Detection Of Early-stage Lung Cancer Research Articles

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 >400 lung cancer samples and >1,000 negative controls. This data was used to generate our novel FEMS (Fragment End Motifs and Sizes) dataframe, containing >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<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<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.

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.

Lightweight Advanced Deep Neural Network (DNN) Model for Early-Stage Lung Cancer Detection.

Background: Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. Methods: We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. Results: Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients' 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. Conclusions: Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients' lives.

103P Epigenetic regulated genes enhanced fragmentomics-based model for early-stage lung cancer detection

103P Epigenetic regulated genes enhanced fragmentomics-based model for early-stage lung cancer detection

Early stage lung cancer detection from speech sounds in natural environments

In the diagnosis of early-stage lung cancer, conventional methods often rely on periodic imaging techniques using medical devices. However, recent studies suggest that speech sounds could offer valuable insights into the diagnosis of disease. This study investigates the different characteristics of speech sounds recorded in natural environments between individuals diagnosed with lung cancer and those who are healthy. Using signal processing techniques and a self-supervised contrastive learning approach, we investigate the classification of these speech sounds for the diagnosis of early-stage lung cancer. Our results show that it is possible to utilize naturally recorded speech sounds. Using the Graph Attention Transformer Fine-Tuning Contrastive Learning (GAT-ftCL) model, which leverages graph neural networks to capture complex relationships in data and fine-tunes the learning process through contrastive learning, we achieve an accuracy of 90.90% in distinguishing individuals diagnosed with lung cancer from healthy individuals. Furthermore, the model achieves a remarkable accuracy of 92.85% in specifically identifying individuals with early stage (stage 1) lung cancer within the stage 1 group and healthy individuals. These results underline the diagnostic potential of natural speech sounds, especially in the detection of early-stage lung cancer.

LUNG CANCER SCREENING WITH LOW-DOSE COMPUTED TOMOGRAPHY: A LITERATURE REVIEW

Relevance: Lung cancer (LC) is the leading cause of death among oncological diseases and occupies a leading position in the number of new cases worldwide. Early detection of symptoms, precise diagnosis, and effective treatment are crucial for increasing lung cancer survival rates. Low-dose computed tomography (LDCT) screening programs represent a promising method for early lung cancer detection, which can substantially decrease mortality rates and improve patient survival prospects. The study aimed to review foreign scientific publications on lung cancer screening using low-dose computed tomography. Methods: The study included the results of foreign randomized controlled trials (RCTs) of lung cancer screening using LDCT, based on articles, meta-analyses, systematic reviews, and reviews. Exclusion criteria included publications published before 2013; publications that were not publicly available. The search results yielded 369 articles, of which 39 literary sources were included in this review. The search covered a depth of 10 years (2013-2023). Results: An analysis of foreign studies was performed that confirmed the effectiveness of low-dose computed tomography in the detection of lung cancer. Data from randomized controlled trials, meta-analyses, systematic reviews and reviews are presented, confirming the potential of this method to improve early stage lung cancer detection, thus improving survival rates and reducing mortality. Conclusion: LDCT has been shown to be effective in reducing lung cancer mortality, as confirmed by the results of numerous studies. However, the strategy to implement the lung cancer screening program should be specific to each country in which it will be implemented, taking into account the specifics of the health system. To achieve optimal results, it is necessary to continue research related to the implementation of this screening method, including an analysis of its economic feasibility, as well as an assessment of long-term results and potential undesirable effects.

Lung Cancer Screening Before and After a Multifaceted Electronic Health Record Intervention

Lung cancer is the deadliest cancer in the US. Early-stage lung cancer detection with lung cancer screening (LCS) through low-dose computed tomography (LDCT) improves outcomes. To assess the association of a multifaceted clinical decision support intervention with rates of identification and completion of recommended LCS-related services. This nonrandomized controlled trial used an interrupted time series design, including 3 study periods from August 24, 2019, to April 27, 2022: baseline (12 months), period 1 (11 months), and period 2 (9 months). Outcome changes were reported as shifts in the outcome level at the beginning of each period and changes in monthly trend (ie, slope). The study was conducted at primary care and pulmonary clinics at a health care system headquartered in Salt Lake City, Utah, among patients aged 55 to 80 years who had smoked 30 pack-years or more and were current smokers or had quit smoking in the past 15 years. Data were analyzed from September 2023 through February 2024. Interventions in period 1 included clinician-facing preventive care reminders, an electronic health record-integrated shared decision-making tool, and narrative LCS guidance provided in the LDCT ordering screen. Interventions in period 2 included the same clinician-facing interventions and patient-facing reminders for LCS discussion and LCS. The primary outcome was LCS care gap closure, defined as the identification and completion of recommended care services. LCS care gap closure could be achieved through LDCT completion, other chest CT completion, or LCS shared decision-making. The study included 1865 patients (median [IQR] age, 64 [60-70] years; 759 female [40.7%]). The clinician-facing intervention (period 1) was not associated with changes in level but was associated with an increase in slope of 2.6 percentage points (95% CI, 2.4-2.7 percentage points) per month in care gap closure through any means and 1.6 percentage points (95% CI, 1.4-1.8 percentage points) per month in closure through LDCT. In period 2, introduction of patient-facing reminders was associated with an immediate increase in care gap closure (2.3 percentage points; 95% CI, 1.0-3.6 percentage points) and closure through LDCT (2.4 percentage points; 95% CI, 0.9-3.9 percentage points) but was not associated with an increase in slope. The overall care gap closure rate was 175 of 1104 patients (15.9%) at the end of the baseline period vs 588 of 1255 patients (46.9%) at the end of period 2. In this study, a multifaceted intervention was associated with an improvement in LCS care gap closure. ClinicalTrials.gov Identifier: NCT04498052.

Optical Nanobiosensor Based on Surface-Enhanced Raman Spectroscopy and Catalytic Hairpin Assembly for Early-Stage Lung Cancer Detection via Blood Circular RNA.

Lung cancer has become the leading cause of cancer-related deaths globally. However, early detection of lung cancer remains challenging, resulting in poor outcomes for the patients. Herein, we developed an optical biosensor integrating surface-enhanced Raman spectroscopy (SERS) with a catalyzed hairpin assembly (CHA) to detect circular RNA (circRNA) associated with tumor formation and progression (circSATB2). The signals of the Raman reporter were considerably enhanced by generating abundant SERS "hot spots" with a core-shell nanoprobe and 2D SERS substrate with calibration capabilities. This approach enabled the sensitive (limit of detection: 0.766 fM) and reliable quantitative detection of the target circRNA. Further, we used the developed biosensor to detect the circRNA in human serum samples, revealing that patients with lung cancer had higher circRNA concentrations than healthy subjects. Moreover, we characterized the unique circRNA concentration profiles of the early stages (IA and IB) and subtypes (IA1, IA2, and IA3) of lung cancer. These results demonstrate the potential of the proposed optical sensing nanoplatform as a liquid biopsy and prognostic tool for the early screening of lung cancer.

Diagnosis, treatment, and prognosis of stage IB non-small cell lung cancer with visceral pleural invasion.

With the increasing implementation of early lung cancer screening and the increasing emphasis on physical examinations, the early-stage lung cancer detection rate continues to rise. Visceral pleural invasion (VPI), which denotes the tumor's breach of the elastic layer or reaching the surface of the visceral pleura, stands as a pivotal factor that impacts the prognosis of patients with non-small cell lung cancer (NSCLC) and directly influences the pathological staging of early-stage cases. According to the latest 9th edition of the TNM staging system for NSCLC, even when the tumor diameter is less than 3 cm, the final T stage remains T2a if VPI is present. There is considerable controversy within the guidelines regarding treatment options for stage IB NSCLC, especially among patients exhibiting VPI. Moreover, the precise determination of VPI is important in guiding treatment selection and prognostic evaluation in individuals with NSCLC. This article aims to provide a comprehensive review of the current status and advancements in studies pertaining to stage IB NSCLC accompanied by VPI.

An Observation and Analysis the role of Convolutional Neural Network towards Lung Cancer Prediction

Lung cancer is one of the most serious and prevalent diseases, causing many deaths each year. Though CT scan images are mostly used in the diagnosis of cancer, the assessment of scans is an error-prone and time-consuming task. Machine learning and AI-based models can identify and classify types of lung cancer quite accurately, which helps in the early-stage detection of lung cancer that can increase the survival rate. In this paper, Convolutional Neural Network is used to classify Adenocarcinoma, squamous cell carcinoma and normal case CT scan images from the Chest CT Scan Images Dataset using different combinations of hidden layers and parameters in CNN models. The proposed model was trained on 1000 CT Scan Images of cancerous and non-cancerous cells to find the best combination of parameters in CNN to predict lung cancer accurately. The proposed system recorded the highest accuracy of 92.79%. In addition to that, the paper addresses 192 observations made using the CNN model.

A novel three-biomarker signature (CA-62, CEA, CYFRA 21-1) and early-stage NSC lung cancer detection.

3038 Background: A double-blind clinical study was conducted on 304 clinically verified blood serum samples, including 141 non-small cell lung cancer (NSCLC), 133 healthy volunteers and 30 patients with chronic obstructive pulmonary disease (COPD). The objectives of the study were: The assessment of various cancer markers and their possible combinations for detection of early (I-II) stages of non-small cell lung cancer (NSCLC) and evaluation of the best cancer markers panel as a pre-screening tool for NSCLC before Low-Dose CT scan. Methods: Quantitative measurement of various tumor markers for serum samples was carried out using electrochemiluminescent immunoassays Elecsys CA-125, ELECSYS CA 19-9, ELECSYS CYFRA 21-1 and ELECSYS SCC (COBAS, Roche Diagnostics GmbH, Germany, EU), enzyme immunoassay CA15-3-ELISA-BEST, CEA-ELISA-BEST, NSE-ELISA-BEST (JSC "VECTOR-BEST", RF) and immunochemiluminescent analysis CLIA-CA-62 (LLC "JVS Diagnostics", RF). The results were compared to the literature data for other biomarkers and their panels. Results: Unlike other tumor markers, which are expressed proportionally to tumor size, the marker for epithelial carcinomas CA-62 is expressed from Stage I and demonstrated the highest diagnostic results in detecting early stages (I-II) of NSCLC. The biomarkers CYFRA 21-1 and SCC do not have sufficient sensitivity and specificity to diagnose asymptomatic lung cancer. However, the addition of cytokeratin 19 CYFRA 21-1 to glycoproteins CA-62 and CEA increases the specificity by eliminating false positive results, which significantly improves the diagnostic value of the cancer marker signature (CA-62, CEA and CYFRA 21-1): 100% Specificity, 93% Sensitivity, 100% PPV, 94% NPV and 94% test accuracy. Conclusions: The results of the study demonstrated that using the biomarkers signature (CA-62, CEA and CYFRA 21-1) allows increasing the specificity of CT scan for patients with suspicious abnormalities on the tomogram, improving the interpretation of visualized localized lesion, and improving the accuracy of differential diagnosis at detecting early stages of LC up to 94%. In the prospective, adding cancer markers panel signature (CA-62, CEA and CYFRA 21-1) to the current lung cancer risk assessment system as a pre-screening tool for LDCT may improve the quality of early-stage Lung cancer detection by significant increasing the sensitivity and by reducing the proportion of false positive results. [Table: see text]

European guidelines for the surgical management of pure ground-glass opacities and part-solid nodules: Task Force of the European Association of Cardio-Thoracic Surgery and the European Society of Thoracic Surgeons.

Pulmonary nodules are often encountered by respiratory physicians, radiologists, and thoracic surgeons alike. The European Society of Thoracic Surgery (ESTS) and European Association of Cardiothoracic Surgery (EACTS) established a multidisciplinary collaboration of clinicians with expertise in managing pulmonary nodules with the aim of producing the first joint comprehensive review of the scientific literature, with a specific focus on the management of pure ground glass opacities and part-solid nodules. The scope of the document has been defined by the EACTS and ESTS governing bodies and focuses on six areas of main interest agreed upon by the Task Force. These include: management of solitary and multiple pure ground glass nodules, solitary part-solid nodules, identifying the non-palpable lesion, the role of minimally invasive surgery and the decision making behind sub-lobar versus lobar resection. The literature revealed that with the increasing use of incidental CT scans and CT lung cancer screening programs, the detection of early-stage lung cancer is going to rise with a higher number of potential cancers presenting on the ground glass and part-solid nodule spectrum. Given that the gold standard for improved survival is surgical resection, there is an urgent need for comprehensive characterisation of these nodules and guidelines that are directed towards their surgical management. It is recommended that standard decision-making tools are used to determine the risk of malignancy and thus guide referral for surgical management and decisions for surgical resection are made in a multidisciplinary setting with equitable consideration given to radiological characteristics, the evolution of the lesion, presence of solid component, patient fitness and co-morbidities. Given the recent surge in robust level I data comparing sublobar and lobar resection with the release of JCOG0802 and CALGB140503 data, a global overview of an individual case must be adopted into clinical practice. This set of recommendations are based on the available literature; however, close collaboration in the design and conduct of randomized controlled trials is still of utmost importance to answer further questions in this rapidly evolving field.

Accurate detection of early-stage lung cancer using a panel of circulating cell-free DNA methylation biomarkers

BackgroundLung cancer remains the leading cause of cancer mortality worldwide. Early detection of lung cancer helps improve treatment and survival. Numerous aberrant DNA methylations have been reported in early-stage lung cancer. Here, we sought to identify novel DNA methylation biomarkers that could potentially be used for noninvasive early diagnosis of lung cancers.MethodsThis prospective-specimen collection and retrospective-blinded-evaluation trial enrolled a total of 317 participants (198 tissues and 119 plasmas) comprising healthy controls, patients with lung cancer and benign disease between January 2020 and December 2021. Tissue and plasma samples were subjected to targeted bisulfite sequencing with a lung cancer specific panel targeting 9,307 differential methylation regions (DMRs). DMRs associated with lung cancer were identified by comparing the methylation profiles of tissue samples from patients with lung cancer and benign disease. Markers were selected with minimum redundancy and maximum relevance algorithm. A prediction model for lung cancer diagnosis was built through logistic regression algorithm and validated independently in tissue samples. Furthermore, the performance of this developed model was evaluated in a set of plasma cell-free DNA (cfDNA) samples.ResultsWe identified 7 DMRs corresponding to 7 differentially methylated genes (DMGs) including HOXB4, HOXA7, HOXD8, ITGA4, ZNF808, PTGER4, and B3GNTL1 that were highly associated with lung cancer by comparing the methylation profiles of lung cancer and benign nodule tissue. Based on the 7-DMR biomarker panel, we developed a new diagnostic model in tissue samples, termed “7-DMR model”, to distinguish lung cancers from benign diseases, achieving AUCs of 0.97 (95%CI: 0.93-1.00)/0.96 (0.92-1.00), sensitivities of 0.89 (0.82–0.95)/0.92 (0.86–0.98), specificities of 0.94 (0.89–0.99)/1.00 (1.00–1.00), and accuracies of 0.90 (0.84–0.96)/0.94 (0.89–0.99) in the discovery cohort (n = 96) and the independent validation cohort (n = 81), respectively. Furthermore, the 7-DMR model was applied to noninvasive discrimination of lung cancers and non-lung cancers including benign lung diseases and healthy controls in an independent validation cohort of plasma samples (n = 106), yielding an AUC of 0.94 (0.86-1.00), sensitivity of 0.81 (0.73–0.88), specificity of 0.98 (0.95-1.00), and accuracy of 0.93 (0.89–0.98).ConclusionThe 7 novel DMRs could be promising methylation biomarkers that merits further development as a noninvasive test for early detection of lung cancer.Graphical abstract

Abstract 5434: Machine-learning-based epigenetic detection of early-stage lung cancers using the EpiCheck liquid biopsy platform

Abstract Alterations in DNA methylation are one of the earliest, most common signatures of cancer development, making them ideal biomarkers for early detection. Methylation profiling of plasma cell-free DNA (cfDNA) has significant potential to expand the use of liquid biopsies to cancer screening. The EpiCheck platform combines methylation-sensitive restriction endonuclease (MSRE) digestion with whole genome sequencing to comprehensively map genome-wide DNA methylation changes with high fidelity. In this proof-of-concept study, MSRE-NGS was used to interrogate a liquid biopsy atlas focused on early-stage lung cancers to i) identify informative NGS methylation biomarkers in plasma, and ii) develop a machine learning method to discriminate between cancer and high-risk, non-cancer controls. The EpiCheck lung cancer atlas was constructed using biospecimens from academic (UBC, Vanderbilt, Cleveland Clinic) and commercial biobanks, and from a prospective multi-center study (NCT04968548). Plasma samples were collected from 93 high-risk primary lung cancer patients (62% stage I) and 90 high-risk individuals without cancer. Extracted DNA was digested with methylation-sensitive endonucleases and sequenced at an average depth of 600x. Methylation levels of ~6 million genomic loci were rank ordered using Student's t-test. Gene set enrichment analysis (GSEA) was performed on the top ranking 1000 differentially methylated loci. A logistic regression classifier with Lasso regularization was trained on 100,000 loci, and performance was examined by mean AUC using 5-fold cross-validation. A total of 23,130 loci exhibited significant differential methylation patterns between cancers and controls (p&amp;lt;0.01, FDR corrected). Of these, 20,159 and 2,971 lung cancer loci were hypermethylated and hypomethylated, respectively. Biological characterization using GSEA identified enrichments in transcriptional regulation and developmental control. In particular, loci were enriched for Polycomb Repressive Complex regulated genes, suggesting a possible connection to abnormal epigenetic regulation via histone modification in lung cancer. Construction of a machine learning logistic regression model based on the five training folds utilized 224 loci on average, and achieved a mean cross-validation AUC of 0.93 when distinguishing plasma cancer cases vs controls. Our findings demonstrate that the MSRE-NGS EpiCheck platform identified putative biomarkers within the plasma methylome for detecting early-stage lung cancer. A machine learning model trained on methylation targets performed with high accuracy in discriminating lung cancer patients from high-risk healthy individuals. Additional studies are required for defining the strength of the approach and for validating its use in non-invasive lung cancer screening. Citation Format: Dvir Netanely, Stephen Lam, Anna McGuire, Stephen Deppen, Eric Grogan, Fabien Maldonado, Michael Gieske, Joseph Seaman, Kimberly Rieger-Christ, Satish Kalanjeri, Luis Herrera, Nichole Tanner, Garrett B. Sherwood, Orna Savin, Shacade Danan, Sarah Zaouch, Nimrod Axelrad, Revital Knirsh, Ofir Shliefer, Keren Manor, Radha Duttagupta, Aharona Shuali, Peter J. Mazzone, Gerard A. Silvestri, Catherine A. Schnabel, Danny Frumkin, Adam Wasserstrom. Machine-learning-based epigenetic detection of early-stage lung cancers using the EpiCheck liquid biopsy platform. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5434.

Abstract 6510: REM-DREAMing: Low-cost digital microfluidic analysis of DNA methylation heterogeneity for enhanced, liquid biopsy-based detection of early-stage lung cancer

Abstract We report the results of a study exploring the ability to exploit molecular heterogeneity in DNA methylation for improving the performance of liquid biopsy-based screening for early-stage (I &amp; II) non-small cell lung cancer (NSCLC). Annual low-dose CT (LDCT) screening is currently recommended for adults aged 50 or older who are at high-risk of developing lung cancer. While this approach has resulted in improvements in survival, the false positive rate of lung nodules detection by LDCT remains over 95%, leading to unnecessary invasive follow-up procedures and further points to the need for new, complementary methods to improve diagnostics performance and reduce patient risk. DNA methylation biomarkers have demonstrated considerable potential as tumor-specific biomarkers for blood-based detection of early-stage NSCLC. Nonetheless, cell-free DNA (cfDNA) assessment techniques, such as methylation-specific PCR (MSP) or bisulfite sequencing, have limited sensitivity to assess epigenetic heterogeneity of rare epiallelic variants in a cost-effective manner. Here we reported a new platform, named REM-DREAMing (Ratiometric-Encoded Multiplex Discrimination of Rare EpiAlleles by Melt), which provides a simple, low-cost solution for multiplexed assessment of loci-specific DNA methylation heterogeneity at single molecule sensitivity. The microfluidic nanoarray contains four independent but identical 10,040 nanowell modules. Methylation biomarkers are differentiated by a ratiometric fluorescence scheme and the assessment of individual epiallele species of each locus are achieved through digitization in the nanoarray and precise high-resolution melt (HRM) analysis. In this study, we explore the potential utility of REM-DREAMing as a complementary assay for improving LDCT screening of NSCLC by testing a cohort of 48 clinical samples (28 cancer and 20 control samples) of low-volume liquid biopsy specimens from patients with CT-scan indeterminant pulmonary nodules. A machine learning algorithm incorporating logistic regression models with leave-one-out cross validation was developed to identify a proper methylation density threshold of each biomarker in the panel. Evaluation of the receiver operation characteristic (ROC) curve yielded an area under the curve (AUC) of 0.97 (95% CI, 0.94-1) with 93% sensitivity at 95% specificity for the REM-DREAMing assay, compared with 93% sensitivity at 62% specificity achieved using a traditional, MSP-based approach. These results suggest that the assessment of intermolecular epigenetic heterogeneity can provide superior clinical performance for cfDNA methylation and noninvasive detection of early-stage NSCLC, in particular. Our results warrant further investigation in a larger sample cohort to validate its utility for improving routine screening of NSCLC in high-risk populations. Citation Format: Yang Zhao, Christine M. O’Keefe, James G. Herman, Thomas R. Pisanic, Tza-Huei Wang. REM-DREAMing: Low-cost digital microfluidic analysis of DNA methylation heterogeneity for enhanced, liquid biopsy-based detection of early-stage lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 6510.

Abstract 3330: Development of a genome-wide multiomic atlas of early-stage lung cancer enables identification of novel methylation biomarkers for disease detection beyond TCGA

Abstract Lung cancer is the leading cause of cancer mortality, mainly due to diagnosis at advanced stages. Early detection reduces mortality and screening by CT is recommended for a high-risk population, however, uptake is low. Biomarkers for early-stage detection may enhance screening. Liquid biopsy and blood circulating tumor DNA (ctDNA) are established plasma surrogates of tumor tissue but their use in early detection remains challenging due to the high noise level of current techniques. We constructed a novel multiomic atlas through whole genome sequencing (WGS) to map all genetic and epigenetic changes associated with early-stage lung cancer as a tool to identify markers. Biospecimens from 48 early-stage lung cancer cases (58% stage I) and 29 cancer-free controls, all high-risk by USPSTF, were acquired from academic (UBC, Vanderbilt, Cleveland Clinic) and commercial biobanks. Cases had tumor and normal lung tissue, whole blood (WB) and plasma samples. Controls had WB and plasma samples. EpiCheck sequencing (ECS) which combines methylation-sensitive restriction endonuclease digestion to detect differential methylation with WGS for multiomic analyses was performed on each sample. Extracted DNA was digested, underwent standard library preparation and sequenced at an average depth of 600x for cfDNA and 80x for tissue and WB. A subset also underwent WG bisulfite sequencing (BS) and standard WGS for comparison. Data analysis was performed using customized software. ECS outperformed BS. Mapping rate was 99.6%, 99.7% and 85.7% and unique mapping rate was 94.1%, 94.3% and 81.4% for WGS, ECS, and BS samples, respectively. Copy number integrity showed Pearson correlations of 0.9 for ECS and 0.67 for BS. Somatic mutation analysis in tissue identified a subset of cases with relatively high ctDNA shedding in plasma that were associated with larger tumors, older age and squamous cell carcinoma histology. This subset was further used to identify tumor derived plasma-based markers and assess fragmentation with high confidence. Shorter ctDNA fragments were observed in some, but not all cases. Additional analysis of WB and plasma identified host derived blood-based markers using methylation and copy number. This orthogonal approach enabled detection of small, low shedding tumors. A discovery panel of 87 markers showed 100% sensitivity and 97% specificity to discriminate cases vs controls. Only 11% of these markers are represented in the TCGA data. ECS generates high integrity sequencing data superior to BS, enabling genome-wide multiomic analyses (methylation, mutation, copy number, fragmentomics), with methylation signatures beyond the scope of TCGA. Results, which require validation, underscore the potential of the EpiCheck lung cancer atlas as a development platform of novel blood biomarkers for early-stage lung cancer detection. Citation Format: Revital Knirsh, Stephen Lam, Anna McGuire, Peter J. Mazzone, Stephen Deppen, Eric Grogan, Fabien Maldonado, Orna Savin, Shacade Danan, Sarah Zaouch, Nimrod Axelrad, Dvir Netanely, Aharona Shuali, Catherine A. Schnabel, Adam Wasserstrom, Danny Frumkin. Development of a genome-wide multiomic atlas of early-stage lung cancer enables identification of novel methylation biomarkers for disease detection beyond TCGA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 3330.

A Comparative Review of the Detection of Early-stage Lung Cancer by Exosomal and Free Nucleic Acids and Standard Screening Methods

Lung cancer (LC), with its high incidence and less effective treatment strategies, is often not detected until it is in an advanced stage, which contributes to its high mortality rate. Hence, screening the DNA and RNA content in exosomes offers a promising method for its early diagnosis. New technologies for the early detection of LC are absolutely necessary to improve patient outcomes. Such an approach could be the exploitation of exosomes and their content. Exosomes contain DNA, different RNA species, proteins, ceramides, and cholesterol. They can transport their oncogenetic cargo derived from tumor cells to healthy cells over a range of distances to help propagate genetic information that could contribute to the initiation of cancer. This review provides an overview of the involvement of exosomes and their DNA/RNA together with cell-free DNA, summarizes potential biomarkers and describes the application of technologies for the characterization of exosomes with their possible tumor markers. Current radiological and scanning methods for the early detection of LC are also described and compared with nucleic acid analysis. The strengths and weaknesses of both approaches are considered.

Combinatorial Blood Platelets-Derived circRNA and mRNA Signature for Early-Stage Lung Cancer Detection

Despite the diversity of liquid biopsy transcriptomic repertoire, numerous studies often exploit only a single RNA type signature for diagnostic biomarker potential. This frequently results in insufficient sensitivity and specificity necessary to reach diagnostic utility. Combinatorial biomarker approaches may offer a more reliable diagnosis. Here, we investigated the synergistic contributions of circRNA and mRNA signatures derived from blood platelets as biomarkers for lung cancer detection. We developed a comprehensive bioinformatics pipeline permitting an analysis of platelet-circRNA and mRNA derived from non-cancer individuals and lung cancer patients. An optimal selected signature is then used to generate the predictive classification model using machine learning algorithm. Using an individual signature of 21 circRNA and 28 mRNA, the predictive models reached an area under the curve (AUC) of 0.88 and 0.81, respectively. Importantly, combinatorial analysis including both types of RNAs resulted in an 8-target signature (6 mRNA and 2 circRNA), enhancing the differentiation of lung cancer from controls (AUC of 0.92). Additionally, we identified five biomarkers potentially specific for early-stage detection of lung cancer. Our proof-of-concept study presents the first multi-analyte-based approach for the analysis of platelets-derived biomarkers, providing a potential combinatorial diagnostic signature for lung cancer detection.

Serum proteomics profiling identifies a preliminary signature for the diagnosis of early-stage lung cancer.

Lung cancer is the most common cause of death from cancer worldwide, largely due to late diagnosis. Thus, there is an urgent need to develop new approaches to improve the detection of early-stage lung cancer, which would greatly improve patient survival. The quantitative protein expression profiles of microvesicles isolated from the sera from 46 lung cancer patients and 41 high-risk non-cancer subjects were obtained using a mass spectrometry method based on a peptide library matching approach. We identified 33 differentially expressed proteins that allow discriminating the two groups. We also built a machine learning model based on serum protein expression profiles that can correctly classify the majority of lung cancer cases and that highlighted a decrease in the levels of Arysulfatase A (ARSA) as the most discriminating factor found in tumors. Our study identified a preliminary, non-invasive protein signature able to discriminate with high specificity and selectivity early-stage lung cancer patients from high-risk healthy subjects. These results provide the basis for future validation studies for the development of a non-invasive diagnostic tool for lung cancer.

Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning

BackgroundLow-dose spiral computed tomography (LDCT) may not lead to a clear treatment path when small to intermediate-sized lung nodules are identified. We have combined flow cytometry and machine learning to develop a sputum-based test (CyPath Lung) that can assist physicians in decision-making in such cases.MethodsSingle cell suspensions prepared from induced sputum samples collected over three consecutive days were labeled with a viability dye to exclude dead cells, antibodies to distinguish cell types, and a porphyrin to label cancer-associated cells. The labeled cell suspension was run on a flow cytometer and the data collected. An analysis pipeline combining automated flow cytometry data processing with machine learning was developed to distinguish cancer from non-cancer samples from 150 patients at high risk of whom 28 had lung cancer. Flow data and patient features were evaluated to identify predictors of lung cancer. Random training and test sets were chosen to evaluate predictive variables iteratively until a robust model was identified. The final model was tested on a second, independent group of 32 samples, including six samples from patients diagnosed with lung cancer.ResultsAutomated analysis combined with machine learning resulted in a predictive model that achieved an area under the ROC curve (AUC) of 0.89 (95% CI 0.83–0.89). The sensitivity and specificity were 82% and 88%, respectively, and the negative and positive predictive values 96% and 61%, respectively. Importantly, the test was 92% sensitive and 87% specific in cases when nodules were < 20 mm (AUC of 0.94; 95% CI 0.89–0.99). Testing of the model on an independent second set of samples showed an AUC of 0.85 (95% CI 0.71–0.98) with an 83% sensitivity, 77% specificity, 95% negative predictive value and 45% positive predictive value. The model is robust to differences in sample processing and disease state.ConclusionCyPath Lung correctly classifies samples as cancer or non-cancer with high accuracy, including from participants at different disease stages and with nodules < 20 mm in diameter. This test is intended for use after lung cancer screening to improve early-stage lung cancer diagnosis.Trial registration ClinicalTrials.gov ID: NCT03457415; March 7, 2018