Detection Of Pulmonary Nodules Research Articles

ICNoduleNet: Enhancing Pulmonary Nodule Detection Performance on Sharp Kernel CT Imaging.

Thoracic computed tomography (CT) currently plays the primary role in pulmonary nodule detection, where the reconstruction kernel significantly impacts performance in computer-aided pulmonary nodule detectors. The issue of kernel selection affecting performance has been overlooked in pulmonary nodule detection. This paper first introduces a novel pulmonary nodule detection dataset named Reconstruction Kernel Imaging for Pulmonary Nodule Detection (RKPN) for quantifying algorithm differences between the two imaging types. The dataset contains pairs of images taken from the same patient on the same date, featuring both smooth (B31f) and sharp kernel (B60f) reconstructions. All other imaging parameters and pulmonary nodule labels remain entirely consistent across these pairs. Extensive quantification reveals mainstream detectors perform better on smooth kernel imaging than on sharp kernel imaging. To address suboptimal detection on the sharp kernel imaging, we further propose an image conversion-based pulmonary nodule detector called ICNoduleNet. A lightweight 3D slice-channel converter (LSCC) module is introduced to convert sharp kernel images into smooth kernel images, which can sufficiently learn inter-slice and inter-channel feature information while avoiding introducing excessive parameters. We conduct thorough experiments that validate the effectiveness of ICNoduleNet, it takes sharp kernel images as input and can achieve comparable or even superior detection performance to the baseline that uses the smooth kernel images. The evaluation shows promising results and proves the effectiveness of ICNoduleNet.

Analysis of the Prevalence Characteristics of Lung Nodules and Their Influencing Factors in The Health Check-Up Population

Objective: To study the prevalence characteristics of pulmonary nodules and their influencing factors in the health check-up population. Methods: A total of 500 cases of health checkups were selected for the data study to analyze the detection and prevalence characteristics of pulmonary nodules. The influencing factors between the pulmonary nodules group and the no pulmonary nodules group were analyzed. Results: A total of 209 cases were detected, of which there were more males than females, and for female patients, the detection rate increased with age (P < 0.05). The distribution of gender, age, smoking, respiratory symptoms, and exposure to kitchen fumes between the two groups was compared (P < 0.05). The multifactorial analysis concluded that risk factors include, respiratory symptoms, older age, exposure to kitchen fumes, and smoking. In addition, patients who exercised more had a lower risk of developing lung nodules. Conclusion: The detection rate of pulmonary nodules was high in the health check-up population and the influencing factors analyzed involved the presence of respiratory symptoms, older age, kitchen fume exposure, and smoking, while the positive influencing factor was increased exercise.

S-Net: an S-shaped network for nodule detection in 3D CT images

Objective. Accurate and automatic detection of pulmonary nodules is critical for early lung cancer diagnosis, and promising progress has been achieved in developing effective deep models for nodule detection. However, most existing nodule detection methods merely focus on integrating elaborately designed feature extraction modules into the backbone of the detection network to extract rich nodule features while ignore disadvantages of the structure of detection network itself. This study aims to address these disadvantages and develop a deep learning-based algorithm for pulmonary nodule detection to improve the accuracy of early lung cancer diagnosis. Approach. In this paper, an S-shaped network called S-Net is developed with the U-shaped network as backbone, where an information fusion branch is used to propagate lower-level details and positional information critical for nodule detection to higher-level feature maps, head shared scale adaptive detection strategy is utilized to capture information from different scales for better detecting nodules with different shapes and sizes and the feature decoupling detection head is used to allow the classification and regression branches to focus on the information required for their respective tasks. A hybrid loss function is utilized to fully exploit the interplay between the classification and regression branches. Main results. The proposed S-Net network with ResSENet and other three U-shaped backbones from SANet, OSAF-YOLOv3 and MSANet (R+SC+ECA) models achieve average CPM scores of 0.914, 0.915, 0.917 and 0.923 on the LUNA16 dataset, which are significantly higher than those achieved with other existing state-of-the-art models. Significance. The experimental results demonstrate that our proposed method effectively improves nodule detection performance, which implies potential applications of the proposed method in clinical practice.

Diagnostic Performance of MRI for the Detection of Pulmonary Nodules: A Systematic Review and Meta-Analysis.

Purpose To perform a meta-analysis of the diagnostic performance of MRI for the detection of pulmonary nodules, with use of CT as the reference standard. Materials and Methods PubMed, Embase, Scopus, and other databases were systematically searched for studies published from January 2000 to March 2023 evaluating the performance of MRI for diagnosis of lung nodules measuring 4 mm or larger, with CT as reference. Studies including micronodules, nodules without size stratification, or those from which data for contingency tables could not be extracted were excluded. Primary outcomes were the per-lesion sensitivity of MRI and the rate of false-positive nodules per patient (FPP). Subgroup analysis by size and meta-regression with other covariates were performed. The study protocol was registered in the International Prospective Register of Systematic Reviews, or PROSPERO (no. CRD42023437509). Results Ten studies met inclusion criteria (1354 patients and 2062 CT-detected nodules). Overall, per-lesion sensitivity of MRI for nodules measuring 4 mm or larger was 87.7% (95% CI: 81.1, 92.2), while the FPP rate was 12.4% (95% CI: 7.0, 21.1). Subgroup analyses demonstrated that MRI sensitivity was 98.5% (95% CI: 90.4, 99.8) for nodules measuring at least 8-10 mm and 80.5% (95% CI: 71.5, 87.1) for nodules less than 8 mm. Conclusion MRI demonstrated a good overall performance for detection of pulmonary nodules measuring 4 mm or larger and almost equal performance to CT for nodules measuring at least 8-10 mm, with a low rate of FPP. Systematic review registry no. CRD42023437509 Keywords: Lung Nodule, Lung Cancer, Lung Cancer Screening, MRI, CT Supplemental material is available for this article. © RSNA, 2024.

Dense Contrastive-based Federated Learning for Dense Prediction Tasks on Medical Images.

Deep learning (DL) models have achieved remarkable success in various domains. But training an accurate DL model requires large amounts of data, which can be challenging to obtain in medical settings due to privacy concerns. Recently, federated learning (FL) has emerged as a promising solution that shares local models instead of raw data. However, FL in medical settings faces challenges of client drift due to the data heterogeneity across dispersed institutions. Although there exist studies to address this challenge, they mainly focus on the classification tasks that learn global representation of an entire image. Few have been studied on the dense prediction tasks, such as object detection. In this study, we propose dense contrastive-based federated learning (DCFL) tailored for dense prediction tasks in FL settings. DCFL introduces dense contrastive learning to FL, which aligns the local optimization objectives towards the global objective by maximizing the agreement of representations between the global and local models. Moreover, to improve the performance of dense target prediction at each level, DCFL applies multi-scale contrastive representation by utilizing multi-scale representations with dense features in contrastive learning. We evaluated DCFL on a set of realistic datasets for pulmonary nodule detection. DCFL demonstrates an overall performance improvement compared with the other federated learning methods in heterogeneous settings-improving the mean average precision by 4.13% and testing recall by 6.07% in highly heterogeneous settings.

Robust deep learning from incomplete annotation for accurate lung nodule detection

Deep learning plays a significant role in the detection of pulmonary nodules in low-dose computed tomography (LDCT) scans, contributing to the diagnosis and treatment of lung cancer. Nevertheless, its effectiveness often relies on the availability of extensive, meticulously annotated dataset. In this paper, we explore the utilization of an incompletely annotated dataset for pulmonary nodules detection and introduce the FULFIL (Forecasting Uncompleted Labels For Inexpensive Lung nodule detection) algorithm as an innovative approach. By instructing annotators to label only the nodules they are most confident about, without requiring complete coverage, we can substantially reduce annotation costs. Nevertheless, this approach results in an incompletely annotated dataset, which presents challenges when training deep learning models.Within the FULFIL algorithm, we employ Graph Convolution Network (GCN) to discover the relationships between annotated and unannotated nodules for self-adaptively completing the annotation. Meanwhile, a teacher–student framework is employed for self-adaptive learning using the completed annotation dataset. Furthermore, we have designed a Dual-Views loss to leverage different data perspectives, aiding the model in acquiring robust features and enhancing generalization. We carried out experiments using the LUng Nodule Analysis (LUNA) dataset, achieving a sensitivity of 0.574 at a False positives per scan (FPs/scan) of 0.125 with only 10% instance-level annotations for nodules. This performance outperformed comparative methods by 7.00%. Experimental comparisons were conducted to evaluate the performance of our model and human experts on test dataset. The results demonstrate that our model can achieve a comparable level of performance to that of human experts. The comprehensive experimental results demonstrate that FULFIL can effectively leverage an incomplete pulmonary nodule dataset to develop a robust deep learning model, making it a promising tool for assisting in lung nodule detection.

Diagnostic challenge and survival analysis of pulmonary oligometastases and primary lung cancer in breast cancer patients.

The aim of this study was to compare breast cancer patients with pulmonary oligometastases (POM) and primary lung cancer (PLC) and to assess whether there were differences in clinical features, CT features, and survival outcomes between the two groups. From January 2010 to December 2021, the clinical records of 437 with malignant pulmonary nodules who had breast cancer patients were reviewed. POM was identified in 45 patients and PLC in 43 patients after the initial detection of pulmonary nodules. The clinicopathological characteristics, CT appearance of pulmonary nodules, and survival of the two groups were compared. Stage II to IV breast tumors (p < 0.001), high pathological grade of breast cancer (p = 0.001), low proportion of luminal-type breast cancer (p = 0.003), and the higher serum CYFRA 21-1 level (p = 0.046) were the clinical characteristics of pulmonary nodules suggestive of POM rather than PLC. The CT features of lung nodules indicative of PLC rather than POM were the subsolid component (p < 0.001), lobulation (p = 0.010), air bronchogram (p < 0.001) and pleural indentation (p = 0.004). Ten-year survival rate for PLC was 93.2%, which was higher compared with 57.8% in those with POM (p = 0.001). Elevated serum CYFRA 21-1 levels and late-stage breast cancer may be beneficial for the diagnosis of POM. CT imaging appearances of the subsolid component, lobulation, air bronchogram, and pleural indentation increase the likelihood of PLC. Breast cancer patients with PLC presented better survival with attentive monitoring than those with POM.

LGDNet: local feature coupling global representations network for pulmonary nodules detection.

Detection of suspicious pulmonary nodules from lung CT scans is a crucial task in computer-aided diagnosis (CAD) systems. In recent years, various deep learning-based approaches have been proposed and demonstrated significant potential for addressing this task. However, existing deep convolutional neural networks exhibit limited long-range dependency capabilities and neglect crucial contextual information, resulting in reduced performance on detecting small-size nodules in CT scans. In this work, we propose a novel end-to-end framework called LGDNet for the detection of suspicious pulmonary nodules in lung CT scans by fusing local features and global representations. To overcome the limited long-range dependency capabilities inherent in convolutional operations, a dual-branch module is designed to integrate the convolutional neural network (CNN) branch that extracts local features with the transformer branch that captures global representations. To further address the issue of misalignment between local features and global representations, an attention gate module is proposed in the up-sampling stage to selectively combine misaligned semantic data from both branches, resulting in more accurate detection of small-size nodules. Our experiments on the large-scale LIDC dataset demonstrate that the proposed LGDNet with the dual-branch module and attention gate module could significantly improve the nodule detection sensitivity by achieving a final competition performance metric (CPM) score of 89.49%, outperforming the state-of-the-art nodule detection methods, indicating its potential for clinical applications in the early diagnosis of lung diseases.

V-3DResNets: a 3D convolutional neural network based on residual network variants and slice grouping for pulmonary nodule detection

V-3DResNets: a 3D convolutional neural network based on residual network variants and slice grouping for pulmonary nodule detection

Pulmonary nodule detection in x-ray images by feature augmentation and context aggregation

Recent developments in x-ray image based pulmonary nodule detection have achieved remarkable results. However, existing methods are focused on transferring off-the-shelf coarse-grained classification models and fine-grained detection models rather than developing a dedicated framework optimized for nodule detection. In this paper, we propose PN-DetX, which as we know is the first dedicated pulmonary nodule detection framework. PN-DetX incorporates feature fusion and self-attention into x-ray based pulmonary nodule detection tasks, achieving improved detection performance. Specifically, PN-DetX adopts CSPDarknet backbone to extract features, and utilizes feature augmentation module to fuse features from different levels followed by context aggregation module to aggregate semantic information. To evaluate the efficacy of our method, we collect a LArge-scale Pulmonary NOdule Detection dataset, LAPNOD, comprising 2954 x-ray images along with expert-annotated ground truths. As we know, this is the first large-scale chest x-ray pulmonary nodule detection dataset. Experiments demonstrates that our method outperforms baseline by 3.8% mAP and 5.1% AP 0.5. The generality of our approach is also evaluated on the publicly available dataset NODE21. We aspire for our method to serve as an inspiration for future research in the field of pulmonary nodule detection. The dataset and codes will be made in public.

Detection of the DNA methylation of seven genes contribute to the early diagnosis of lung cancer

BackgroundLow-dose Computed Tomography (CT) is used for the detection of pulmonary nodules, but the ambiguous risk evaluation causes overdiagnosis. Here, we explored the significance of the DNA methylation of 7 genes including TAC1, CDO1, HOXA9, ZFP42, SOX17, RASSF1A and SHOX2 in the blood cfDNA samples in distinguishing lung cancer from benign nodules and healthy individuals.MethodA total of 149 lung cancer patients [72 mass and 77 ground-glass nodules (GGNs)], 5 benign and 48 healthy individuals were tested and analyzed in this study. The lasso-logistic regression model was built for distinguishing cancer and control/healthy individuals or IA lung cancer and non-IA lung cancer cases.ResultsThe positive rates of methylation of 7 genes were higher in the cancer group as compared with the healthy group. We constructed a model using age, sex and the ΔCt value of 7 gene methylation to distinguish lung cancer from benign and healthy individuals. The sensitivity, specificity and AUC (area under the curve) were 86.7%, 81.4% and 0.891, respectively. Also, we assessed the significance of 7 gene methylation together with patients’ age and sex in distinguishing of GGNs type from the mass type. The sensitivity, specificity and AUC were 77.1%, 65.8% and 0.753, respectively. Furthermore, the methylation positive rates of CDO1 and SHOX2 were different between I-IV stages of lung cancer. Specifically, the positive rate of CDO1 methylation was higher in the non-IA group as compared with the IA group.ConclusionCollectively, this study reveals that the methylation of 7 genes has a big significance in the diagnosis of lung cancer with high sensitivity and specificity. Also, the 7 genes present with certain significance in distinguishing the GGN type lung cancer, as well as different stages.

Grating-based x-ray dark-field CT for lung cancer diagnosis in mice

BackgroundThe low absorption of x-rays in lung tissue and the poor resolution of conventional computed tomography (CT) limits its use to detect lung disease. However, x-ray dark-field imaging can sense the scattered x-rays deflected by the structures being imaged. This technique can facilitate the detection of small alveolar lesions that would be difficult to detect with conventional CT. Therefore, it may provide an alternative imaging modality to diagnose lung disease at an early stage.MethodsEight mice were inoculated with lung cancers simultaneously. Each time two mice were scanned using a grating-based dark-field CT on days 4, 8, 12, and 16 after the introduction of the cancer cells. The detectability index was calculated between nodules and healthy parenchyma for both attenuation and dark-field modalities. High-resolution micro-CT and pathological examinations were used to crosscheck and validate our results. Paired t-test was used for comparing the ability of dark-field and attenuation modalities in pulmonary nodule detection.ResultsThe nodules were shown as a signal decrease in the dark-field modality and a signal increase in the attenuation modality. The number of nodules increased from day 8 to day 16, indicating disease progression. The detectability indices of dark-field modality were higher than those of attenuation modality (p = 0.025).ConclusionsCompared with the standard attenuation CT, the dark-field CT improved the detection of lung nodules.Relevance statementDark-field CT has a higher detectability index than conventional attenuation CT in lung nodule detection. This technique could improve the early diagnosis of lung cancer.Key points• Lung cancer progression was observed using x-ray dark-field CT.• Dark-field modality complements with attenuation modality in lung nodule detection.• Dark-field modality showed a detectability index higher than that attenuation in nodule detection.Graphical

Prediction of positive pulmonary nodules based on machine learning algorithm combined with central carbon metabolism data

BackgroundLung cancer causes a huge disease burden, and early detection of positive pulmonary nodules (PPNs) as an early sign of lung cancer is extremely important for effective intervention. It is necessary to develop PPNs risk recognizer based on machine learning algorithm combined with central carbon metabolomics.MethodsThe study included 2248 participants at high risk for lung cancer from the Ma'anshan Community Lung Cancer Screening cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to screen 18 central carbon-related metabolites in plasma, recursive feature elimination (RFE) was used to select all 42 features, followed by five machine learning algorithms for model development. The performance of the model was evaluated using area under the receiver operator characteristic curve (AUC), accuracy, precision, recall, and F1 scores. In addition, SHapley Additive exPlanations (SHAP) was performed to assess the interpretability of the final selected model and to gain insight into the impact of features on the predicted results.ResultsFinally, the two prediction models based on the random forest (RF) algorithm performed best, with AUC values of 0.87 and 0.83, respectively, better than other models. We found that homogentisic acid, fumaric acid, maleic acid, hippuric acid, gluconic acid, and succinic acid played a significant role in both PPNs prediction model and NPNs vs PPNs model, while 2-oxadipic acid only played a role in the former model and phosphopyruvate only played a role in the NPNs vs PPNs model. This model demonstrates the potential of central carbon metabolism for PPNs risk prediction and identification.ConclusionWe developed a series of predictive models for PPNs, which can help in the early detection of PPNs and thus reduce the risk of lung cancer.

Establishing and validation of the VBV score for assessing Lung ground-glass nodules based on high-resolution computed tomography

BackgroundThe widespread utilization of chest High-resolution Computed Tomography (HRCT) has prompted detection of pulmonary ground-glass nodules (GGNs) in otherwise asymptomatic individuals. We aimed to establish a simple clinical risk score model for assessing GGNs based on HRCT.MethodsWe retrospectively analyzed 574 GGNs in 574 patients undergoing HOOK-WIRE puncture and pulmonary nodule surgery from January 2014 to November 2018. Clinical characteristics and imaging features of the GGNs were assessed. We analyzed the differences between malignant and benign nodules using binary logistic regression analysis and constructed a simple risk score model, the VBV Score, for predicting the malignancy status of GGNs. Then, we validated this model via other 1200 GGNs in 1041 patients collected from three independent clinical centers in 2022.ResultsFor the exploratory phase of this study, out of the 574 GGNs, 481 were malignant and 93 were benign. Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. Then, we derived a VBV Score = vacuole sign + air bronchogram + intra-nodular vessel sign, to predict the malignancy of GGNs, with a sensitivity, specificity, and accuracy of 95.6%, 80.6%, and 93.2%, respectively. We also validated it on other 1200 GGNs, with a sensitivity, specificity, and accuracy of 96.0%, 82.6%, and 95.0%, respectively.ConclusionsVacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. VBV Score showed good sensitivity, specificity, and accuracy for differentiating benign and malignant pulmonary GGNs.

Robust explanation supervision for false positive reduction in pulmonary nodule detection.

Lung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin-sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities. The standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error-prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection. A robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset are used for training, validation, and testing. Using only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre-defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions. A pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.

Diagnostic value of artificial intelligence based on computed tomography (CT) density in benign and malignant pulmonary nodules: a retrospective investigation.

To evaluate the diagnostic value of artificial intelligence (AI) in the detection and management of benign and malignant pulmonary nodules (PNs) using computed tomography (CT) density. A retrospective analysis was conducted on the clinical data of 130 individuals diagnosed with PNs based on pathological confirmation. The utilization of AI and physicians has been employed in the diagnostic process of distinguishing benign and malignant PNs. The CT images depicting PNs were integrated into AI-based software. The gold standard for evaluating the accuracy of AI diagnosis software and physician interpretation was the pathological diagnosis. Out of 226 PNs screened from 130 patients diagnosed by AI and physician reading based on CT, 147 were confirmed by pathology. AI had a sensitivity of 94.69% and radiologists had a sensitivity of 85.40% in identifying PNs. The chi-square analysis indicated that the screening capacity of AI was superior to that of physician reading, with statistical significance (p <0.05). 195 of the 214 PNs suggested by AI were confirmed pathologically as malignant, and 19 were identified as benign; among the 29 PNs suggested by AI as low risk, 13 were confirmed pathologically as malignant, and 16 were identified as benign. From the physician reading, 193 PNs were identified as malignant, 183 were confirmed malignant by pathology, and 10 appeared benign. Physician reading also identified 30 low-risk PNs, 19 of which were pathologically malignant and 11 benign. The physician readings and AI had kappa values of 0.432 and 0.547, respectively. The physician reading and AI area under curves (AUCs) were 0.814 and 0.798, respectively. Both of the diagnostic techniques had worthy diagnostic value, as indicated by their AUCs of >0.7. It is anticipated that the use of AI-based CT diagnosis in the detection of PNs would increase the precision in early detection of lung carcinoma, as well as yield more precise evidence for clinical management.

Differential Diagnosis of Benign and Malignant Pulmonary Nodules in CT Images Based on Multitask Learning.

Artificial intelligence-based aided diagnostic systems for pulmonary nodules can be divided into subtasks such as nodule detection, segmentation, and benign and malignant differentiation. Most current studies are limited to single-target tasks. However, aided diagnosis aims to distinguish benign from malignant pulmonary nodules, which requires the fusion of multiple-scale features and comprehensive discrimination based on the results of multiple learning tasks. This study focuses on the aspects of model design, network structure, and constraints and proposes a novel model that integrates the learning tasks of pulmonary nodule detection, segmentation, and classification under weakly supervised conditions. The main innovations include the following three aspects: (1) a two-dimensional sequence detection model based on a ConvLSTM (Convolutional Long Short-Term Memory) network and U-shaped structure network is proposed to obtain the context space features of image slices fully; (2) a differential diagnosis of benign and malignant pulmonary nodules based on multitask learning is proposed, which uses the annotated data of different types of tasks to mine the potential common features among tasks; and (3) an optimization strategy incorporating prior knowledge of computed tomography images and dynamic weight adjustment of multiple tasks is proposed to ensure that each task can efficiently complete training and learning. Experiments on the LIDC-IDRI and LUNA16 datasets showed that our proposed method achieved a final competition performance metric score of 87.80% for nodule detection and a Dice similarity coefficient score of 83.95% for pulmonary nodule segmentation. The cross-validation results of the LIDC-IDRI and LUNA16 datasets show that our model achieved 87.80% of the final competition performance metric score for nodule detection and 83.95% of the DSC score for pulmonary nodule segmentation, representing the optimal result for that dataset.

SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention.

Lung cancer is the leading cause of cancer death worldwide. The best solution for lung cancer is to diagnose the pulmonary nodules in the early stage, which is usually accomplished with the aid of thoracic computed tomography (CT). As deep learning thrives, convolutional neural networks (CNNs) have been introduced into pulmonary nodule detection to help doctors in this labor-intensive task and demonstrated to be very effective. However, the current pulmonary nodule detection methods are usually domain-specific, and cannot satisfy the requirement of working in diverse real-world scenarios. To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks. This attention module works in the axial, coronal, and sagittal directions. In each direction, we divide the input feature into groups, and for each group, we utilize a universal adapter bank to capture the feature subspaces of the domains spanned by all pulmonary nodule datasets. Then the bank outputs are combined from the perspective of domain to modulate the input group. Extensive experiments demonstrate that SGDA enables substantially better multi-domain pulmonary nodule detection performance compared with the state-of-the-art multi-domain learning methods.

A Novel Model Using Serum Thymidine Kinase 1 and Low-dose Computed Tomography Parameters to Predict Three-year Lung Cancer Risk in People with Pulmonary Nodules: A Retrospective Study.

This study was designed to develop a model of serum thymidine kinase 1 protein (STK1p) concentration in combination with low-dose computed tomography (LDCT) to predict the risk of benign pulmonary nodules progressing into lung cancer within three years in a large screening population. The study included a retrospective cohort of 6,841 individuals aged > 30 years who had LDCT-detected pulmonary nodules, but no cancer history or baseline cancer. The outcome was a lung cancer diagnosis recorded within three years after the first detection of pulmonary nodules. The adaptive least absolute shrinkage and selection operator was used to select candidate predictors and fit a logistic model. The model was validated internally by examining discrimination (area under the receiver operating characteristic curve (AUC), calibration (calibration plot)) and net benefit. A web application was developed based on the model. The results showed that the proportion of incident lung cancer cases was 0.79% (n=52). Predictors selected for the model were STK1p and three LDCT parameters (nodule size, type, and count). The AUC of the model was 0.91 (95% confidence interval (CI): 0.86, 0.96). The model had satisfactory discrimination at internal validation (AUC: 0.90 (0.84, 0.96)) and in subgroups (AUC=0.69-0.93). The high-risk group identified by the model exhibited a significantly higher three-year lung cancer risk than the low-risk group (odds ratio (OR): 66.03 (95% CI: 30.49, 162.98)). We concluded that the novel model of STK1p and LDCT parameters together can be used to accurately predict the three-year risk of lung cancer in people with pulmonary nodules.

Application of computer-aided detection for NCCN-based follow-up recommendation in subsolid nodules: Effect on inter-observer agreement.

Computer-aided detection (CAD) of pulmonary nodules reduces the impact of observer variability, improving the reliability and reproducibility of nodule assessments in clinical practice. Therefore, this study aimed to assess the impact of CAD on inter-observer agreement in the follow-up management of subsolid nodules. A dataset comprising 60 subsolid nodule cases was constructed based on the National Cancer Center lung cancer screening data. Five observers independently assessed all low-dose computed tomography scans and assigned follow-up management strategies to each case according to the National Comprehensive Cancer Network (NCCN) guidelines, using both manual measurements and CAD assistance. The linearly weighted Cohen's kappa test was used to measure agreement between paired observers. Agreement among multiple observers was evaluated using the Fleiss kappa statistic. The agreement of the five observers for NCCN follow-up management categorization was moderate when measured manually, with a Fleiss kappa score of 0.437. Utilizing CAD led to a notable enhancement in agreement, achieving a substantial consensus with a Fleiss kappa value of 0.623. After using CAD, the proportion of major and substantial management discrepancies decreased from 27.5% to 15.8% and 4.8% to 1.5%, respectively (p < 0.01). In 23 lung cancer cases presenting as part-solid nodules, CAD significantly elevates the average sensitivity in detecting lung cancer cases presenting as part-solid nodules (overall sensitivity, 82.6% vs. 92.2%; p < 0.05). The application of CAD significantly improves inter-observer agreement in the follow-up management strategy for subsolid nodules. It also demonstrates the potential to reduce substantial management discrepancies and increase detection sensitivity in lung cancer cases presenting as part-solid nodules.