Phase-contrast virtual chest radiography.

Respiratory X-ray imaging enhanced by phase contrast has shown improved airway visualization in animal models. Limitations in current X-ray technology have nevertheless hindered clinical translation, leaving the potential clinical impact an open question. Here, we explore phase-contrast chest radiography in a realistic in silico framework. Specifically, we use preprocessed virtual patients to generate in silico chest radiographs by Fresnel-diffraction simulations of X-ray wave propagation. Following a reader study conducted with clinical radiologists, we predict that phase-contrast edge enhancement will have a negligible impact on improving solitary pulmonary nodule detection (6 to 20 mm). However, edge enhancement of bronchial walls visualizes small airways (< 2 mm), which are invisible in conventional radiography. Our results show that phase-contrast chest radiography could play a future role in observing small-airway obstruction (e.g., relevant for asthma or early-stage chronic obstructive pulmonary disease), which cannot be directly visualized using current clinical methods, thereby motivating the experimental development needed for clinical translation. Finally, we discuss quantitative requirements on distances and X-ray source/detector specifications for clinical implementation of phase-contrast chest radiography.

MRUNet-3D: A multi-stride residual 3D UNet for lung nodule segmentation.

Obtaining an accurate segmentation of the pulmonary nodules in computed tomography (CT) images is challenging. This is due to: (1) the heterogeneous nature of the lung nodules; (2) comparable visual characteristics between the nodules and their surroundings. A robust multi-scale feature extraction mechanism that can effectively obtain multi-scale representations at a granular level can improve segmentation accuracy. As the most commonly used network in lung nodule segmentation, UNet, its variants, and other image segmentation methods lack this robust feature extraction mechanism. In this study, we propose a multi-stride residual 3D UNet (MRUNet-3D) to improve the segmentation accuracy of lung nodules in CT images. It incorporates a multi-slide Res2Net block (MSR), which replaces the simple sequence of convolution layers in each encoder stage to effectively extract multi-scale features at a granular level from different receptive fields and resolutions while conserving the strengths of 3D UNet. The proposed method has been extensively evaluated on the publicly available LUNA16 dataset. Experimental results show that it achieves competitive segmentation performance with an average dice similarity coefficient of 83.47 % and an average surface distance of 0.35 mm on the dataset. More notably, our method has proven to be robust to the heterogeneity of lung nodules. It has also proven to perform better at segmenting small lung nodules. Ablation studies have shown that the proposed MSR and RFIA modules are fundamental to improving the performance of the proposed model.

Distribution of Solid Lung Nodules Presence and Size by Age and Sex in a Northern European Nonsmoking Population.

Background Most of the data regarding prevalence and size distribution of solid lung nodules originates from lung cancer screening studies that target high-risk populations or from Asian general cohorts. In recent years, the identification of lung nodules in non-high-risk populations, scanned for clinical indications, has increased. However, little is known about the presence of solid lung nodules in the Northern European nonsmoking population. Purpose To study the prevalence and size distribution of solid lung nodules by age and sex in a nonsmoking population. Materials and Methods Participants included nonsmokers (never or former smokers) from the population-based Imaging in Lifelines study conducted in the Northern Netherlands. Participants (age ≥ 45 years) with completed lung function tests underwent chest low-dose CT scans. Seven trained readers registered the presence and size of solid lung nodules measuring 30 mm3 or greater using semiautomated software. The prevalence and size of lung nodules (≥30 mm3), clinically relevant lung nodules (≥100 mm3), and actionable nodules (≥300 mm3) are presented by 5-year categories and by sex. Results A total of 10 431 participants (median age, 60.4 years [IQR, 53.8-70.8 years]; 56.6% [n = 5908] female participants; 46.1% [n = 4812] never smokers and 53.9% [n = 5619] former smokers) were included. Of these, 42.0% (n = 4377) had at least one lung nodule (male participants, 47.5% [2149 of 4523]; female participants, 37.7% [2228 of 5908]). The prevalence of lung nodules increased from age 45-49.9 years (male participants, 39.4% [219 of 556]; female participants, 27.7% [236 of 851]) to age 80 years or older (male participants, 60.7% [246 of 405]; female participants, 50.9% [163 of 320]). Clinically relevant lung nodules were present in 11.1% (1155 of 10 431) of participants, with prevalence increasing with age (male participants, 8.5%-24.4%; female participants, 3.7%-15.6%), whereas actionable nodules were present in 1.1%-6.4% of male participants and 0.6%-4.9% of female participants. Conclusion Lung nodules were present in a substantial proportion of all age groups in the Northern European nonsmoking population, with slightly higher prevalence for male participants than female participants. © RSNA, 2024 Supplemental material is available for this article.

Who is at risk of lung nodules on low-dose CT in a Western country? A population-based approach.

BACKGROUND: This population-based study aimed to identify the risk factors for lung nodules in a Western European general population. METHODS: We quantified the presence or absence of lung nodules among 12 055 participants of the Dutch population-based ImaLife (Imaging in Lifelines) study (age ≥45 years) who underwent low-dose chest computed tomography. Outcomes included the presence of 1) at least one solid lung nodule (volume ≥30 mm3) and 2) a clinically relevant lung nodule (volume ≥100 mm3). Fully adjusted multivariable logistic regression models were applied overall and stratified by smoking status to identify independent risk factors for the presence of nodules. RESULTS: Among the 12 055 participants (44.1% male; median age 60 years; 39.9% never-smokers; 98.7% White), we found lung nodules in 41.8% (5045 out of 12 055) and clinically relevant nodules in 11.4% (1377 out of 12 055); the corresponding figures among never-smokers were 38.8% and 9.5%, respectively. Factors independently associated with increased odds of having any lung nodule included male sex, older age, low educational level, former smoking, asbestos exposure and COPD. Among never-smokers, a family history of lung cancer increased the odds of both lung nodules and clinically relevant nodules. Among former and current smokers, low educational level was positively associated with lung nodules, whereas being overweight was negatively associated. Among current smokers, asbestos exposure and low physical activity were associated with clinically relevant nodules. CONCLUSIONS: The study provides a large-scale evaluation of lung nodules and associated risk factors in a Western European general population: lung nodules and clinically relevant nodules were prevalent, and never-smokers with a family history of lung cancer were a non-negligible group.

Lung nodule malignancy classification with associated pulmonary fibrosis using 3D attention-gated convolutional network with CT scans.

BACKGROUND: Chest Computed tomography (CT) scans detect lung nodules and assess pulmonary fibrosis. While pulmonary fibrosis indicates increased lung cancer risk, current clinical practice characterizes nodule risk of malignancy based on nodule size and smoking history; little consideration is given to the fibrotic microenvironment. PURPOSE: To evaluate the effect of incorporating fibrotic microenvironment into classifying malignancy of lung nodules in chest CT images using deep learning techniques. MATERIALS AND METHODS: We developed a visualizable 3D classification model trained with in-house CT dataset for the nodule malignancy classification task. Three slightly-modified datasets were created: (1) nodule alone (microenvironment removed); (2) nodule with surrounding lung microenvironment; and (3) nodule in microenvironment with semantic fibrosis metadata. For each of the models, tenfold cross-validation was performed. Results were evaluated using quantitative measures, such as accuracy, sensitivity, specificity, and area-under-curve (AUC), as well as qualitative assessments, such as attention maps and class activation maps (CAM). RESULTS: The classification model trained with nodule alone achieved 75.61% accuracy, 50.00% sensitivity, 88.46% specificity, and 0.78 AUC; the model trained with nodule and microenvironment achieved 79.03% accuracy, 65.46% sensitivity, 85.86% specificity, and 0.84 AUC. The model trained with additional semantic fibrosis metadata achieved 80.84% accuracy, 74.67% sensitivity, 84.95% specificity, and 0.89 AUC. Our visual evaluation of attention maps and CAM suggested that both the nodules and the microenvironment contributed to the task. CONCLUSION: The nodule malignancy classification performance was found to be improving with microenvironment data. Further improvement was found when incorporating semantic fibrosis information.

Differentiation of granulomatous nodules with lobulation and spiculation signs from solid lung adenocarcinomas using a CT deep learning model.

BACKGROUND: The diagnosis of solitary pulmonary nodules has always been a difficult and important point in clinical research, especially granulomatous nodules (GNs) with lobulation and spiculation signs, which are easily misdiagnosed as malignant tumors. Therefore, in this study, we utilised a CT deep learning (DL) model to distinguish GNs with lobulation and spiculation signs from solid lung adenocarcinomas (LADCs), to improve the diagnostic accuracy of preoperative diagnosis. METHODS: 420 patients with pathologically confirmed GNs and LADCs from three medical institutions were retrospectively enrolled. The regions of interest in non-enhanced CT (NECT) and venous contrast-enhanced CT (VECT) were identified and labeled, and self-supervised labels were constructed. Cases from institution 1 were randomly divided into a training set (TS) and an internal validation set (IVS), and cases from institutions 2 and 3 were treated as an external validation set (EVS). Training and validation were performed using self-supervised transfer learning, and the results were compared with the radiologists' diagnoses. RESULTS: The DL model achieved good performance in distinguishing GNs and LADCs, with area under curve (AUC) values of 0.917, 0.876, and 0.896 in the IVS and 0.889, 0.879, and 0.881 in the EVS for NECT, VECT, and non-enhanced with venous contrast-enhanced CT (NEVECT) images, respectively. The AUCs of radiologists 1, 2, 3, and 4 were, respectively, 0.739, 0.783, 0.883, and 0.901 in the (IVS) and 0.760, 0.760, 0.841, and 0.844 in the EVS. CONCLUSIONS: A CT DL model showed great value for preoperative differentiation of GNs with lobulation and spiculation signs from solid LADCs, and its predictive performance was higher than that of radiologists.

Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images.

OBJECTIVES: To establish deep learning models for malignancy risk estimation of sub-centimeter pulmonary nodules incidentally detected by chest CT and managed in clinical settings. MATERIALS AND METHODS: Four deep learning models were trained using CT images of sub-centimeter pulmonary nodules from West China Hospital, internally tested, and externally validated on three cohorts. The four models respectively learned 3D deep features from the baseline whole lung region, baseline image patch where the nodule located, baseline nodule box, and baseline plus follow-up nodule boxes. All regions of interest were automatically segmented except that the nodule boxes were additionally manually checked. The performance of models was compared with each other and that of three respiratory clinicians. RESULTS: There were 1822 nodules (981 malignant) in the training set, 806 (416 malignant) in the testing set, and 357 (253 malignant) totally in the external sets. The area under the curve (AUC) in the testing set was 0.754, 0.855, 0.928, and 0.942, respectively, for models derived from baseline whole lung, image patch, nodule box, and the baseline plus follow-up nodule boxes. When baseline models externally validated (follow-up images not available), the nodule-box model outperformed the other two with AUC being 0.808, 0.848, and 0.939 respectively in the three external datasets. The resident, junior, and senior clinicians achieved an accuracy of 67.0%, 82.5%, and 90.0%, respectively, in the testing set. The follow-up model performed comparably to the senior clinician. CONCLUSION: The deep learning algorithms solely mining nodule information can efficiently predict malignancy of incidental sub-centimeter pulmonary nodules. CLINICAL RELEVANCE STATEMENT: The established models may be valuable for supporting clinicians in routine clinical practice, potentially reducing the number of unnecessary examinations and also delays in diagnosis. KEY POINTS: • According to different regions of interest, four deep learning models were developed and compared to evaluate the malignancy of sub-centimeter pulmonary nodules by CT images. • The models derived from baseline nodule box or baseline plus follow-up nodule boxes demonstrated sufficient diagnostic accuracy (86.4% and 90.4% in the testing set), outperforming the respiratory resident (67.0%) and junior clinician (82.5%). • The proposed deep learning methods may aid clinicians in optimizing follow-up recommendations for sub-centimeter pulmonary nodules and may lead to fewer unnecessary diagnostic interventions.

CT-guided microcoil localization of pulmonary nodules before VATS: clinical experience in 1059 patients.

OBJECTIVE: To retrospectively evaluate the efficacy and safety of CT-guided microcoil localization of pulmonary nodules before video-assisted thoracoscopic surgery (VATS). METHODS: A total of 1059 consecutive patients with 1331 pulmonary nodules treated between July 2018 and April 2021 were included in this study. Of the 1331 nodules, 1318 were localized using the tailed method and 13 were localized using the non-tailed method. The localization technical success rate and complications of the microcoil localization procedure were assessed. Univariate and multivariate logistic regression analyses were used to determine potential risk factors for technical failure, pneumothorax, and pulmonary hemorrhage. RESULTS: The technical success rate of the localization procedure was 98.4% (1310/1331 nodules). Nodule location in the lower lobes (p = 0.015) and need for a longer needle path (p < 0.001) were independent predictors of technical failure. All localization procedure-related complications were minor (grade 1 or 2) adverse events, with the exception of one grade 3 complication. The most common complications were pneumothorax (302/1331 nodules [22.7%]) and pulmonary hemorrhage (328/1331 nodules [24.6%]). Male sex (p = 0.001), nodule location in the middle (p = 0.003) and lower lobes (p = 0.025), need for a longer needle path (p < 0.001), use of transfissural puncture (p = 0.042), and simultaneous multiple localizations (p < 0.001) were independent risk factors for pneumothorax. Female sex (p = 0.015), younger age (p = 0.023), nodules location in the upper lobes (p = 0.011), and longer needle path (p < 0.001) were independent risk factors for pulmonary hemorrhage. CONCLUSIONS: CT-guided microcoil localization of pulmonary nodules before VATS using either the tailed or non-tailed method is effective and safe. CLINICAL RELEVANCE STATEMENT: CT-guided microcoil localization of pulmonary nodules before VATS resection is effective and safe when using either the tailed or non-tailed method. Nodules requiring transfissural puncture and multiple nodules requiring simultaneous localizations can also be successfully localized with this method. KEY POINTS: • Pre-VATS CT-guided microcoil localization of pulmonary nodules by tailed or non-tailed method was effective and safe. • When the feasible puncture path was beyond the scope of wedge resection, localization could be performed using the non-tailed method. • Although transfissural puncture and simultaneous multiple localization were independent risk factors for pneumothorax, they remained clinically feasible.

A novel image deep learning-based sub-centimeter pulmonary nodule management algorithm to expedite resection of the malignant and avoid over-diagnosis of the benign.

OBJECTIVES: With the popularization of chest computed tomography (CT) screening, there are more sub-centimeter (≤ 1 cm) pulmonary nodules (SCPNs) requiring further diagnostic workup. This area represents an important opportunity to optimize the SCPN management algorithm avoiding "one-size fits all" approach. One critical problem is how to learn the discriminative multi-view characteristics and the unique context of each SCPN. METHODS: Here, we propose a multi-view coupled self-attention module (MVCS) to capture the global spatial context of the CT image through modeling the association order of space and dimension. Compared with existing self-attention methods, MVCS uses less memory consumption and computational complexity, unearths dimension correlations that previous methods have not found, and is easy to integrate with other frameworks. RESULTS: In total, a public dataset LUNA16 from LIDC-IDRI, 1319 SCPNs from 1069 patients presenting to a major referral center, and 160 SCPNs from 137 patients from three other major centers were analyzed to pre-train, train, and validate the model. Experimental results showed that performance outperforms the state-of-the-art models in terms of accuracy and stability and is comparable to that of human experts in classifying precancerous lesions and invasive adenocarcinoma. We also provide a fusion MVCS network (MVCSN) by combining the CT image with the clinical characteristics and radiographic features of patients. CONCLUSION: This tool may ultimately aid in expediting resection of the malignant SCPNs and avoid over-diagnosis of the benign ones, resulting in improved management outcomes. CLINICAL RELEVANCE STATEMENT: In the diagnosis of sub-centimeter lung adenocarcinoma, fusion MVCSN can help doctors improve work efficiency and guide their treatment decisions to a certain extent. KEY POINTS: • Advances in computed tomography (CT) not only increase the number of nodules detected, but also the nodules that are identified are smaller, such as sub-centimeter pulmonary nodules (SCPNs). • We propose a multi-view coupled self-attention module (MVCS), which could model spatial and dimensional correlations sequentially for learning global spatial contexts, which is better than other attention mechanisms. • MVCS uses fewer huge memory consumption and computational complexity than the existing self-attention methods when dealing with 3D medical image data. Additionally, it reaches promising accuracy for SCPNs' malignancy evaluation and has lower training cost than other models.

Performance Analysis in Children of Traditional and Deep Learning CT Lung Nodule Computer-Aided Detection Systems Trained on Adults.

BACKGROUND. Although primary lung cancer is rare in children, chest CT is commonly performed to assess for lung metastases in children with cancer. Lung nodule computer-aided detection (CAD) systems have been designed and studied primarily using adult training data, and the efficacy of such systems when applied to pediatric patients is poorly understood. OBJECTIVE. The purpose of this study was to evaluate in children the diagnostic performance of traditional and deep learning CAD systems trained with adult data for the detection of lung nodules on chest CT scans and to compare the ability of such systems to generalize to children versus to other adults. METHODS. This retrospective study included pediatric and adult chest CT test sets. The pediatric test set comprised 59 CT scans in 59 patients (30 boys, 29 girls; mean age, 13.1 years; age range, 4-17 years), which were obtained from November 30, 2018, to August 31, 2020; lung nodules were annotated by fellowship-trained pediatric radiologists as the reference standard. The adult test set was the publicly available adult Lung Nodule Analysis (LUNA) 2016 subset 0, which contained 89 deidentified scans with previously annotated nodules. The test sets were processed through the traditional FlyerScan (github.com/rhardie1/FlyerScanCT) and deep learning Medical Open Network for Artificial Intelligence (MONAI; github.com/Project-MONAI/model-zoo/releases) lung nodule CAD systems, which had been trained on separate sets of CT scans in adults. Sensitivity and false-positive (FP) frequency were calculated for nodules measuring 3-30 mm; nonoverlapping 95% CIs indicated significant differences. RESULTS. Operating at two FPs per scan, on pediatric testing data FlyerScan and MONAI showed significantly lower detection sensitivities of 68.4% (197/288; 95% CI, 65.1-73.0%) and 53.1% (153/288; 95% CI, 46.7-58.4%), respectively, than on adult LUNA 2016 subset 0 testing data (83.9% [94/112; 95% CI, 79.1-88.0%] and 95.5% [107/112; 95% CI, 90.0-98.4%], respectively). Mean nodule size was smaller (p < .001) in the pediatric testing data (5.4 ± 3.1 [SD] mm) than in the adult LUNA 2016 subset 0 testing data (11.0 ± 6.2 mm). CONCLUSION. Adult-trained traditional and deep learning-based lung nodule CAD systems had significantly lower sensitivity for detection on pediatric data than on adult data at a matching FP frequency. The performance difference may relate to the smaller size of pediatric lung nodules. CLINICAL IMPACT. The results indicate a need for pediatric-specific lung nodule CAD systems trained on data specific to pediatric patients.

Clinical Outcomes of Resected Pure Ground-Glass, Heterogeneous Ground-Glass, and Part-Solid Pulmonary Nodules.

BACKGROUND. Increased (but not definitively solid) attenuation within pure ground-glass nodules (pGGNs) may indicate invasive adenocarcinoma and the need for resection rather than surveillance. OBJECTIVE. The purpose of this study was to compare the clinical outcomes among resected pGGNs, heterogeneous ground-glass nodules (GGNs), and part-solid nodules (PSNs). METHODS. This retrospective study included 469 patients (335 female patients and 134 male patients; median age, 68 years [IQR, 62.5-73.5 years]) who, between January 2012 and December 2020, underwent resection of lung adenocarcinoma that appeared as a subsolid nodule on CT. Two radiologists, using lung windows, independently classified each nodule as a pGGN, a heterogeneous GGN, or a PSN, resolving discrepancies through discussion. A heterogeneous GGN was defined as a GGN with internal increased attenuation not quite as dense as that of pulmonary vessels, and a PSN was defined as having an internal solid component with the same attenuation as that of the pulmonary vessels. Outcomes included pathologic diagnosis of invasive adenocarcinoma, 5-year recurrence rates (locoregional or distant), and recurrence-free survival (RFS) and overall survival (OS) over 7 years, as analyzed by Kaplan-Meier and Cox proportional hazards regression analyses, with censoring of patients with incomplete follow-up. RESULTS. Interobserver agreement for nodule type, expressed as a kappa coefficient, was 0.69. Using consensus assessments, 59 nodules were pGGNs, 109 were heterogeneous GGNs, and 301 were PSNs. The frequency of invasive adenocarcinoma was 39.0% in pGGNs, 67.9% in heterogeneous GGNs, and 75.7% in PSNs (for pGGNs vs heterogeneous GGNs, p < .001; for pGGNs vs PSNs, p < .001; and for heterogeneous GGNs vs PSNs, p = .28). The 5-year recurrence rate was 0.0% in patients with pGGNs, 6.3% in those with heterogeneous GGNs, and 10.8% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .06; for pGGNs vs PSNs, p = .02; and for heterogeneous GGNs vs PSNs, p = .18). At 7 years, RFS was 97.7% in patients with pGGNs, 82.0% in those with heterogeneous GGNs, and 79.4% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .02; for pGGNs vs PSNs, p = .006; and for heterogeneous GGNs vs PSNs, p = .40); OS was 98.0% in patients with pGGNs, 84.6% in those with heterogeneous GGNs, and 82.9% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .04; for pGGNs vs PSNs, p = .01; and for heterogeneous GGNs vs PSNs, p = .50). CONCLUSION. Resected pGGNs had excellent clinical outcomes. Heterogeneous GGNs had relatively worse outcomes, more closely resembling outcomes for PSNs. CLINICAL IMPACT. The findings support surveillance for truly homogeneous pGGNs versus resection for GGNs showing internal increased attenuation even if not having a true solid component.

Clinical value of deep learning image reconstruction on the diagnosis of pulmonary nodule for ultra-low-dose chest CT imaging.

PURPOSE: To compare the image quality and pulmonary nodule detectability between deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V) in ultra-low-dose CT (ULD-CT). METHODS: 142 participants required lung examination who underwent simultaneously ULD-CT (UL-A, 0.57 ± 0.04 mSv or UL-B, 0.33 ± 0.03 mSv), and standard CT (SDCT, 4.32 ± 0.33 mSv) plain scans were included in this prospective study. SDCT was the reference standard using ASIR-V at 50% strength (50%ASIR-V). ULD-CT was reconstructed with 50%ASIR-V, DLIR at medium and high strength (DLIR-M, DLIR-H). The noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective scores were measured. The presence and accuracy of nodules were analyzed using a combination of a deep learning-based nodule evaluation system and a radiologist. RESULTS: A total of 710 nodules were detected by SDCT, including 358 nodules in UL-A and 352 nodules in UL-B. DLIR-H exhibited superior noise, SNR, and CNR performance, and achieved comparable or even higher subjective scores compared to 50%ASIR-V in ULD-CT. Nodules sensitivity detection of 50%ASIR-V, DLIR-M, and DLIR-H in ULD-CT were identical (96.90%). In multivariate analysis, body mass index (BMI), nodule diameter, and type were independent predictors for the sensitivity of nodule detection (p<.001). DLIR-H provided a lower absolute percent error (APE) in volume (3.10% ± 95.11% vs 8.29% ± 99.14%) compared to 50%ASIR-V of ULD-CT (P<.001). CONCLUSIONS: ULD-CT scanning has a high sensitivity for detecting pulmonary nodules. Compared with ASIR-V, DLIR can significantly reduce image noise, and improve image quality, and accuracy of the nodule measurement in ULD-CT.

The influence of respiratory movement on preoperative CT-guided localization of lung nodules.

AIM: To evaluate the motion amplitude of lung nodules in different locations during preoperative computed tomography (CT)-guided localization, and the influence of respiratory movement on CT-guided percutaneous lung puncture. MATERIALS AND METHODS: A consecutive cohort of 398 patients (123 men and 275 women with a mean age of 53.9 ± 10.7 years) who underwent preoperative CT-guided lung nodule localization from May 2021 to Apr 2022 were included in this retrospective study. The respiratory movement-related nodule amplitude in the cranial-caudal direction during the CT scan, characteristics of patients, lesions, and procedures were statistically analyzed. Univariate and multivariate logistic regression analyses were used to evaluate the influence of these factors on CT-guided localization. RESULTS: The nodule motion distribution showed a statistically significant correlation within the upper/middle (lingular) and lower lobes (p<0.001). Motion amplitude was an independent risk factor for CT scan times (p=0.011) and procedure duration (p=0.016), but not for the technical failure rates or the incidence of complications. Puncture depth was an independent risk factor for the CT scan times, procedure duration, technical failure rates, and complications (p<0.01). Female, prone, and supine (as opposed to lateral) positions were significant protective factors for pneumothorax, while the supine position was an independent risk factor for parenchymal hemorrhage (p=0.025). CONCLUSION: Respiratory-induced motion amplitude of nodules was greater in the lower lobes, resulting in more CT scan times/radiation dose and longer localization duration, but showed no statistically significant influence on the technical success rates or the incidence of complications during preoperative CT-guided localization.

Consequences of Losing Incidental Pulmonary Nodules to Follow-Up: Unmonitored Nodules Progressing to Stage IV Lung Cancer.

INTRODUCTION: Lung cancer is the leading cause of cancer-related death globally. Incidental pulmonary nodules represent a golden opportunity for early diagnosis, which is critical for improving survival rates. This study explores the impact of missed pulmonary nodules on the progression of lung cancer. METHODS: A total of 4,066 stage IV lung cancer cases from 2019 to 2021 in Danish hospitals were investigated to determine whether a chest computed tomography (CT) had been performed within 2 years before diagnosis. CT reports and images were reviewed to identify nodules that had been missed by radiologists or were not appropriately monitored, despite being mentioned by the radiologist, and to assess whether these nodules had progressed to stage IV lung cancer. RESULTS: Among stage IV lung cancer patients, 13.6% had undergone a chest CT scan before their diagnosis; of these, 44.4% had nodules mentioned. Radiologists missed a nodule in 7.6% of cases. In total, 45.3% of nodules were not appropriately monitored. An estimated 2.5% of stage IV cases could have been detected earlier with proper surveillance. CONCLUSION: This study underlines the significance of monitoring pulmonary nodules and proposes strategies for enhancing detection and surveillance. These strategies include centralized monitoring and the implementation of automated registries to prevent gaps in follow-up.

Shape-Sensing Robotic-Assisted Bronchoscopy versus Computed Tomography-Guided Transthoracic Biopsy for the Evaluation of Subsolid Pulmonary Nodules.

INTRODUCTION: Lung cancer remains the leading cause of cancer death worldwide. Subsolid nodules (SSN), including ground-glass nodules (GGNs) and part-solid nodules (PSNs), are slow-growing but have a higher risk for malignancy. Therefore, timely diagnosis is imperative. Shape-sensing robotic-assisted bronchoscopy (ssRAB) has emerged as reliable diagnostic procedure, but data on SSN and how ssRAB compares to other diagnostic interventions such as CT-guided transthoracic biopsy (CTTB) are scarce. In this study, we compared diagnostic yield of ssRAB versus CTTB for evaluating SSN. METHODS: A retrospective study of consecutive patients who underwent either ssRAB or CTTB for evaluating GGN and PSN with a solid component less than 6 mm from February 2020 to April 2023 at Mayo Clinic Florida and Rochester. Clinicodemographic information, nodule characteristics, diagnostic yield, and complications were compared between ssRAB and CTTB. RESULTS: A total of 66 nodules from 65 patients were evaluated: 37 PSN and 29 GGN. Median size of PSN solid component was 5 mm (IQR: 4.5, 6). Patients were divided into two groups: 27 in the ssRAB group and 38 in the CTTB group. Diagnostic yield was 85.7% for ssRAB and 89.5% for CTTB (p = 0.646). Sensitivity for malignancy was similar between ssRAB and CTTB (86.4% vs. 88.5%; p = 0.828), with no statistical difference. Complications were more frequent in CTTB with no significant difference (8 vs. 2; p = 0.135). CONCLUSION: Diagnostic yield for SSN was similarly high for ssRAB and CTTB, with ssRAB presenting less complications and allowing mediastinal staging within the same procedure.

Presurgical computed tomography-guided localization of lung ground glass nodules: comparing hook-wire and indocyanine green.

BACKGROUND: Presurgical computed tomography (CT)-guided localization is frequently employed to reduce the thoracotomy conversion rate, while increasing the rate of successful sublobar resection of ground glass nodules (GGNs) via video-assisted thoracoscopic surgery (VATS). In this study, we compared the clinical efficacies of presurgical CT-guided hook-wire and indocyanine green (IG)-based localization of GGNs. METHODS: Between January 2018 and December 2021, we recruited 86 patients who underwent CT-guided hook-wire or IG-based GGN localization before VATS resection in our hospital, and compared the clinical efficiency and safety of both techniques. RESULTS: A total of 38 patients with 39 GGNs were included in the hook-wire group, whereas 48 patients with 50 GGNs were included in the IG group. There were no significant disparities in the baseline data between the two groups of patients. According to our investigation, the technical success rates of CT-based hook-wire- and IG-based localization procedures were 97.4% and 100%, respectively (P = 1.000). Moreover, the significantly longer localization duration (15.3 ± 6.3 min vs. 11.2 ± 5.3 min, P = 0.002) and higher visual analog scale (4.5 ± 0.6 vs. 3.0 ± 0.5, P = 0.001) were observed in the hook-wire patients, than in the IG patients. Occurrence of pneumothorax was significantly higher in hook-wire patients (27.3% vs. 6.3%, P = 0.048). Lung hemorrhage seemed higher in hook-wire patients (28.9% vs. 12.5%, P = 0.057) but did not reach statistical significance. Lastly, the technical success rates of VATS sublobar resection were 97.4% and 100% in hook-wire and IG patients, respectively (P = 1.000). CONCLUSIONS: Both hook-wire- and IG-based localization methods can effectively identified GGNs before VATS resection. Furthermore, IG-based localization resulted in fewer complications, lower pain scores, and a shorter duration of localization.

Morphological Predictors of Primary Lung Cancer among Part-Solid Ground-Grass Nodules on High-Resolution CT.

Recent advancements in computed tomography (CT) scanning have improved the detection rates of peripheral pulmonary nodules, including those with ground-glass opacities (GGOs). This study focuses on part-solid pure ground-glass nodules (GGNs) and aims to identify imaging predictors that can reliably differentiate primary lung cancer from nodules with other diagnoses among part-solid GGNs on high-resolution CT (HRCT). A retrospective study was conducted on 609 patients who underwent surgical treatment or observation for lung nodules. Radiological findings from pre-operative HRCT scans were reviewed and several CT imaging features of part-solid GGNs were examined for their positive predictive value to identify primary lung cancer. The proportions of the nodules with a final diagnosis of primary lung cancer were significantly higher in part-solid GGNs (91.9%) compared with solid nodules (70.3%) or pure GGNs (66.7%). Among CT imaging features of part-solid GGNs that were evaluated, consolidation-to-tumor ratio (CTR) < 0.5 (98.1%), pleural indentation (96.4%), and clear tumor border (96.7%) had high positive predictive value to identify primary lung cancer. When two imaging features were combined, the combination of CTR < 0.5 and a clear tumor border was identified to have 100% positive predictive values with a sensitivity of 40.8%. Thus we conclude that part-solid GGNs with a CTR < 0.5 accompanied by a clear tumor border evaluated by HRCT are very likely to be primary lung cancers with an acceptable sensitivity. Preoperative diagnostic procedures to obtain a pathological diagnosis may potentially be omitted in patients harboring such part-solid GGNs.

Dual-branch feature fusion S3D V-Net network for lung nodules segmentation.

BACKGROUND: Accurate segmentation of lung nodules can help doctors get more accurate results and protocols in early lung cancer diagnosis and treatment planning, so that patients can be better detected and treated at an early stage, and the mortality rate of lung cancer can be reduced. PURPOSE: Currently, the improvement of lung nodule segmentation accuracy has been limited by his heterogeneous performance in the lungs, the imbalance between segmentation targets and background pixels, and other factors. We propose a new 2.5D lung nodule segmentation network model for lung nodule segmentation. This network model can well improve the extraction of edge information of lung nodules, and fuses intra-slice and inter-slice features, which makes good use of the three-dimensional structural information of lung nodules and can more effectively improve the accuracy of lung nodule segmentation. METHODS: Our approach is based on a typical encoding-decoding network structure for improvement. The improved model captures the features of multiple nodules in both 3-D and 2-D CT images, complements the information of the segmentation target's features and enhances the texture features at the edges of the pulmonary nodules through the dual-branch feature fusion module (DFFM) and the reverse attention context module (RACM), and employs central pooling instead of the maximal pooling operation, which is used to preserve the features around the target and to eliminate the edge-irrelevant features, to further improve the performance of the segmentation of the pulmonary nodules. RESULTS: We evaluated this method on a wide range of 1186 nodules from the LUNA16 dataset, and averaging the results of ten cross-validated, the proposed method achieved the mean dice similarity coefficient (mDSC) of 84.57%, the mean overlapping error (mOE) of 18.73% and average processing of a case is about 2.07 s. Moreover, our results were compared with inter-radiologist agreement on the LUNA16 dataset, and the average difference was 0.74%. CONCLUSION: The experimental results show that our method improves the accuracy of pulmonary nodules segmentation and also takes less time than more 3-D segmentation methods in terms of time.

Artificial intelligence-based graded training of pulmonary nodules for junior radiology residents and medical imaging students.

BACKGROUND: To evaluate the efficiency of artificial intelligence (AI)-assisted diagnosis system in the pulmonary nodule detection and diagnosis training of junior radiology residents and medical imaging students. METHODS: The participants were divided into three groups. Medical imaging students of Grade 2020 in the Jinzhou Medical University were randomly divided into Groups 1 and 2; Group 3 comprised junior radiology residents. Group 1 used the traditional case-based teaching mode; Groups 2 and 3 used the 'AI intelligent assisted diagnosis system' teaching mode. All participants performed localisation, grading and qualitative diagnosed of 1,057 lung nodules in 420 cases for seven rounds of testing after training. The sensitivity and number of false positive nodules in different densities (solid, pure ground glass, mixed ground glass and calcification), sizes (less than 5 mm, 5-10 mm and over 10 mm) and positions (subpleural, peripheral and central) of the pulmonary nodules in the three groups were detected. The pathological results and diagnostic opinions of radiologists formed the criteria. The detection rate, diagnostic compliance rate, false positive number/case, and kappa scores of the three groups were compared. RESULTS: There was no statistical difference in baseline test scores between Groups 1 and 2, and there were statistical differences with Group 3 (P = 0.036 and 0.011). The detection rate of solid, pure ground glass and calcified nodules; small-, medium-, and large-diameter nodules; and peripheral nodules were significantly different among the three groups (P<0.05). After seven rounds of training, the diagnostic compliance rate increased in all three groups, with the largest increase in Group 2. The average kappa score increased from 0.508 to 0.704. The average kappa score for Rounds 1-4 and 5-7 were 0.595 and 0.714, respectively. The average kappa scores of Groups 1,2 and 3 increased from 0.478 to 0.658, 0.417 to 0.757, and 0.638 to 0.791, respectively. CONCLUSION: The AI assisted diagnosis system is a valuable tool for training junior radiology residents and medical imaging students to perform pulmonary nodules detection and diagnosis.

Limitations of GPT-3.5 and GPT-4 in Applying Fleischner Society Guidelines to Incidental Lung Nodules.

Purpose: To evaluate the accuracy of GPT-3.5, GPT-4, and a fine-tuned GPT-3.5 model in applying Fleischner Society recommendations to lung nodules. Methods: We generated 10 lung nodule descriptions for each of the 12 nodule categories from the Fleischner Society guidelines, incorporating them into a single fictitious report (n = 120). GPT-3.5 and GPT-4 were prompted to make follow-up recommendations based on the reports. We then incorporated the full guidelines into the prompts and re-submitted them. Finally, we re-submitted the prompts to a fine-tuned GPT-3.5 model. Results were analyzed using binary accuracy analysis in R. Results: GPT-3.5 accuracy in applying Fleischner Society guidelines was 0.058 (95% CI: 0.02, 0.12). GPT-4 accuracy was improved at 0.15 (95% CI: 0.09, 0.23; P = .02 for accuracy comparison). In recommending PET-CT and/or biopsy, both GPT-3.5 and GPT-4 had an F-score of 0.00. After explicitly including the Fleischner Society guidelines in the prompt, GPT-3.5 and GPT-4 significantly improved their accuracy to 0.42 (95% CI: 0.33, 0.51; P < .001) and to 0.66 (95% CI: 0.57, 0.74; P < .001), respectively. GPT-4 remained significantly better than GPT-3.5 (P < .001). The fine-tuned GPT-3.5 model accuracy was 0.46 (95% CI: 0.37, 0.55), not different from the GPT-3.5 model with guidelines included (P = .53). Conclusion: GPT-3.5 and GPT-4 performed poorly in applying widely known guidelines and never correctly recommended biopsy. Flawed knowledge and reasoning both contributed to their poor performance. While GPT-4 was more accurate than GPT-3.5, its inaccuracy rate was unacceptable for clinical practice. These results underscore the limitations of large language models for knowledge and reasoning-based tasks.