Performance of Lung-RADS in different target populations: a systematic review and meta-analysis.

OBJECTIVES: Multiple lung cancer screening studies reported the performance of Lung CT Screening Reporting and Data System (Lung-RADS), but none systematically evaluated its performance across different populations. This systematic review and meta-analysis aimed to evaluate the performance of Lung-RADS (versions 1.0 and 1.1) for detecting lung cancer in different populations. METHODS: We performed literature searches in PubMed, Web of Science, Cochrane Library, and Embase databases on October 21, 2022, for studies that evaluated the accuracy of Lung-RADS in lung cancer screening. A bivariate random-effects model was used to estimate pooled sensitivity and specificity, and heterogeneity was explored in stratified and meta-regression analyses. RESULTS: A total of 31 studies with 104,224 participants were included. For version 1.0 (27 studies, 95,413 individuals), pooled sensitivity was 0.96 (95% confidence interval [CI]: 0.90-0.99) and pooled specificity was 0.90 (95% CI: 0.87-0.92). Studies in high-risk populations showed higher sensitivity (0.98 [95% CI: 0.92-0.99] vs. 0.84 [95% CI: 0.50-0.96]) and lower specificity (0.87 [95% CI: 0.85-0.88] vs. 0.95 (95% CI: 0.92-0.97]) than studies in general populations. Non-Asian studies tended toward higher sensitivity (0.97 [95% CI: 0.91-0.99] vs. 0.91 [95% CI: 0.67-0.98]) and lower specificity (0.88 [95% CI: 0.85-0.90] vs. 0.93 [95% CI: 0.88-0.96]) than Asian studies. For version 1.1 (4 studies, 8811 individuals), pooled sensitivity was 0.91 (95% CI: 0.83-0.96) and specificity was 0.81 (95% CI: 0.67-0.90). CONCLUSION: Among studies using Lung-RADS version 1.0, considerable heterogeneity in sensitivity and specificity was noted, explained by population type (high risk vs. general), population area (Asia vs. non-Asia), and cancer prevalence. CLINICAL RELEVANCE STATEMENT: Meta-regression of lung cancer screening studies using Lung-RADS version 1.0 showed considerable heterogeneity in sensitivity and specificity, explained by the different target populations, including high-risk versus general populations, Asian versus non-Asian populations, and populations with different lung cancer prevalence. KEY POINTS: • High-risk population studies showed higher sensitivity and lower specificity compared with studies performed in general populations by using Lung-RADS version 1.0. • In non-Asian studies, the diagnostic performance of Lung-RADS version 1.0 tended to be better than in Asian studies. • There are limited studies on the performance of Lung-RADS version 1.1, and evidence is lacking for Asian populations.

Deep learning in pulmonary nodule detection and segmentation: a systematic review.

OBJECTIVES: The accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature. METHODS: This study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information. RESULTS: After screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient. CONCLUSIONS: This study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research. CLINICAL RELEVANCE STATEMENT: Deep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility. KEY POINTS: Deep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

First-in-human use of a new robotic electromagnetic navigation bronchoscopic platform with integrated Tool-in-Lesion Tomosynthesis (TiLT) technology for peripheral pulmonary lesions: The FRONTIER study.

BACKGROUND AND OBJECTIVE: As the presentation of pulmonary nodules increases, the importance of a safe and accurate method of sampling peripheral pulmonary nodules is highlighted. First-generation robotic bronchoscopy has successfully assisted navigation and improved peripheral reach during bronchoscopy. Integrating tool-in-lesion tomosynthesis (TiLT) may further improve yield. METHODS: We performed a first-in-human clinical trial of a new robotic electromagnetic navigation bronchoscopy system with integrated digital tomosynthesis technology (Galaxy System, Noah Medical). Patients with moderate-risk peripheral pulmonary nodules were enrolled in the study. Robotic bronchoscopy was performed using electromagnetic navigation with TiLT-assisted lesion guidance. Non-specific results were followed up until either a clear diagnosis was achieved or repeat radiology at 6 months demonstrated stability. RESULTS: Eighteen patients (19 nodules) were enrolled. The average lesion size was 20 mm, and the average distance from the pleura was 11.6 mm. The target was successfully reached in 100% of nodules, and the biopsy tool was visualized inside the target lesion in all cases. A confirmed specific diagnosis was achieved in 17 nodules, 13 of which were malignant. In one patient, radiological monitoring confirmed a true non-malignant result. This translates to a yield of 89.5% (strict) to 94.7% (intermediate). Complications included one pneumothorax requiring observation only and another requiring an overnight chest drain. There was one case of severe pneumonia following the procedure. CONCLUSION: In this first-in-human study, second-generation robotic bronchoscopy using electromagnetic navigation combined with integrated digital tomosynthesis was feasible with an acceptable safety profile and demonstrated a high diagnostic yield for small peripheral lung nodules.

A combined diagnostic model based on circulating tumor cell in patients with solitary pulmonary nodules.

BACKGROUND: Although many prediction models in diagnosis of solitary pulmonary nodules (SPNs) have been developed, few are widely used in clinical practice. It is therefore imperative to identify novel biomarkers and prediction models supporting early diagnosis of SPNs. This study combined folate receptor-positive circulating tumor cells (FR+ CTC) with serum tumor biomarkers, patient demographics and clinical characteristics to develop a prediction model. METHODS: A total of 898 patients with a solitary pulmonary nodule who received FR+ CTC detection were randomly assigned to a training set and a validation set in a 2:1 ratio. Multivariate logistic regression was used to establish a diagnostic model to differentiate malignant and benign nodules. The receiver operating curve (ROC) and the area under the curve (AUC) were calculated to assess the diagnostic efficiency of the model. RESULTS: The positive rate of FR+ CTC between patients with non-small cell lung cancer (NSCLC) and benign lung disease was significantly different in both the training and the validation dataset (p < 0.001). The FR+ CTC level was significantly higher in the NSCLC group compared with that of the benign group (p < 0.001). FR+ CTC (odds ratio, OR, 95% confidence interval, CI: 1.13, 1.07-1.19, p < 0.0001), age (OR, 95% CI: 1.06, 1.01-1.12, p = 0.03) and sex (OR, 95% CI: 1.07, 1.01-1.13, p = 0.01) were independent risk factors of NSCLC in patients with a solitary pulmonary nodule. The area under the curve (AUC) of FR+ CTC in diagnosing NSCLC was 0.650 (95% CI, 0.587-0.713) in the training set and 0.700 (95% CI, 0.603-0.796) in the validation set, respectively. The AUC of the combined model was 0.725 (95% CI, 0.659-0.791) in the training set and 0.828 (95% CI, 0.754-0.902) in the validation set, respectively. CONCLUSIONS: We confirmed the value of FR+ CTC in diagnosing SPNs and developed a prediction model based on FR+ CTC, demographic characteristics, and serum biomarkers for differential diagnosis of solitary pulmonary nodules.

Serum lncRNA THRIL predicts benign and malignant pulmonary nodules and promotes the progression of pulmonary malignancies.

BACKGROUND: This project aimed to research the significance of THRIL in the diagnosis of benign and malignant solitary pulmonary nodules (SPNs) and to investigate the role of THRIL/miR-99a in malignant SPNs. METHODS: The study groups consisted of 169 patients with SPN and 74 healthy subjects. The differences in THRIL levels were compared between the two groups and the healthy group. The receiver operating characteristic curve (ROC) was utilized to analyze the THRIL's significance in detecting benign and malignant SPN. Pearson correlation and binary regression coefficients represented the association between THRIL and SPN. CCK-8 assay, Transwell assay, and flow cytometry were utilized to detect the regulatory effect of THRIL silencing. The interaction between THRIL, miR-99a, and IGF1R was confirmed by the double luciferase reporter gene. RESULTS: There were differences in THRIL expression in the healthy group, benign SPN group, and malignant SPN group. High accuracy of THRIL in the diagnosis of benign SPN and malignant SPN was observed. THRIL was associated with the development of SPN. The expression of THRIL was upregulated and miR-99a was downregulated in lung cancer cells. The double luciferase report experiment confirmed the connections between THRIL/miR-99a/IGF1R. Silencing THRIL could suppress cell proliferation, migration, and invasion and promote cell apoptosis by binding miR-99a. CONCLUSION: The detection of THRIL in serum is useful for the assessment of malignant SPN. THRIL can regulate the expression of IGF1R through miR-99a, thereby promoting the growth of lung cancer cells and inhibiting apoptosis.

Radiologists with and without deep learning-based computer-aided diagnosis: comparison of performance and interobserver agreement for characterizing and diagnosing pulmonary nodules/masses.

OBJECTIVES: To compare the performance of radiologists in characterizing and diagnosing pulmonary nodules/masses with and without deep learning (DL)-based computer-aided diagnosis (CAD). METHODS: We studied a total of 101 nodules/masses detected on CT performed between January and March 2018 at Osaka University Hospital (malignancy: 55 cases). SYNAPSE SAI Viewer V1.4 was used to analyze the nodules/masses. In total, 15 independent radiologists were grouped (n = 5 each) according to their experience: L (< 3 years), M (3-5 years), and H (> 5 years). The likelihoods of 15 characteristics, such as cavitation and calcification, and the diagnosis (malignancy) were evaluated by each radiologist with and without CAD, and the assessment time was recorded. The AUCs compared with the reference standard set by two board-certified chest radiologists were analyzed following the multi-reader multi-case method. Furthermore, interobserver agreement was compared using intraclass correlation coefficients (ICCs). RESULTS: The AUCs for ill-defined boundary, irregular margin, irregular shape, calcification, pleural contact, and malignancy in all 15 radiologists, irregular margin and irregular shape in L and ill-defined boundary and irregular margin in M improved significantly (p < 0.05); no significant improvements were found in H. L showed the greatest increase in the AUC for malignancy (not significant). The ICCs improved in all groups and for nearly all items. The median assessment time was not prolonged by CAD. CONCLUSIONS: DL-based CAD helps radiologists, particularly those with < 5 years of experience, to accurately characterize and diagnose pulmonary nodules/masses, and improves the reproducibility of findings among radiologists. KEY POINTS: • Deep learning-based computer-aided diagnosis improves the accuracy of characterizing nodules/masses and diagnosing malignancy, particularly by radiologists with < 5 years of experience. • Computer-aided diagnosis increases not only the accuracy but also the reproducibility of the findings across radiologists.

Detection efficacy of analog [18F]FDG PET/CT, digital [18F]FDG, and [13N]NH3 PET/CT: a prospective, comparative study of patients with lung adenocarcinoma featuring ground glass nodules.

OBJECTIVES: This prospective study compared the detection efficacy of analog 18F-fluoro-2-deoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) (aF PET/CT), digital [18F]FDG PET/CT (dF PET/CT), and digital 13N-ammonia (13N-NH3) PET/CT (dN PET/CT) for patients with lung adenocarcinoma featuring ground glass nodules (GGNs). METHODS: Eighty-seven patients with lung adenocarcinoma featuring GGNs who underwent dF and dN PET/CT were enrolled. Based on the GGN component, diameter, and solid-part size, 87 corresponding patients examined using aF PET/CT were included, with age, sex, and lesion characteristics closely matched. Images were visually evaluated, and the tumor to background ratio (TBR) was used for semi-quantitative analysis. RESULTS: Ultimately, 40 and 47 patients with pure GGNs (pGGNs) and mixed GGNs (mGGNs), respectively, were included. dF PET/CT revealed more positive lesions and higher tracer uptake in GGNs than did aF PET/CT (53/87 vs. 26/87, p < 0.05; TBR: 3.08 ± 4.85 vs. 1.42 ± 0.93, p < 0.05), especially in mGGNs (44/47 vs. 26/47, p < 0.05; TBR: 4.48 ± 6.17 vs. 1.78 ± 1.16, p < 0.05). However, dN PET/CT detected more positive lesions than did dF PET/CT (71/87 vs. 53/87, p < 0.05), especially in pGGNs (24/40 vs. 9/40, p < 0.05). CONCLUSIONS: dF PET/CT provides superior detection efficacy over aF PET/CT for patients with lung adenocarcinoma featuring GGNs, particularly mGGNs. dN PET/CT revealed superior detection efficacy over dF PET/CT, particularly in pGGNs. aF, dF, and dN PET/CT are valuable non-invasive examinations for lung cancer featuring GGNs, with dN PET/CT offering the best detection performance. KEY POINTS: • Digital PET/CT provides superior detection efficacy over analog PET/CT in patients with lung adenocarcinoma featuring GGNs. • dN PET/CT can offer more help in the early detection of malignant GGN.

Routine radiology-pathology concordance evaluation of CT-guided percutaneous lung biopsies increases the number of cancers identified.

BACKGROUND: Routine concordance evaluation between pathology and imaging findings was introduced for CT-guided biopsies. PURPOSE: To analyze malignancy rate in concordant, discordant, and indeterminate non-malignant results of CT-guided lung biopsies. METHODS: Concordance between pathology results and imaging findings of consecutive patients undergoing CT-guided lung biopsy between 7/1/2016 and 9/30/2021 was assessed during routine meetings by procedural radiologists. Concordant was defined as pathology consistent with imaging findings; discordant was used when pathology could not explain imaging findings; indeterminate when pathology could explain imaging findings but there was concern for malignancy. Recommendations for discordant and indeterminate were provided. All the malignant results were concordant. Pathology of repeated biopsy, surgical sample, or follow-up was considered reference standard. RESULTS: Consecutive 828 CT-guided lung biopsies were performed on 795 patients (median age 70 years, IQR 61-77), 423/828 (51%) women. On pathology, 224/828 (27%) were non-malignant. Among the non-malignant, radiology-pathology concordance determined 138/224 (62%) to be concordant with imaging findings, 54/224 (24%) discordant, and 32/224 (14%) indeterminate. When compared to the reference standard, 33/54 (61%) discordant results, 6/30 (20%) indeterminate, and 3/133 (2%) concordant were malignant. The prevalence of malignancy in the three groups was significantly different (p < 0.001). Time to diagnosis was significantly different between patients who reached the diagnosis with imaging follow-up (median 114 days, IQR 69-206) compared to repeat biopsy (33 days, IQR 18-133) (p = 0.01). CONCLUSION: Routine radiology-pathology concordance evaluation of CT-guided lung biopsy correctly identifies patients at high risk for missed diagnosis of malignancy. Repeat biopsy is the fastest method to reach diagnosis. CLINICAL RELEVANCE STATEMENT: A routine radiology-pathology concordance assessment identifies patients with non-malignant CT-guided lung biopsy result who are at greater risk of missed diagnosis of malignancy. KEY POINTS: • A routine radiology-pathology concordance evaluation of CT-guided lung biopsies classified 224 non-malignant results as concordant, discordant, or indeterminate. • The percentage of malignancy on follow-up was significantly different in concordant (2%), discordant (61%), and indeterminate (20%) (p < 0.001). • Time to definitive diagnosis was significantly shorter with repeat biopsy (33 days), compared to imaging follow-up (114 days), p = 0.01.

Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? A systematic review.

OBJECTIVES: To provide an overarching evaluation of the value of peritumoral CT radiomics features for predicting the prognosis of non-small cell lung cancer and to assess the quality of the available studies. METHODS: The PubMed, Embase, Web of Science, and Cochrane Library databases were searched for studies predicting the prognosis in patients with non-small cell lung cancer (NSCLC) using CT-based peritumoral radiomics features. Information about the patient, CT-scanner, and radiomics analyses were all extracted for the included studies. Study quality was assessed using the Radiomics Quality Score (RQS) and the Prediction Model Risk of Bias Assessment Tool (PROBAST). RESULTS: Thirteen studies were included with 2942 patients from 2017 to 2022. Only one study was prospective, and the others were all retrospectively designed. Manual segmentation and multicenter studies were performed by 69% and 46% of the included studies, respectively. 3D-Slicer and MATLAB software were most commonly used for the segmentation of lesions and extraction of features. The peritumoral region was most frequently defined as dilated from the tumor boundary of 15 mm, 20 mm, or 30 mm. The median RQS of the studies was 13 (range 4-19), while all of included studies were assessed as having a high risk of bias (ROB) overall. CONCLUSIONS: Peritumoral radiomics features based on CT images showed promise in predicting the prognosis of NSCLC, although well-designed studies and further biological validation are still needed. KEY POINTS: • Peritumoral radiomics features based on CT images are promising and encouraging for predicting the prognosis of non-small cell lung cancer. • The peritumoral region was often dilated from the tumor boundary of 15 mm or 20 mm because these were considered safe margins. • The median Radiomics Quality Score of the included studies was 13 (range 4-19), and all of studies were considered to have a high risk of bias overall.

Ultrathin Bronchoscopy for the Diagnosis of Peripheral Pulmonary Lesions: A Meta-Analysis.

BACKGROUND: Ultrathin bronchoscopy (external diameter, ≤3.5 mm) is useful for the diagnosis of peripheral pulmonary lesions because of its good accessibility. OBJECTIVES: We performed a meta-analysis to investigate the diagnostic yield of ultrathin bronchoscopy for peripheral pulmonary lesions. METHODS: We performed a systematic search of MEDLINE and EMBASE (from inception to May 2021), and meta-analysis was performed using R software. The diagnostic yield was evaluated by dividing the number of successful diagnoses by the total number of lesions, and subgroup analysis was performed to identify related factors. RESULTS: Nineteen studies with a total of 1,977 peripheral pulmonary lesions were included. The pooled diagnostic yield of ultrathin bronchoscopy was 0.65 (95% confidence interval, 0.60-0.70). Significant heterogeneity was observed among studies (χ2, 87.75; p < 0.01; I2, 79.5%). In a subgroup analysis, ultrathin bronchoscopy with 1.2 mm channel size showed a diagnostic yield of 0.61 (95% confidence interval, 0.53-0.68), whereas ultrathin bronchoscopy with 1.7 mm channel size showed 0.70 (95% confidence interval, 0.66-0.74) (χ2, 5.35; p = 0.02). In addition, there was a significant difference in diagnostic yield based on lesion size, histologic diagnosis (malignant vs. benign), bronchus sign, and lesion location from the hilum, whereas no significant difference was found based on lobar location. The overall complication rate of ultrathin bronchoscopy was 2.7% (pneumothorax, 1.1%). CONCLUSIONS: Ultrathin bronchoscopy is an excellent tool for peripheral pulmonary lesion diagnosis with a low complication rate. The diagnostic yield of ultrathin bronchoscopy was significantly higher with larger channel size, which might be attributed to the availability of radial endobronchial ultrasound.

Molecular characterization of solitary pulmonary nodules in dual-energy CT nonlinear image fusion technology.

OBJECTIVE: To investigate the feasibility and to optimize the parameters of nonlinear blending technique in dual-energy CT on solitary pulmonary nodules (SPN). METHODS: The simulated enhanced SPN were used the mixture of nonionic iodinated contrast agent (Iopromide 370mgI/100 ml) and normal saline and then randomly placed inside an anthropomorphic chest phantom. The phantom was examined on SOMATOM definition flash with dual mode (80/140 kV) and single energy mode (120 kV) (the same CTDIvol). Nonlinear blending images and linear blending images with a weighting factor of 0.3 were generated and the image qualities were analyzed. RESULTS: For different simulated density SPN, when 0 HU was chosen as the Blending Center (BC) and 0 to 30 HU were chosen as the Blending width (BW), the nonlinear blending images yielded a higher contrast-to-noise (CNR). There were significant differences in the image noise and signal-to-noise (SNR) of different simulated density SPN at non-linear blending images, linear blending images and 120 kV images (p < .05); But the differences of CNR between the three groups were not statistically significant (p > .05). The SNR of different simulated density SPN at non-linear blending images was significantly increased compared with it at linear blending images and 120 kV images (p < .05); And the image noise at non-linear blending was lower than it at linear blending images (p < .05). CONCLUSION: Nonlinear blending technique in dual-energy CT can increase the SNR of enhanced SPN, and it is helpful in diagnosis of SPN.

The role of computer-assisted radiographer reporting in lung cancer screening programmes.

OBJECTIVES: Successful lung cancer screening delivery requires sensitive, timely reporting of low-dose computed tomography (LDCT) scans, placing a demand on radiology resources. Trained non-radiologist readers and computer-assisted detection (CADe) software may offer strategies to optimise the use of radiology resources without loss of sensitivity. This report examines the accuracy of trained reporting radiographers using CADe support to report LDCT scans performed as part of the Lung Screen Uptake Trial (LSUT). METHODS: In this observational cohort study, two radiographers independently read all LDCT performed within LSUT and reported on the presence of clinically significant nodules and common incidental findings (IFs), including recommendations for management. Reports were compared against a 'reference standard' (RS) derived from nodules identified by study radiologists without CADe, plus consensus radiologist review of any additional nodules identified by the radiographers. RESULTS: A total of 716 scans were included, 158 of which had one or more clinically significant pulmonary nodules as per our RS. Radiographer sensitivity against the RS was 68-73.7%, with specificity of 92.1-92.7%. Sensitivity for detection of proven cancers diagnosed from the baseline scan was 83.3-100%. The spectrum of IFs exceeded what could reasonably be covered in radiographer training. CONCLUSION: Our findings highlight the complexity of LDCT reporting requirements, including the limitations of CADe and the breadth of IFs. We are unable to recommend CADe-supported radiographers as a sole reader of LDCT scans, but propose potential avenues for further research including initial triage of abnormal LDCT or reporting of follow-up surveillance scans. KEY POINTS: • Successful roll-out of mass screening programmes for lung cancer depends on timely, accurate CT scan reporting, placing a demand on existing radiology resources. • This observational cohort study examines the accuracy of trained radiographers using computer-assisted detection (CADe) software to report lung cancer screening CT scans, as a potential means of supporting reporting workflows in LCS programmes. • CADe-supported radiographers were less sensitive than radiologists at identifying clinically significant pulmonary nodules, but had a low false-positive rate and good sensitivity for detection of confirmed cancers.

Marking ground glass nodules with pulmonary nodules localization needle prior to video-assisted thoracoscopic surgery.

OBJECTIVES: To evaluate the efficacy and safety of marking ground glass nodules (GGNs) with pulmonary nodules localization needle (PNLN) prior to video-assisted thoracoscopic surgery (VATS). MATERIALS AND METHODS: From June 2020 to February 2021, all patients with GGNs who received CT-guided localization using PNLN before VATS were enrolled. Clinical and imaging data were retrospectively analyzed. RESULTS: A total of 352 consecutive patients with 395 GGNs were included in the study. The mean diameter of GGNs was 0.95 ± 0.48 cm, and the shortest distance from nodules to the pleura was 1.73 ± 0.96 cm. All 395 GGNs were marked using PNLNs. The time required for marking was 7.8 ± 2.2 min. The marking success rate was 99.0% (391/395). The marking failure of four nodules was all due to the unsatisfactory position of PNLNs. No marker dislocation occurred. Marking-related complications included pneumothorax in 63 cases (17.9%), hemorrhage in 34 cases (9.7%), and hemoptysis in 6 cases (1.7%). All the complications were minor and did not need special treatment. Localization and VATS were performed on the same day in 95 cases and on different days in 257 cases. All GGNs were successfully removed by VATS. No patient converted to thoracotomy. Histopathological examination revealed 74 (18.7%) benign nodules and 321 (81.3%) malignant nodules. CONCLUSIONS: It is safe and reliable to perform preoperative localization of GGNs using PNLNs, which can effectively guide VATS to remove GGNs. KEY POINTS: • Preoperative localization of GGNs could effectively guide VATS to remove GGNs. • PNLN was based on the marking principle of hook-wire, through the improvement of its material, specially designed to mark pulmonary nodules. • The application of PNLN to mark GGNs had high success rate, good patient tolerance, and no dislocation. Meanwhile, VATS could be performed 2 to 3 days after marking GGNs with PNLN.

Development and validation of a preoperative CT-based radiomic nomogram to predict pathology invasiveness in patients with a solitary pulmonary nodule: a machine learning approach, multicenter, diagnostic study.

OBJECTIVES: To develop and validate a preoperative CT-based nomogram combined with radiomic and clinical-radiological signatures to distinguish preinvasive lesions from pulmonary invasive lesions. METHODS: This was a retrospective, diagnostic study conducted from August 1, 2018, to May 1, 2020, at three centers. Patients with a solitary pulmonary nodule were enrolled in the GDPH center and were divided into two groups (7:3) randomly: development (n = 149) and internal validation (n = 54). The SYSMH center and the ZSLC Center formed an external validation cohort of 170 patients. The least absolute shrinkage and selection operator (LASSO) algorithm and logistic regression analysis were used to feature signatures and transform them into models. RESULTS: The study comprised 373 individuals from three independent centers (female: 225/373, 60.3%; median [IQR] age, 57.0 [48.0-65.0] years). The AUCs for the combined radiomic signature selected from the nodular area and the perinodular area were 0.93, 0.91, and 0.90 in the three cohorts. The nomogram combining the clinical and combined radiomic signatures could accurately predict interstitial invasion in patients with a solitary pulmonary nodule (AUC, 0.94, 0.90, 0.92) in the three cohorts, respectively. The radiomic nomogram outperformed any clinical or radiomic signature in terms of clinical predictive abilities, according to a decision curve analysis and the Akaike information criteria. CONCLUSIONS: This study demonstrated that a nomogram constructed by identified clinical-radiological signatures and combined radiomic signatures has the potential to precisely predict pathology invasiveness. KEY POINTS: • The radiomic signature from the perinodular area has the potential to predict pathology invasiveness of the solitary pulmonary nodule. • The new radiomic nomogram was useful in clinical decision-making associated with personalized surgical intervention and therapeutic regimen selection in patients with early-stage non-small-cell lung cancer.

Undiagnosed solitary caseating granulomas: Is lung resection surgery a feasible method for diagnosis and treatment?

BACKGROUND: In many patients, low-dose computed tomography (CT) screening for lung cancer reveals asymptomatic pulmonary nodules. Lung resection surgery may be indicated in these patients; however, distinguishing malignancies from benign lesions preoperatively can be challenging. METHODS: From 2013 to 2018, 4181 patients undergoing surgery for pulmonary nodules were reviewed at National Taiwan University Hospital, and 837 were diagnosed with benign pathologies. Only patients with pathological diagnosis as caseating granulomatous inflammation were included, sixty-nine patients were then analyzed for preoperative clinical and imaging characteristics, surgical methods and complications, pathogens, medical treatment and outcomes. Mycobacterial evidence was obtained from the culture of respiratory or surgical specimen. RESULTS: Overall, 68% of the patients were asymptomatic before surgery. More than half of the nodules were in the upper lobes, and all patients underwent video-assisted thoracoscopic surgery (VATS). Some patients (14.5%) developed grade I complications, and the mean postoperative hospital stay was 4 days. The final pathology reports of 20% benign entities postoperatively, and caseating granulomatous inflammation accounted for a significant part. MTB and NTM were cultured from one-fourth of the patients respectively. All patients with confirmed MTB infection received antimycobacterial treatment, while the medical treatment in NTM-infected patients was decided by the infectious disease specialists. The mean follow-up period was 736 days, and no recurrence was found. CONCLUSION: Lung resection surgery is an aggressive but safe and feasible method for diagnosing MTB- or NTM-associated pulmonary nodules, and, potentially, an effective therapeutic tool for patients with undiagnosed MTB- or NTM-associated pulmonary nodules.

Impact of solitary pulmonary nodule size on qualitative and quantitative assessment using 18F-fluorodeoxyglucose PET/CT: the SPUTNIK trial.

PURPOSE: To compare qualitative and semi-quantitative PET/CT criteria, and the impact of nodule size on the diagnosis of solitary pulmonary nodules in a prospective multicentre trial. METHODS: Patients with an SPN on CT ≥ 8 and ≤ 30 mm were recruited to the SPUTNIK trial at 16 sites accredited by the UK PET Core Lab. Qualitative assessment used a five-point ordinal PET-grade compared to the mediastinal blood pool, and a combined PET/CT grade using the CT features. Semi-quantitative measures included SUVmax of the nodule, and as an uptake ratio to the mediastinal blood pool (SURBLOOD) or liver (SURLIVER). The endpoints were diagnosis of lung cancer via biopsy/histology or completion of 2-year follow-up. Impact of nodule size was analysed by comparison between nodule size tertiles. RESULTS: Three hundred fifty-five participants completed PET/CT and 2-year follow-up, with 59% (209/355) malignant nodules. The AUCs of the three techniques were SUVmax 0.87 (95% CI 0.83;0.91); SURBLOOD 0.87 (95% CI 0.83; 0.91, p = 0.30 versus SUVmax); and SURLIVER 0.87 (95% CI 0.83; 0.91, p = 0.09 vs. SUVmax). The AUCs for all techniques remained stable across size tertiles (p > 0.1 for difference), although the optimal diagnostic threshold varied by size. For nodules < 12 mm, an SUVmax of 1.75 or visual uptake equal to the mediastinum yielded the highest accuracy. For nodules > 16 mm, an SUVmax ≥ 3.6 or visual PET uptake greater than the mediastinum was the most accurate. CONCLUSION: In this multicentre trial, SUVmax was the most accurate technique for the diagnosis of solitary pulmonary nodules. Diagnostic thresholds should be altered according to nodule size. TRIAL REGISTRATION: ISRCTN - ISRCTN30784948. ClinicalTrials.gov - NCT02013063.

Proposing a deep learning-based method for improving the diagnostic certainty of pulmonary nodules in CT scan of chest.

OBJECTIVE: To compare the performance of a deep learning (DL)-based method for diagnosing pulmonary nodules compared with radiologists' diagnostic approach in computed tomography (CT) of the chest. MATERIALS AND METHODS: A total of 150 pathologically confirmed pulmonary nodules (60% malignant) assessed and reported by radiologists were included. CT images were processed by the proposed DL-based method to generate the probability of malignancy (0-100%), and the nodules were divided into the groups of benign (0-39.9%), indeterminate (40.0-59.9%), and malignant (60.0-100%). Taking the pathological results as the gold standard, we compared the diagnostic performance of the proposed DL-based method with the radiologists' diagnostic approach using the McNemar-Bowker test. RESULTS: There was a statistically significant difference between the diagnosis results of the proposed DL-based method and the radiologists' diagnostic approach (p < 0.001). Moreover, there was no statistically significant difference in the composition of the diagnosis results between the proposed DL-based method and the radiologists' diagnostic approach (all p > 0.05). The difference in diagnostic accuracy between the proposed DL-based method (70%) and radiologists' diagnostic performance (64%) was not statistically significant (p = 0.243). CONCLUSIONS: The proposed DL-based method achieved an accuracy comparable with the radiologists' diagnostic approach in clinical practice. Furthermore, its advantage in improving diagnostic certainty may raise the radiologists' confidence in diagnosing pulmonary nodules and may help clinical management. Therefore, the proposed DL-based method showed great potential in a certain clinical application. KEY POINTS: • Deep learning-based method for diagnosing the pulmonary nodules in computed tomography provides a higher diagnostic certainty.

Evaluation of a novel deep learning-based classifier for perifissural nodules.

OBJECTIVES: To evaluate the performance of a novel convolutional neural network (CNN) for the classification of typical perifissural nodules (PFN). METHODS: Chest CT data from two centers in the UK and The Netherlands (1668 unique nodules, 1260 individuals) were collected. Pulmonary nodules were classified into subtypes, including "typical PFNs" on-site, and were reviewed by a central clinician. The dataset was divided into a training/cross-validation set of 1557 nodules (1103 individuals) and a test set of 196 nodules (158 individuals). For the test set, three radiologically trained readers classified the nodules into three nodule categories: typical PFN, atypical PFN, and non-PFN. The consensus of the three readers was used as reference to evaluate the performance of the PFN-CNN. Typical PFNs were considered as positive results, and atypical PFNs and non-PFNs were grouped as negative results. PFN-CNN performance was evaluated using the ROC curve, confusion matrix, and Cohen's kappa. RESULTS: Internal validation yielded a mean AUC of 91.9% (95% CI 90.6-92.9) with 78.7% sensitivity and 90.4% specificity. For the test set, the reader consensus rated 45/196 (23%) of nodules as typical PFN. The classifier-reader agreement (k = 0.62-0.75) was similar to the inter-reader agreement (k = 0.64-0.79). Area under the ROC curve was 95.8% (95% CI 93.3-98.4), with a sensitivity of 95.6% (95% CI 84.9-99.5), and specificity of 88.1% (95% CI 81.8-92.8). CONCLUSION: The PFN-CNN showed excellent performance in classifying typical PFNs. Its agreement with radiologically trained readers is within the range of inter-reader agreement. Thus, the CNN-based system has potential in clinical and screening settings to rule out perifissural nodules and increase reader efficiency. KEY POINTS: • Agreement between the PFN-CNN and radiologically trained readers is within the range of inter-reader agreement. • The CNN model for the classification of typical PFNs achieved an AUC of 95.8% (95% CI 93.3-98.4) with 95.6% (95% CI 84.9-99.5) sensitivity and 88.1% (95% CI 81.8-92.8) specificity compared to the consensus of three readers.

Natural history of pathologically confirmed pulmonary subsolid nodules with deep learning-assisted nodule segmentation.

OBJECTIVE: To explore the natural history of pulmonary subsolid nodules (SSNs) with different pathological types by deep learning-assisted nodule segmentation. METHODS: Between June 2012 and June 2019, 95 resected SSNs with preoperative long-term follow-up were enrolled in this retrospective study. SSN detection and segmentation were performed on preoperative follow-up CTs using the deep learning-based Dr. Wise system. SSNs were categorized into invasive adenocarcinoma (IAC, n = 47) and non-IAC (n = 48) groups; according to the interval change during the preoperative follow-up, SSNs were divided into growth (n = 68), nongrowth (n = 22), and new emergence (n = 5) groups. We analyzed the cumulative percentages and pattern of SSN growth and identified significant factors for IAC diagnosis and SSN growth. RESULTS: The mean preoperative follow-up was 42.1 ± 17.0 months. More SSNs showed growth or new emergence in the IAC than in the non-IAC group (89.4% vs. 64.6%, p = 0.009). Volume doubling time was non-significantly shorter for IACs than for non-IACs (1436.0 ± 1188.2 vs. 2087.5 ± 1799.7 days, p = 0.077). Median mass doubling time was significantly shorter for IACs than for non-IACs (821.7 vs. 1944.1 days, p = 0.001). Lobulated sign (p = 0.002) and SSN mass (p = 0.004) were significant factors for differentiating IACs. IACs showed significantly higher cumulative growth percentages than non-IACs in the first 70 months of follow-up. The growth pattern of SSNs may conform to the exponential model. The initial volume (p = 0.042) was a predictor for SSN growth. CONCLUSIONS: IACs appearing as SSNs showed an indolent course. The mean growth rate was larger for IACs than for non-IACs. SSNs with larger initial volume are more likely to grow. KEY POINTS: • Invasive adenocarcinomas (IACs) appearing as subsolid nodules (SSNs), with a mean volume doubling time (VDT) of 1436.0 ± 1188.2 days and median mass doubling time (MDT) of 821.7 days, showed an indolent course. • The VDT was shorter for IACs than for non-IACs (1436.0 ± 1188.2 vs. 2087.5 ± 1799.7 days), but the difference was not significant (p = 0.077). The median MDT was significantly shorter for IACs than for non-IACs (821.7 vs. 1944.1 days, p = 0.001). • SSNs with lobulated sign and larger mass (> 390.5 mg) may very likely be IACs. SSNs with larger initial volume are more likely to grow.

The value of various peritumoral radiomic features in differentiating the invasiveness of adenocarcinoma manifesting as ground-glass nodules.

OBJECTIVES: To evaluate the ability of CT radiomic features extracted from peritumoral parenchyma of 2 mm and 5 mm distinguishing invasive adenocarcinoma (IAC) from adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA). METHODS: For this retrospective study, 121 lung adenocarcinomas appearing as ground-glass nodules on thin-section CT were evaluated. Quantitative radiomic features were extracted from the peritumoral parenchymal region of 2 mm and 5 mm on CT imaging, and the radiomic models of External2 and External5 were constructed. The ROC curves were used to evaluate the performance of different models. Differences between the AUCs were evaluated using DeLong's method. RESULTS: The radiomic scores of IAC were statistically higher than those of MIA/AIS in both the External2 and External5 models. The AUCs of the External2 and External5 models were 0.882, 0.778 in the training cohort and 0.888, 0.804 in the validation cohort, respectively. The AUC of the External2 model was not statistically different from the External5 model both in the training cohort (p = 0.116) and validation cohort (p = 0.423). CONCLUSIONS: The radiomic features extracted from the peritumoral region of 2 mm and 5 mm at thin-section CT showed good predictive values to differentiate the IAC from AIS/MIA. The radiomic features from the peritumoral region of 5 mm provide no additional benefit in distinguishing IAC from MIA/AIS than that of the 2 mm region. KEY POINTS: • The radiomic models from various peritumoral lung parenchyma were developed and validated to predict invasiveness of adenocarcinoma. • The peritumoral parenchyma of lung adenocarcinoma may contain useful information. • Radiomics from peritumoral lung parenchyma of 5 mm provides no added efficiency of the prediction for invasiveness of lung adenocarcinoma.