A pilot pragmatic randomized controlled trial of a nicotine metabolite ratio-guided smoking cessation intervention in a lung health and screening program.

Introduction: Patients with pulmonary nodules detected through lung cancer screening or as incidental findings are often followed in lung health and screening programs. The use of personalized pharmacotherapy for smoking cessation informed by the nicotine metabolite ratio (NMR), a measure of nicotine metabolism, has not yet been evaluated in this setting. This pilot randomized controlled trial (RCT) evaluated the feasibility of conducting a larger trial. Methods: Through a pragmatic RCT design, participants were recruited from a Mid-Atlantic lung health and screening program. Eligible participants smoked >5 cigarettes per day and completed a blood draw to determine NMR before being randomized to standard or NMR-guided care treatment arms. Standard care participants were offered nicotine replacement therapy (NRT) or varenicline and a referral to phone-based smoking cessation counseling. NMR-guided participants received standard care except they were provided a personalized medication recommendation based on their NMR. Study outcomes included measures of feasibility, medication uptake, and treatment matching (i.e., uptake of the optimal medication). Results: More than 80 % of 205 screened patients were eligible. However, only 37 (22 %) of these patients enrolled in the study, with a mean age of 65 years, 43 % female, and 25 % Black. Nearly all patients who declined cited a disinterest in smoking cessation. Participants in both treatment arms had high rates of medication uptake (68 %), with NMR-guided participants showing a trend towards greater treatment matching (55 % vs. 29 %). Conclusions: The results of this pilot study provide support for conducting a larger RCT of an NMR-guided smoking cessation intervention in a lung health and screening setting. Consideration should be given to augmenting the intervention to address barriers to study entry.

Unravelling diagnostic challenges: A case report of pulmonary langerhans cell histiocytosis with atypical radiologic presentation.

This clinical case highlights the diagnostic challenges encountered in a young adult smoker presenting with undifferentiated pulmonary nodules. Initial investigations were inconclusive, necessitating surgical lung biopsy due to the nodules' size and location. The histopathological examination revealed pulmonary Langerhans cell histiocytosis (PLCH). This emphasizes the importance of considering PLCH in the differential diagnosis of pulmonary nodules, particularly in smokers. Moreover, it underscores the value of surgical biopsy in cases where other diagnostic techniques are limited. Early recognition and accurate diagnosis are crucial for optimal management and outcomes in PLCH.

Incidental pulmonary nodules: Natural language processing analysis of radiology reports.

BACKGROUND: Pulmonary nodules are a common incidental finding on chest Computed Tomography scans (CT), most of the time outside of lung cancer screening (LCS). We aimed to evaluate the number of incidental pulmonary nodules (IPN) found in 1 year in our hospital, as well as the follow-up (FUP) rate and the clinical and radiological features associated with FUP. METHODS: We trained a Natural Language Processing (NLP) tool to identify the transcripts mentioning the presence of a pulmonary nodule, among a large population of patients from a French hospital. We extracted nodule characteristics using keyword analysis. NLP algorithm accuracy was determined through manual reading from a sample of our population. Electronic health database and medical record analysis by clinician allowed us to obtain information about FUP and cancer diagnoses. RESULTS: In this retrospective observational study, we analyzed 101,703 transcripts corresponding to the entire CTs performed in 2020. We identified 1,991 (2 %) patients with an IPN. NLP accuracy for nodule detection in CT reports was 99 %. Only 41 % received a FUP between January 2020 and December 2021. Patient age, nodule size, and the mention of the nodule in the impression part were positively associated with FUP, while nodules diagnosed in the context of COVID-19 were less followed. 36 (2 %) lung cancers were subsequently diagnosed, with 16 (45 %) at a non-metastatic stage. CONCLUSIONS: We identified a high prevalence of IPN with a low FUP rate, encouraging the implementation of IPN management program. We also highlighted the potential of NLP for database analysis in clinical research.

Safety and efficacy of percutaneous biopsy and microwave ablation in patients with pulmonary nodules on antithrombotic therapy: A study with rivaroxaban bridging.

BACKGROUND: To evaluate the safety and efficacy of percutaneous biopsy and microwave ablation (B + MWA) in patients with pulmonary nodules (PNs) who are receiving antithrombotic therapy by rivaroxaban as bridging therapy. METHODS: The study comprised 187 patients with PNs who underwent 187 B + MWA sessions from January 1, 2020, to December 31, 2021. The enrolled patients were divided into two groups: Group A, who received antithrombotic therapy five days before the procedure and received rivaroxaban as a bridging drug during hospitalization, and group B, who had no antithrombotic treatment. Information about the technical success rate, positive biopsy rate, complete ablative rate, and major complications were collected and analyzed. RESULTS: Group A comprised 53 patients and group B comprised 134 patients. The technical success rate was 100% in both groups. The positive biopsy rates were 88.68% and 91.04%, respectively (p = 0.6211, X2 = 0.2443). In groups A and B, the complete ablative rates at 6, 12, and 24 months were 100.0% versus 99.25%, 96.23% versus 96.27%, and 88.68% versus 89.55%, respectively. There were no significant differences in bleeding and thrombotic complications between the two groups. No grade 5 complications occurred. CONCLUSIONS: It is generally considered safe and effective that patients who are on antithrombotic therapy by rivaroxaban as bridging to undergo B + MWA for treating PNs.

[Implementation of Lung Nodule Detection Model Based on Incremental Meta-Learning].

In response to the issue that traditional lung nodule detection models cannot dynamically optimize and update with the increase of new data, a new lung nodule detection model-task incremental meta-learning model (TIMLM) is proposed. This model comprises of two loops: the inner loop imposes incremental learning regularization update constraints, while the outer loop employs a meta-update strategy to sample old and new knowledge and learn a set of generalized parameters that adapt to old and new data. Under the condition that the main structure of the model is not changed as much as possible, it preserves the old knowledge that was learned previously. Experimental verification on the publicly available lung dataset showed that, compared with traditional deep network models and mainstream incremental models, TIMLM has greatly improved in terms of accuracy, sensitivity, and other indicators, demonstrating good continuous learning and anti-forgetting capabilities.

The Role of CT Perfusion in Differentiating Benign Versus Malignant Focal Pulmonary Lesions.

BACKGROUND: Contrast-enhanced CT scan is the standard imaging for the characterization and evaluation of focal parenchymal lung lesions. It relies on morphology and enhancement patterns for the characterization of lung lesions. However, there is significant overlap among imaging features of various malignant and benign lesions. Hence, it is often necessary to obtain tissue diagnosis with invasive percutaneous or endoscopic-guided tissue sampling. It is often desirable to have non-invasive techniques that can differentiate malignant and benign lung lesions. CT perfusion is an emerging CT technology that allows functional assessment of tissue vascularity through various parameters and can help in differentiating benign and malignant focal lung lesions. OBJECTIVE: The purpose of this study was to assess the role of the CT perfusion technique in differentiating malignant and benign focal parenchymal lung lesions. MATERIALS AND METHODS: In this prospective observational study, CT perfusion was performed on 41 patients with focal parenchymal lung lesions from December 2020 to June 2022. The four-dimensional range was planned to cover the entire craniocaudal extent of the lesion, followed by a volume perfusion CT (VPCT) of the lesion. A total of 27 dynamic datasets were acquired with a scan interval of 1.5 seconds and a total scan time of 42 seconds. CT perfusion parameters of blood flow (BF), blood volume (BV), and k-trans of the lesion were measured with mathematical algorithms available in the Syngo.via CT perfusion software (Siemens Healthcare, Erlangen, Germany). RESULTS: The median BV in benign lesions was found to be 5.5 mL/100 g, with an interquartile range of 3.3-6.9 and a p-value < 0.001. The median BV in malignant lesions was found to be 11.35 mL/100 g, with an interquartile range of 9.57-13.21 and a p-value ≤ 0.001. The median BF for benign lesions was 45.5 mL/100 g/min, with an interquartile range of 33.8-48.5 and a p-value ≤ 0.001. The median BF for malignant lesion was 61.77 mL/100 g/min, with an interquartile range of 33.8-48.5 and a p-value ≤ 0.001. The median k-trans in the case of benign lesions was found to be 4.2 mL/100 g/min, with an interquartile range of 3.13-6.8 and a p-value ≤ 0.001. The median k-trans in the case of the malignant lesion was found to be 12.05 mL/100g/min, with an interquartile range of 7.20-33.42 and a p-value < 0.001. Our study has also shown BV to have an accuracy of 92.68%, sensitivity of 93.3%, and specificity of 90.01%. CONCLUSION: Our study has shown that CT perfusion values of BV, BF, and k-trans can be used to differentiate between benign and malignant focal lung parenchymal lesions. K-trans is the most sensitive parameter while BV and BF have greater accuracy and specificity.

Ultrasound for Intra-Operative Detection of Peri-Centimetric Pulmonary Nodules in Uniportal Video-Assisted Thoracic Surgery (VATS): A Comparison with Conventional Techniques in Multiportal VATS.

Background: Video-assisted thoracic surgery (VATS) has become the gold-standard approach for lung resections. Given the impossibility of digital palpation, we witnessed the progressive development of peri-centimetric and deeply located pulmonary nodule alternative detection techniques. Intra-operative lung ultrasound is an increasingly effective diagnostic method, although only a few small studies have evaluated its accuracy. This study analyzed the effectiveness and sensitivity of uniportal VATS with intra-operative lung ultrasound (ILU), in comparison to multiportal VATS, for visualizing solitary and deep-sited pulmonary nodules. Methods: Patient data from October 2021 to October 2023, from a single center, were retrospectively gathered and analyzed. In total, 31 patients who received ILU-aided uniportal VATS (Group A) were matched for localization time, operative time, sensitivity, and post-operative complications, with 33 undergoing nodule detection with conventional techniques, such as manual or instrumental palpation, in multiportal VATS (Group B). Surgeries were carried out by the same team and ILU was performed by a certified operator. Results: Group A presented a significantly shorter time for nodule detection [median (IQR): 9 (8-10) vs. 14 (12.5-15) min; p < 0.001] and operative time [median (IQR): 33 (29-38) vs. 43 (39-47) min; p < 0.001]. All nodules were correctly localized and resected in Group A (sensitivity 100%), while three were missed in Group B (sensitivity 90.9%). Two patients in Group B presented with a prolonged air leak that was conservatively managed, compared to none in Group A, resulting in a post-operative morbidity rate of 6.1% vs. 0% (p = 0.16). Conclusions: ILU-aided uniportal VATS was faster and more effective than conventional techniques in multiportal VATS for nodule detection.

Prevalence of pulmonary nodules detected incidentally on noncancer-related imaging: a review.

Pulmonary nodules are common incidental findings requiring surveillance. Follow-up recommendations vary depending on risk factors, size and solid or subsolid characteristics. This review aimed to evaluate the prevalence of clinically significant nodules detected on noncancer-dedicated imaging and the prevalence of part-solid and ground-glass nodules. We conducted a systematic search of literature and screened texts for eligibility. Clinically significant nodules were noncalcified nodules >4-6 mm. Prevalence estimates were calculated for all studies and risk of bias was assessed by one reviewer. Twenty-four studies were included, with a total of 30 887 participants, and 21 studies were cross-sectional in design. Twenty-two studies used computed tomography (CT) imaging with cardiac-related CT being the most frequent. Prevalence of significant nodules was highest in studies with large field of view of the chest and low size thresholds for reporting nodules. The prevalence of part-solid and ground-glass nodules was only described in two cardiac-related CT studies. The overall risk of bias was low in seven studies and moderate in 17 studies. While current literature frequently reports incidental nodules on cardiovascular-related CT, there is minimal reporting of subsolid characteristics. Unclear quantification of smoking history and heterogeneity of imaging protocol also limits reliable evaluation of nodule prevalence in nonscreening cohorts.

Estimation of pathological subtypes in subsolid lung nodules using artificial intelligence.

Objective: This study aimed to investigate the value of artificial intelligence (AI) for distinguishing pathological subtypes of invasive pulmonary adenocarcinomas in patients with subsolid nodules (SSNs). Materials and methods: This retrospective study included 110 consecutive patients with 120 SSNs. The qualitative and quantitative imaging characteristics of SSNs were extracted automatically using an artificially intelligent assessment system. Then, radiologists had to verify these characteristics again. We split all cases into two groups: non-IA including 11 Atypical adenomatous hyperplasia (AAH) and 25 adenocarcinoma in situ (AIS) or IA including 7 minimally invasive adenocarcinoma (MIA) and 77 invasive adenocarcinoma (IAC). Variables that exhibited statistically significant differences between the non-IA and IA in the univariate analysis were included in the multivariate logistic regression analysis. Receiver operating characteristic (ROC) analyses were conducted to determine the cut-off values and their diagnostic performances. Results: Multivariate logistic regression analysis showed that the major diameter (odds ratio [OR] = 1.38; 95 % confidence interval [CI], 1.02-1.87; P = 0.036) and entropy of three-dimensional(3D) CT value (OR = 3.73, 95 % CI, 1.13-2.33, P = 0.031) were independent risk factors for adenocarcinomas. The cut-off values of the major diameter and the entropy of 3D CT value for the diagnosis of invasive adenocarcinoma were 15.5 mm and 5.17, respectively. To improve the classification performance, we fused the major diameter and the entropy of 3D CT value as a combined model, and the (AUC） of the model was 0.868 (sensitivity = 0.845, specificity = 0.806). Conclusion: The major diameter and entropy of 3D CT value can distinguish non-IA from IA. AI can improve performance in distinguishing pathological subtypes of invasive pulmonary adenocarcinomas in patients with SSNs.

Extracting Pulmonary Nodules and Nodule Characteristics from Radiology Reports of Lung Cancer Screening Patients Using Transformer Models.

 Pulmonary nodules and nodule characteristics are important indicators of lung nodule malignancy. However, nodule information is often documented as free text in clinical narratives such as radiology reports in electronic health record systems. Natural language processing (NLP) is the key technology to extract and standardize patient information from radiology reports into structured data elements. This study aimed to develop an NLP system using state-of-the-art transformer models to extract pulmonary nodules and associated nodule characteristics from radiology reports. We identified a cohort of 3080 patients who underwent LDCT at the University of Florida health system and collected their radiology reports. We manually annotated 394 reports as the gold standard. We explored eight pretrained transformer models from three transformer architectures including bidirectional encoder representations from transformers (BERT), robustly optimized BERT approach (RoBERTa), and A Lite BERT (ALBERT), for clinical concept extraction, relation identification, and negation detection. We examined general transformer models pretrained using general English corpora, transformer models fine-tuned using a clinical corpus, and a large clinical transformer model, GatorTron, which was trained from scratch using 90 billion words of clinical text. We compared transformer models with two baseline models including a recurrent neural network implemented using bidirectional long short-term memory with a conditional random fields layer and support vector machines. RoBERTa-mimic achieved the best F1-score of 0.9279 for nodule concept and nodule characteristics extraction. ALBERT-base and GatorTron achieved the best F1-score of 0.9737 in linking nodule characteristics to pulmonary nodules. Seven out of eight transformers achieved the best F1-score of 1.0000 for negation detection. Our end-to-end system achieved an overall F1-score of 0.8869. This study demonstrated the advantage of state-of-the-art transformer models for pulmonary nodule information extraction from radiology reports. Supplementary Information: The online version contains supplementary material available at 10.1007/s41666-024-00166-5.

Fully automated classification of pulmonary nodules in positron emission tomography-computed tomography imaging using a two-stage multimodal learning approach.

Background: Lung cancer is a malignant tumor, for which pulmonary nodules are considered to be significant indicators. Early recognition and timely treatment of pulmonary nodules can contribute to improving the survival rate of patients with cancer. Positron emission tomography-computed tomography (PET/CT) is a noninvasive, fusion imaging technique that can obtain both functional and structural information of lung regions. However, studies of pulmonary nodules based on computer-aided diagnosis have primarily focused on the nodule level due to a reliance on the annotation of nodules, which is superficial and unable to contribute to the actual clinical diagnosis. The aim of this study was thus to develop a fully automated classification framework for a more comprehensive assessment of pulmonary nodules in PET/CT imaging data. Methods: We developed a two-stage multimodal learning framework for the diagnosis of pulmonary nodules in PET/CT imaging. In this framework, Stage I focuses on pulmonary parenchyma segmentation using a pretrained U-Net and PET/CT registration. Stage II aims to extract, integrate, and recognize image-level and feature-level features by employing the three-dimensional (3D) Inception-residual net (ResNet) convolutional block attention module architecture and a dense-voting fusion mechanism. Results: In the experiments, the proposed model's performance was comprehensively validated using a set of real clinical data, achieving mean scores of 89.98%, 89.21%, 84.75%, 93.38%, 86.83%, and 0.9227 for accuracy, precision, recall, specificity, F1 score, and area under curve values, respectively. Conclusions: This paper presents a two-stage multimodal learning approach for the automatic diagnosis of pulmonary nodules. The findings reveal that the main reason for limiting model performance is the nonsolitary property of nodules in pulmonary nodule diagnosis, providing direction for future research.

Imaging diagnostics of pulmonary ground-glass nodules: a narrative review with current status and future directions.

Background and Objective: The incidence rate of lung cancer, which also has the highest mortality rates for both men and women worldwide, is increasing globally. Due to advancements in imaging technology and the growing inclination of individuals to undergo screening, the detection rate of ground-glass nodules (GGNs) has surged rapidly. Currently, artificial intelligence (AI) methods for data analysis and interpretation, image processing, illness diagnosis, and lesion prediction offer a novel perspective on the diagnosis of GGNs. This article aimed to examine how to detect malignant lesions as early as possible and improve clinical diagnostic and treatment decisions by identifying benign and malignant lesions using imaging data. It also aimed to describe the use of computed tomography (CT)-guided biopsies and highlight developments in AI techniques in this area. Methods: We used PubMed, Elsevier ScienceDirect, Springer Database, and Google Scholar to search for information relevant to the article's topic. We gathered, examined, and interpreted relevant imaging resources from the Second Affiliated Hospital of Nanchang University's Imaging Center. Additionally, we used Adobe Illustrator 2020 to process all the figures. Key Content and Findings: We examined the common signs of GGNs, elucidated the relationship between these signs and the identification of benign and malignant lesions, and then described the application of AI in image segmentation, automatic classification, and the invasiveness prediction of GGNs over the last three years, including its limitations and outlook. We also discussed the necessity of conducting biopsies of persistent pure GGNs. Conclusions: A variety of imaging features can be combined to improve the diagnosis of benign and malignant GGNs. The use of CT-guided puncture biopsy to clarify the nature of lesions should be considered with caution. The development of new AI tools brings new possibilities and hope to improving the ability of imaging physicians to analyze GGN images and achieving accurate diagnosis.

Does needle gauge affect complication rates of computed tomography-guided lung biopsy?

Background: It has been thought a larger bore biopsy needle may yield a better sample for molecular testing, but this could potentially expose the patient to higher pneumothorax rates. This study aims to determine if a larger bore biopsy system results in more complications. Methods: A total of 193 patients who underwent computed tomography (CT)-guided lung biopsy in a single tertiary center from 2013-2021 were evaluated retrospectively. Patients were divided into two groups, patients who underwent lung biopsy using the 17/18-gauge (18G) biopsy system and the 19/20-gauge (20G) biopsy system. Data recorded included biopsy needle gauge, nodule location and size, plug use, positioning, the length of the intraparenchymal tract, number of biopsy passes, pneumothorax, chest tube insertion, and admission. Results: The mean age was 64.1±12.4 years. The median diameter of the lung nodules was 1.95 cm, and the median depth of the intraparenchymal needle tract was 2.7 cm. Pneumothorax was identified during the procedure by CT fluoroscopy or on post-procedural chest X-ray (CXR). The overall rate of pneumothorax among all patients was 35.2%, and 10.9% of the study population (i.e., 30.1% of patients with pneumothorax) required chest tube insertion. The rate of pneumothorax or chest tube insertion was not significantly different between patients who underwent lung biopsy using 17/18G or 19/20G biopsy system. Patients who developed pneumothorax were older, with smaller-sized pulmonary nodules and longer length of the intraparenchymal tract. The pathologic sensitivity of the 18G gun was higher than that of the 20G gun (93% sensitivity, 100% specificity vs. 79.5% sensitivity, 100% specificity). In the multivariate logistic regression fitted model, the length of the intraparenchymal tract was the only factor predictive of post-procedural pneumothorax and chest tube insertion. An intraparenchymal needle tract length of greater than 2 cm was identified to have the best threshold to predict pneumothorax [sensitivity: 73.5%; false positive rate: 57.6%; area under the curve: 66.27%]. Conclusions: Findings suggest similar rates of pneumothorax and chest tube insertion using small 19/20G vs. 17/18G biopsy systems. The 18G system was more sensitive compared to the 20G system in determining pathologic results. Increasing length of lung parenchyma needle tract and smaller lung nodules appear to be risk factors for pneumothorax. Physicians should plan on intraparenchymal tracts that are less than 2 cm to decrease the chance of pneumothorax.

A prediction model based on computed tomography characteristics for identifying malignant from benign sub-centimeter solid pulmonary nodules.

Background: Distinguishing benign from malignant sub-centimeter solid pulmonary nodules (SSPNs) continues to be challenging in clinical practice. Earlier diagnosis is crucial for improving patient survival and prognosis. This study aimed to investigate the risk factors of malignant SSPNs and establish and validate a prediction model based on computed tomography (CT) characteristics to assist in their early diagnosis. Methods: A total of 261 consecutive participants with 261 SSPNs were retrospectively recruited between January 2012 and July 2023 from National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College (Center 1), including 161 malignant lesions and 100 benign lesions. Patients were randomly assigned to the training set (n=183) and validation set (n=78) according to a 7:3 ratio. Malignant nodules were confirmed by pathology; and benign nodules were confirmed by follow-up or pathology. Clinical data and CT features were collected to estimate the independent predictors of malignancy of SSPN with multivariate logistic analysis. A clinical prediction model was subsequently established by logistic regression. Furthermore, an additional 69 consecutive patients with 69 SSPNs from The Fourth Hospital of Hebei Medical University (Center 2) between January 2022 and December 2022 were retrospectively included as an external cohort to validate the predictive efficacy of the model. The performance of the prediction model was assessed by sensitivity, specificity, and the area under the receiver operating characteristic curve. Results: There were 113 (61.7%), 48 (61.5%) and 28 (40.6%) malignant SSPNs in the training, internal and external validation sets, respectively. Multivariate logistic analysis revealed four independent predictors of malignant SSPNs: tumor-lung interface (P=0.002), spiculation (P=0.04), air bronchogram (P=0.047), and invisible at the mediastinal window (P=0.003). The area under the curve (AUC) for the prediction model in the training set was 0.875 [95% confidence interval (CI): 0.818, 0.933]; and the sensitivity and specificity were 94.7% and 68.6%, respectively. The AUCs in the internal and external validation set were (0.781; 95% CI: 0.664, 0.897) and (0.873; 95% CI: 0.791, 0.955), respectively; the sensitivity and specificity were 66.7% and 83.3% for the internal validation data, and 100.0% and 61.0% for the external validation data, respectively. Conclusions: The prediction model based on CT characteristics could be helpful for distinguishing malignant SSPNs from benign ones.

Efficacy, safety and patient satisfaction of two-stage versus single-stage computed tomography guided localization and resection of pulmonary nodules.

Background: Low-dose computed tomography (CT) has been increasingly utilized for lung cancer screening. Localization of solitary pulmonary nodules (SPN) is crucial for resection. Two-stage localization method involves dye injection by radiologists prior to the operation. The significant interval between localization and resection is associated with a higher risk of marker failure, psychological distress and procedural complications. Single-stage localization and resection procedure under general anesthesia poses unique challenges. The aim of the study is to compare the safety, efficacy and patient satisfaction between the two methods. Methods: This is a retrospective study comparing outcomes between two-stage and single-stage pre-operative localization of SPN. The primary study outcome was total operating time. Secondary outcomes included successful lesion localization, complication rate, 30-day readmission, mortality, patient satisfaction, and pain level. Results: A total of 26 and 56 patients were included for the single and two-stage group respectively. Total operative time was significantly longer in the single-stage arm (mean: 188 min) than that of the two-stage arm (mean: 172 min, P<0.001) due to the additional time needed for intra-operative localization. Mean satisfaction score was significantly higher in the single-stage group than that of the two-stage group (92 vs. 52.69, P=0.004). Pain level assessed by numerical rating scales was better in the single-stage arm compared to the two-stage arm (mean: 8.8 vs. 4.85, P=0.007). Conclusions: Single-stage localization and resection resulted in a minor increase in total operative time, higher patient satisfaction and less pain with comparable safety and efficacy to conventional two-stage approach.

Application of artificial intelligence in lung cancer screening: A real-world study in a Chinese physical examination population.

BACKGROUND: With the rapid increase of chest computed tomography (CT) images, the workload faced by radiologists has increased dramatically. It is undeniable that the use of artificial intelligence (AI) image-assisted diagnosis system in clinical treatment is a major trend in medical development. Therefore, in order to explore the value and diagnostic accuracy of the current AI system in clinical application, we aim to compare the detection and differentiation of benign and malignant pulmonary nodules between AI system and physicians, so as to provide a theoretical basis for clinical application. METHODS: Our study encompassed a cohort of 23 336 patients who underwent chest low-dose spiral CT screening for lung cancer at the Health Management Center of West China Hospital. We conducted a comparative analysis between AI-assisted reading and manual interpretation, focusing on the detection and differentiation of benign and malignant pulmonary nodules. RESULTS: The AI-assisted reading exhibited a significantly higher screening positive rate and probability of diagnosing malignant pulmonary nodules compared with manual interpretation (p < 0.001). Moreover, AI scanning demonstrated a markedly superior detection rate of malignant pulmonary nodules compared with manual scanning (97.2% vs. 86.4%, p < 0.001). Additionally, the lung cancer detection rate was substantially higher in the AI reading group compared with the manual reading group (98.9% vs. 90.3%, p < 0.001). CONCLUSIONS: Our findings underscore the superior screening positive rate and lung cancer detection rate achieved through AI-assisted reading compared with manual interpretation. Thus, AI exhibits considerable potential as an adjunctive tool in lung cancer screening within clinical practice settings.

Deep Learning-Based Reconstruction Algorithm With Lung Enhancement Filter for Chest CT: Effect on Image Quality and Ground Glass Nodule Sharpness.

OBJECTIVE: To assess the effect of a new lung enhancement filter combined with deep learning image reconstruction (DLIR) algorithm on image quality and ground-glass nodule (GGN) sharpness compared to hybrid iterative reconstruction or DLIR alone. MATERIALS AND METHODS: Five artificial spherical GGNs with various densities (-250, -350, -450, -550, and -630 Hounsfield units) and 10 mm in diameter were placed in a thorax anthropomorphic phantom. Four scans at four different radiation dose levels were performed using a 256-slice CT (Revolution Apex CT, GE Healthcare). Each scan was reconstructed using three different reconstruction algorithms: adaptive statistical iterative reconstruction-V at a level of 50% (AR50), Truefidelity (TF), which is a DLIR method, and TF with a lung enhancement filter (TF + Lu). Thus, 12 sets of reconstructed images were obtained and analyzed. Image noise, signal-to-noise ratio, and contrast-to-noise ratio were compared among the three reconstruction algorithms. Nodule sharpness was compared among the three reconstruction algorithms using the full-width at half-maximum value. Furthermore, subjective image quality analysis was performed. RESULTS: AR50 demonstrated the highest level of noise, which was decreased by using TF + Lu and TF alone (P = 0.001). TF + Lu significantly improved nodule sharpness at all radiation doses compared to TF alone (P = 0.001). The nodule sharpness of TF + Lu was similar to that of AR50. Using TF alone resulted in the lowest nodule sharpness. CONCLUSION: Adding a lung enhancement filter to DLIR (TF + Lu) significantly improved the nodule sharpness compared to DLIR alone (TF). TF + Lu can be an effective reconstruction technique to enhance image quality and GGN evaluation in ultralow-dose chest CT scans.

Mimicking rib osteochondroma as pulmonary nodule in a pediatric patient: A case report from Damascus, Syria.

Osteochondromas, the most frequent type of bone tumor, develop from the metaphysis region of bones. Osteochondroma often occurs in bones, however, it is rare when it comes to rib tumors. It is often asymptomatic and observed incidentally. We present a case of a 14-year-old male patient who had been experiencing cough and mild fever for approximately a week. We requested a CXR PA and LAT. It showed a pulmonary nodule measuring 1.5 cm in diameter in the upper segment of the left lower lobe. Taking into account the unclear nature of the diagnosis, we requested CT scan with contrast of the chest to obtain a better view. It showed: The nodule visualized on the CXR corresponded to a posteriorly directed, well-defined lesion arising from the costal cartilage of the third left rib, measuring 1.2 × 1.3 × 1.1 cm, likely representing an osteochondroma. The case we discussed highlights a rib osteochondroma that initially seemed like a pulmonary nodule on an X-ray, pointing out the importance of using CT scans for accurate diagnosis in such cases, and reminding us to consider osteochondroma when we see similar symptoms and to regularly check the tumor with medical imaging after it's been confirmed by a pathological test.

Improving Radial EBUS Signal with Creation of False Airway to Target Lesion During Electromagnetic Navigational Bronchoscopy: A Case Series.

Navigational bronchoscopy is increasingly used to target peripheral pulmonary nodules using electromagnetic navigational platforms (ENB), fluoroscopic navigation, or robotic-assisted bronchoscopy. The selection of equipment largely depends on the availability of technology, expertise, and the characteristics of the nodule and patient. Radial EBUS (r-EBUS) is often combined with these techniques for real-time confirmation of the nodule location. A bronchus sign is considered to have a higher diagnostic yield when biopsy tools can directly reach the nodule. We describe a case series of creating a false airway into the nodule when an eccentric r-EBUS signal is seen to subsequently obtain a concentric signal.

Assessment of Follow-Up for Pulmonary Nodules from Radiology Reports with Natural Language Processing.

Radiology reports are an essential communication method for ensuring smooth workflow in healthcare. However, many of these reports are described in free text, and findings documented by radiologists may not be adequately addressed. In this study, focusing on pulmonary nodules, we evaluated whether cases in which radiologists described follow-up as recommended were receiving appropriate treatment. Reports recommending follow-up for pulmonary nodules were automatically extracted using natural language processing. In our evaluation, out of 10,507 reports, 1,501 cases (14.3%) were classified as "reports recommending follow-up for pulmonary nodules." Among these, 958 cases underwent additional imaging tests within 400 days. From the remaining 543 cases, we randomly sampled 42 cases and conducted chart reviews by clinicians to confirm patient care status. Our assessment found that follow-up was not documented in 17 of the 42 cases (40.5%), indicating a high likelihood that appropriate care was not provided.