on non-ECG-synchronized, non-contrast low-dose chest computed tomography scans using a validated deep-learning algorithm. Multivariable survival regression analyses were then utilized to determine the associations of epicardial adipose tissue volume and density with all-cause and cardiovascular mortality (myocardial infarction and stroke).ResultsHere we show in 24,090 adult heavy smokers (59% men; 61 ± 5 years) that epicardial adipose tissue volume and density are independently associated with all-cause (adjusted hazard ratios: 1.10 and 1.38; P < 0.001) and cardiovascular mortality (adjusted hazard ratios: 1.14 and 1.78; P < 0.001) beyond demographics, clinical risk factors, body habitus, level of education, and coronary artery calcium score.ConclusionsOur findings suggest that automated assessment of epicardial adipose tissue from low-dose lung cancer screening images offers prognostic value in heavy smokers, with potential implications for cardiovascular risk stratification in this high-risk population.

Long-term statin therapy is associated with severe coronary artery calcification.

Atherosclerosis and consequent risk of cardiovascular events or mortality can be accurately assessed by quantifying coronary artery calcium score (CACS) derived from computed tomography. HMG-CoA-reductase inhibitors (statins) are the primary pharmacotherapy used to reduce cardiovascular events, yet there is growing data that support statin use may increase coronary calcification. We set out to determine the likelihood of severe CACS in the context of chronic statin therapy. We established a retrospective, case-control study of 1,181 U.S. veterans without coronary artery disease (CAD) from a single site, the Providence VA Medical Center. Duration of statin therapy for primary prevention was divided into 5-year categorical increments. The primary outcome was CACS derived from low-dose lung cancer screening computed tomography (LCSCT), stratified by CACs severity (none = 0; mild = 1-99; moderate = 100-399; and severe ≥400 AU). Statin duration of zero served as the referent control. Ordinal logistic regression analysis determined the association between duration of statin use and CACS categories. Proportional odds assumption was tested using likelihood ratio test. Atherosclerotic cardiovascular disease (ASCVD) risk score, body mass index, and CKD (glomerular filtration rate of <60 ml/min/1.73 m2) were included in the adjustment models. The mean age of the study population was 64.7±7.2 years, and 706 (60%) patients were prescribed a statin at baseline. Duration of statin therapy was associated with greater odds of having increased CACS (>0-5 years, OR: 1.71 [CI: 1.34-2.18], p<0.001; >5-10 years, OR: 2.80 [CI: 2.01-3.90], p<0.001; >10 years, OR: 5.30 [CI: 3.23-8.70], p<0.001), and the relationship between statin duration and CACS remained significant after multivariate adjustment (>0-5 years, OR: 1.49 [CI: 1.16-1.92], p = 0.002; >5-10 years, OR: 2.38 [CI: 1.7-3.35], p<0.001; >10 years, OR: 4.48 [CI: 2.7-7.43], p<0.001). Long-term use of statins is associated with increased likelihood of severe CACS in patients with significant smoking history. The use of CACS to interpret cardiovascular event risk may require adjustment in the context of chronic statin therapy.

OA01.02 Smoking Recidivism in a Low Dose Lung Cancer Screening Program Despite Point of Care Counseling

OA01.02 Smoking Recidivism in a Low Dose Lung Cancer Screening Program Despite Point of Care Counseling

CHARACTERISTICS OF LUNG-RADS 4A AND 4B CATEGORY NODULES DETECTED DURING&#x0D; LUNG CANCER SCREENING USING LOW-DOSE COMPUTED TOMOGRAPHY

Relevance: With the introduction of low-dose lung cancer screening, it became necessary to study the radiological characteristics of detected&#x0D; nodules in order to determine the optimal tactics for managing patients, reduce mortality by detecting early stages, and also to reduce the number&#x0D; of false-positive results.&#x0D; The study aimed to investigate the radiological semiotics of lung lesions detected by low-dose lung cancer screening and classified as categories 4A and 4B according to the Lung-RADS 1.1 and establish the relationship between their characteristics and possible malignancy.&#x0D; Methods: We studied the results of 167 LDCT images of the chest. All LDCT examinations were performed on CT scanners with a low dose&#x0D; protocol that did not exceed 1 mSv.&#x0D; Results: Of the 167 identified lesions in the lungs, 89 (53.3%) were pathologically verified: 6 (7.1%) cases from the Lung-RADS 4A category&#x0D; and 83 (100%) from the Lung-RADS 4B category. According to pathomorphological examination, 74 (83.1%) out of 89 participants had malignant&#x0D; tumors. In the studied categories, the association between the development of lung cancer and gender Odds Ratio was statistically significant –&#x0D; 2.320 (95% CI 1.230-4.376). Most lung cancer cases had solid nodules (83.8%) with tuberous contours (43.2%), a density of 20-35 HU, and the&#x0D; reaction of the adjacent pleura (58.1%).&#x0D; Conclusion: The study of pathognomonic radiological characteristics of lung lesions will improve the early diagnosis of lung cancer and&#x0D; reduce the number of false-positive results.

CHARACTERISTICS OF LUNG-RADS 4A AND 4B CATEGORY NODULES DETECTED DURING LUNG CANCER SCREENING USING LOW-DOSE COMPUTED TOMOGRAPHY

Relevance: With the introduction of low-dose lung cancer screening, it became necessary to study the radiological characteristics of&#x0D; detected nodules to determine the optimal tactics for managing patients, reduce mortality by detecting early stages, and reduce the number&#x0D; of false-positive results.&#x0D; The study aimed to investigate the radiological semiotics of lung lesions detected by low-dose lung cancer screening and classified&#x0D; as categories 4A and 4B according to the Lung-RADS 1.1 and establish the relationship between their characteristics and possible malignancy.&#x0D; Methods: We studied the results of 167 LDCT images of the chest. All LDCT examinations were performed on CT scanners with a low&#x0D; dose protocol that did not exceed 1 mSv.&#x0D; Results: Of the 167 identified lesions in the lungs, 89 (53.3%) were pathologically verified: 6 (7.1%) cases from the Lung-RADS 4A&#x0D; category and 83 (100%) from the Lung-RADS 4B category. According to pathomorphological examination, 74 (83.1%) out of 89 participants had malignant tumors. In the studied categories, the association between the development of lung cancer and gender Odds Ratio was&#x0D; statistically significant – 2.320 (95% CI 1.230-4.376). Most lung cancer cases had solid nodules (83.8%) with tuberous contours (43.2%),&#x0D; a density of 20-35 HU, and the reaction of the adjacent pleura (58.1%).&#x0D; Conclusion: The study of pathognomonic radiological characteristics of lung lesions will improve the early diagnosis of lung cancer&#x0D; and reduce the number of false-positive results

Mediastinal Lymphadenopathy in the National Lung Screening Trial (NLST) Is Associated with Interval Lung Cancer.

Background There are currently no evidence-based guidelines for the management of enlarged mediastinal lymph nodes found on lung cancer screening (LCS) CT scans. Purpose To assess the frequency and clinical significance of enlarged mediastinal lymph nodes on the initial LCS CT scans in National Lung Screening Trial (NLST) participants. Materials and Methods A retrospective review of the NLST database identified all CT trial participants with at least one enlarged (≥1.0 cm) mediastinal lymph node identified by site readers on initial CT scans. Each study was reviewed independently by two thoracic radiologists to measure the two largest nodes and to record morphologic characteristics. Scans with extensively calcified mediastinal lymph nodes or nodes measuring less than 1 cm were excluded. Frequency and time to lung cancer diagnosis, lung cancer stage, and histologic findings were compared between NLST participants with and without lymphadenopathy. Results Of the 26 722 NLST participants, 422 (1.6%) had enlarged noncalcified mediastinal lymph nodes on the initial LCS CT scan. Mediastinal lymphadenopathy was associated with an increase in lung cancer cases (72 of 422 participants [17.1%; 95% CI: 13.6, 21.0] vs 1017 of 26 300 [3.9%; 95% CI: 3.6, 4.1]; P < .001), earlier diagnosis (restricted mean survival time ± standard error, 2285 days ± 44 vs 2611 days ± 2; P < .001), the presence of lung nodules (P < .001), advanced stage at presentation (22 of 72 participants [31%] with cancer at stage IIIA vs 410 of 1017 [40.3%] at stage IA; P < .001), and increased mortality (P < .001). The majority of participants with lung cancers in the LCS group with mediastinal lymphadenopathy were detected at initial LCS CT (50 of 422 participants [11.8%; 95% CI: 8.9, 15.3] vs T1-T7, 22 of 422 [5.3%; 95% CI: 3.3, 7.8]; P < .001). There was no association between mediastinal lymphadenopathy and lung cancer histologic findings, CT appearance, or location of lung nodules (P > .05 based on unadjusted pairwise association analyses). Conclusion Noncalcified mediastinal lymphadenopathy in the low-dose lung cancer screening study sample was associated with an increase in lung cancer, an earlier diagnosis, more advanced-stage disease, and increased mortality. More aggressive treatment of these patients appears warranted. © RSNA, 2021 Online supplemental material is available for this article. See also the editorials by McLoud and by Mascalchi and Zompatori in this issue.

Detectability of Lung Nodules in Ultra-low Dose CT.

Investigation of the influence of different ultra-low dose computed tomography (ULDCT) protocols on the detection of solid and subsolid nodules in a phantom study. A chest phantom with pulmonary nodules was scanned with different CT protocols ranging from ultra-low dose settings with spectral shaping to a standard low dose lung cancer screening protocol. Image analysis was performed with different reconstruction algorithms and dedicated computer aided detection (CAD), which was compared to manual readout. The highest sensitivity rates (83%) were achieved for the 90 mAs and 120 mAs protocols when reconstructed with ADMIRE 3 or 5 and manual readout. The only statistically significant difference was found for subsolid nodules with preference of manual readout compared to CAD (p<0.05). Dose levels for the mAs settings ranged from 0.029 to 0.2 mSv. Reliable detectability rates for solid nodules were achieved; CAD software did not prove reliable for subsolid nodules.

Characteristics and Outcomes of Lung Cancers Detected on Low-Dose Lung Cancer Screening CT.

Lung cancer screening (LCS) with low-dose CT (LDCT) was implemented in the United States following the National Lung Screening Trial (NLST). The real-world benefits of implementing LCS are yet to be determined with outcome-oriented data. The study objective is to investigate the characteristics and outcomes of screening-detected lung cancers. This single-institution retrospective study included LCS patients between June 2014 and December 2019. Patient demographics, number of screening rounds, imaging features, clinical workup, disease extent, histopathology, treatment, complications, and mortality outcomes of screening-detected lung cancers were extracted and compared with NLST data. LCS LDCTs (7,480) were performed on 4,176 patients. The cancer detection rate was 3.8%, higher than reported by NLST (2.4%, P < 0.0001), and cancers were most often found in patients ≥65 years (62%), older than those in NLST (41%, P < 0.0001). The patients' ethnicity was similar to NLST, P = 0.87. Most LCS-detected cancers were early stage I tumors (71% vs. 54% in NLST, P < 0.0001). Two thirds of cancers were detected in the first round of screening (67.1%) and were multifocal lung cancers in 15%. As in NLST, the complication rate after invasive workup or surgery was low (24% vs. 28% in NLST, P = 0.32). Over a median follow-up of 3.3 years, the mortality rate was 0.45%, lower than NLST (1.33%, P < 0.0001). LCS implementation achieved a higher cancer detection rate, detection of early-stage cancers, and more multifocal lung cancers compared with the NLST, with low complications and mortality. The real-world implementation of LCS has been successful for detection of lung cancer with favorable outcomes.

Reproducibility of lung nodule radiomic features: Multivariable and univariable investigations that account for interactions between CT acquisition and reconstruction parameters.

Recent studies have demonstrated a lack of reproducibility of radiomic features in response to variations in CT parameters. In addition, reproducibility of radiomic features has not been well established in clinical datasets. We aimed to investigate the effects of a wide range of CT acquisition and reconstruction parameters on radiomic features in a realistic setting using clinical low dose lung cancer screening cases. We performed univariable and multivariable explorations to consider the effects of individual parameters and the simultaneous interactions between three different acquisition/reconstruction parameters of radiation dose level, reconstructed slice thickness, and kernel. A cohort of 89 lung cancer screening patients were collected that each had a solid lung nodule >4mm diameter. A computational pipeline was used to perform a simulation of dose reduction of the raw projection data, collected from patient scans. This was followed by reconstruction of raw data with weighted filter back projection (wFBP) algorithm and automatic lung nodule detection and segmentation using a computer-aided detection tool. For each patient, 36 different image datasets were created corresponding to dose levels of 100%, 50%, 25%, and 10% of the original dose level, three slice thicknesses of 0.6mm, 1mm, and 2mm, as well as three reconstruction kernels of smooth, medium, and sharp. For each nodule, 226 well-known radiomic features were calculated at each image condition. The reproducibility of radiomic features was first evaluated by measuring the intercondition agreement of the feature values among the 36 image conditions. Then in a series of univariable analyses, the impact of individual CT parameters was assessed by selecting subsets of conditions with one varying and two constant CT parameters. In each subset, intraparameter agreements were assessed. Overall concordance correlation coefficient (OCCC) served as the measure of agreement. An OCCC≥0.9 implied strong agreement and reproducibility of radiomic features in intercondition or intraparameter comparisons. Furthermore, the interaction of CT parameters in impacting radiomic feature values was investigated via ANOVA. All included radiomic features lacked intercondition reproducibility (OCCC<0.9) among all the 36 conditions. Out of 226 radiomic features analyzed, only 17 and 18 features were considered reproducible (OCCC≥0.9) to dose and kernel variation, respectively, within the corresponding condition subsets. Slice thickness demonstrated the largest impact on radiomic feature values where only one to five features were reproducible at a few condition subsets. ANOVA revealed significant interactions (P<0.05) between CT parameters affecting the variability of >50% of radiomic features. We systematically explored the multidimensional space of CT parameters in affecting lung nodule radiomic features. Univariable and multivariable analyses of this study not only showed the lack of reproducibility of the majority of radiomic features but also revealed existing interactions among CT parameters, meaning that the effect of individual CT parameters on radiomic features can be conditional upon other CT acquisition and reconstruction parameters. Our findings advise on careful radiomic feature selection and attention to the inclusion criteria for CT image acquisition protocols within the datasets of radiomic studies.

Abstract D135: Early low-dose lung cancer screening education

Abstract Research results of the Terminate Lung Cancer (TLC) low dose CT early lung cancer screening and detection campaign in three regional study groups in rural East Kentucky. Results include the identification of effective field-tested communication protocols for lung cancer prevention, screening and detection with rural Appalachian population that included many hard to engage participants. Citation Format: David R Reese. Early low-dose lung cancer screening education [abstract]. In: Proceedings of the Twelfth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2019 Sep 20-23; San Francisco, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(6 Suppl_2):Abstract nr D135.

Patient size matters: Effect of tube current modulation on size-specific dose estimates (SSDE) and image quality in low-dose lung cancer screening CT.

PurposeWe compare the effect of tube current modulation (TCM) and fixed tube current (FTC) on size‐specific dose estimates (SSDE) and image quality in lung cancer screening with low‐dose CT (LDCT) for patients of all sizes.MethodsInitially, 107 lung screening examinations were performed using FTC, which satisfied the Centers for Medicare & Medicaid Services' volumetric CT dose index (CTDIvol) limit of 3.0 mGy for standard‐sized patients. Following protocol modification, 287 examinations were performed using TCM. Patient size and examination parameters were collected and water‐equivalent diameter (Dw) and SSDE were determined for each patient. Regression models were used to correlate CTDIvol and SSDE with Dw. Objective and subjective image quality were measured in 20 patients who had consecutive annual screenings with both FTC and TCM.ResultsCTDIvol was 2.3 mGy for all FTC scans and increased exponentially with Dw (range = 0.96–4.50 mGy, R2 = 0.73) for TCM scans. As patient Dw increased, SSDE decreased for FTC examinations (R2 = 1) and increased for TCM examinations (R2 = 0.54). Image quality measurements were superior with FTC for smaller sized patients and with TCM for larger sized patients (R2 > 0.5, P < 0.005). Radiologist graded all images acceptable for diagnostic evaluation of lung cancer screening.ConclusionAlthough FTC protocol offered a consistently low CTDIvol for all patients, it yielded unnecessarily high SSDE for small patients and increased image noise for large patients. Lung cancer screening with LDCT using TCM produces radiation doses that are appropriately reduced for small patients and increased for large patients with diagnostic image quality for all patients.

Lung Cancer Screening: How We do It and Why

Abstract Low dose lung cancer screening plays an important role in finding asymptomatic patients with potentially curable lung cancers. This exam has been rapidly implemented since the national lung cancer trial of 2011, and has been studied extensively for benefit of lung cancer–specific mortality in high risk patients. Although the exam itself is straight forward there are several considerations when beginning a screening exam. Additionally, there are challenges in reporting and the need to continually evaluate the effectiveness of, and improve delivery of, a screening program. We review the value of lung cancer screening and outline key aspects of a screening program.

Disparities in Follow-Up After Low-Dose Lung Cancer Screening

The National Lung Cancer Screening Trial (NLST) demonstrated an improvement in overall survival with lung cancer screening. Achieving follow-up for a positive screen is essential to impact early intervention for lung cancer. The objective of this study was to determine predictors of follow-up after a positive lung cancer screening test. The NLST database was queried for participants with a positive lung cancer screening exam. This cohort was then subdivided into patients who had follow-up and those who did not. Pairwise comparison was performed within different subgroups. A logistic regression model was then utilized to identify predictive factors associated with follow-up. Of the 53,454 patients who participated in the study, we identified 14,000 patients who had a positive lung cancer screening test. Of those patients, 12,503 followed up appropriately (89.3%). Women had a statistically higher follow-up rate compared to men (90% vs 88.8%, P ≤ 0.05). Patients reported as married or living as married also showed a higher rate of follow-up compared to patients reported as never married, divorced, separated, or widowed (90.2% vs 87.5%, P ≤ 0.05). The rate of follow-up among African-American patients was 82.8%, while those in white patients was 89.6%, this was statistically significant (P ≤ 0.05). Education level was not a significant factor in follow-up rates. Current smokers followed up at lower rates compared to former smokers (87.9 % vs 90.6%, P ≤ 0.05). Logistic regression determined gender, marital status, race, and smoking status to be predictors of follow-up. Follow-up rates after a positive lung cancer screening test were associated with a patient's gender, marital status, race, and smoking status.

Organ doses from CT localizer radiographs: Development, validation, and application of a Monte Carlo estimation technique.

The purpose of this study was to simulate and validate organ doses from different computed tomography (CT) localizer radiograph geometries using Monte Carlo methods for a population of patients. A Monte Carlo method was developed to estimate organ doses from CT localizer radiographs using PENELOPE. The method was validated by comparing dosimetry estimates with measurements using an anthropomorphic phantom imbedded with thermoluminescent dosimeters (TLDs) scanned on a commercial CT system (Siemens SOMATOM Flash). The Monte Carlo simulation platform was then applied to conduct a population study with 57 adult computational phantoms (XCAT). In the population study, clinically relevant chest localizer protocols were simulated with the x-ray tube in anterior-posterior (AP), right lateral, and PA positions. Mean organ doses and associated standard deviations (in mGy) were then estimated for all simulations. The obtained organ doses were studied as a function of patient chest diameter. Organ doses for breast and lung were compared across different views and represented as a percentage of organ doses from rotational CT scans. The validation study showed an agreement between the Monte Carlo and physical TLD measurements with a maximum percent difference of 15.5% and a mean difference of 3.5% across all organs. The XCAT population study showed that breast dose from AP localizers was the highest with a mean value of 0.24mGy across patients, while the lung dose was relatively consistent across different localizer geometries. The organ dose estimates were found to vary across the patient population, partially explained by the changes in the patient chest diameter. The average effective dose was 0.18mGy for AP, 0.09mGy for lateral, and 0.08mGy for PA localizer. A platform to estimate organ doses in CT localizer scans using Monte Carlo methods was implemented and validated based on comparison with physical dose measurements. The simulation platform was applied to a virtual patient population, where the localizer organ doses were found to range within 0.4%-8.6% of corresponding organ doses for a typical CT scan, 0.2%-3.3% of organ doses for a CT pulmonary angiography scan, and 1.1%-20.8% of organ doses for a low-dose lung cancer screening scan.

Low-dose lung cancer screening: nodule measurement and management

Lung cancer screening by low-dose computed tomography (LDCT) is recommended for high-risk individuals by US guidelines, while lung cancer programs in Europe and Asia are being prepared. This review will mainly focus on two most recent concepts and discusses the latest developments. First, while a pulmonary nodule has an infinite number of diameters, it possesses only one volume. Traditionally, nodule size has been determined by diameter measurement, however semi-automated measurement of nodule volume is becoming increasingly available. Secondly, nodules that develop newly after baseline should distinguished from nodules already present at baseline. Until recently, new nodule management was mostly based on expert-opinion or data derived from baseline nodules.

The Added Value of Computer-aided Detection of Small Pulmonary Nodules and Missed Lung Cancers.

Lung cancer at its earliest stage is typically manifested on computed tomography as a pulmonary nodule, which could be detected by low-dose multidetector computed tomography technology and the use of thinner collimation. Within the last 2 decades, computer-aided detection (CAD) of pulmonary nodules has been developed to meet the increasing demand for lung cancer screening computed tomography with a larger set of images per scan. This review introduced the basic techniques and then summarized the up-to-date applications of CAD systems in clinical and research programs and in the low-dose lung cancer screening trials, especially in the detection of small pulmonary nodules and missed lung cancers. Many studies have already shown that the CAD systems could increase the sensitivity and reduce the false-positive rate in the diagnosis of pulmonary nodules, especially for the small and isolated nodules. Further improvements to the current CAD schemes are needed to detect nodules accurately, particularly for subsolid nodules.

ES01.01 Image Quality Characteristics and Nodule Growth Measurement, Medical Physics and Machine Parameters

Modern CT scanners are routinely being used to determine the malignancy potential of small sub-centimeter pulmonary nodules. Increasingly, this involves CT scanning and quantitative volume measurement of lung nodules over short time intervals (e.g. 3 or 6 months) to determine whether a change in nodule size consistent with malignant growth has occurred. Although it may appear that current CT scanners are more than capable of reliably performing these quantitative measurements with high quality due to their ability to obtain sub-millimeter resolution lung images, many clinical sites are not taking the steps needed to achieve consistent high quality small lung nodule measurement results. A study of volume measurement performance in a phase II clinical trial observed multiple clinical sites using CT scanners which resulted in errors in volume change measurements as high as 43% [1]. In addition, a 2016 crowd-sourcing study of CT scanner image quality performance using the site’s low dose CT lung cancer screening acquisition protocol revealed that 37% of sites used insufficient slice thickness (<= 1.25mm slice thickness is needed) and only 19% of sites used the needed slice thickness and a reconstruction kernel that avoided excessive smoothing and avoided high levels of edge enhancement [2]. Poor CT image acquisition performance has the potential to result in poor lung nodule volume measurement performance which can negatively impact patient care by contributing to unnecessary biopsies and delays in early lung cancer diagnosis. To address these issues the RSNA’s Quantitative Imaging Biomarkers Alliance (QIBA®) has developed the QIBA CT Small Lung Nodule Profile that provides a comprehensive set of specifications to ensure that a clinical site attains a minimum level of quantitative imaging performance necessary to achieve a specified lung nodule volume measurement accuracy. The Small Lung Nodule Profile outlines six fundamental image quality characteristics that are needed throughout the full scanner field of view to support precise volumetric measurement of small lung nodules. These characteristics are (1) Edge Enhancement, (2) Three-Dimensional Resolution, (3) Resolution Aspect Ratio, (4) CT linearity, (5) Spatial Warping, and (6) Noise. In general, CT scanners achieve highest fundamental image quality performance at scanner iso-center with some scanners and image acquisition protocols exhibiting large losses in image quality performance as a function of distance from scanner iso-center [3]. These fundamental image quality properties can now be quickly and easily measured by a technologist at any clinical site using a new image quality measurement phantom and fully automated and cloud-based phantom analysis software. To determine the clinical impact of achieved CT image quality performance, a new set of modeling and simulation tools has been developed that can create simulated CT images given the image quality characteristics for a CT scanner and image acquisition protocol [4]. Quantitative measurement software can then be applied to these images resulting in expected measurement performance for a clinical task, such as the bias and precision of solid lung nodule volume change measurement for virtual lung nodules of different sizes. Having these estimates of a CT scanners performance can further be used to one day quantitatively determine the minimum time interval needed in order to be able to distinguish malignant nodule volume growth from a stable lung nodule. Regularly performing these measurements also has the potential to offer numerous advantages to lung cancer screening sites including the ability to determine if scans from two different CT scanner models will produce sufficiently similar image quality and measurement performance. In summary, a new set of phantoms and cloud-based software tools is available that enables more careful control and optimization of CT lung cancer imaging performance based on fundamental image quality properties. These new tools provide several new opportunities for clinical sites to more precisely perform CT lung cancer imaging studies and measurements. [1] Henschke CI, Yankelevitz DF, Yip R, Archer A, Zahlmann G, Krishnan K, Helba B, Avila R, “Tumor volume measurement error using computed tomography imaging in a phase II clinical trial in lung cancer.” Journal of Medical Imaging 3(3), 035505 (Jul–Sep 2016). [2] Avila R, Yankelevitz D, Yip R, Henschke C, “P1.03-021 Initial Results from A Novel and Low Cost Method For Measuring CT Image Quality,” January 2017. Journal of Thoracic Oncology 12(1):S554-S555. [3] Avila R, Subramaniam R, Henschke C, Yankelevitz D, “Hot Topic: Clinical Implications of CT Image Quality Variation in Low Dose Lung Cancer Screening Scans,” 4th World Congress of Thoracic Imaging Proceedings, Journal of Thoracic Imaging, accepted for oral presentation, 2017. [4] Avila R, Jirapatnakul A, Subramaniam R, Yankelevitz D, “A new method for predicting CT lung nodule volume measurement performance,” SPIE Medical Imaging Proceedings, 2017. "lung cancer screening", "Image Quality"

Low-dose Lung Cancer Screening at an Academic Medical Center: Initial Experience and Dose Reduction Strategies

Implementation of low dose computed tomography (LDCT) lung cancer screening programs has followed the demonstration of reduced lung cancer mortality in the National Lung Screening Trial and subsequent consensus screening recommendations. Here we aim to assess the initial results of a screening program at an academic medical center, to discuss the challenges of implementing such a program, and suggest strategies for reducing patient dose. Retrospective review of all patients who underwent LDCT lung cancer screening at our institution between March 2015 and July 2016 was performed to assess the lung cancer detection rate, the spectrum of imaging findings (nodule or mass characteristics, degree of emphysema, etc.), and patient radiation dose indices. A total of 272 patients were screened during the study period. Approximately 50% (n = 135) were women. The lung cancer detection rate was 2.2% (n = 6). One patient underwent chemoradiation therapy, whereas the remainder underwent uneventful thoracoscopic resection. Approximately, 80% of screened patients met United States Preventative Services Task Force criteria for LDCT screening. The median pack-years of smoking was 42 pack-years. The mean volume CT dose index for the screening CTs was 3.12 mGy. Utilizing tube current modulation and iterative reconstruction, where available, resulted in lower patient doses. Initial LDCT lung cancer screening at our institution yielded results similar to those of the National Lung Screening Trial. Thorough prescreening evaluation, joint decision-making, centralized coordination of screening-related care, and patient size conscious scanning protocols are critical elements of a safe and successful lung cancer screening program.