Low-dose CT Research Articles

Reconstructing and analyzing the invariances of low-dose CT image denoising networks.

Deep learning-based methods led to significant advancements in many areas of medical imaging, most of which are concerned with the reduction of artifacts caused by motion, scatter, or noise. However, with most neural networks being black boxes, they remain notoriously difficult to interpret, hindering their clinical implementation. In particular, it has been shown that networks exhibit invariances w.r.t. input features, that is, they learn to ignore certain information in the inputdata. To improve the interpretability of deep learning-based low-dose CT image denoisingnetworks. We learn a complete data representation of low-dose input images using a conditional variational autoencoder (cVAE). In this representation, invariances of any given denoising network are then disentangled from the information it is not invariant to using a conditional invertible neural network (cINN). At test time, image-space invariances are generated by applying the inverse of the cINN and subsequent decoding using the cVAE. We propose two methods to analyze sampled invariances and to find those that correspond to alterations of anatomicalstructures. The proposed method is applied to four popular deep learning-based low-dose CT image denoising networks. We find that the networks are not only invariant to noise amplitude and realizations, but also to anatomicalstructures. The proposed method is capable of reconstructing and analyzing invariances of deep learning-based low-dose CT image denoising networks. This is an important step toward interpreting deep learning-based methods for medical imaging, which is essential for their clinical implementation.

A Hybrid Approach for CT Image Noise Reduction Combining Method Noise-CNN and Shearlet Transform

The presence of gaussian noise commonly weakens the diagnostic precision of low-dose CT imaging. A novel CT image denoising technique that integrates the non-subsampled shearlet transform (NSST) with Bayesian thresholding, and incorporates a modern method noise Deep Convolutional neural network (DCNN) based post-processing operation on denoised images to strengthen low-dose CT imaging quality. The hybrid method commences with NSST and Bayesian thresholding to mitigate the initial noise while preserving crucial image features, such as corners and edges. The novel aspect of the proposed approach is its successive application of a DnCNN on initial denoised image, which learns and removes residual noise patterns from denoised images, thereby enhancing fine detail preservation. This dual-phase strategy addresses both noise suppression and image-detail preservation. The proposed technique is evaluated through the use of metrics, such as PSNR, SNR, SSIM, ED, and UIQI. The results demonstrate that the hybrid approach outperforms standard denoising techniques in preserving image quality and fine details.

Circulating RKIP and pRKIP in Early-Stage Lung Cancer: Results from a Pilot Study

Background: Lung cancer (LC) is the leading cause of cancer-related deaths. Although low-dose computed tomography (LD-CT) reduces mortality, its clinical use is limited by cost, radiation, and false positives. Therefore, there is an urgent need for non-invasive and cost-effective biomarkers. The Raf Kinase Inhibitor Protein (RKIP) plays a crucial role in cancer development and progression and may also contribute to regulating the tumor–immune system axis. This protein has recently been described in biological fluids. Therefore, we conducted a pilot case–control study to assess RKIP and phosphorylated RKIP (pRKIP) levels in the urine and blood of LC patients. Methods: A novel enzyme linked immunosorbent assay (ELISA) assay was used to measure RKIP and pRKIP levels in urine and blood samples of two cohorts of LC patients and healthy controls (HSs). Furthermore, the biomarkers levels were correlated with tumor characteristics. Results: Serum, but not urine, levels of RKIP were significantly elevated in LC patients, distinguishing them from low- and high-risk healthy subjects with 93% and 74% accuracy, respectively. The RKIP/pRKIP ratio (RpR score) showed an accuracy of 90% and 79% in distinguishing LC patients from HS and HR-HS, respectively. Additionally, the RpR score correlated better with dimension, stage, and lymph node involvement in the tumor group. Conclusions: The serum RKIP and pRKIP profile may be a promising novel biomarker for early-stage LC.

Cost-effectiveness of lung cancer screening with volume computed tomography in Portugal.

Aim: Lung cancer is the most common cause of cancer death in Portugal. The Dutch-Belgian lung cancer screening (LCS) study (NELSON), the biggest European LCS study, showed a lung cancer mortality reduction in a high-risk population when being screened. In this study, the cost-effectiveness of LCS, based on the NELSON study protocol and outcomes, was evaluated compared with no screening in Portugal. Methods: The present study modified an established decision tree by incorporating a state-transition Markov model to evaluate the health-related advantages and economic implications of low-dose computed tomography (LDCT) LCS from the healthcare standpoint in Portugal. The analysis compared screening versus no screening for a high-risk population aged 50-75 with a smoking history. Various metrics, including clinical outcomes, costs, quality-adjusted life years (QALYs), life-years (LYs) and the incremental cost-effectiveness ratio (ICER), were calculated to measure the impact of LDCT LCS. Furthermore, scenario and sensitivity analyses were executed to assess the robustness of the obtained results. Results: Annual LCS with volume-based LDCT resulted in €558million additional costs and 86,678 additional QALYs resulting in an ICER of €6440 per QALY for one screening group and a lifetime horizon. In total, 13,217 premature lung cancer deaths could be averted, leading to 1.41 additional QALYs gained per individual diagnosed with lung cancer. Results are robust based on the sensitivity analyses. Conclusion: This study showed that annual LDCT LCS for a high-risk population could be cost-effective in Portugal based on a willingness to pay a threshold of one-time the GDP (€19,290 per QALY gained).

A clinically effective model based on cell-free DNA methylation and low-dose CT for risk stratification of pulmonary nodules

Accurate, non-invasive, and cost-effective tools are needed to assist pulmonary nodule diagnosis and management due to increasing detection by low-dose computed tomography (LDCT). We perform genome-wide methylation sequencing on malignant and non-malignant lung tissues and designed a panel of 263 differential DNA methylation regions, which is used for targeted methylation sequencing on blood cell-free DNA (cfDNA) in two prospectively collected and retrospectively analyzed multicenter cohorts. We develop and optimize an integrative model for risk stratification of pulmonary nodules based on 40 cfDNA methylation biomarkers, age, and five simple computed tomography (CT) imaging features using machine learning approaches and validate its good performance in two cohorts. Using the two-threshold strategy can effectively reduce unnecessary invasive surgeries, overtreatment costs, and injury for patients with benign nodules while advising immediate treatment for patients with lung cancer, which can potentially improve the overall diagnosis of lung cancer following LDCT/CT screening.

Non-small-cell lung cancer.

Non-small-cell lung cancer (NSCLC) is one of the most frequent cancer types and is responsible for the majority of cancer-related deaths worldwide. The management of NSCLC has improved considerably, especially in the past 10 years. The systematic screening of populations at risk with low-dose CT, the implementation of novel surgical and radiotherapeutic techniques and a deeper biological understanding of NSCLC that has led to innovative systemic treatment options have improved the prognosis of patients with NSCLC. In non-metastatic NSCLC, the combination of various perioperative strategies and adjuvant immunotherapy in locally advanced disease seem to enhance cure rates. In metastatic NSCLC, the implementation of novel drugs might prolong disease control together with preserving quality of life. The further development of predictive clinical and genetic markers will be essential for the next steps in individualized treatment concepts.

Coronary artery calcification detected on low-dose computed tomography in high-risk participants of an Australian lung cancer screening program: A prospective observational study.

Coronary artery calcification (CAC) is a frequent additional finding on lung cancer screening (LCS) low-dose computed tomography (LDCT). Cardiovascular disease (CVD) is a major cause of death in LCS participants. We aimed to describe prevalence of incidental CAC detected on LDCT in LCS participants without prior history of coronary artery disease (CAD), evaluate their CVD risk and describe subsequent investigation and management. Prospective observational nested cohort study including all participants enrolled at a single Australian site of the International Lung Screen Trial. Baseline LDCTs were reviewed for CAC, and subsequent information collected regarding cardiovascular health. 5-year CVD risk was calculated using the AusCVD risk calculator. 55% (226/408) of participants had CAC on LDCT and no prior history of CAD, including 23% with moderate-severe CAC. Mean age of participants with CAC was 65 years, 68% were male. 53% were currently smoking. Majority were high risk (51%) or intermediate risk (32%) of a cardiovascular event in 5 years. 21% of participants were re-stratified to a higher CVD risk group when CAC detected on LCS was incorporated. Only 10% of participants with CAC received lifestyle advice (only 3% currently smoking received smoking cessation advice). 80% of participants at high-risk did not meet guideline recommendations, with 47% of this group remaining without cholesterol lowering therapy. LCS with LDCT offers the potential to identify and communicate CVD risk in this population. This may improve health outcomes for high-risk LCS participants and further personalize management once screening results are known.

Noise suppression in photon-counting computed tomography using unsupervised Poisson flow generative models

Deep learning (DL) has proven to be important for computed tomography (CT) image denoising. However, such models are usually trained under supervision, requiring paired data that may be difficult to obtain in practice. Diffusion models offer unsupervised means of solving a wide range of inverse problems via posterior sampling. In particular, using the estimated unconditional score function of the prior distribution, obtained via unsupervised learning, one can sample from the desired posterior via hijacking and regularization. However, due to the iterative solvers used, the number of function evaluations (NFE) required may be orders of magnitudes larger than for single-step samplers. In this paper, we present a novel image denoising technique for photon-counting CT by extending the unsupervised approach to inverse problem solving to the case of Poisson flow generative models (PFGM)++. By hijacking and regularizing the sampling process we obtain a single-step sampler, that is NFE = 1. Our proposed method incorporates posterior sampling using diffusion models as a special case. We demonstrate that the added robustness afforded by the PFGM++ framework yields significant performance gains. Our results indicate competitive performance compared to popular supervised, including state-of-the-art diffusion-style models with NFE = 1 (consistency models), unsupervised, and non-DL-based image denoising techniques, on clinical low-dose CT data and clinical images from a prototype photon-counting CT system developed by GE HealthCare.

“I've been really happy since I got that letter!”: Longitudinal patient perspectives on lung cancer screening communication

ObjectiveExperts recommend structured shared decision making when discussing lung cancer screening (LCS) and reporting low-dose computed tomography (LDCT) results. We examined patients' reactions to pre- and post-LDCT results communication processes at three medical centers in the US with established LCS programs. MethodsMulticenter, qualitative, longitudinal study of patients considering and receiving LCS using data from semi-structured interviews guided by a patient-centered communication model using conventional content analysis. We conducted 61 interviews among 32 patients (sixteen of whom had a nodule on their LDCT) at one month and 12 months after an initial LCS decision making interaction. ResultsParticipants were mostly satisfied with LCS communication processes pre- and post-LDCT even though guideline concordant shared decision making was rare. Most participants reported no more than mild distress even if the LDCT detected a pulmonary nodule, felt relief after getting the results, and reported the perceived benefits of LCS outweighed their distress. Nearly all participants were satisfied with recommended follow-up plans. They reported that they trusted their clinicians and health care system to provide appropriate care and recommendations. They did not appear to regret their decision since almost all participants planned to get their next LDCT. However, they were at risk of non-adherence to follow-up recommendations since they often relied on the health care system to ensure they received timely follow-up. ConclusionsDespite receiving guideline discordant decision-making communication, patients seem very satisfied, rarely experience severe distress, and have low decisional regret after LCS decision making and receiving the results of their LDCT.

Abstract A132: Missed Opportunities? Regional availability of Low Dose CT lung cancer screening facility locations in the year prior to diagnoses: A descriptive comparison of American Indian and Non-Hispanic White lung cancer patients in North Carolina

Abstract INTRODUCTION American Indians (AI) have much higher incidence rates of lung cancer (LC) compared with non-Hispanic Whites (NHW) in the US. While low-dose computed tomography (LDCT) screening facilitates early detection of lung cancer, it is unknown how available LDCT screenings are to racially and geographically diverse populations in North Carolina (NC). To address this gap in knowledge, we conducted a descriptive study to characterize incident LC cases among AIs and NHWs, the distance from their location at diagnosis to the nearest LDCT screening facility and explored whether distance was associated with late-stage LC diagnoses. Methods Data were obtained from the Cancer Information and Population Health Resource (CIPHR), which comprise data from NC Central Cancer Registry (CCR) as well as public and private health insurance claims for the state. We identified ZIP codes and dates of rendered service for facilities providing LDCT by searching through claims from 2015-20. In addition, we identified incident LC cases among AIs and NHWs aged ≥18 years, from 2015-19. We assembled lists of LDCT facilities that existed in the year prior to each incident LC case. We calculated the minimum centroid to centroid distance to all facilities. Clinical attributes included age at diagnosis, sex, histology, stage at diagnosis, and rurality as measured by Rural Urban Commuting Area. Risk ratios were calculated for late-stage LC diagnoses across a range of thresholds for patient’s distance to nearest LDCT screening facility for AIs and NHWs. Results We identified 388 AI and 26,867 NHW incident LC cases in NC between 2015-20. Compared to NHWs, the median age at diagnosis for AIs was 5 years younger (AI: 65 vs. NHW: 69); more frequently male (AI: 54% vs NHW: 51%); and almost twice as likely to reside in rural areas (AI: 52% vs. NHW: 28%). There were no differences in late-stage LC diagnoses (AI: 54% vs. NHW: 52%). For distance (in miles) to the nearest LDCT screening facility, the median [Interquartile range] was twice as high for AIs (9.9 miles [0.8, 16.30]) compared to NHWs (5.3 miles [0, 12.1]). Among NHWs, there were statistically significant associations between distance and late-stage LC diagnosis at the shortest distance threshold of 5 miles (RR=1.04; 95%CL: 1.02, 1.07) through the threshold of 30 miles (RR=1.10 95%CL: 1.05, 1.15). There was no association across any distance threshold among AI lung cancer patients. Conclusions The large difference in accessibility of LDCT screening was not strongly associated with metastatic lung cancer diagnoses, possibly because so many patients were diagnosed late, reflecting poor early detection across all populations. We found that 80% of AIs with LC lived more than 10 miles away from LDCT screening facilities. This geographic distance may increase difficulty accessing cancer care geographically, and contribute to suboptimal LC screening rates. If efforts are to be made to increase early detection and improve survival, accessibility needs to be addressed on different dimensions. Citation Format: Bradford E. Jackson, Marc Emerson, Daniel Carrizosa, Chris Baggett, Lisa Spees, Joel Begay, Ana Salas, Yadurshirni Raveendran, Tomi Akinyemiju, Rachel Denlinger-Apte, Stephanie Wheeler, Ronny Bell. Missed Opportunities? Regional availability of Low Dose CT lung cancer screening facility locations in the year prior to diagnoses: A descriptive comparison of American Indian and Non-Hispanic White lung cancer patients in North Carolina [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A132.

Abstract B037: Reach of digital interventions to address disparities in repeat lung cancer screening in Washington State

Abstract Lung cancer is the leading cause of cancer morbidity and mortality in the United States. Annual screening with low-dose computed tomography (LDCT) reduces lung cancer mortality. However, annual adherence to screening is suboptimal. To improve annual adherence to lung cancer screening (LCS), additional patient education beyond shared-decision making is needed to normalize the screening process. Interventions which leverage digital modes of delivery might have broad reach, but only if patients actively engage with messages from clinical providers. Furthermore, there may be disparities in access to digital communication by patient demographics which will need to be addressed to advance health equity through digital technology. The objective of this study was to understand factors associated with engagement with patient portal messaging. This study was nested within a pragmatic clinical trial to test the “Patient Voices Video” relative to usual care to determine if participants opened video intervention communication delivered through the patient portal. The video-based intervention (Patient Voices Video) incorporated patient testimonials to acknowledge LCS receipt, reminds patients they are due in 12 months for next scan, and reassurance to reduce fear of LCS and role of loved ones to support health choices. Study participants were Kaiser Permanente Washington members aged 50-78 years with recent normal LCS scan and were randomized to either Patient Voices Video or usual care. Study analyses were restricted to those assigned to video arm. Participants randomized to the video arm received a web link via a patient portal message 3 weeks after normal scan. We generated descriptive statistics to summarize differences in proportions in pre-specified demographic factors associated with opening the video message in the patient portal among those in the video arm and registered in patient portal (n=614). Overall, 85% of participants opened their patient portal message. Patient factors associated with not opening patient portal message included: current tobacco use (currently smoking 56% in group that did not open portal message vs 42% in group that opened portal message) and race/ethnicity (18% non-White in group that did not open portal message vs 10% in group that opened portal message). A higher proportion (8%) of those in non-metro areas opened portal message compared to 3% not opening message. There were no differences in likelihood of opening the portal message by age, sex, prior LCS experience, or area deprivation. Patient portal messages can be a successful delivery mode for LCS interventions with high utilization, but disparities in reach are still prevalent by race and ethnicity and tobacco status. Citation Format: Anjali Vasavada, Lorella Palazzo, Matthew Triplette, Hongyuan Gao, Melissa Anderson, Casey Luce, Yu-Ru Su, James Ralston, Kristine Rogers, Nadia Bezman, Beverly B Green, Lisa Carter-Bawa, Karen J Wernli. Reach of digital interventions to address disparities in repeat lung cancer screening in Washington State [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B037.

Abstract A125: A nationwide initiative to expand access to lung cancer screening: Results and impact of the Color/American Cancer Society Lung Screening Access Program

Abstract Lung cancer is a leading health challenge in the United States – it is the third most common cancer and disproportionately impacts people of color. Early detection of lung cancer is possible through routine screenings using low-dose lung CT scans. Despite the efficacy of screening, 80-85% of people eligible for screening are not up-to-date. The underutilization of regular screening has often been attributed to gaps in primary care and insufficient support following an abnormal result. In an effort to improve access, Color and the American Cancer Society (ACS), launched a nationwide initiative to make lung cancer screening readily accessible and free across all 50 states based on ACS guidelines. The program simplifies the screening process by managing all logistical steps from physician orders to finding and booking appointments at local clinics to assisting with next steps if abnormalities are detected.Since the program launched in November 2023, 74 people completed the online health risk assessment. On average participants were 54 years of age (range: 18-81 years), 64% (n=41) female, and 65% (n=48) White. 28% (n=19) respondents currently smoked, 50% (n=34) had a former history of smoking, and average smoking history was 23.0 pack years (range: 0.1 - 66 pack years). While the program primarily supports individuals who meet ACS lung screening guidelines, all participants can speak with a clinician about screening.Of those who completed the health risk assessment, 45.6% (n=31) met ACS eligibility criteria for lung screening. Eligible participants were on average 62 years of age (range: 51 - 77 years), 74% (n=23) were female, and 87% (n=27) were White. Eligible participants resided in 21 states, with Georgia and Ohio having the highest number of eligible individuals.To date, 9 people have completed a lung CT and 3 are in progress of scheduling. On average, appointments were scheduled within 25 days from the initial referral submission (range: 8-55 days) and all appointments were within 17 miles from the individual’s preferred location (average: 6.8 miles, range: 0.5-17 miles).3 participants had a change in their lung screening plan based on their result, with 2 participants having Lung-RADS 3 category nodules (follow-up in 6 months) and 1 having Lung-RADS 4A nodules (follow-up in 6 months). Other findings included an ascending aortic aneurysm (4.2 cm), a hiatal hernia, an indeterminate adrenal nodule, and mild coronary artery calcification, some of which required additional follow-up care with a PCP or cardiologist within 3-12 months. No participants were recommended to have immediate diagnostic testing for lung cancer based on their results. The Color/ACS Lung Screening Access Program demonstrates the impact that a virtual lung cancer screening program has on closing screening gaps. It underscores the critical role of supporting patients not only in undergoing cancer screening, but also in navigating the complexities of follow-up care, thereby enhancing the overall efficacy of lung cancer prevention and early detection strategies. Citation Format: Deanna Brockman, Jennifer Fung, Ashly Emig, Gabrielle Hands, Wendy McKennon, Jennifer Cho, Robert Smith, William Dahut, Alicia Zhou, Keegan Duchicela. A nationwide initiative to expand access to lung cancer screening: Results and impact of the Color/American Cancer Society Lung Screening Access Program [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A125.

Abstract B046: Factors influencing patient decision-making to complete Low Dose CT screening for lung cancer

Abstract As part of a randomized, controlled trial (RCT) to increase lung cancer screening (LCS) with low-dose CT scan (LDCT) within the Choctaw Nation of Oklahoma’s tribal health system, we conducted a qualitative study to explore the barriers behind patient decisions to forego screening. Thirty eligible participants who had been in the RCT for at least one year were identified as LCS completers (n=7) or non-completers (n=23). A single interviewer completed all interviews using a semi-structured interview guide, designed to explore experiences, barriers/facilitators to LCS, factors influencing screening decisions, and suggested strategies for expanding the LCS program into the community. Interviews were recorded and transcribed verbatim. Data were analyzed using conventional content analysis. Most non-completers reported having no conversations about the availability of LCS with their primary care provider (PCP) or receiving any information about the LCS program. In contrast, the completers all reported PCP-initiated discussions about the LCS program, their risk factors, and an overview of the testing process. Key themes that emerged included fears, e.g., being unsure about what the test involves, afraid of being diagnosed with lung cancer and what might follow, and afraid of dying. Some voiced concerns, e.g., feeling guilty as active smokers and being stigmatized should they be diagnosed with lung cancer. Many participants posited that there was no reason for screening without symptoms. Lack of understanding, especially about cancer care, was identified as a contributing factor. Suggested strategies to increase the reach into the community included using existing infrastructure within Choctaw Nation, such as disseminating information through the tribal newsletter, inserts in prescription refills, and notifications via the patient portal. Community education programs at local community centers, particularly around senior citizen meals, were offered as strategies to change the perception that lung cancer is a death sentence. Hosting an informational booth at the annual tribal Labor Day festival was commonly suggested. In conclusion, multiple reasons were cited for forgoing LDCT screening. In this tribal setting, findings are similar to ones documented in other settings. This suggests that interventions to overcome these challenges may build off known evidence-based interventions, such as the recommendations for cancer prevention documented by the Community Preventive Services Task Force. Addressing fears through multiple educational approaches and adapting strategies from the American Lung Association to address stigma could lead to enhanced interventions. Finally, capitalizing on tribal resources (newsletter) and tribal events to increase LCS awareness may be promising strategies to improve screening in the local tribal setting. Citation Format: Kathleen Dwyer, Zsolt Nagykaldi, Mark Doescher, Dorothy A. Rhoades. Factors influencing patient decision-making to complete Low Dose CT screening for lung cancer [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B046.

Abstract A145: Race and sex disparities in lung cancer screening and evaluation of alternative identifiers in patients’ electronic medical record to better identify lung cancer screening candidates

Abstract Introduction: The US Preventive Services Task Force (USPSTF) recommends lung cancer screening with a low dose CT scan in patients who are 50 – 80 years old with at least a 20 pack-year smoking history and currently smoke or quit in the last 15 years. Yet, only 5.8 percent of eligible Americans were screened in 2022. We investigated demographic screening patterns and evaluated for alternative identifiers in patients’ electronic medical record (EMR) to identify lung cancer screening candidates at a large and diverse cancer center in Los Angeles. Methods: We examined 607 patients with non-small cell lung cancer (NSCLC) treated at the University of Southern California Norris Comprehensive Care Center or Los Angeles General Medical Center from 2009-2023. EMR data included age of diagnosis, sex, race/ethnicity, smoking history, and stage at diagnosis; for patients with unknown number of pack years (n=25) they counted as not qualified for screening. Identifiers investigated were International Classification of Disease, Tenth Revision (ICD-10) code for chronic obstructive pulmonary disease (COPD), prescription of inhaled steroids, and documented lung cancer history. Fisher’s exact test was used to compare proportion of qualified screeners among groups. Results: 35% (215/607) of patients would have qualified for lung cancer screening according to the USPSTF guidelines, including a greater proportion of males 52% (164/313) versus females 17% (51/293) (p<0.0001). In males, Non-Hispanic Whites (NHW) 59% (55/93) had a greater proportion that would qualify compared to Hispanics 41% (31/75) (p=0.0295). In females, NHW 34% (30/89) had the highest proportion of qualifiers while Asians 6% (6/104) and Hispanics 9% (6/66) had the lowest proportion of qualifiers (p<0.0001). 65% (215/332) of smokers qualified for screening; males had a higher percentage who qualified for screening versus females (164/234, 70% vs. 51/98, 52%, p=0.0024). By race, NHW male smokers had the highest proportion of qualifiers 77% (55/71) while Hispanic women had the lowest proportion of qualifiers 50% (6/12). 27% (89/332) of patients were found to have an ICD-10 code for COPD, including 18% (21/117) had an ICD-10 code for COPD who did not qualify. 19% (63/332) smokers received a prescription for inhaled steroids, including 15% (18/117) of them who didn’t qualify for screening. 12% had a family history of lung cancer (39/332), while 9% (10/117) of these patients didn’t qualify for screening. Conclusion: There were significant race and sex screening disparities among known NSCLC patients including under 10% of Asian and Hispanic females. There were about 10-15% known lung cancer patients who would not have qualified for screening found to have an ICD-10 code for COPD, an inhaled steroids prescription, or documented family history. These alternative identifiers may serve as identifiers for lung cancer screening candidates in the EMR to help address race and sex disparities in screening. Future directions should include simulation of these identifiers in larger patient datasets. Citation Format: Darin Poei, Aubree Mades, Iris Yao, Nick Ahn, Ajay Prasad, Jennifer Tsui, Jacob S Thomas, Jorge J Nieva, Robert Hsu. Race and sex disparities in lung cancer screening and evaluation of alternative identifiers in patients’ electronic medical record to better identify lung cancer screening candidates [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A145.

Deep learning-based reconstruction improves the image quality of low-dose CT enterography in patients with inflammatory bowel disease

Deep learning-based reconstruction improves the image quality of low-dose CT enterography in patients with inflammatory bowel disease

Improvement in Image Quality of Low-Dose CT of Canines with Generative Adversarial Network of Anti-Aliasing Generator and Multi-Scale Discriminator.

Computed tomography (CT) imaging is vital for diagnosing and monitoring diseases in both humans and animals, yet radiation exposure remains a significant concern, especially in animal imaging. Low-dose CT (LDCT) minimizes radiation exposure but often compromises image quality due to a reduced signal-to-noise ratio (SNR). Recent advancements in deep learning, particularly with CycleGAN, offer promising solutions for denoising LDCT images, though challenges in preserving anatomical detail and image sharpness persist. This study introduces a novel framework tailored for animal LDCT imaging, integrating deep learning techniques within the CycleGAN architecture. Key components include BlurPool for mitigating high-resolution image distortion, PixelShuffle for enhancing expressiveness, hierarchical feature synthesis (HFS) networks for feature retention, and spatial channel squeeze excitation (scSE) blocks for contrast reproduction. Additionally, a multi-scale discriminator enhances detail assessment, supporting effective adversarial learning. Rigorous experimentation on veterinary CT images demonstrates our framework's superiority over traditional denoising methods, achieving significant improvements in noise reduction, contrast enhancement, and anatomical structure preservation. Extensive evaluations show that our method achieves a precision of 0.93 and a recall of 0.94. This validates our approach's efficacy, highlighting its potential to enhance diagnostic accuracy in veterinary imaging. We confirm the scSE method's critical role in optimizing performance, and robustness to input variations underscores its practical utility.

Automated abdominal organ segmentation algorithms for non-enhanced CT for volumetry and 3D radiomics analysis

Abstract Purpose To develop fully-automated abdominal organ segmentation algorithms from non-enhanced abdominal CT and low-dose chest CT and assess their feasibility for automated CT volumetry and 3D radiomics analysis of abdominal solid organs. Methods Fully-automated nnU-Net-based models were developed to segment the liver, spleen, and both kidneys in non-enhanced abdominal CT, and the liver and spleen in low-dose chest CT. 105 abdominal CTs and 60 low-dose chest CTs were used for model development, and 55 abdominal CTs and 10 low-dose chest CTs for external testing. The segmentation performance for each organ was assessed using the Dice similarity coefficients, with manual segmentation results serving as the ground truth. Agreements between ground-truth measurements and model estimates of organ volume and 3D radiomics features were assessed using the Bland–Altman analysis and intraclass correlation coefficients (ICC). Results The models accurately segmented the liver, spleen, right kidney, and left kidney in abdominal CT and the liver and spleen in low-dose chest CT, showing mean Dice similarity coefficients in the external dataset of 0.968, 0.960, 0.952, and 0.958, respectively, in abdominal CT, and 0.969 and 0.960, respectively, in low-dose chest CT. The model-estimated and ground truth volumes of these organs exhibited mean differences between − 0.7% and 2.2%, with excellent agreements. The automatically extracted mean and median Hounsfield units (ICCs, 0.970–0.999 and 0.994–0.999, respectively), uniformity (ICCs, 0.985–0.998), entropy (ICCs, 0.931–0.993), elongation (ICCs, 0.978–0.992), and flatness (ICCs, 0.973–0.997) showed excellent agreement with ground truth measurements for each organ; however, skewness (ICCs, 0.210–0.831), kurtosis (ICCs, 0.053–0.933), and sphericity (ICCs, 0.368–0.819) displayed relatively low and inconsistent agreement. Conclusion Our nnU-Net-based models accurately segmented abdominal solid organs in non-enhanced abdominal and low-dose chest CT, enabling reliable automated measurements of organ volume and specific 3D radiomics features.

Diagnostic performance of rapid on‐site evaluation during bronchoscopy for lung cancer: A comprehensive meta‐analysis

AbstractBackgroundLung cancer is the leading cause of cancer‐related mortality worldwide. Screening high‐risk populations for lung cancer with low‐dose computed tomography (LDCT) reduces lung cancer mortality. Bronchoscopy is a diagnostic procedure used to monitor patients suspected of having lung cancer after LDCT. Rapid on‐site evaluation (ROSE) can improve the diagnostic accuracy of endobronchial ultrasound–guided transbronchial needle aspiration (EBUS‐TBNA), although its diagnostic value remains unclear. In this meta‐analysis, the authors evaluated the diagnostic accuracy of ROSE during bronchoscopy.MethodsThe PubMed, Embase, and Cochrane Library databases were searched for studies evaluating the diagnostic accuracy of ROSE for lung cancer during bronchoscopy. Studies evaluating the performance of ROSE and articles providing sufficient data for constructing a 2 × 2 table on a per‐lesion basis were included. A meta‐analysis was conducted using a bivariate random‐effects model.ResultsIn total, 32 studies involving 8243 lung lesions were included with a pooled sensitivity of 91.8% and a pooled specificity of 94.9%. Subgroup analysis of 12 studies involving 2929 specimens from patients who underwent computed tomography revealed a pooled sensitivity of 93.8% and a pooled specificity of 96%. Further subgroup analysis of seven studies on the diagnostic outcomes of ROSE for intrathoracic or mediastinal lymph nodes through EBUS‐TBNA for lung cancer staging revealed a pooled sensitivity of 90.1% and a pooled specificity of 96.9%.ConclusionsROSE exhibited high sensitivity and specificity for diagnosing lung cancer during bronchoscopy. It also exhibited high sensitivity in detecting lung cancer in patients undergoing LDCT and higher specificity for nodal staging with EBUS‐TBNA.

Quantitative aortic Na[18F]F positron emission tomography computed tomography as a tool to associate vascular calcification with major adverse cardiovascular events

Abstract Purpose Sodium[18F]fluoride (Na[18F]F) used in positron emission tomography (PET) binds to active calcification and correlates consistently with higher cardiovascular risk. This study aims to investigate the feasibility of aortic Na[18F]F-PET in hybrid combination with low-dose computed tomography (CT) as a risk model for major adverse cardiovascular events (MACE). Methods Patient data and Na[18F]F-PET/CT scans from January 2019 to February 2022 were retrospectively collected at the University Medical Center Groningen (UMCG), the Netherlands. MACE-outcome was a composite of time to first documented myocardial infarction, cerebral vascular accident (CVA), acute heart failure hospitalization, and aortic aneurysms. MACE dates were recorded from the day of the scan until follow-up in December 2023. The aorta was manually segmented in all low-dose CT scans. To minimize spill-over effects from the vertebrae, the vertebrae were automatically segmented using an open-source model, dilated with 10 mm, and subtracted from the aortic mask. The total aortic Na[18F]F corrected maximum standardized uptake value (cSUVmax) and total aortic Agatston score were automatically calculated using SEQUOIA. Kaplan–Meier and Cox regression survival analysis were performed, stratifying patients into high, medium, and low cSUVmax and Agatston categories. Cox regression models were adjusted for age. Results Out of 280 identified scans, 216 scans of unique patients were included. During a median follow-up of 3.9 years, 12 MACE occurred. Kaplan–Meier survival analysis demonstrated a significant difference in MACE-free survival among the high cSUVmax group compared to the medium and low groups (p = 0.03 and p < 0.01, respectively). Similarly, patients with high Agatston scores had a significantly lower MACE-free survival probability compared to those with medium and low scores (both p < 0.01). Conclusion This study highlights the potential clinical utility of Na[18F]F-PET/CT as an imaging tool to predict the risk of MACE. Clinical validation of this novel proof-of-concept method is needed to confirm these results and expand the clinical context.

Low-dose high-resolution chest CT in adults with cystic fibrosis: intraindividual comparison between photon-counting and energy-integrating detector CT

BackgroundRegular disease monitoring with low-dose high-resolution (LD-HR) computed tomography (CT) scans is necessary for the clinical management of people with cystic fibrosis (pwCF). The aim of this study was to compare the image quality and radiation dose of LD-HR protocols between photon-counting CT (PCCT) and energy-integrating detector system CT (EID-CT) in pwCF.MethodsThis retrospective study included 23 pwCF undergoing LD-HR chest CT with PCCT who had previously undergone LD-HR chest CT with EID-CT. An intraindividual comparison of radiation dose and image quality was conducted. The study measured the dose-length product, volumetric CT dose index, effective dose and signal-to-noise ratio (SNR). Three blinded radiologists assessed the overall image quality, image sharpness, and image noise using a 5-point Likert scale ranging from 1 (deficient) to 5 (very good) for image quality and image sharpness and from 1 (very high) to 5 (very low) for image noise.ResultsPCCT used approximately 42% less radiation dose than EID-CT (median effective dose 0.54 versus 0.93 mSv, p < 0.001). PCCT was consistently rated higher than EID-CT for overall image quality and image sharpness. Additionally, image noise was lower with PCCT compared to EID-CT. The average SNR of the lung parenchyma was lower with PCCT compared to EID-CT (p < 0.001).ConclusionIn pwCF, LD-HR chest CT protocols using PCCT scans provided significantly better image quality and reduced radiation exposure compared to EID-CT.Relevance statementIn pwCF, regular follow-up could be performed through photon-counting CT instead of EID-CT, with substantial advantages in terms of both lower radiation exposure and increased image quality.Key PointsPhoton-counting CT (PCCT) and energy-integrating detector system CT (EID-CT) were compared in 23 people with cystic fibrosis (pwCF).Image quality was rated higher for PCCT than for EID-CT.PCCT used approximately 42% less radiation dose and offered superior image quality than EID-CT.Graphical