Weakly supervised low-dose computed tomography denoising based on generative adversarial networks.

Background: Low-dose computed tomography (LDCT) is a diagnostic imaging technique designed to minimize radiation exposure to the patient. However, this reduction in radiation may compromise computed tomography (CT) image quality, adversely impacting clinical diagnoses. Various advanced LDCT methods have emerged to mitigate this challenge, relying on well-matched LDCT and normal-dose CT (NDCT) image pairs for training. Nevertheless, these methods often face difficulties in distinguishing image details from nonuniformly distributed noise, limiting their denoising efficacy. Additionally, acquiring suitably paired datasets in the medical domain poses challenges, further constraining their applicability. Hence, the objective of this study was to develop an innovative denoising framework for LDCT images employing unpaired data. Methods: In this paper, we propose a LDCT denoising network (DNCNN) that alleviates the need for aligning LDCT and NDCT images. Our approach employs generative adversarial networks (GANs) to learn and model the noise present in LDCT images, establishing a mapping from the pseudo-LDCT to the actual NDCT domain without the need for paired CT images. Results: Within the domain of weakly supervised methods, our proposed model exhibited superior objective metrics on the simulated dataset when compared to CycleGAN and selective kernel-based cycle-consistent GAN (SKFCycleGAN): the peak signal-to-noise ratio (PSNR) was 43.9441, the structural similarity index measure (SSIM) was 0.9660, and the visual information fidelity (VIF) was 0.7707. In the clinical dataset, we conducted a visual effect analysis by observing various tissues through different observation windows. Our proposed method achieved a no-reference structural sharpness (NRSS) value of 0.6171, which was closest to that of the NDCT images (NRSS =0.6049), demonstrating its superiority over other denoising techniques in preserving details, maintaining structural integrity, and enhancing edge contrast. Conclusions: Through extensive experiments on both simulated and clinical datasets, we demonstrated the superior efficacy of our proposed method in terms of denoising quality and quantity. Our method exhibits superiority over both supervised techniques, including block-matching and 3D filtering (BM3D), residual encoder-decoder convolutional neural network (RED-CNN), and Wasserstein generative adversarial network-VGG (WGAN-VGG), and over weakly supervised approaches, including CycleGAN and SKFCycleGAN.

Qualitative interviews for hospitalists addressing lung cancer screening.

Novel strategies are needed to improve low rates of lung cancer screening (LCS) in the US. Seeking to determine hospitalists' perspectives on leveraging hospitalizations to identify patients eligible for LCS, we performed qualitative interviews with eight hospitalists from two hospitals within a large integrated healthcare system. The interviews used semi-structured questions to assess (1) knowledge and practice of general screening and LCS guidelines from the United States Preventive Services Task Force (USPSTF), (2) identification of smoking history, and (3) hospitalists' views on how data obtained during hospitalization may be utilized to improve general screening and LCS post hospitalization. We ultimately reached the conclusion that hospitalists would support a dedicated program to identify hospitalized patients eligible for LCS and facilitate testing after discharge. Efforts to identify patients and arrange subsequent screening should be performed by team members outside the inpatient team.

Shall We Screen Lung Cancer with Volume Computed Tomography in Austria? A Cost-Effectiveness Modelling Study.

This study assessed the cost-effectiveness of a lung cancer screening (LCS) program using low-dose computed tomography (LDCT) in Austria. An existing decision tree with an integrated Markov model was used to analyze the cost-effectiveness of LCS versus no screening from a healthcare payer perspective over a lifetime horizon. A simulation was conducted to model annual LCS for an asymptomatic high-risk population cohort aged 50-74 with a smoking history using the Dutch-Belgian Lung Cancer Screening Study (NEderlands-Leuvens Longkanker ScreeningsONderzoek, NELSON) screening outcomes. The principal measure utilized to assess cost-effectiveness was the incremental cost-effectiveness ratio (ICER). Sensitivity and scenario analyses were employed to determine uncertainties surrounding the key model inputs. At an uptake rate of 50%, 300,277 eligible individuals would participate in the LCS program, yielding 56,122 incremental quality-adjusted life years (QALYs) and 84,049 life years gained compared to no screening, with an ICER of EUR 24,627 per QALY gained or EUR 16,444 per life-year saved. Additionally, LCS led to the detection of 25,893 additional early-stage lung cancers and averted 11,906 premature lung cancer deaths. It was estimated that LCS would incur EUR 945 million additional screening costs and EUR 386 million additional treatment costs. These estimates were robust in sensitivity analyses. Implementation of annual LCS with LDCT for a high-risk population, using the NELSON screening outcomes, is cost-effective in Austria, at a threshold of EUR 50,000 per QALY.

Dose robustness of deep learning models for anatomic segmentation of computed tomography images.

Purpose: The trend towards lower radiation doses and advances in computed tomography (CT) reconstruction may impair the operation of pretrained segmentation models, giving rise to the problem of estimating the dose robustness of existing segmentation models. Previous studies addressing the issue suffer either from a lack of registered low- and full-dose CT images or from simplified simulations. Approach: We employed raw data from full-dose acquisitions to simulate low-dose CT scans, avoiding the need to rescan a patient. The accuracy of the simulation is validated using a real CT scan of a phantom. We consider down to 20% reduction of radiation dose, for which we measure deviations of several pretrained segmentation models from the full-dose prediction. In addition, compatibility with existing denoising methods is considered. Results: The results reveal the surprising robustness of the TotalSegmentator approach, showing minimal differences at the pixel level even without denoising. Less robust models show good compatibility with the denoising methods, which help to improve robustness in almost all cases. With denoising based on a convolutional neural network (CNN), the median Dice between low- and full-dose data does not fall below 0.9 (12 for the Hausdorff distance) for all but one model. We observe volatile results for labels with effective radii less than 19 mm and improved results for contrasted CT acquisitions. Conclusion: The proposed approach facilitates clinically relevant analysis of dose robustness for human organ segmentation models. The results outline the robustness properties of a diverse set of models. Further studies are needed to identify the robustness of approaches for lesion segmentation and to rank the factors contributing to dose robustness.

Opportunistic use of chest low-dose computed tomography (LDCT) imaging for low bone mineral density and osteoporosis screening: cutoff thresholds for the attenuation values of the lower thoracic and upper lumbar vertebrae.

Background: Osteoporosis remains substantially underdiagnosed and undertreated worldwide. Chest low-dose computed tomography (LDCT) may provide a valuable and popular opportunity for osteoporosis screening. This study sought to evaluate the feasibility of the screening of low bone mineral density (BMD) and osteoporosis with mean attenuation values of the lower thoracic compared to upper lumbar vertebrae. The cutoff thresholds of the mean attenuation values in Hounsfield units (HU) were derived to facilitate implementation of opportunistic screening using chest LDCT. Methods: The participants aged 30 years or older who underwent chest LDCT and quantitative computed tomography (QCT) examinations from August 2018 to October 2020 in our hospital were consecutively included in this retrospective study. A region of interest (ROI) was placed in the trabecular bone of each vertebral body to measure the HU values. The correlations of mean HU values of lower thoracic (T11-T12) and upper lumbar (L1-L2) vertebrae with age and lumbar BMD obtained with QCT were performed using the Pearson correlation coefficient, respectively. The area under the curve (AUC) of the receiver operator characteristic (ROC) curve was generated to determine the cutoff thresholds for distinguishing low BMD from normal and osteoporosis from non-osteoporosis. Results: A total of 1,112 participants were included in the final study cohort (743 men and 369 women, mean age 58.2±8.9 years; range, 32-88 years). The mean HU values of T11-T12 and L1-L2 were significantly different among 3 QCT-defined BMD categories of osteoporosis, osteopenia, and normal (P<0.001). The differences in HU values between T11-T12 and L1-L2 in each category of bone status were statistically significant (P<0.001). The mean HU values of T11-T12 (r=-0.453, P<0.001) and L1-L2 (r=-0.498, P<0.001) had negative correlations with age. Positive correlations were observed between the mean HU values of T11-T12 (r=0.872, P<0.001) and L1-L2 (r=0.899, P<0.001) with BMD. The optimal cutoff thresholds for distinguishing low BMD from normal were average T11-T12 ≤157 HU [AUC =0.941, 95% confidence interval (CI): 0.925-0.954, P<0.001] and L1-L2 ≤138 HU (AUC =0.950, 95% CI: 0.935-0.962, P<0.001), as well as distinguishing osteoporosis from non-osteoporosis were average T11-T12 ≤125 HU (AUC =0.960, 95% CI: 0.947-0.971, P<0.001) and L1-L2 ≤107 HU (AUC =0.961, 95% CI: 0.948-0.972, P<0.001). There was no significant difference between the AUC values of T11-T12 and L1-L2 for low BMD (P=0.07) and osteoporosis (P=0.92) screening. Conclusions: We have conducted a study on low BMD and osteoporosis screening using mean attenuation values of lower thoracic and upper lumbar vertebrae. Assessment of mean attenuation values of T11-T12 and L1-L2 can be used interchangeably for low BMD and osteoporosis screening using chest LDCT, and their cutoff thresholds were established.

The pros and cons of lung cancer screening.

Several trials have shown that low-dose computed tomography-based lung cancer screening (LCS) allows a substantial reduction in lung cancer-related mortality, carrying the potential for other clinical benefits. There are, however, some uncertainties to be clarified and several aspects to be implemented to optimize advantages and minimize the potential harms of LCS. This review summarizes current evidence on LCS, discussing some of the well-established and potential benefits, including lung cancer (LC)-related mortality reduction and opportunity for smoking cessation interventions, as well as the disadvantages of LCS, such as overdiagnosis and overtreatment. CLINICAL RELEVANCE STATEMENT: Different perspectives are provided on LCS based on the updated literature. KEY POINTS: Lung cancer is a leading cancer-related cause of death and screening should reduce associated mortality. This review summarizes current evidence related to LCS. Several aspects need to be implemented to optimize benefits and minimize potential drawbacks of LCS.

Pulmonary nodule detection in low dose computed tomography using a medical-to-medical transfer learning approach.

Purpose: Lung cancer is the second most common cancer and the leading cause of cancer death globally. Low dose computed tomography (LDCT) is the recommended imaging screening tool for the early detection of lung cancer. A fully automated computer-aided detection method for LDCT will greatly improve the existing clinical workflow. Most of the existing methods for lung detection are designed for high-dose CTs (HDCTs), and those methods cannot be directly applied to LDCTs due to domain shifts and inferior quality of LDCT images. In this work, we describe a semi-automated transfer learning-based approach for the early detection of lung nodules using LDCTs. Approach: In this work, we developed an algorithm based on the object detection model, you only look once (YOLO) to detect lung nodules. The YOLO model was first trained on CTs, and the pre-trained weights were used as initial weights during the retraining of the model on LDCTs using a medical-to-medical transfer learning approach. The dataset for this study was from a screening trial consisting of LDCTs acquired from 50 biopsy-confirmed lung cancer patients obtained over 3 consecutive years (T1, T2, and T3). About 60 lung cancer patients' HDCTs were obtained from a public dataset. The developed model was evaluated using a hold-out test set comprising 15 patient cases (93 slices with cancerous nodules) using precision, specificity, recall, and F1-score. The evaluation metrics were reported patient-wise on a per-year basis and averaged for 3 years. For comparative analysis, the proposed detection model was trained using pre-trained weights from the COCO dataset as the initial weights. A paired t-test and chi-squared test with an alpha value of 0.05 were used for statistical significance testing. Results: The results were reported by comparing the proposed model developed using HDCT pre-trained weights with COCO pre-trained weights. The former approach versus the latter approach obtained a precision of 0.982 versus 0.93 in detecting cancerous nodules, specificity of 0.923 versus 0.849 in identifying slices with no cancerous nodules, recall of 0.87 versus 0.886, and F1-score of 0.924 versus 0.903. As the nodule progressed, the former approach achieved a precision of 1, specificity of 0.92, and sensitivity of 0.930. The statistical analysis performed in the comparative study resulted in a p -value of 0.0054 for precision and a p -value of 0.00034 for specificity. Conclusions: In this study, a semi-automated method was developed to detect lung nodules in LDCTs using HDCT pre-trained weights as the initial weights and retraining the model. Further, the results were compared by replacing HDCT pre-trained weights in the above approach with COCO pre-trained weights. The proposed method may identify early lung nodules during the screening program, reduce overdiagnosis and follow-ups due to misdiagnosis in LDCTs, start treatment options in the affected patients, and lower the mortality rate.

3D U-Net Neural Network Architecture-Assisted LDCT to Acquire Vertebral Morphology Parameters: A Vertebral Morphology Comprehensive Analysis in a Chinese Population.

To evaluate the feasibility of acquiring vertebral height from chest low-dose computed tomography (LDCT) images using an artificial intelligence (AI) system based on 3D U-Net vertebral segmentation technology and the correlation and features of vertebral morphology with sex and age of the Chinese population. Patients who underwent chest LDCT between September 2020 and April 2023 were enrolled. The Altman and Pearson's correlation analyses were used to compare the correlation and consistency between the AI software and manual measurement of vertebral height. The anterior height (Ha), middle height (Hm), posterior height (Hp), and vertebral height ratios (VHRs) (Ha/Hp and Hm/Hp) were measured from T1 to L2 using an AI system. The VHR is the ratio of Ha to Hp or the ratio of Hm to Hp of the vertebrae, which can reflect the shape of the anterior wedge and biconcave vertebrae. Changes in these parameters, particularly the VHR, were analysed at different vertebral levels in different age and sex groups. The results of the AI methods were highly consistent and correlated with manual measurements. The Pearson's correlation coefficients were 0.855, 0.919, and 0.846, respectively. The trend of VHRs showed troughs at T7 and T11 and a peak at T9; however, Hm/Hp showed slight fluctuations. Regarding the VHR, significant sex differences were found at L1 and L2 in all age bands. This innovative study focuses on vertebral morphology for opportunistic analysis in the mainland Chinese population and the distribution tendency of vertebral morphology with ageing using a chest LDCT aided by an AI system based on 3D U-Net vertebral segmentation technology. The AI system demonstrates the potential to automatically perform opportunistic vertebral morphology analyses using LDCT scans obtained during lung cancer screening. We advocate the use of age-, sex-, and vertebral level-specific criteria for the morphometric evaluation of vertebral osteoporotic fractures for a more accurate diagnosis of vertebral fractures and spinal pathologies.

Incidental Findings in Lung Cancer Screening.

While low-dose computed tomography (LDCT) for lung cancer screening (LCS) has been recognized for its effectiveness in reducing lung cancer mortality, it often simultaneously leads to the detection of incidental findings (IFs) unrelated to the primary screening indication. These IFs present diagnostic and management challenges, potentially causing unnecessary anxiety and further invasive diagnostic procedures for patients. This review article provides an overview of IFs encountered in LDCT, emphasizing their clinical significance and recommended management strategies. We categorize IFs based on their anatomical locations (intrathoracic-intrapulmonary, intrathoracic-extrapulmonary, and extrathoracic) and discuss the most common findings. We highlight the importance of utilizing guidelines and standardized reporting systems by the American College of Radiology (ACR) to guide appropriate follow-ups. For each category, we present specific IF examples, their radiologic features, and the suggested management approach. This review aims to provide radiologists and clinicians with a comprehensive understanding of IFs in LCS for accurate assessment and management, ultimately enhancing patient care. Finally, we outline a few key aspects for future research and development in managing IFs.

Cost-Effectiveness of Low-Dose Computed Tomography Screenings for Lung Cancer in High-Risk Populations: A Markov Model.

Background: Domestic and foreign studies on lung cancer have been oriented to the medical efficacy of low-dose computed tomography (LDCT), but there is a lack of studies on the costs, value and cost-effectiveness of the treatment. There is a scarcity of conclusive evidence regarding the cost-effectiveness of LDCT within the specific context of Taiwan. This study is designed to address this gap by conducting a comprehensive analysis of the cost-effectiveness of LDCT and chest X-ray (CXR) as screening methods for lung cancer. Methods: Markov decision model simulation was used to estimate the cost-effectiveness of biennial screening with LDCT and CXR based on a health provider perspective. Inputs are based on probabilities, health status utility (quality-adjusted life years (QALYs)), costs of lung cancer screening, diagnosis, and treatment from the literatures, and expert opinion. A total of 1,000 simulations and five cycles of Markov bootstrapping simulations were performed to compare the incremental cost-utility ratio (ICUR) of these two screening strategies. Probability and one-way sensitivity analyses were also performed. Results: The ICUR of early lung cancer screening compared LDCT to CXR is $-24,757.65/QALYs, and 100% of the probability agree to adopt it under a willingness-to-pay (WTP) threshold of the Taiwan gross domestic product (GDP) per capita ($35,513). The one-way sensitivity analysis also showed that ICUR depends heavily on recall rate. Based on the prevalence rate of 39.7 lung cancer cases per 100,000 people in 2020, it could be estimated that LDCT screening for high-risk populations could save $17,154,115. Conclusion: LDCT can detect more early lung cancers, reduce mortality and is cost-saving than CXR in a long-term simulation of Taiwan's healthcare system. This study provides valuable insights for healthcare decision-makers and suggests analyzing cost-effectiveness for additional variables in future research.

Navigating the Pitfalls of Lung Cancer Screening: A Case Study on the Risks and Costs of Negative Screenings.

Lung cancer is the leading cause of cancer-related deaths in the United States. Low-dose computed tomography is the preferred screening method for high-risk individuals. However, with a false-negative rate reaching 15%, this method can underestimate disease prevalence and delay necessary treatment. This case examines a 61-year-old female smoker with chronic obstructive pulmonary disease who initially received a negative result from screening. Her imaging findings were categorized as Lung Imaging Reporting and Data System (Lung-RADS) 2 but advanced to small cell lung carcinoma. This progression emphasizes the imperative of thoroughly evaluating screening results and patient history. False-negative results from screenings have profound implications, leading to delayed diagnoses, adversely affecting patient outcomes, and increasing healthcare costs. The necessity for vigilant follow-up enhanced diagnostic precision and transparent communication about limitations is paramount. An economic analysis emphasizes the significant financial impact of diagnosing lung cancer at advanced stages, highlighting the need for timely and accurate diagnostics. Comprehensive strategies, such as physician education, patient awareness, and stringent quality control, are crucial to improving the efficacy of lung cancer screening. Addressing the issue of false negatives is vital for enhancing early detection rates, decreasing healthcare expenses, and advancing patient care in lung cancer management. Continuous evaluation and adjustment of screening protocols are essential to reduce risks and optimize outcomes.

Race, age at diagnosis and histological characteristics of lung cancer in never-smokers (LCINS) and ever-smokers in low-dose computed tomography (LDCT) screening: a systematic review and meta-analysis.

Background: We previously demonstrated in a meta-analysis there was no difference in risk ratio (RR) of lung cancer detected by low-dose computed tomography (LDCT) screening among female never-smokers (NS) and male ever-smokers (ES) in Asia. LDCT screening significantly decreased lung cancer death among Asian NS compared to Asian ES (RR =0.27, P<0.001). Methods: We investigated if race, age at diagnosis, and histology further differentiate lung cancer diagnosed by LDCT among in NS and ES using the 14 studies from our previous meta-analysis. Results: Twelve publications reported relevant data utilized in this study. From five Asian and one international studies, Asian ES had similar risk of lung cancer diagnosed at baseline screening as Asian NS [RR =0.96; 95% confidence interval (CI): 0.74-1.24] but among non-Asian ES had a 4.56 times significantly higher risk than non-Asian NS (RR =4.56; 95% CI: 2.85-7.28). The baseline incidence of lung cancer in never-smoker (LCINS) was approximately 2.3 times higher among Asian NS than non-Asian NS (0.62% vs. 0.27%, P=0.001). Asian ES had about half the baseline incidence of lung cancer diagnosed as non-Asian ES (0.65% vs. 1.26%). LCINS was diagnosed at 1.98 years younger than ES (95% CI: -3.38 to -0.58) (four studies) and exhibited a higher proportion of adenocarcinoma (ADC) (96.58% vs. 70.37%). Conclusions: Among normal-risk individuals, LCINS had a significantly higher likelihood of being diagnosed among Asians than non-Asians, predominantly manifesting as ADC and diagnosed approximately 2 years younger than ES suggesting that the age limit to initiate lung cancer screening in NS may be set lower compared to LDCT lung cancer screening among ES.

Parallel processing model for low-dose computed tomography image denoising.

Low-dose computed tomography (LDCT) has gained increasing attention owing to its crucial role in reducing radiation exposure in patients. However, LDCT-reconstructed images often suffer from significant noise and artifacts, negatively impacting the radiologists' ability to accurately diagnose. To address this issue, many studies have focused on denoising LDCT images using deep learning (DL) methods. However, these DL-based denoising methods have been hindered by the highly variable feature distribution of LDCT data from different imaging sources, which adversely affects the performance of current denoising models. In this study, we propose a parallel processing model, the multi-encoder deep feature transformation network (MDFTN), which is designed to enhance the performance of LDCT imaging for multisource data. Unlike traditional network structures, which rely on continual learning to process multitask data, the approach can simultaneously handle LDCT images within a unified framework from various imaging sources. The proposed MDFTN consists of multiple encoders and decoders along with a deep feature transformation module (DFTM). During forward propagation in network training, each encoder extracts diverse features from its respective data source in parallel and the DFTM compresses these features into a shared feature space. Subsequently, each decoder performs an inverse operation for multisource loss estimation. Through collaborative training, the proposed MDFTN leverages the complementary advantages of multisource data distribution to enhance its adaptability and generalization. Numerous experiments were conducted on two public datasets and one local dataset, which demonstrated that the proposed network model can simultaneously process multisource data while effectively suppressing noise and preserving fine structures. The source code is available at https://github.com/123456789ey/MDFTN .

Impact of annual trend volume of low-dose computed tomography for lung cancer screening on overdiagnosis, overmanagement, and gender disparities.

BACKGROUND: With the increasing prevalence of nonsmoking-related lung cancer in Asia, Asian countries have increasingly adopted low-dose computed tomography (LDCT) for lung cancer screening, particularly in private screening programs. This study examined how annual LDCT volume affects lung cancer stage distribution, overdiagnosis, and gender disparities using a hospital-based lung cancer database. METHODS: This study analyzed the annual utilized LDCT volume, clinical characteristics of lung cancer, stage shift distribution, and potential overdiagnosis. At the individual level, this study also investigated the relationship between stage 0 lung cancer (potential strict definition regarding overdiagnosis) and the clinical characteristics of lung cancer. RESULTS: This study reviewed the annual trend of 4971 confirmed lung cancer cases from 2008 to 2021 and conducted a link analysis with an LDCT imaging examination database over these years. As the volume of lung cancer screenings has increased over the years, the number and proportion of stage 0 lung cancers have increased proportionally. Our study revealed that the incidence of stage 0 lung cancer increased with increasing LDCT scan volume, particularly during the peak growth period from 2017 to 2020. Conversely, stage 4 lung cancer cases remained consistent across different time intervals. Furthermore, the increase in the lung cancer screening volume had a more pronounced effect on the increase in stage 0 lung cancer cases among females than it had among males. The estimated potential for overdiagnosis brought about by the screening process, compared to non-participating individuals, ranged from an odds ratio of 7.617 to one of 17.114. Both strict and lenient definitions of overdiagnosis (evaluating cases of stage 0 lung cancer and stages 0 to 1 lung cancer) were employed. CONCLUSIONS: These results provide population-level evidence of potential lung cancer overdiagnosis in the Taiwanese population due to the growing use of LDCT screening, particularly concerning the strict definition of stage 0 lung cancer. The impact was greater in the female population than in the male population, especially among females younger than 40 years. To improve lung cancer screening in Asian populations, creating risk-based prediction models for smokers and nonsmokers, along with gender-specific strategies, is vital for ensuring survival benefits and minimizing overdiagnosis.

DistilIQA: Distilling Vision Transformers for no-reference perceptual CT image quality assessment.

No-reference image quality assessment (IQA) is a critical step in medical image analysis, with the objective of predicting perceptual image quality without the need for a pristine reference image. The application of no-reference IQA to CT scans is valuable in providing an automated and objective approach to assessing scan quality, optimizing radiation dose, and improving overall healthcare efficiency. In this paper, we introduce DistilIQA, a novel distilled Vision Transformer network designed for no-reference CT image quality assessment. DistilIQA integrates convolutional operations and multi-head self-attention mechanisms by incorporating a powerful convolutional stem at the beginning of the traditional ViT network. Additionally, we present a two-step distillation methodology aimed at improving network performance and efficiency. In the initial step, a "teacher ensemble network" is constructed by training five vision Transformer networks using a five-fold division schema. In the second step, a "student network", comprising of a single Vision Transformer, is trained using the original labeled dataset and the predictions generated by the teacher network as new labels. DistilIQA is evaluated in the task of quality score prediction from low-dose chest CT scans obtained from the LDCT and Projection data of the Cancer Imaging Archive, along with low-dose abdominal CT images from the LDCTIQAC2023 Grand Challenge. Our results demonstrate DistilIQA's remarkable performance in both benchmarks, surpassing the capabilities of various CNNs and Transformer architectures. Moreover, our comprehensive experimental analysis demonstrates the effectiveness of incorporating convolutional operations within the ViT architecture and highlights the advantages of our distillation methodology.

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

BACKGROUND: 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. OBJECTIVE: 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. METHODS: 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. RESULTS: 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 23 mm and 12 mm, respectively. CONCLUSION: 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.

Safety net hospital risk model demonstrates stronger, population-specific applicability in characterizing lung cancer risk.

Background: Determining lung cancer (LC) risk using personalized risk stratification may improve screening effectiveness. While the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) is a well-established stratification model for LC screening, it was derived from a predominantly Caucasian population and its effectiveness in a safety net hospital (SNH) population is unknown. We have developed a model more tailored to the SNH population and compared its performance to the PLCO model in a SNH setting. Methods: Retrospective dataset was compiled from patients screened for LC at SNH from 2015 to 2019. Descriptive statistics were calculated using the following variables: age, sex, race, education, body mass index (BMI), smoking history, personal cancer history, family LC history, chronic obstructive pulmonary disease (COPD), and emphysema. Variables distribution was compared using t- and chi-square tests. LC risk scores were calculated using SNH and PLCO models and categorized as low (scores <0.65%), moderate (0.65-1.49%), and high (>1.5%). Linear regression was applied to evaluate the relationship between models and covariates. Results: Of 896 individuals, 38 were diagnosed with LC. Data reflected the SNH patient demographics, which predominantly were African American (53.5%), current smokers (69.9%), and with emphysema (70.1%). Among the non-LC cohort, SNH model most frequently categorized patients as low risk, while PLCO model most frequently classified patients as moderate risk. Among the LC cohort, there was no significant difference between mean scores or risk stratification. SNH model showed 92.1% sensitivity and 96.8% specificity while PLCO model showed 89.4% sensitivity and 26.1% specificity. Emphysema demonstrated a strong association in SNH model (P<0.001) while race showed no relation. Conclusions: SNH model demonstrated greater specificity for characterizing LC risk in a SNH population. The results demonstrated the importance of study sample representation when identifying risk factors in a stratification model.

A systematic review and meta-analysis of randomized controlled trials comparing low-dose versus standard-dose computed tomography-guided lung biopsy.

BACKGROUND: Despite the existence of several Randomized Controlled Trials (RCTs) investigating Low-Dose Computed Tomography (LDCT) as a guide in lung biopsies, conclusive findings remain elusive. To address this contention, we conducted a systematic review and meta-analysis to evaluate the efficacy and safety of LDCT-guided lung biopsies. METHODS: A comprehensive search across major databases identified RCTs comparing the effectiveness of LDCT-guided with Standard-Dose Computed Tomography (SDCT)-guided lung biopsies. Subsequently, we utilized a random-effects model meta-analysis to assess diagnostic accuracy, radiation dose, operation duration, and clinical complications associated with these procedures. RESULTS: Out of 292 scrutinized studies, six RCTs representing 922 patients were included in the final analysis. Results indicated the differences between the LDCT and SDCT groups were not different with statistical significance in terms of diagnostic accuracy rates (Intent-to-Treat (ITT) populations: Relative Risk (RR) 1.01, 95% Confidence interval [CI] 0.97-1.06, p = 0.61; Per-Protocol (PP) populations: RR 1.01, 95% CI 0.98-1.04, p = 0.46), incidence of pneumothorax (RR 1.00, 95% CI 0.75-1.35, p = 0.98), incidence of hemoptysis (RR 0.95, 95% CI 0.63-1.43, p = 0.80), and operation duration (minutes) (Mean Differences [MD] -0.34, 95% CI -1.67-0.99, p = 0.61). Notably, LDCT group demonstrated a lower radiation dose (mGy·cm) with statistical significance (MD -188.62, 95% CI -273.90 to -103.34, p < 0.0001). CONCLUSIONS: The use of LDCT in lung biopsy procedures demonstrated equivalent efficacy and safety to standard methods while notably reducing patient radiation exposure.

Screening for lung cancer using thin-slice low-dose computed tomography in southwestern China: a population-based real-world study.

OBJECTIVES: Lung cancer is one of the most common malignant tumors threatening human life and health. At present, low-dose computed tomography (LDCT) screening for the high-risk population to achieve early diagnosis and treatment of lung cancer has become the first choice recommended by many authoritative international medical organizations. To further optimize the lung cancer screening method, we conducted a real-world study of LDCT lung cancer screening in a large sample of a healthy physical examination population, comparing differences in lung nodules and lung cancer detection between thin and thick-slice LDCT scanning. METHODS: A total of 29 296 subjects who underwent low-dose thick-slice CT scanning (5 mm thickness) from January 2015 to December 2015 and 28 058 subjects who underwent low-dose thin-slice CT scanning (1 mm thickness) from January 2018 to December 2018 in West China Hospital were included. The positive detection rate, detection rate of lung cancer, pathological stage of lung cancer, and mortality rate of lung cancer were analyzed and compared between the two groups. RESULTS: The positive rate of LDCT screening in the thin-slice scanning group was significantly higher than that in the thick-slice scanning group (20.1% vs. 14.4%, p < 0.001). In addition, the lung cancer detection rate in the thin-slice LDCT screening positive group was significantly higher than that in the thick-slice scanning group (78.0% vs. 52.9%, p < 0.001). CONCLUSIONS: The screening positive rate of low-dose thin-slice CT scanning is higher and more early-stage lung cancer (IA1 stage) can be detected in the screen-positive group.

[Lung cancer screening: new frontiers]. / Lungenkrebsscreening: neue Horizonte.

CLINICAL/METHODICAL ISSUE: Lung cancer is the leading cause of cancer-related deaths worldwide. In early, asymptomatic stages, curative treatment is possible, but the disease is often diagnosed too late. STANDARD RADIOLOGICAL METHODS: Lung cancer screening (LCS) using low-dose computed tomography (LDCT) helps to detect potentially malignant lesions in early stages and to reduce lung cancer mortality. METHODOLOGICAL INNOVATIONS: The application of artificial intelligence (AI) algorithms enables a more precise analysis of LDCT scans. PERFORMANCE: A meta-analysis of eight LCS studies revealed a statistically significant 12% relative reduction in lung cancer mortality. ACHIEVEMENTS: Based on strong scientific evidence, a recommendation for a structured lung cancer screening program using LDCT for the high-risk population in Germany was issued. PRACTICAL RECOMMENDATIONS: The holistic LCS program requires a clear definition of the high-risk population, individual risk assessment, qualified personnel for conducting and reading examinations, verification of all diagnostic and therapeutic steps, central documentation and quality assurance, as well as the integration of tobacco cessation programs.