Lung Nodules Research Articles

Radiomics-Based Support Vector Machine Distinguishes Molecular Events Driving the Progression of Lung Adenocarcinoma

IntroductionAn increasing number of early-stage lung adenocarcinomas (LUAD) are detected as lung nodules. The radiological features related to LUAD progression warrant further investigation. Exploration is required to bridge the gap between radiomics-based features and molecular characteristics of lung nodules. MethodsConsensus clustering was applied to the radiomic features of 1212 patients to establish stable clustering. Clusters were illustrated using clinicopathological and next-generation sequencing. A classifier was constructed to further investigate the molecular characteristics in patients with paired computed tomography and RNA sequencing data. ResultsPatients were clustered into four clusters. Cluster 1 was associated with a low consolidation-to-tumor ratio, preinvasion, grade I disease, and good prognosis. Clusters 2 and 3 reported increasing malignancy with a higher consolidation-to-tumor ratio, higher pathologic grade, and poor prognosis. Cluster 2 possessed more spread through air spaces and cluster 3 reported a higher proportion of pleural invasion. Cluster 4 had similar clinicopathological features as cluster 1 except but a proportion of grade II disease. RNA sequencing indicated that cluster 1 represented nodules with indolent growth and good differentiation, whereas cluster 4 reported progression in cell development but still had low proliferative activity. Nodules with high proliferation were classified into clusters 2 and 3. In addition, the radiomics classifier distinguished cluster 2 as nodules harboring an activated immune environment, whereas cluster 3 represented nodules with a suppressive immune environment. Furthermore, signatures associated with the prognosis of early-stage LUAD were validated in external datasets. ConclusionsRadiomics features can manifest molecular events driving the progression of LUAD. Our study provides molecular insight into radiomics features and assists in the diagnosis and treatment of early-stage LUAD.

Outcomes of incidental pulmonary nodules detected in oral and oropharyngeal cancer patients

Computed tomography (CT) of the chest is routinely performed as part of head and neck cancer (HNC) staging. Pulmonary nodules incidentally encountered present a clinical dilemma, as they may indicate early malignancy. Clinically indeterminant nodules are those that cannot be classed as definitively malignant or benign. This study aimed to assess the outcomes of pulmonary nodules detected on initial staging chest CT in a consecutive cohort of patients with oral and oropharyngeal squamous cell carcinoma (SCC). A retrospective cohort study of newly diagnosed oral or oropharyngeal SCC patients with pulmonary nodules identified on staging chest CT at a single institution was conducted. Pulmonary nodules were categorised as benign, indeterminant, or malignant. Indeterminant nodules underwent further investigations with either repeat imaging or needle biopsy to exclude malignancy. Descriptive and bivariate statistics were used to evaluate the association between pulmonary metastasis and patient demographics, disease characteristics, and nodular features. P values of ≤ 0.05 were considered statistically significant. Of 579 patients diagnosed with HNC who had undergone staging chest CT between 2010 and 2015, 154 had pulmonary nodules. Indeterminant pulmonary nodules at staging in 26 patients (16.9%) were later confirmed to be lung metastases. Pulmonary nodules of subsolid type found in patients with N2/N3 disease were significantly more likely to be metastatic. Isolated pulmonary nodules in the right lung were more likely to be benign. A HNC-specific protocol for the management of incidental pulmonary nodules should now be developed to guide the interval and duration of required clinical and radiological surveillance, taking into account the disease characteristics and nodular features.

A Rare Cause of a Growing Solitary Pulmonary Nodule

A Rare Cause of a Growing Solitary Pulmonary Nodule

Integration of adjunct imaging for peripheral lung nodule sampling: a comprehensive review

Integration of adjunct imaging for peripheral lung nodule sampling: a comprehensive review

The probability of implantation metastasis after peripheral lung cancer biopsy.

At present, it is known that there is a possibility of pleural cavity and needle tract implantation metastasis after lung cancer puncture biopsy, but clinicians have not paid attention to this phenomenon, and the probability of occurrence is unknown. In this study, we aimed to study the probability of implantation metastasis after peripheral lung cancer biopsy. The intraoperative isolated completely collapsed fresh intact human lung lobes of 30 patients with peripheral lung cancer were taken, and the tumor body was punctured. The pleural pinholes and puncture needle tips were repeatedly rinsed with normal saline respectively. The flushing solution was prepared as inoculum, and then the inoculum was smeared for microscopic examination to find cancer cells. The inoculum was inoculated subcutaneously into nude mice, and then the probability of pleural cavity and needle tract implantation metastasis after lung biopsy was indirectly obtained by obtaining the nude mice tumorigenesis rate. The tumorigenesis rate of nude mice in the pleural pinholes group was 3.3%, and the tumorigenesis rate of nude mice in the puncture needle tip group was 3.3%. Patients with lung nodules suspected of being early stage cancer and who are fit for surgical resection may benefit from forgoing lung biopsies to avoid pleural cavity or needle tract seeding with tumor cells.

Combining Multistaged Filters and Modified Segmentation Network for Improving Lung Nodules Classification.

Advancements in computational technology have led to a shift towards automated detection processes in lung cancer screening, particularly through nodule segmentation techniques. These techniques employ thresholding to distinguish between soft and firm tissues, including cancerous nodules. The challenge of accurately detecting nodules close to critical lung structures such as blood vessels, bronchi, and the pleura highlights the necessity for more sophisticated methods to enhance diagnostic accuracy. This paper proposed combined processing filters for data preparation before using one of the modified Convolutional Neural Networks (CNNs) as the classifier. With refined filters, the nodule targets are solid, semi-solid, and ground glass, ranging from low-stage cancer (cancer screening data) to high-stage cancer. Furthermore, two additional works were added to address juxta-pleural nodules while the pre-processing end and classification are done in a 3-dimensional domain in opposition to the usual image classification. The accuracy output indicates that even using a simple Segmentation Network if modified correctly, can improve the classification result compared to the other eight models. The proposed sequence total accuracy reached 99.7%, with 99.71% cancer class accuracy and 99.82% non-cancer accuracy, much higher than any previous research, which can improve the detection efforts of the radiologist.

Enhanced tumor targeting and penetration of fluorophores via iRGD peptide conjugation: a strategy for the precision targeting of lung cancer.

Accurate real-time tumor delineation is essential for achieving curative resection (R0 resection) during non-small cell lung cancer (NSCLC) surgery. The unique characteristics of lung tissue structure significantly challenge the use of video-assisted thoracoscopic surgery in the identification of lung nodules. This difficulty often results in an inability to discern the margins of lung nodules, necessitating either an expansion of the resection scope, or a transition to open surgery. Due to its high spatial resolution, ease of operation, and capacity for real-time observation, near-infrared fluorescence (NIRF) navigation in oncological surgery has emerged as a focal point of clinical research. Targeted NIRF probes, which accumulate preferentially in tumor tissues and are rapidly cleared from normal tissues, enhance diagnostic sensitivity and surgical outcomes. The imaging effect of the clinically approved NIRF probe indocyanine green (ICG) varies significantly from person to person. Therefore, we hope to develop a new generation of targeted NIRF probes targeting lung tumor-specific targets. First, the peptide iRGD (sequence: CRGDKGPDC) fluorescent tracer was synthesized, and characterized through mass spectrometry (MS), proton nuclear magnetic resonance (1H NMR), and high-performance liquid chromatography (HPLC). Fluorescence properties were tested subsequently. Safety was performed in vitro using both human normal liver cells and human normal breast cells. Second, Metabolism and optimal imaging time were determined by tail vein injection of iRGD fluorescent tracer. Finally, Orthotopic and metastatic lung tumor models were used to evaluate the targeting properties of the iRGD fluorescent tracer. We successfully synthesized an iRGD fluorescent tracer specifically designed to target NSCLC. The molecular docking analyses indicated that this tracer has receptor affinity comparable to that of iRGD for αvβ3 integrin, with a purity ≥98%. Additionally, the tracer is highly soluble in water, and its excitation and emission wavelengths are 767 and 799 nm, respectively, positioning it within the near-infrared spectrum. The cellular assays confirmed the tracer's minimal cytotoxicity, underscoring its excellent biosafety profile. In vivo studies further validated the tracer's capacity for specific NSCLC detection at the cellular level, alongside a prolonged imaging window of 6 days or more. Notably, the tracer demonstrated superior specificity in localizing very small lung nodules, which are otherwise clinically indiscernible, outperforming non-targeted ICG. Fluorescence intensity analyses across various organs revealed that the tracer is predominantly metabolized by the liver and kidneys, with excretion via bile and urine, and exhibits minimal toxicity to these organs as well as the lungs. The iRGD fluorescent tracer selectively accumulates in NSCLC tissues by specifically targeting αvβ3 receptors, which are overexpressed on the surface of tumor cells. This targeted approach facilitates the real-time intraoperative localization of NSCLC, presenting an improved strategy for intraoperative tumor identification with significant potential for clinical application.

Assessment of needle-based confocal laser endomicroscopy (nCLE) as a tool for real-time diagnosis of non-small cell lung cancer.

The widespread deployment of screening programs has increased the number of suspected pulmonary nodules diagnosed. The main objective of this retrospective study was to evaluate the concordance between needle-based confocal laser endomicroscopy (nCLE) image patterns and pathology reports. In this retrospective study, we reviewed all cases of endobronchial navigational bronchoscopy (ENB) performed using the nCLE system as a guide for injecting a dye marker or for biopsy of a lung nodule. All surgeries were performed at the Thoracic Surgery Department, University Hospital Nancy, France, between June and October 2023. All navigation procedures were performed under general anesthesia by a senior resident supervised by a senior surgeon, and endobronchial positioning assistance was provided by using the nCLE probe. A total of 30 patients were included in this study. The median size of the suspicious lesions was 16 mm [interquartile range (IQR), 13 mm]. The average time the nCLE system was in contact with the lesion was 5 minutes (IQR, 5 minutes). In 22/30 patients, dark, enlarged pleomorphic cells were visualized, and for one patient, a mix of dark clusters and dark enlarged pleomorphic cells was visualized, leading to a diagnosis of cancer in 22/23 patients (95.6%). For five patients, dark clusters were visualized, resulting in a diagnosis of cancer in 100% of patients. Pathology was performed for 6/30 patients/21 (20%) by endobronchial biopsy and for 24 patients by surgical resection of the suspicious lesion (80%). By retrospectively analyzing the nCLE lung cancer criteria published by Wijmans et al. in 2019, we observed 95.6% and 100% positive diagnoses according to the images visualized during the assistance of positioning. We believe that this type of technology could be used in the future for endobronchial analysis of suspected lesions and eventually for replacing frozen section analysis. However, the diagnostic value of this system needs to be confirmed, particularly for benign lesions.

Peritumoral radiomics increases the efficiency of classification of pure ground-glass lung nodules: a multicenter study

PurposeWe aimed to evaluate the efficiency of computed tomography (CT) radiomic features extracted from gross tumor volume (GTV) and peritumoral volumes (PTV) of 5, 10, and 15 mm to identify the tumor grades corresponding to the new histological grading system proposed in 2020 by the Pathology Committee of the International Association for the Study of Lung Cancer (IASLC).MethodsA total of 151 lung adenocarcinomas manifesting as pure ground-glass lung nodules (pGGNs) were included in this randomized multicenter retrospective study. Four radiomic models were constructed from GTV and GTV + 5/10/15-mm PTV, respectively, and compared. The diagnostic performance of the different models was evaluated using receiver operating characteristic curve analysisResultsThe pGGNs were classified into grade 1 (117), 2 (34), and 3 (0), according to the IASLC grading system. In all four radiomic models, pGGNs of grade 2 had significantly higher radiomic scores than those of grade 1 (P < 0.05). The AUC of the GTV and GTV + 5/10/15-mm PTV were 0.869, 0.910, 0.951, and 0.872 in the training cohort and 0.700, 0.715, 0.745, and 0.724 in the validation cohort, respectively.ConclusionsThe radiomic features we extracted from the GTV and PTV of pGGNs could effectively be used to differentiate grade-1 and grade-2 tumors. In particular, the radiomic features from the PTV increased the efficiency of the diagnostic model, with GTV + 10 mm PTV exhibiting the highest efficacy.

Lung adenocarcinoma concurrent with pulmonary cryptococcosis: a case report and literature review

Pulmonary cryptococcosis (PC) is a common opportunistic fungal infection caused by Cryptococcus neoformans or Cryptococcus gattii. PC primarily invades the respiratory system, followed by the central nervous system. Few clinical reports have examined the coexistence of PC and lung cancer. This study reports the case of a 54-year-old immunocompetent PC patient with lung adenocarcinoma. Chest CT revealed multiple nodules in the right lung, with the largest nodule located in the dorsal segment of the right lower lobe. 18 F‑FDG positron emission tomography-computed tomography (PET-CT) revealed elevated glucose metabolism in the dorsal segment of the right lower lobe, which suggested lung cancer. The metabolism level of the nodule in the basal segment of the right lower lobe and the anterior segment of the right upper lobe was not abnormally increased, but the possibility of a malignant tumour could not be excluded. The pulmonary nodules in the dorsal segment and the basal segment of the right lower lobe were simultaneously resected via video-assisted thoracic surgery (VATS), and the final histopathology revealed primary lung adenocarcinoma and pulmonary cryptococcal infection, respectively. After surgery, antifungal treatment was administered for 3 months. Over the 3-year follow-up, contrast-enhanced computed tomography (CT) revealed no recurrence of either disease. This case study highlights the possibility of dualism in the diagnosis of multiple pulmonary nodules on chest CT, such as the coexistence of lung cancer and PC. Surgical resection is recommended for micronodules that are not easy to diagnose via needle biopsy; in addition, early diagnosis and treatment are helpful for ensuring a good prognosis. This paper reports the clinical diagnosis and treatment of one patient with pulmonary cryptococcal infection of the right lung complicated with lung adenocarcinoma, including 3 years of follow-up, providing a reference for clinical practice.

Simultaneously Detected Liver and Lung Metastases from Colorectal Carcinoma: A Potential Treatment Strategy.

No clear treatment strategy for simultaneously detected liver and lung metastases (SLLM) of colorectal carcinoma has been established, to date. We aimed to identify the prognostic factors for SLLM and propose an appropriate treatment option. This retrospective study included 64 patients with SLLM: 32 underwent pulmonary resection after hepatectomy in 32, while the other 32 underwent hepatectomy alone in 32. Poor prognostic factors and a suitable strategy for SLLM were assessed. Multivariate analysis showed that preoperative carcinoembryonic antigen (CEA) level ≥20 ng/ml (p=0.001) and unresected lung metastases (p=0.001) were independent prognostic factors for poor overall survival. Compared with the non-pulmonary resection group, the rate of R1 resection of liver tumors (46.8% vs. 15.6%; p=0.007), incidence of complications after hepatectomy (Clavien-Dindo grade ≥III: 21.8% vs. 0%; p=0.005) and having four or more metastatic lung nodules (40.6% vs. 3.2%; p=0.001) were significantly higher in the group that underwent hepatectomy only. Preoperative CEA ≥20 ng/ml and unresectable pulmonary nodules were prognostic factors for poor survival of patients with SLLM. Furthermore, the presence of more than four pulmonary nodules was a preoperative predictive factor for unresectable pulmonary nodules. R1 resection and the occurrence of complications after hepatectomy should be avoided; a smooth transition from hepatectomy to pulmonary resection is important.

Giant Cystic Pneumocytoma in a Young Male: Rare Diagnostic Conundrum with Clinicoradiological and Histopathological Features

AbstractPulmonary sclerosing pneumocytoma is a rare benign neoplasm typically seen in middle-aged women. The exact preoperative diagnosis is quite challenging considering its nonspecific clinical and radiologic features along with complex histology. Moreover, obtaining an exact histopathological diagnosis can be difficult especially with the small biopsy specimens. Most patients are generally asymptomatic with incidental detection of peripheral, homogenous, solitary pulmonary nodule. It is essential to differentiate it from other mimickers including malignant lesions as limited surgical resection is curative in these cases without adjuvant therapy. We present a rare giant cystic variant of pneumocytoma, in a young male, which was initially mimicking inflammatory myofibroblastic tumor even on preoperative histology.

Growth dynamics of lung nodules: implications for classification in lung cancer screening

BackgroundLung nodules observed in cancer screening are believed to grow exponentially, and their associated volume doubling time (VDT) has been proposed for nodule classification. This retrospective study aimed to elucidate the growth dynamics of lung nodules and determine the best classification as either benign or malignant.MethodsData were analyzed from 180 participants (73.7% male) enrolled in the I-ELCAP screening program (140 primary lung cancer and 40 benign) with three or more annual CT examinations before resection. Attenuation, volume, mass and growth patterns (decelerated, linear, subexponential, exponential and accelerated) were assessed and compared as classification methods.ResultsMost lung cancers (83/140) and few benign nodules (11/40) exhibited an accelerated, faster than exponential, growth pattern. Half (50%) of the benign nodules versus 26.4% of the malignant ones displayed decelerated growth. Differences in growth patterns allowed nodule malignancy to be classified, the most effective individual variable being the increase in volume between two-year-interval scans (ROC-AUC = 0.871). The same metric on the first two follow-ups yielded an AUC value of 0.769. Further classification into solid, part-solid or non-solid, improved results (ROC-AUC of 0.813 in the first year and 0.897 in the second year).ConclusionsIn our dataset, most lung cancers exhibited accelerated growth in contrast to their benign counterparts. A measure of volumetric growth allowed discrimination between benign and malignant nodules. Its classification power increased when adding information on nodule compactness. The combination of these two meaningful and easily obtained variables could be used to assess malignancy of lung cancer nodules.

Radiomics Analysis for the Identification of Invasive Pulmonary Subsolid Nodules From Longitudinal Presurgical CT Scans.

Effective identification of malignant part-solid lung nodules is crucial to eliminate risks due to therapeutic intervention or lack thereof. We aimed to develop delta radiomics and volumetric signatures, characterize changes in nodule properties over three presurgical time points, and assess the accuracy of nodule invasiveness identification when combined with immediate presurgical time point radiomics signature and clinical biomarkers. Cohort included 156 part-solid lung nodules with immediate presurgical CT scans and a subset of 122 nodules with scans at 3 presurgical time points. Region of interest segmentation was performed using ITK-SNAP, and feature extraction using CaPTk. Image parameter heterogeneity was mitigated at each time point using nested ComBat harmonization. For 122 nodules, delta radiomics features (ΔRAB= (RB-RA)/RA) and delta volumes (ΔVAB= (VB-VA)/VA) were computed between the time points. Principal Component Analysis was performed to construct immediate presurgical radiomics (Rs1) and delta radiomics signatures (ΔRs31+ ΔRs21+ ΔRs32). Identification of nodule pathology was performed using logistic regression on delta radiomics and immediate presurgical time point signatures, delta volumes (ΔV31+ ΔV21+ ΔV32), and clinical variable (smoking status, BMI) models (train test split (2:1)). In delta radiomics analysis (n= 122 nodules), the best-performing model combined immediate pre-surgical time point and delta radiomics signatures, delta volumes, and clinical factors (classification accuracy [AUC]): (77.5% [0.73]) (train); (71.6% [0.69]) (test). Delta radiomics and volumes can detect changes in nodule properties over time, which are predictive of nodule invasiveness. These tools could improve conventional radiologic assessment, allow for earlier intervention for aggressive nodules, and decrease unnecessary intervention-related morbidity.

An end-to-end deep learning method for mass spectrometry data analysis to reveal disease-specific metabolic profiles

Untargeted metabolomic analysis using mass spectrometry provides comprehensive metabolic profiling, but its medical application faces challenges of complex data processing, high inter-batch variability, and unidentified metabolites. Here, we present DeepMSProfiler, an explainable deep-learning-based method, enabling end-to-end analysis on raw metabolic signals with output of high accuracy and reliability. Using cross-hospital 859 human serum samples from lung adenocarcinoma, benign lung nodules, and healthy individuals, DeepMSProfiler successfully differentiates the metabolomic profiles of different groups (AUC 0.99) and detects early-stage lung adenocarcinoma (accuracy 0.961). Model flow and ablation experiments demonstrate that DeepMSProfiler overcomes inter-hospital variability and effects of unknown metabolites signals. Our ensemble strategy removes background-category phenomena in multi-classification deep-learning models, and the novel interpretability enables direct access to disease-related metabolite-protein networks. Further applying to lipid metabolomic data unveils correlations of important metabolites and proteins. Overall, DeepMSProfiler offers a straightforward and reliable method for disease diagnosis and mechanism discovery, enhancing its broad applicability.

Retraction Note: Optimized convolutional neural network for automatic lung nodule detection with a new active contour segmentation

Retraction Note: Optimized convolutional neural network for automatic lung nodule detection with a new active contour segmentation

Examination of Firefighting as an Occupational Exposure Criteria for Lung Cancer Screening.

Firefighting is known to be carcinogenic to humans. However, current lung cancer screening guidelines do not account for occupational exposure. We hypothesize that firefighting is an independent risk factor associated with the development of high-risk lung nodules on low-dose CT (LDCT). Members of a firefighter's union underwent LDCT at a single institution between April 2022 and June 2023 within a lung cancer screening program. Results were interpreted by designated chest radiologists and reported using the Lung-RADS scoring system. Demographic and radiographic data were recorded, and summary statistics are reported. 1347 individuals underwent lung cancer screening, with a median age of 51years (IQR 42-58), including 56 (4.2%) females. Overall, 899 (66.7%) were never smokers, 345 (25.6%) were former smokers, and 103 (7.7%) were current smokers. There were 41 firefighters (3.0%) who had high-risk (Lung-RADS 3 or 4) nodules requiring intervention or surveillance, of which 21 (1.5%) were Lung-RADS 3 and 20 (1.5%) that were Lung-RADS 4. Of the firefighters with high-risk nodules, only 6 (14.6%) were eligible for LDCT based on current screening guidelines. There were 7 high-risk nodules (0.5%) that required procedural intervention, 6 (85.7%) of which were from the non-screening eligible cohort. There were also 20 never-smoking firefighters (57.1%) with high-risk nodules that were non-screening eligible. Firefighting, even in the absence of smoking history, may be associated with the development of high-risk lung nodules on LDCT. Carefully selected occupational exposures should be considered in the development of future lung cancer screening guidelines.

A survey on comparative study of lung nodules applying machine learning and deep learning techniques

A survey on comparative study of lung nodules applying machine learning and deep learning techniques

Cytologic Findings and Ancillary Tests Results of Sclerosing Pneumocytoma: Our Institutional Experience.

Sclerosing pneumocytoma (SP) is a rare benign tumor and a potential diagnostic pitfall. Our aim was to review the cytologic features of our surgically diagnosed SP cases including the clinical, immunohistochemical and available molecular findings. A computerized search from 2013 to 2020 for surgical cases with corresponding cytology specimens diagnosed as SP was performed. The clinical data, cytology, and surgical specimens were collated for analysis. Six cytology specimens were collected. All were female (mean age = 35). Three have incidental lung nodules and three with cough. Cytologic findings showed variable architectural pattern (papillary, solid, singly scattered, acinar/rosette-like) and cellular heterogeneity (surface, stromal, epithelioid, plasmacytoid cells). Atypia was identified in 4/6 cases. The original cytology diagnoses were negative = 1, SP = 2 and adenocarcinoma = 3. The latter diagnoses were amended to SP after review of the surgical specimens. The three false positive cases on review have cytologic features mimicking adenocarcinoma. Immunohistochemical stains showed tumor cells (surface and stromal) were positive for TTF-1, and EMA with only the surface cells positive for pancytokeratin and Napsin A. Though two cases sent for molecular testing were negative for AKT1 or CTNNB1 exon 3 mutation, our panel did not evaluate AKT1 exon 4. SP is a diagnostic pitfall with 50% initially misdiagnosed as adenocarcinoma. Integrating the clinical/radiologic findings, cytologic features, and performance of immunohistochemistry on cell block are helpful in avoiding misdiagnosis. Molecular testing for recurrent mutations, if present, could be helpful for diagnosis and possible therapy options. However, routinely used molecular testing may not always capture relevant molecular markers for SP.

Speed and efficiency: evaluating pulmonary nodule detection with AI-enhanced 3D gradient echo imaging.

Evaluating the diagnostic feasibility of accelerated pulmonary MR imaging for detection and characterisation of pulmonary nodules with artificial intelligence-aided compressed sensing. In this prospective trial, patients with benign and malignant lung nodules admitted between December 2021 and December 2022 underwent chest CT and pulmonary MRI. Pulmonary MRI used a respiratory-gated 3D gradient echo sequence, accelerated with a combination of parallel imaging, compressed sensing, and deep learning image reconstruction with three different acceleration factors (CS-AI-7, CS-AI-10, and CS-AI-15). Two readers evaluated image quality (5-point Likert scale), nodule detection and characterisation (size and morphology) of all sequences compared to CT in a blinded setting. Reader agreement was determined using the intraclass correlation coefficient (ICC). Thirty-seven patients with 64 pulmonary nodules (solid n = 57 [3-107 mm] part-solid n = 6 [ground glass/solid 8 mm/4-28 mm/16 mm] ground glass nodule n = 1 [20 mm]) were analysed. Nominal scan times were CS-AI-7 3:53 min; CS-AI-10 2:34 min; CS-AI-15 1:50 min. CS-AI-7 showed higher image quality, while quality remained diagnostic even for CS-AI-15. Detection rates of pulmonary nodules were 100%, 98.4%, and 96.8% for CS-AI factors 7, 10, and 15, respectively. Nodule morphology was best at the lowest acceleration and was inferior to CT in only 5% of cases, compared to 10% for CS-AI-10 and 23% for CS-AI-15. The nodule size was comparable for all sequences and deviated on average < 1 mm from the CT size. The combination of compressed sensing and AI enables a substantial reduction in the scan time of lung MRI while maintaining a high detection rate of pulmonary nodules. Incorporating compressed sensing and AI in pulmonary MRI achieves significant time savings without compromising nodule detection or characteristics. This advancement holds clinical promise, enhancing efficiency in lung cancer screening without sacrificing diagnostic quality. Lung cancer screening by MRI may be possible but would benefit from scan time optimisation. Significant scan time reduction, high detection rates, and preserved nodule characteristics were achieved across different acceleration factors. Integrating compressed sensing and AI in pulmonary MRI offers efficient lung cancer screening without compromising diagnostic quality.