Stage Lung Cancer Research Articles

Proposed Ninth Edition TNM Staging System for Lung Cancer: Guide for Radiologists.

Lung cancer continues to be the primary cause of cancer-related deaths globally. Precise staging is imperative for the development of successful treatment approaches and improvement of patient outcomes. Traditionally, lung cancer staging has depended on the TNM staging system, and the International Association for the Study of Lung Cancer (IASLC) has recently recommended modifications. The updated classification for the ninth edition of the TNM staging system (TNM-9), slated to take effect in January 2025, is derived from a thorough analysis of a newly established large international database of lung cancer cases compiled by the IASLC. Proposed changes in TNM-9 include the following: (a) The mediastinal nodal category (N2) was split into single-station (N2a) and multiple-station (N2b) subcategories, and (b) multiple extrathoracic metastatic lesions (M1c) were split into single organ system (M1c1) and multiple organ systems (M1c2) subcategories. Considering these revisions, adjustments have been made to the established stage groups. In terms of pathologic nodal staging, patients in the post-neoadjuvant ypN category demonstrated worse prognosis than those in the similar non-neoadjuvant pN category. Understanding the fundamental changes introduced in TNM-9 enables radiologists to precisely determine the clinical stage of lung cancer and enhance therapeutic approaches.

Drainless Uniportal VATS Wedge Resection for Early Non-Small Cell Lung Cancer: Propensity Analysis of the Effect of Polyglycolic Acid Sheet (NeoveilTM)

Objectives: Absorbable biomaterials as adjuvant therapy after thoracoscopy are sometimes used in clinical scenarios. With the prevalence of enhanced rapid recovery in thoracic surgery, drainless video-assisted thoracoscopy surgery (VATS) is often adopted by thoracic surgeons. Here, we discuss utilizing an absorbable biomaterial, NeoveilTM (Polyglycolic Acid sheet), for drainless VATS to treat early lung cancer. Methods: This single-center retrospective study was conducted from January 2018 to December 2022 at the National Taiwan University Hospital. We included patients who underwent drainless VATS for early-stage non-small cell lung cancer (NSCLC) in our institute. Propensity analysis was used to minimize selection bias. Outcome measurements were in-hospital stay, operation time, rate of thoracocentesis or chest drain re-insertion, complication rate, and perioperative course. Results: During the study period, 158 lung cancer patients were performed with drainless VATS wedge resection. Among them, Neoveil for stapling line coverage was done in 72 patients, while 86 patients did not receive Neoveil. After propensity analysis, we had 58 patients using Neoveil after drainless thoracoscopic lung resection, compared fairly with 58 patients without Neoveil after the same procedure. The basic characteristics are comparable regarding age, gender, BMI, operation methods, and lung cancer stage after propensity matching. The in-hospital stay (3.2 days in the Neoveil group and 5.6 days in the non-Neoveil group) and operation time (95.7 min in the Neoveil group and 59.3 min in the non-Neoveil group) are significantly different (p = 0.0001). One versus four patients was noted for postoperative conversion chest drainage insertion in each group (p = 0.17). Neither late complications nor recurrence/metastasis occurred in both groups during the following. Conclusions: Based on our 5-year retrospective study, which is balanced with propensity analysis, drainless thoracoscopic surgery treating early lung cancer can be enhanced by Neoveil with faster recovery by reducing the hospital stay, though with longer operation time.

Multi-center study on the application potential of Siaα-2,6Gal in early and differential diagnosis of lung cancer.

This study aimed to investigate the application potential of the abnormal glycan structure Siaα-2,6Gal in the early and differential diagnosis of lung cancer. Clinical data and serum samples from 730 patients and 120 healthy individuals participating in clinical trials on Siaα-2,6Gal were collected at three medical centers between January 2022 and June 2023. The levels of Siaα-2,6Gal, carcinoembryonic antigen (CEA), cytokeratin 19 fragment antigen (CYFRA21-1), squamous cell carcinoma antigen (SCC), neuron-specific enolase (NSE), and pro-gastrin-releasing peptide (ProGRP) in serum were measured. The application potentials of these markers in the early and differential diagnosis, classification, and staging of lung cancer were explored. (1) Serum Siaα-2,6Gal levels in the lung cancer group were 2,606 (1,970-3,458) U/mL, significantly higher than those in the benign lung disease, miscellaneous malignant tumor, miscellaneous benign disease, and healthy individual groups at 1,359 (950-1,528), 1,252 (903-1,532), 1,196 (850-1,490), and 1,210 (1,100-1,287) U/mL (P < 0.0001). (2) Serum Siaα-2,6Gal levels in the early-stage lung cancer (stages 0-II) group were 2,576 (1,929-3,338) U/mL, significantly higher than those in the benign pulmonary nodule group at 1,419 (1,105-1,820) U/mL (P < 0.0001). (3) Receiver operating characteristic curves showed that Siaα-2,6Gal had a high diagnostic efficiency for lung cancer (area under the curve (AUC) = 0.9217), significantly superior to CEA, CYFRA21-1, SCC, NSE, and ProGRP (AUCs of 0.6618, 0.6605, 0.5783, 0.5985, and 0.6381). Siaα-2,6Gal is a promising biomarker for lung cancer diagnosis and may offer superior differential diagnosis of early-stage lung cancer from benign pulmonary nodules compared to traditional tumor markers.

Abstract B058: Novel machine learning lung cancer classifier shows significant correlation with cancer-specific fragmentomics features

Abstract Lung cancer is the second most prevalent cancer, and the leading cause of cancer-related deaths, in the US. Since the survival rate of patients diagnosed with lung cancer at earlier stages is dramatically higher than those diagnosed at later stages, technologies that shift lung cancer diagnosis to an earlier stage would be expected to improve survival rates. Fragmentomics, the study of short circulating cell-free DNA (cfDNA) fragments in the blood, is an emerging field in cancer diagnostics that has the potential to catalyze such a shift. Studies have shown that fragmentomics features, such as fragment sizes and end motifs, can be used to discriminate normal cfDNA from circulating tumor DNA (ctDNA) generated through tumor necrosis and apoptosis. Using this knowledge, machine learning tools, trained to identify ctDNA-specific features, are being leveraged in novel liquid biopsy assays to improve early-stage lung cancer detection. To create a machine learning classifier that detects discrete signals of ctDNA in individuals with lung cancer, Genece Health utilized low pass (∼3x coverage) whole genome sequencing (Illumina) of plasma extracted cfDNA from &amp;gt;400 lung cancer samples and &amp;gt;1,000 negative controls. This data was used to generate our novel FEMS (Fragment End Motifs and Sizes) dataframe, containing &amp;gt;30,000 features, by combining fragment lengths with their corresponding 5’ 4bp end motifs. The FEMS dataframe was then used to train a neural network machine learning classifier. To evaluate the performance of our machine learning classifier, we investigated whether the classifier scores correlated with well-known hallmarks of ctDNA. First, consistent with published ctDNA characteristics, we observed significant (p&amp;lt;0.01) enrichment of fragment sizes ≤167bp in lung cancer samples. Concordantly, our classifier scores are significantly correlated with this fragment size enrichment. Also, both fragment size enrichment and our classifier scores are correlated with lung cancer stage, with higher enrichment and higher scores observed in later stages. Next, we show that our classifier scores are correlated with specific end motif enrichments or depletions in lung cancer samples. For example, in lung cancer samples, CCCA end motifs were significantly enriched (p&amp;lt;0.01) in fragment sizes 120-140bp (max at 128bp), while significantly depleted in fragment sizes 190-210bp (min at 204bp). Once again, our classifier scores were significantly correlated with both the enrichment of this end motif in short fragments and its depletion in long fragments. Last, we assessed the classifier’s performance in an independent cohort (46 lung cancer and 132 non-cancer samples) and show 89.2% sensitivity with 90.4% specificity (auROC=0.957). The correlation observed between our classifier scores and published ctDNA characteristics, combined with the strong performance in an independent cohort, suggests that Genece’s novel machine learning classifier is effectively leveraging ctDNA-specific fragmentomics features for the identification of lung cancer in patient samples. Citation Format: Carlos Guzman, Michael L Salmans, Mengchi Wang, Byung In Lee, Andrew R Carson. Novel machine learning lung cancer classifier shows significant correlation with cancer-specific fragmentomics features [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr B058.

Comparison of whole-body 18F-FDG-PET/CT with 18F-FDG-PET/CT limited to skull base to upper abdomen for primary staging of lung cancer - a retrospective explorative analysis.

The gold standard for ruling out distant metastases as part of primary staging in lung cancer is whole-body 18F-FDG-PET/CT, but this method is resource-intensive. Recent evidence suggests that examining only the thorax and upper abdomen may be sufficient 1 2 3. If a limited 18F-FDG-PET/CT approach proves effective for proper staging, it could lead to quicker examinations and reduced radiation exposure. This study aimed to determine whether limited 18F-FDG-PET/CT is adequate for the primary staging of lung cancer.In this study, a retrospective analysis of 161 patients (87 men, 74 women; age range 31-88 y) with recent or suspected lung cancer who had undergone a whole-body 18F-FDG-PET/CT examination for primary staging at our clinic between 2018 and 2022 was conducted. None of these patients showed evidence of extrathoracic metastases before the 18F-FDG-PET/CT examination. The images were divided into three regions: "head-neck" (HN), "thorax-upper abdomen" (TUA), and "lower abdomen-hip" (LAH). TNM staging based on the HN plus TUA region was compared with TNM staging based on the whole body.Among the 161 subjects, 7 (4%) showed malignancy-suspect lesions in HN, 110 (68%) in TUA and 7 (4%) had suspected distant metastases in LAH. The TNM staging based on HN plus TUA corresponded to TNM staging based on the whole body in 161 (100%) examinations. This finding aligns with similar results in previous literature. 18F-FDG-PET/CT limited to HN and TUA yielded accurate staging in all cases. Adopting this method could facilitate the examination and correct staging of more individuals, reducing exam waiting times and physician reporting time and minimising radiation exposure.

Changes in Staging and Management of Non-Small Cell Lung Cancer (NSCLC) Patients Following the Implementation of Low-Dose Chest Computed Tomography (LDCT) Screening at Kaohsiung Medical University Hospital

Background: Low-dose computed tomography (LDCT) has been widely adopted for lung cancer screening due to its proven ability to reduce lung cancer mortality, especially among high-risk populations. Methods: This retrospective study aims to evaluate the impact of LDCT screening on non-small cell lung cancer (NSCLC) staging at Kaohsiung Medical University Hospital (KMUH) from 2011 to 2020, following the introduction of LDCT in 2013. The study examines the correlation between LDCT screening volume and changes in the distribution of NSCLC stages, particularly early-stage (stages 0 and I) and late-stage (stage IV) diagnoses. Additionally, it explores the differences in histopathological subtypes, focusing on adenocarcinoma and squamous cell carcinoma, and assesses the impact of early detection on five-year survival rates. Results: The results show a significant increase in early-stage NSCLC diagnoses, particularly in adenocarcinoma cases, where early-stage diagnoses rose from 10.4% in 2010 to 38.7% in 2019. However, the number of stage IV cases remained stable, indicating that LDCT may not substantially reduce late-stage diagnoses. Pearson’s correlation analysis demonstrated a strong positive correlation between LDCT screening and early-stage NSCLC detection, particularly for adenocarcinoma (p &lt; 0.001), though the early detection of squamous cell carcinoma and small cell carcinoma remained limited. Conclusions: The study concludes that LDCT screening plays a crucial role in improving early NSCLC detection and five-year survival rates. Future research should focus on optimizing screening strategies to capture more at-risk populations and enhance the detection of harder-to-diagnose subtypes like squamous cell carcinoma.

Enhanced NSCLC subtyping and staging through attention-augmented multi-task deep learning: A novel diagnostic tool

ObjectivesThe objective of this study is to develop a novel multi-task learning approach with attention encoders for classifying histologic subtypes and clinical stages of non-small cell lung cancer (NSCLC), with superior performance compared to currently popular deep-learning models. Material and methodsData were collected from six publicly available datasets in The Cancer Imaging Archive (TCIA). Following the inclusion and exclusion criteria, a total of 4548 CT slices from 758 cases were allocated. We evaluated multiple multi-task learning models that integrate attention mechanisms to resolve challenges in NSCLC subtype classification and clinical staging. These models utilized convolution-based modules in their shared layers for feature extraction, while the task layers were dedicated to histological subtype classification and staging. Each branch sequentially processed features through convolution-based and attention-based modules prior to classification. ResultsOur study evaluated 758 NSCLC patients (mean age, 66.2 years ± 10.3; 473 men), spanning ADC and SCC cases. In the classification of histological subtypes and clinical staging of NSCLC, the MobileNet-based multi-task learning model enhanced with attention mechanisms (MN-MTL-A) demonstrated superior performance, achieving Area Under the Curve (AUC) scores of 0.963 (95 % CI: 0.943, 0.981) and 0.966 (95 % CI: 0.945, 0.982) for each task, respectively. The model significantly surpassed its counterparts lacking attention mechanisms and those configured for single-task learning, as evidenced by P-values of 0.01 or less for both tasks, according to DeLong’s test. ConclusionsThe integration of attention encoder blocks into our multi-task learning network significantly enhanced the accuracy of NSCLC histological subtyping and clinical staging. Given the reduced reliance on precise radiologist annotation, our proposed model shows promising potential for clinical application.

Glutathione inhibits lung cancer development by reducing interleukin-6 expression and reversing the Warburg effect

Reduced glutathione (GSH) is widely used as an antioxidant in clinical practice, but whether GSH affects the development of early lung cancer remains unclear. Herein, we investigated the mechanism underlying the anticancer effect of GSH in patients with pulmonary nodules. Thirty patients with pulmonary nodules were treated with GSH intravenously for 10 days at a dose of 1.8 g/d, followed by oral administration of the drug at a dose of 0.4 g three times daily for 6 months. The results showed that GSH treatment promoted nodule absorption and reduced the IL-6 level in the peripheral blood of the patients. GSH reduced IL-6 expression in inflammatory BEAS-2B and lung cancer cells and inhibited the proliferation of lung cancer cell lines in vitro. In addition, GSH reduced IL-6 expression by decreasing ROS via down-regulating PI3K/AKT/FoxO pathways. Finally, GSH reversed the Warburg effect, restored mitochondrial function, and reduced the IL-6 expression via PI3K/AKT/FoxO pathways. The in vivo experiment confirmed that GSH inhibited lung cancer growth, improved mitochondrial function, and reduced the IL-6 expression by regulating key enzymes via the PI3K/AKT/FoxO pathway. In conclusion, we uncovered that GSH exerts an unprecedentedly potent anti-cancer effect to prevent the transformation of lung nodules to lung cancer by improving the mitochondrial function and suppressing inflammation via PI3K/AKT/FoxO pathway. This investigation innovatively positions GSH as a potentially safe and efficacious old drug with new uses, inhibiting inflammation and early lung cancer. The use of the drug offers a promising preventive strategy when administered during the early stages of lung cancer.

Quantitative analysis of imaging characteristics in lung adenocarcinoma in situ using artificial intelligence.

With the rising incidence of pulmonary nodules (PNs), lung adenocarcinoma in situ (AIS) is a critical early stage of lung cancer, necessitating accurate diagnosis for early intervention. This study applies artificial intelligence (AI) for quantitative imaging analysis to differentiate AIS from atypical adenomatous hyperplasia (AAH) and minimally invasive adenocarcinoma (MIA), aiming to enhance clinical diagnosis and prevent misdiagnosis. The study analyzed 1215 PNs with confirmed AAH, AIS, and MIA from six centers using the Shukun AI diagnostic module. Parameters evaluated included demographic data and various CT imaging metrics to identify indicators for clinical application, focusing on the mean CT value's predictive value. Significant differences were found in several parameters between AAH and AIS, with nodule mass showing the highest predictive value. When comparing AIS to MIA, total nodule volume was the best predictor, followed by the maximum CT value. The mean CT value has limited discriminative power for AIS diagnosis. Instead, the maximum CT value and maximum 3D diameter are recommended for clinical differentiation. Nodule mass and volume of solid components are strong indicators for differentiating AIS from AAH and MIA, respectively.

The capture of circulating tumor cells by Labyrinth system as a tool for early stage lung cancer detection.

We focus on utilizing the Labyrinth system for the detection of circulating tumor cells (CTCs) in patients with lung nodules. Our aim is to evaluate CTCs isolated through the Labyrinth system as a biomarker for early-stage lung cancer (LC) detection. 167 patients with low dose computed tomography (LDCT) diagnostic results for lung nodules and 31 healthy volunteers (HV) were enrolled. Blood samples were processed for CTC detection. LDCT positive (LDCT+) patients underwent surgery and were categorized into those with LC and those with benign lung diseases (BLD) based on their biopsy results. BLD Patients, LDCT negative (LDCT-) patients and HV served as controls. The correlation of CTC counts with LC, BLD, LDCT- and HV was investigated. Receiver operating characteristic (ROC) curves were used to assess the Labyrinth system's diagnostic potential for early-stage LC. Median CTC counts for LC, BLD, LDCT- and HV were 2.7 CTC/mL, 0.6 CTC/mL, 0.4 CTC/mL, 0 CTC/mL, respectively. Statistical analysis indicated CTC counts could distinguish LC from BLD, LDCT- and HV (p-Values < 0.001). Using a cut-off of 1 CTC/mL, the study showed 84.4% sensitivity and 82.4% specificity for LDCT+ patients. Specificity increased to 85.9% for patients with lung nodules and 88.2% for all participants. In conclusion, CTCs detected by the Labyrinth system can serve as a biomarker for early-stage LC detection for patients with lung nodules. CTCs identified by the Labyrinth system are a promising biomarker for early-stage LC detection in clinical practice.

Lung cancer screening: Real screening site data, Vojvodina, Serbia

Abstract Background Lung cancer (LC) is the top cause of cancer-related deaths globally and in Serbia, often diagnosed in advanced stage of disease with when 5-year survival is 10% to 20%. LC screening with low-dose CT (LDCT) can decrease LC mortality and overall mortality. The first pilot LC screening program in Serbia started in the Institute for Pulmonary Diseases of Vojvodina in September 2020. The main objective of this study was to analyze LC patient characteristics according to their screening status. Methods This retrospective study utilized LC hospital registry data from September 2020 to December 2023, including gender, age at diagnosis, settlement area, smoking habits, cancer histological type, TNM classification, disease stage (1-4), and data on participation in LC screening. Group differences were assessed using chi-square and Student’s t-tests, with analyses conducted in SPSS v24.0. Results During observed period from a total of 4649 LC cases 2948 (63.4%) were males, and 73 (1.6%) were included in LC screening. Average age of all LC patients was 66 years, without differences between groups (p = 0.778). Significant differences between groups by gender were find (p = 0.042). Non-screened LC patients were significantly common males compared to females (63.6% vs 36.4%), while among screened difference by gender were lower (52.1% vs 47.9%, respectively). Screened compared to non-screened LC patients have significantly lower percentage of SCLC (9.6% vs 19.1%), and higher percentage of NSCLC (90.4% vs 80.9%), (p = 0.040). According to LC stage, screened compared to non-screened patients were significantly common diagnosed in stage I of disease (45.8% vs 7.8%), and significantly less common in higher LC stages; stage IIIB (11.1% vs 22.5%), and in stage IV (22.2% vs 45.7%), (p &amp;lt; 0.001). Conclusions LC screening with LDCT is proven secondary preventive measure with significant influence on decreasing LC mortality by increasing number of LC patients in early stages of disease. Key messages • Lung cancer screening with low-dose CT significantly increases early-stage diagnoses, improving survival chances. • Population strategies to prevent smoking and screening programs for high-risk groups are needed to reduce lung cancer incidence and mortality rates in Serbia.

Exploring Multilingual Large Language Models for Enhanced TNM Classification of Radiology Report in Lung Cancer Staging.

This study aimed to investigate the accuracy of Tumor, Node, Metastasis (TNM) classification based on radiology reports using GPT3.5-turbo (GPT3.5) and the utility of multilingual large language models (LLMs) in both Japanese and English. Utilizing GPT3.5, we developed a system to automatically generate TNM classifications from chest computed tomography reports for lung cancer and evaluate its performance. We statistically analyzed the impact of providing full or partial TNM definitions in both languages using a generalized linear mixed model. The highest accuracy was attained with full TNM definitions and radiology reports in English (M = 94%, N = 80%, T = 47%, and TNM combined = 36%). Providing definitions for each of the T, N, and M factors statistically improved their respective accuracies (T: odds ratio [OR] = 2.35, p < 0.001; N: OR = 1.94, p < 0.01; M: OR = 2.50, p < 0.001). Japanese reports exhibited decreased N and M accuracies (N accuracy: OR = 0.74 and M accuracy: OR = 0.21). This study underscores the potential of multilingual LLMs for automatic TNM classification in radiology reports. Even without additional model training, performance improvements were evident with the provided TNM definitions, indicating LLMs' relevance in radiology contexts.

Improving Patient Understanding and Outcomes in Lung Cancer Using an Animated Patient's Guide with Visual Formats of Learning.

Lung cancer patient education resources that address barriers to health literacy, improve understanding, and demonstrate improved patient outcomes are limited. Our study aim was to evaluate and report on learner knowledge improvement and intent to implement behavior change, and validate the benefits of the You and Lung Cancer website and YouTube resources. Our study occurred from November 2017 to December 2023. We evaluated audience reach (visit sessions, unique visitors, country origins, page views) and calculated top views by media type (animations, expert videos, patient videos). We assessed the impact and commitment to change through learner surveys (areas of interest, intention to modify behaviors, and intention to discuss disease management with providers) and tested the knowledge of learners pre- and post-reviewing of website content. Our program reached 794,203 views globally; 467,546 were unique visitors; and 243,124 (51%) were unique visitors from the USA. Of US visitors, 46% identified as lung cancer patients. These were patients in treatment (38%), survivors (8%), family members or caregivers (21%), and healthcare providers (14%) with other audiences unspecified (19%). Three areas of highest learner importance were the animations "Understanding Non-Small Cell Lung Cancer" (180,591), "Staging of Lung Cancer" (144,238), and "Treatment and Management of Small Cell Lung Cancer" (49,244). Our study confirmed areas of importance to lung cancer patients and suggests that visual formats of learning, such as animations, can mitigate health literacy barriers and help improve patient understanding and outcomes. Exporting this format of learning to other cancers has the potential to benefit patients and improve health outcomes.

Recommendation for Clinical T Staging in Patients with Non-Small Cell Lung Cancer: Volumetric Measurement: A Retrospective Study from Turkey.

Currently, clinical T staging in non-small cell lung cancer (NSCLC) is based on the largest radiological diameter observed on computed tomography (CT). Under this system, tumors with varying shapes-such as spherical, amorphous, or spiculated tumors- can be assigned the same T stage even with different volumes. We aimed to propose a 3-dimensional (3D) volumetric staging system for NSCLC as an alternative to diameter-based T staging and to conduct comparative survival analyses between these methods. We retrospectively analyzed data from patients who underwent surgery for pT1-4N0M0 primary NSCLC between January 2018 and May 2022. Digital Imaging and Communications in Medicine data from patient CT scans were uploaded to 3D Slicer software for volumetric tumor measurement. Using the paired samples t-test or the Wilcoxon test, we compared the expected tumor volumes, calculated by tumor diameter, with the actual volumes measured by 3D Slicer. Receiver operating characteristic analysis was employed to determine the cut-off value for tumor volume. Kaplan-Meier analysis was utilized to assess overall survival, while the log-rank method was applied to compare survival differences between groups. The significance of changes in T stage was evaluated using the marginal homogeneity test. The study included 136 patients. Significant differences were observed between expected and actual tumor volumes (p=0.01), and associated changes in T stage were also significant (p=0.04). The survival analysis performed using tumor volume (p=0.009) yielded superior results compared to that based on diameter (p=0.04) in paients with early tumor stage. T-factor staging based on tumor volume could represent an alternative staging method for NSCLC.

Comparative Analysis of Vitamin D, Folic Acid, and Antioxidant Minerals in Various Stages of Lung Cancer

Comparative Analysis of Vitamin D, Folic Acid, and Antioxidant Minerals in Various Stages of Lung Cancer

Interpretable Machine Learning-Aided Optical Deciphering of Serum Exosomes for Early Detection, Staging, and Subtyping of Lung Cancer.

Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, underscoring an urgent need for strategies that enable early detection and phenotypic classification. Here, we conducted a label-free surface-enhanced Raman spectroscopic (SERS) analysis of serum exosomes from 643 participants to elucidate the biochemical deregulation associated with LC progression and the unique phenotypes of different LC subtypes. Iodide-modified silver nanofilms were prepared to rapidly acquire SERS spectra with a high signal-to-noise ratio using 0.5 μL of patient exosomes. We performed interpretable and automated machine learning (ML) analysis of differential SERS features of serum exosomes to build LC diagnostic models, which achieved accuracies of 100% and 81% for stage I lung adenocarcinoma and its preneoplasia, respectively. In addition, the ML-derived exosomal SERS models effectively recognized different LC subtypes and disease stages to guide precision treatment. Our findings demonstrate that spectral fingerprinting of circulating exosomes holds promise for decoding the clinical status of LC, thus aiding in improving the clinical management of patients.

Risk score model for predicting mortality among patients with lung cancer.

To develop an accurate mortality risk predictive model among patients with lung cancer. The development cohort included 96,255 patients with lung cancer aged ≥19 years, who underwent a Korean National Health Insurance Service health check-up from 2005 to 2015. The validation cohort consisted of 18,432 patients (≥19 years) with lung cancer from another region. The outcome was all-cause mortality between January 1, 2005, and December 31, 2020. Approximately 60.5% of the development cohort died within a median follow-up period of 2.32 (0.72-5.00) years. Risk score was highest in participants aged ≥65 years, followed by those who underwent treatment, had a history of emergency room visits, and were current smokers. Participants treated by surgery had the lowest risk score, followed by combined surgery and chemotherapy, combined surgery and radiation therapy, women, and regular exercisers. The C statistic in the development and validation cohorts was 0.78 (95% confidence interval, 0.77-0.78) and 0.81 (95% confidence interval, 0.78-0.84), respectively. Advanced age, lung cancer stage, and treatment type were strong risk factors of mortality in lung cancer patients, while being a woman and exercise were preventive factors. These will aid in the prediction of mortality and management of lung cancer patients.

Factors Influencing the Timeliness and Completeness of Appropriate Staging Investigations for Patients with Stage I-III Lung Cancer in Southeastern Ontario.

(1) Background: Comprehensive and timely lung cancer (LC) staging is essential for prognosis and management. The Lung Diagnostic Assessment Program (LDAP) in Southeastern (SE) Ontario aims to provide rapid, guideline-concordant care for suspected LC patients. We evaluated factors affecting the completeness and timeliness of staging for stage I-III LC patients in SE Ontario, including the impact of LDAP management. (2) Methods: This was a population-based retrospective cohort study using the LDAP database (January 2017-December 2019), linked with the Ontario Cancer Registry, to identify newly diagnosed LC patients. A Cox model approach identified variables associated with staging completeness and timeliness. (3) Results: Among 755 patients, 459 (60.8%) were managed through LDAP. Optimal staging was achieved in 596 patients (78.9%), 23 (3.0%) had alternative staging, and 136 (18.0%) had incomplete staging. In the adjusted analyses, LDAP management was associated with a higher likelihood of complete staging (OR 2.29, p < 0.0001) and faster staging completion (β = -18.53, p < 0.0001). Increased distance to PET centres was associated with a longer time to complete staging (β = 8.95 per 100 km, p = 0.0007), as was longer time to diagnosis (β = 21.63 per 30 days, p < 0.0001). (4) Conclusions: LDAP management in SE Ontario significantly improved staging completeness and shortened staging time for stage I-III LC patients.

Advanced artificial intelligence framework for T classification of TNM lung cancer in 18FDG-PET/CT imaging

The integration of artificial intelligence (AI) into lung cancer management offers immense potential to revolutionize diagnostic and treatment strategies. The aim is to develop a resilient AI framework capable of two critical tasks: firstly, achieving accurate and automated segmentation of lung tumors and secondly, facilitating the T classification of lung cancer according to the ninth edition of TNM staging 2024 based on PET/CT imaging. This study presents a robust AI framework for the automated segmentation of lung tumors and T classification of lung cancer using PET/CT imaging. The database includes axial DICOM CT and18FDG-PET/CT images. A modified ResNet-50 model was employed for segmentation, achieving high precision and specificity. Reconstructed 3D models of segmented slices enhance tumor boundary visualization, which is essential for treatment planning. The Pulmonary Toolkit facilitated lobe segmentation, providing critical diagnostic insights. Additionally, the segmented images were used as input for the T classification using a CNN ResNet-50 model. Our classification model demonstrated excellent performance, particularly for T1a, T2a, T2b, T3 and T4 tumors, with high precision, F1 scores, and specificity. The T stage is particularly relevant in lung cancer as it determines treatment approaches (surgery, chemotherapy and radiation therapy or supportive care) and prognosis assessment. In fact, for Tis-T2, each increase of one centimeter in tumor size results in a worse prognosis. For locally advanced tumors (T3-T4) and regardless of size, the prognosis is poorer. This AI framework marks a significant advancement in the automation of lung cancer diagnosis and staging, promising improved patient outcomes.

Potential of Chest Radiography in Primary Diagnosis of Lung Cancer

Objective: to evaluate the effectiveness of diagnostics for non-small cell lung cancer (LC) based on chest radiography/fluorography data for LC screening diagnostics during preventive medical examination and check-ups.Material and methods. The work was organized as a retrospective cohort study. The starting point of the study was chest radiography, the final point was the diagnosis of LC based on the results of low-dose computed tomography (LDCT) and tumor morphological examination. The patient sample was composed using inclusion and exclusion criteria and initially included 800 patients, then narrowed down to 788. Patients were divided into groups according to LC stage and depending on whether radiography during preventive measures made it possible to suspect LC verified within 3 months via LDCT for any reasons not related to the suspicion of a tumor process. The diagnostic coefficient and informative value of radiography were calculated for each stage of the established LC diagnosis.Results. The study showed that chest radiography does not allow establishing stage I LC diagnosis (J=0.00; p&lt;0.05), it is low informative for stage II LC (J=0.25; p&lt;0.05), and medium informative for stage III LC (J=0.80; p&lt;0.05). Chest radiography does not reliably detect LC signs at early stages in 84.3% of cases.Conclusion. The obtained results indicate an insufficient sensitivity of radiography as a screening method, primarily for early LC diagnosis. The introduction of chest LDCT instead of radiography into the procedure for preventive medical examination and check-ups of the adult population approved by the Ministry of Health of the Russian Federation will increase LC detection at early stages by 5.37 times (95% confidence interval 3,77–7,64).