Evaluation of an in-use chest CT protocol in lung cancer screening - A single institutional study.

Background: Lung cancer is the most common cause of cancer-related death worldwide and therefore there has been a growing demand for low-dose computed tomography (LDCT) protocols. Purpose: To investigate and evaluate the dose and image quality of patients undergoing lung cancer screening (LCS) using LDCT in Norway. Materials and Methods: Retrospective dosimetry data, volumetric CT dose index (CTDIvol) and dose-length product (DLP), from 70 average-size and 70 large-size patients who underwent LDCT scan for LCS were included in the survey. Effective dose and size-specific dose were calculated for each examination and were compared with the American Association of Physicists in Medicine (AAPM) requirement. For a quantitative image quality analysis, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were determined for different regions in the chest with two iterative reconstruction techniques, iDose and Iterative Model Reconstruction. Differences in dose and image quality between average-size and large-size patients were evaluated by Independent sample t test, and Wilcoxon signed rank test within the same patient group. Results: The independent sample t test revealed significant differences (p < .05) in dose values between average-size and large-size patients. Mean CTDIvol and DLP for average-size patients were 2.8 mGy and 115 mGy.cm, respectively, with appropriate increment for the large-size patients. Image quality (image noise, SNR, and CNR) did not significantly differ between patient groups when images were reconstructed with a model based iterative reconstruction algorithm. Conclusion: The screening protocol assessed in this study resulted in CTDIvol values that were compliant with AAPM recommendation. No significant differences in objective image quality were found between patient groups.

Facing an un-met need in lung cancer screening: The never smokers.

Lung cancer (LC) is the leading cause of cancer-related deaths worldwide and the second most common cancer in both men and women. In addition to smoking, other risk factors, such as environmental tobacco smoke, air pollution, biomass combustion, radon gas, occupational exposure, lung disease, family history of cancer, geographic variability, and genetic factors, play an essential role in developing LC. Current screening guidelines and eligibility criteria have limited efficacy in identifying LC cases (50 %), as most screening programs primarily target subjects with a smoking history as the leading risk factor. Implementing LC screening programs in people who have never smoked (PNS) can significantly impact cancer-specific survival and early disease detection. However, the available evidence regarding the feasibility and effectiveness of such programs is limited. Therefore, further research on LC screening in PNS is warranted to determine the necessary techniques for accurately identifying individuals who should be included in screening programs.

Deep learning-based low-dose CT simulator for non-linear reconstruction methods.

BACKGROUND: Computer algorithms that simulate lower-doses computed tomography (CT) images from clinical-dose images are widely available. However, most operate in the projection domain and assume access to the reconstruction method. Access to commercial reconstruction methods may often not be available in medical research, making image-domain noise simulation methods useful. However, the introduction of non-linear reconstruction methods, such as iterative and deep learning-based reconstruction, makes noise insertion in the image domain intractable, as it is not possible to determine the noise textures analytically. PURPOSE: To develop a deep learning-based image-domain method to generate low-dose CT images from clinical-dose CT (CDCT) images for non-linear reconstruction methods. METHODS: We propose a fully image domain-based method, utilizing a series of three convolutional neural networks (CNNs), which, respectively, denoise CDCT images, predict the standard deviation map of the low-dose image, and generate the noise power spectra (NPS) of local patches throughout the low-dose image. All three models have U-net-based architectures and are partly or fully three-dimensional. As a use case for this study and with no loss of generality, we use paired low-dose and clinical-dose brain CT scans. A dataset of 326 $\hskip.001pt 326$ paired scans was retrospectively obtained. All images were acquired with a wide-area detector clinical system and reconstructed using its standard clinical iterative algorithm. Each pair was registered using rigid registration to correct for motion between acquisitions. The data was randomly partitioned into training ( 251 $\hskip.001pt 251$ samples), validation ( 25 $\hskip.001pt 25$ samples), and test ( 50 $\hskip.001pt 50$ samples) sets. The performance of each of these three CNNs was validated separately. For the denoising CNN, the local standard deviation decrease, and bias were determined. For the standard deviation map CNN, the real and estimated standard deviations were compared locally. Finally, for the NPS CNN, the NPS of the synthetic and real low-dose noise were compared inside and outside the skull. Two proof-of-concept denoising studies were performed to determine if the performance of a CNN- or a gradient-based denoising filter on the synthetic low-dose data versus real data differed. RESULTS: The denoising network had a median decrease in noise in the cerebrospinal fluid by a factor of 1.71 $1.71$ and introduced a median bias of + 0.7 $ + 0.7$ HU. The network for standard deviation map estimation had a median error of + 0.1 $ + 0.1$ HU. The noise power spectrum estimation network was able to capture the anisotropic and shift-variant nature of the noise structure by showing good agreement between the synthetic and real low-dose noise and their corresponding power spectra. The two proof of concept denoising studies showed only minimal difference in standard deviation improvement ratio between the synthetic and real low-dose CT images with the median difference between the two being 0.0 and +0.05 for the CNN- and gradient-based filter, respectively. CONCLUSION: The proposed method demonstrated good performance in generating synthetic low-dose brain CT scans without access to the projection data or to the reconstruction method. This method can generate multiple low-dose image realizations from one clinical-dose image, so it is useful for validation, optimization, and repeatability studies of image-processing algorithms.

[Results of Lung Cancer Screening with Low-dose Computed Tomography 
and Exploration of Risk Factors in Guangzhou].

BACKGROUND: Both of lung cancer incidence and mortality rank first among all cancers in China. Previous lung cancer screening trials were mostly selective screening for high-risk groups such as smokers. Non-smoking women accounted for a considerable proportion of lung cancer cases in Asia. This study aimed to evaluate the outcome of community-based mass screening in Guangzhou and identify the high-risk factors for lung cancer. METHODS: Residents aged 40-74 years in Guangzhou were screened with low-dose computed tomography (LDCT) for lung cancer and the pulmonary nodules were classified and managed according to China National Lung Cancer Screening Guideline with Low-dose Computed Tomography (2018 version). The detection rate of positive nodules was calculated. Before the LDCT examination, residents were required to complete a "lung cancer risk factors questionnaire". The risk factors of the questionnaire were analyzed by least absolute shrinkage and selection operator (LASSO) penalized Logistic regression analysis. RESULTS: A total of 6256 residents were included in this study. 1228 positive nodules (19.63%) and 117 lung cancers were confirmed, including 6 cases of Tis, 103 cases of stage I (accounting for 88.03% of lung cancer). The results of LASSO penalized Logistic regression analysis indicated that age ≥50 yr (OR=1.07, 95%CI: 1.06-1.07), history of cancer (OR=3.29, 95%CI: 3.22-3.37), textile industry (OR=1.10, 95%CI: 1.08-1.13), use coal for cooking in childhood (OR=1.14, 95%CI: 1.13-1.16) and food allergy (OR=1.10, 95%CI: 1.07-1.13) were risk factors of lung cancer for female in this district. CONCLUSIONS: This study highlighted that numerous early stages of lung cancer cases were detected by LDCT, which could be applied to screening of lung cancer in women. Besides, age ≥50 yr, personal history of cancer, textile industry and use coal for cooking in childhood are risk factors for women in this district, which suggested that it's high time to raise the awareness of early lung cancer screening in this group.

Intraindividual Comparison of Dose Reduction and Coronary Calcium Scoring Accuracy Using Kilovolt-independent and Tin Filtration CT Protocols.

Purpose To investigate the ability of kilovolt-independent (hereafter, kV-independent) and tin filter spectral shaping to accurately quantify the coronary artery calcium score (CACS) and radiation dose reductions compared with the standard 120-kV CT protocol. Materials and Methods This prospective, blinded reader study included 201 participants (mean age, 60 years ± 9.8 [SD]; 119 female, 82 male) who underwent standard 120-kV CT and additional kV-independent and tin filter research CT scans from October 2020 to July 2021. Scans were reconstructed using a Qr36f kernel for standard scans and an Sa36f kernel for research scans simulating artificial 120-kV images. CACS, risk categorization, and radiation doses were compared by analyzing data with analysis of variance, Kruskal-Wallis test, Mann-Whitney test, Bland-Altman analysis, Pearson correlations, and κ analysis for agreement. Results There was no evidence of differences in CACS across standard 120-kV, kV-independent, and tin filter scans, with median CACS values of 1 (IQR, 0-48), 0.6 (IQR, 0-58), and 0 (IQR, 0-51), respectively (P = .85). Compared with standard 120-kV scans, kV-independent and tin filter scans showed excellent correlation in CACS values (r = 0.993 and r = 0.999, respectively), with high agreement in CACS risk categorization (κ = 0.95 and κ = 0.93, respectively). Standard 120-kV scans had a mean radiation dose of 2.09 mSv ± 0.84, while kV-independent and tin filter scans reduced it to 1.21 mSv ± 0.85 and 0.26 mSv ± 0.11, cutting doses by 42% and 87%, respectively (P < .001). Conclusion The kV-independent and tin filter research CT acquisition techniques showed excellent agreement and high accuracy in CACS estimation compared with standard 120-kV scans, with large reductions in radiation dose. Keywords: CT, Cardiac, Coronary Arteries, Radiation Safety, Coronary Artery Calcium Score, Radiation Dose Reduction, Low-Dose CT Scan, Tin Filter, kV-Independent Supplemental material is available for this article. © RSNA, 2024.

Baseline Cell-Free DNA Can Predict Malignancy of Nodules Observed in the ITALUNG Screening Trial.

The role of total plasma cell-free DNA (cfDNA) in lung cancer (LC) screening with low-dose computed tomography (LDCT) is uncertain. We hypothesized that cfDNA could support differentiation between malignant and benign nodules observed in LDCT. The baseline cfDNA was measured in 137 subjects of the ITALUNG trial, including 29 subjects with screen-detected LC (17 prevalent and 12 incident) and 108 subjects with benign nodules. The predictive capability of baseline cfDNA to differentiate malignant and benign nodules was compared to that of Lung-RADS classification and Brock score at initial LDCT (iLDCT). Subjects with prevalent LC showed both well-discriminating radiological characteristics of the malignant nodule (16 of 17 were classified as Lung-RADS 4) and markedly increased cfDNA (mean 18.8 ng/mL). The mean diameters and Brock scores of malignant nodules at iLDCT in subjects who were diagnosed with incident LC were not different from those of benign nodules. However, 75% (9/12) of subjects with incident LC showed a baseline cfDNA ≥ 3.15 ng/mL, compared to 34% (37/108) of subjects with benign nodules (p = 0.006). Moreover, baseline cfDNA was correlated (p = 0.001) with tumor growth, measured with volume doubling time. In conclusion, increased baseline cfDNA may help to differentiate subjects with malignant and benign nodules at LDCT.

Structure-aware diffusion for low-dose CT imaging.

Reducing the radiation dose leads to the x-ray computed tomography (CT) images suffering from heavy noise and artifacts, which inevitably interferes with the subsequent clinic diagnostic and analysis. Leading works have explored diffusion models for low-dose CT imaging to avoid the structure degeneration and blurring effects of previous deep denoising models. However, most of them always begin their generative processes with Gaussian noise, which has little or no structure priors of the clean data distribution, thereby leading to long-time inference and unpleasant reconstruction quality. To alleviate these problems, this paper presents a Structure-Aware Diffusion model (SAD), an end-to-end self-guided learning framework for high-fidelity CT image reconstruction. First, SAD builds a nonlinear diffusion bridge between clean and degraded data distributions, which could directly learn the implicit physical degradation prior from observed measurements. Second, SAD integrates the prompt learning mechanism and implicit neural representation into the diffusion process, where rich and diverse structure representations extracted by degraded inputs are exploited as prompts, which provides global and local structure priors, to guide CT image reconstruction. Finally, we devise an efficient self-guided diffusion architecture using an iterative updated strategy, which further refines structural prompts during each generative step to drive finer image reconstruction. Extensive experiments on AAPM-Mayo and LoDoPaB-CT datasets demonstrate that our SAD could achieve superior performance in terms of noise removal, structure preservation, and blind-dose generalization, with few generative steps, even one step only.

Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening.

Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; P = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; P = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; P < .001) and the Brock model (NRI, 0.12; P = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. Keywords: Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 Supplemental material is available for this article.

Harnessing Opportunity: Pilot Intervention to Improve Lung Cancer Screening for Women Undergoing Breast Screening Mammography.

Introduction: The screening mammogram could be a "teachable moment" to improve lung cancer screening (LCS) uptake. The aim of our project was to combine patient self-referral with eligibility identification by providers as a two-pronged approach to increase rates of LCS among eligible women. Methods: LCS education materials were created to stimulate patient education and encourage self-referral. Chart review of patients scheduled for screening mammography was performed to identify patients who met LCS criteria. The primary outcome was rate of acceptance of targeted interventions as measured by qualitative survey material and rate of LCS uptake. Results: Between August 2022 and August 2023, 116 patients were identified by providers for potential eligibility for LCS and 34 patients (29.3%) deemed eligible based on the U.S. Preventative Services Task Force 2021 guidelines. There were 19 patients (56%) who completed LCS with three patients (16%) with screen-detected nodules that led to further workup. Post-implementation qualitative survey results reveal that 100% of the participants rated their shared decision-making visit experience as "very helpful" and 67% responded "very likely" to seek simultaneous breast and LCS in the future. Informational materials were rated as 80% favorable among all respondents; however, the rate of self-referral alone was 0%. The combined rates of eligible patients lost to follow-up or refusal was 24%. Conclusion: The self-referral aspect of the intervention revealed that patients are unlikely to self-refer for LCS. Nevertheless, patients undergoing screening mammograms individually identified for LCS were very responsive to learning more about dual screening.

Lung Cancer Screening: All That Glitters Is Not Gold.

Lung cancer screening with low-dose computed tomography (LDCT) can significantly improve survival rates with early detection. With the increased amount of imaging studies being performed for screening, there are more incidental lesions found. Malignancy and pulmonary infections are two of the major differentials when a lesion is found on CT. Neither a CT scan nor a positron emission tomography can reliably differentiate between malignancy and infectious lesions. Here, we present an unexpected case of multiple nodules detected on LDCT that was performed for lung cancer screening and the workup that was done to lead to a diagnosis.

Ultra-low-dose vs. standard-of-care-dose CT of the chest in patients with post-COVID-19 conditions-a prospective intra-patient multi-reader study.

OBJECTIVES: To conduct an intrapatient comparison of ultra-low-dose computed tomography (ULDCT) and standard-of-care-dose CT (SDCT) of the chest in terms of the diagnostic accuracy of ULDCT and intrareader agreement in patients with post-COVID conditions. METHODS: We prospectively included 153 consecutive patients with post-COVID-19 conditions. All participants received an SDCT and an additional ULDCT scan of the chest. SDCTs were performed with standard imaging parameters and ULDCTs at a fixed tube voltage of 100 kVp (with tin filtration), 50 ref. mAs (dose modulation active), and iterative reconstruction algorithm level 5 of 5. All CT scans were separately evaluated by four radiologists for the presence of lung changes and their consistency with post-COVID lung abnormalities. Radiation dose parameters and the sensitivity, specificity, and accuracy of ULDCT were calculated. RESULTS: Of the 153 included patients (mean age 47.4 ± 15.3 years; 48.4% women), 45 (29.4%) showed post-COVID lung abnormalities. In those 45 patients, the most frequently detected CT patterns were ground-glass opacities (100.0%), reticulations (43.5%), and parenchymal bands (37.0%). The accuracy, sensitivity, and specificity of ULDCT compared to SDCT for the detection of post-COVID lung abnormalities were 92.6, 87.2, and 94.9%, respectively. The median total dose length product (DLP) of ULDCTs was less than one-tenth of the radiation dose of our SDCTs (12.6 mGy*cm [9.9; 15.5] vs. 132.1 mGy*cm [103.9; 160.2]; p < 0.001). CONCLUSION: ULDCT of the chest offers high accuracy in the detection of post-COVID lung abnormalities compared to an SDCT scan at less than one-tenth the radiation dose, corresponding to only twice the dose of a standard chest radiograph in two views. CLINICAL RELEVANCE STATEMENT: Ultra-low-dose CT of the chest may provide a favorable, radiation-saving alternative to standard-dose CT in the long-term follow-up of the large patient cohort of post-COVID-19 patients.

[Low-dose CT reconstruction based on high-dimensional partial differential equation projection recovery].

OBJECTIVE: We propose a low-dose CT reconstruction method using partial differential equation (PDE) denoising under high-dimensional constraints. METHODS: The projection data were mapped into a high-dimensional space to construct a high-dimensional representation of the data, which were updated by moving the points in the high-dimensional space. The data were denoised using partial differential equations and the CT image was reconstructed using the FBP algorithm. RESULTS: Compared with those by FBP, PWLS-QM and TGV-WLS methods, the relative root mean square error of the Shepp-Logan image reconstructed by the proposed method were reduced by 68.87%, 50.15% and 27.36%, the structural similarity values were increased by 23.50%, 8.83% and 1.62%, and the feature similarity values were increased by 17.30%, 2.71% and 2.82%, respectively. For clinical image reconstruction, the proposed method, as compared with FBP, PWLS-QM and TGV-WLS methods, resulted in reduction of the relative root mean square error by 42.09%, 31.04% and 21.93%, increased the structural similarity values by 18.33%, 13.45% and 4.63%, and increased the feature similarity values by 3.13%, 1.46% and 1.10%, respectively. CONCLUSION: The new method can effectively reduce the streak artifacts and noises while maintaining the spatial resolution in reconstructed low-dose CT images.

Unsupervised low-dose CT denoising using bidirectional contrastive network.

BACKGROUND AND OBJECTIVE: Low-dose computed tomography (LDCT) scans significantly reduce radiation exposure, but introduce higher levels of noise and artifacts that compromise image quality and diagnostic accuracy. Supervised learning methods have proven effective in denoising LDCT images, but are hampered by the need for large, paired datasets, which pose significant challenges in data acquisition. This study aims to develop a robust unsupervised LDCT denoising method that overcomes the reliance on paired LDCT and normal-dose CT (NDCT) samples, paving the way for more accessible and practical denoising techniques. METHODS: We propose a novel unsupervised network model, Bidirectional Contrastive Unsupervised Denoising (BCUD), for LDCT denoising. This model innovatively combines a bidirectional network structure with contrastive learning theory to map the precise mutual correspondence between the noisy LDCT image domain and the clean NDCT image domain. Specifically, we employ dual encoders and discriminators for domain-specific data generation, and use unique projection heads for each domain to adaptively learn customized embedded representations. We then align corresponding features across domains within the learned embedding spaces to achieve effective noise reduction. This approach fundamentally improves the model's ability to match features in latent space, thereby improving noise reduction while preserving fine image detail. RESULTS: Through extensive experimental validation on the AAPM-Mayo public dataset and real-world clinical datasets, the proposed BCUD method demonstrated superior performance. It achieved a peak signal-to-noise ratio (PSNR) of 31.387 dB, a structural similarity index measure (SSIM) of 0.886, an information fidelity criterion (IFC) of 2.305, and a visual information fidelity (VIF) of 0.373. Notably, subjective evaluation by radiologists resulted in a mean score of 4.23, highlighting its advantages over existing methods in terms of clinical applicability. CONCLUSIONS: This paper presents an innovative unsupervised LDCT denoising method using a bidirectional contrastive network, which greatly improves clinical applicability by eliminating the need for perfectly matched image pairs. The method sets a new benchmark in unsupervised LDCT image denoising, excelling in noise reduction and preservation of fine structural details.

Demographics and socioeconomic determinants of health predict continued participation in a CT lung cancer screening program.

PURPOSE: We developed machine learning (ML) models to assess demographic and socioeconomic status (SES) variables' value in predicting continued participation in a low-dose CT lung cancer screening (LCS) program. MATERIALS AND METHODS: 480 LCS subjects were retrospectively examined for the following outcomes: (#1) no follow-up (single LCS scan) vs. multiple follow-ups (220 and 260 subjects respectively) and (#2) absent or delayed (>1 month past the due date) follow-up vs timely follow-up (356 and 124 subjects respectively). We quantified the contributions of 14 socioeconomic, demographic, and clinical predictors to LCS adherence, and validated and compared prediction performances of multivariate logistic regression (MLR), support vector machine (SVM) and shallow neural network (NN) models. RESULTS: For outcome #1, age, sex, race, insurance status, personal cancer history, and median household income were found to be associated with returning for follow-ups. For outcome #2, age, sex, race, and insurance status were significant predictor of absent/delayed LCS follow-up. Across 5-fold cross-validation, the MLR model achieved an average AUC of 0.732 (95% CI, 0.661-0.803) for outcome #1 and 0.633 (95% CI, 0.602-0.664) for outcome #2 and is the model with best predictive performance overall, whereas NN and SVM tended to overfit training data and fell short on testing data performance for either outcome. CONCLUSIONS: We identified significant predictors of LCS adherence, and our ML models can predict which subjects are at higher risk of receiving no or delayed LCS follow-ups. Our results could inform data-driven interventions to engage vulnerable populations and extend the benefits of LCS.

Evaluation of low-dose computed tomography reconstruction using spatial-radon domain total generalized variation regularization.

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction (SIR) based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches.

Multi-scale feature aggregation and fusion network with self-supervised multi-level perceptual loss for textures preserving low-dose CT denoising.

Objective. The textures and detailed structures in computed tomography (CT) images are highly desirable for clinical diagnosis. This study aims to expand the current body of work on textures and details preserving convolutional neural networks for low-dose CT (LDCT) image denoising task.Approach. This study proposed a novel multi-scale feature aggregation and fusion network (MFAF-net) for LDCT image denoising. Specifically, we proposed a multi-scale residual feature aggregation module to characterize multi-scale structural information in CT images, which captures regional-specific inter-scale variations using learned weights. We further proposed a cross-level feature fusion module to integrate cross-level features, which adaptively weights the contributions of features from encoder to decoder by using a spatial pyramid attention mechanism. Moreover, we proposed a self-supervised multi-level perceptual loss module to generate multi-level auxiliary perceptual supervision for recovery of salient textures and structures of tissues and lesions in CT images, which takes advantage of abundant semantic information at various levels. We introduced parameters for the perceptual loss to adaptively weight the contributions of auxiliary features of different levels and we also introduced an automatic parameter tuning strategy for these parameters.Main results. Extensive experimental studies were performed to validate the effectiveness of the proposed method. Experimental results demonstrate that the proposed method can achieve better performance on both fine textures preservation and noise suppression for CT image denoising task compared with other competitive convolutional neural network (CNN) based methods.Significance. The proposed MFAF-net takes advantage of multi-scale receptive fields, cross-level features integration and self-supervised multi-level perceptual loss, enabling more effective recovering of fine textures and detailed structures of tissues and lesions in CT images.

Texture-preserving low dose CT image denoising using Pearson divergence.

Objective.The mean squared error (MSE), also known asL2loss, has been widely used as a loss function to optimize image denoising models due to its strong performance as a mean estimator of the Gaussian noise model. Recently, various low-dose computed tomography (LDCT) image denoising methods using deep learning combined with the MSE loss have been developed; however, this approach has been observed to suffer from the regression-to-the-mean problem, leading to over-smoothed edges and degradation of texture in the image.Approach.To overcome this issue, we propose a stochastic function in the loss function to improve the texture of the denoised CT images, rather than relying on complicated networks or feature space losses. The proposed loss function includes the MSE loss to learn the mean distribution and the Pearson divergence loss to learn feature textures. Specifically, the Pearson divergence loss is computed in an image space to measure the distance between two intensity measures of denoised low-dose and normal-dose CT images. The evaluation of the proposed model employs a novel approach of multi-metric quantitative analysis utilizing relative texture feature distance.Results.Our experimental results show that the proposed Pearson divergence loss leads to a significant improvement in texture compared to the conventional MSE loss and generative adversarial network (GAN), both qualitatively and quantitatively.Significance.Achieving consistent texture preservation in LDCT is a challenge in conventional GAN-type methods due to adversarial aspects aimed at minimizing noise while preserving texture. By incorporating the Pearson regularizer in the loss function, we can easily achieve a balance between two conflicting properties. Consistent high-quality CT images can significantly help clinicians in diagnoses and supporting researchers in the development of AI-diagnostic models.

Visual scoring of osteoporosis on low-dose CT in lung cancer screening population.

OBJECTIVES: The risk factors for lung cancer screening eligibility, age as well as smoking history, are also present for osteoporosis. This study aims to develop a visual scoring system to identify osteoporosis that can be applied to low-dose CT scans obtained for lung cancer screening. MATERIALS AND METHODS: We retrospectively reviewed 1000 prospectively enrolled participants in the lung cancer screening program at the Mount Sinai Hospital. Optimal window width and level settings for the visual assessment were chosen based on a previously described approach. Visual scoring of osteoporosis and automated measurement using dedicated software were compared. Inter-reader agreement was conducted using six readers with different levels of experience who independently visually assessed 30 CT scans. RESULTS: Based on previously validated formulas for choosing window and level settings, we chose osteoporosis settings of Width = 230 and Level = 80. Of the 1000 participants, automated measurement was successfully performed on 774 (77.4 %). Among these, 138 (17.8 %) had osteoporosis. There was a significant correlation between the automated measurement and the visual score categories for osteoporosis (Kendall's Tau = -0.64, p < 0.0001; Spearman's rho = -0.77, p < 0.0001). We also found substantial to excellent inter-reader agreement on the osteoporosis classification among the 6 radiologists (Fleiss κ = 0.91). CONCLUSIONS: Our study shows that a simple approach of applying specific window width and level settings to already reconstructed sagittal images obtained in the context of low-dose CT screening for lung cancer is highly feasible and useful in identifying osteoporosis.

The prognostic value of visual and automatic coronary calcium -scoring from low dose CT-[15O]-water PET.

PURPOSE: Firstly, to validate automatically and visually scored coronary artery calcium (CAC) on low dose CT (LDCT) scans with a dedicated calcium scoring CT (CSCT) scan. Secondly, to assess the added value of CAC scored from LDCT scans acquired during [15O]-water-PET myocardial perfusion imaging (MPI) on prediction of major adverse cardiac events (MACE). METHODS: 572 consecutive patients with suspected coronary artery disease, who underwent [15O]-water-PET MPI with LDCT and a dedicated CSCT scan were included. In the reference CSCT scans, manual CAC scoring was performed, while LDCT scans were scored visually and automatically using deep learning approach. Subsequently, based on CAC score results from CSCT and LDCT scans, each patient's scan was assigned to one out of five cardiovascular risk groups (0; 1-100; 101-400; 401-1000; >1000) and the agreement in risk group classification between CSCT and LDCT scans was investigated. MACE was defined as a composite of all-cause death, nonfatal myocardial infarction, coronary revascularization, and unstable angina. RESULTS: The agreement in risk group classification between reference CSCT manual scoring and visual/automatic LDCT scoring from LDCT was 0.66 (95% CI: 0.62-0.70) and 0.58 (95% CI: 0.53-0.62), respectively. Based on visual and automatic CAC scoring from LDCT scans, patients with CAC>100 and CAC>400, respectively, were at increased risk of MACE, independently of ischemic information from the [15O]-water-PET scan. CONCLUSIONS: There is a moderate agreement in risk classification between visual and automatic CAC scoring from LDCT and reference CSCT scans. Visual and automatic CAC scoring from LDCT scans improve identification of patients at higher risk of MACE.