EARLY DETECTION OF LUNGS CANCER USING MACHINE LEARNING ALGORITHMS

Exosomal lipids for classifying early and late stage non-small cell lung cancer

The incidence and mortality rates of lung cancer have been increasing in many countries. However, the true effectiveness of screening for lung cancer is still controversial. This study aimed to examine the growth pattern of lung cancer and to evaluate the efficacy of screening. The authors linked the records of annual radiologic screening to cancer registry data and conducted a retrospective follow-up study of radiographs in all patients with lung cancer arising in a population undergoing screening. Among a total of 305,934 participants, screening detected 206 lung cancers, 103 of which were Stage I disease. Seventy-one of the 131 adenocarcinomas were Stage I, and 58% of them showed evidence of cancer for 2 years on a retrospective review of radiographs. Presentation as small faint lesions overlapping the normal chest structures delayed the early detection of adenocarcinoma. The overall sensitivity of screening was 70%, 52% for squamous cell carcinoma and 50% for small cell carcinoma. Rapidly growing Stage II-IV tumors without retrospective evidence of cancer on previous radiographs accounted for most of the cancers detected during the intervals between screening. Both the low detectability of Stage I adenocarcinoma and the late recognition of rapidly growing small cell and squamous cell carcinomas reduced the effectiveness of screening. More effective imaging methods and an antismoking campaign are required to reduce lung cancer mortality.

A review of detection methods for the early diagnosis of lung cancer

Electrochemical biosensors for the detection of lung cancer biomarkers: A review

The Johns Hopkins Lung Project was designed to determine whether the addition of cytologic screening to the radiographic screening of high-risk volunteers could enhance the early detection of asymptomatic lung cancer and whether early therapeutic intervention in detected cases could significantly reduce the mortality from this disease. Male volunteers, 45 yr of age and older, who smoked at least 1 pack of cigarettes per day were recruited from the Baltimore metropolitan area. All of the 10,387 acceptable high-risk volunteers received annual chest radiographic screening. By random assignment, one half received cytologic examination of induced sputum in addition to the roentgenogram. This report describes the results of the initial screening. Compared with usual methods of clinical diagnosis, screening by both roentgenography and cytology identified a greater proportion of the lung cancer cases at an earlier stage. Screening by sputum cytology was found to improve the detection only of squamous cell carcinoma. In the dual-screen group, sputum cytology accounted for 28% of the detected cases, and resulted in 39% additional detection of lung cancer over that achieved by roentgenography. There was no corresponding decrease in prevalence. Lung cancers detected by cytology alone were found at very early stages. Although there has been an increase in average survival, much of this increase, if not all, may have resulted from lead-time and sampling bias.

Lung cancer remains one of the leading causes of death worldwide, with many sufferers unaware of their condition until it is too late for treatment. Therefore, high-accuracy prediction methods are urgently needed for early detection of lung cancer. This research uses the Random Forest algorithm, known for its excellent performance in medical data classification. In this study, modeling was optimized by implementing hyperparameter optimization using Optuna. The results of the generated model show an accuracy rate of 98.6%, which is highly significant in the context of early lung cancer detection. Additionally, this algorithm demonstrated 100% recall for the positive class and 97% for the negative class, indicating that the model is highly effective in identifying patients who truly have lung cancer. Another advantage of this model is seen in the AUC (Area Under the Curve) value reaching 1, indicating 100% accurate predictions. With these results, this research affirms the importance of using the Random Forest algorithm in developing early detection systems for lung cancer. This not only can improve treatment success rates but also significantly reduce mortality rates from lung cancer.

BackgroundDetection of lung cancer at earlier stage can greatly improve patient survival. We aim to develop, validate, and implement a cost-effective ctDNA-methylation-based plasma test to aid lung cancer early detection.MethodsCase-control studies were designed to select the most relevant markers to lung cancer. Patients with lung cancer or benign lung disease and healthy individuals were recruited from different clinical centers. A multi-locus qPCR assay, LunaCAM, was developed for lung cancer alertness by ctDNA methylation. Two LunaCAM models were built for screening (-S) or diagnostic aid (-D) to favor sensitivity or specificity, respectively. The performance of the models was validated for different intended uses in clinics.ResultsProfiling DNA methylation on 429 plasma samples including 209 lung cancer, 123 benign diseases and 97 healthy participants identified the top markers that detected lung cancer from benign diseases and healthy with an AUC of 0.85 and 0.95, respectively. The most effective methylation markers were verified individually in 40 tissues and 169 plasma samples to develop LunaCAM assay. Two models corresponding to different intended uses were trained with 513 plasma samples, and validated with an independent collection of 172 plasma samples. In validation, LunaCAM-S model achieved an AUC of 0.90 (95% CI: 0.88–0.94) between lung cancer and healthy individuals, whereas LunaCAM-D model stratified lung cancer from benign pulmonary diseases with an AUC of 0.81 (95% CI: 0.78–0.86). When implemented sequentially in the validation set, LunaCAM-S enables to identify 58 patients of lung cancer (90.6% sensitivity), followed by LunaCAM-D to remove 20 patients with no evidence of cancer (83.3% specificity). LunaCAM-D significantly outperformed the blood test of carcinoembryonic antigen (CEA), and the combined model can further improve the predictive power for lung cancer to an overall AUC of 0.86.ConclusionsWe developed two different models by ctDNA methylation assay to sensitively detect early-stage lung cancer or specifically classify lung benign diseases. Implemented at different clinical settings, LunaCAM models has a potential to provide a facile and inexpensive avenue for early screening and diagnostic aids for lung cancer.

Lung cancer, especially non-small cell lung cancer (NSCLC), is one of the most-deadly malignancies worldwide. Lung cancer has a worse 5-year survival rate than many primary malignancies. Thus, the early detection and prognosis prediction of lung cancer are crucial. The early detection and prognosis prediction of lung cancer have improved with the widespread use of artificial intelligence (AI) technologies. This meta-analysis examined the accuracy and efficacy of AI-based models in predicting lymph node metastasis (LNM) in NSCLC patients using imaging data. Our findings could help clinicians predict patient prognosis and select alternative therapies. We searched the PubMed, Web of Science, Cochrane Library, and Embase databases for relevant articles published up to January 31, 2024. Two reviewers individually evaluated all the retrieved articles to assess their eligibility for inclusion in the meta-analysis. The systematic assessment and meta-analysis comprised articles that satisfied the inclusion criteria (e.g., randomized or non-randomized trials, and observational studies) and exclusion criteria (e.g., articles not published in English), and provided data for the quantitative synthesis. The quality of the included articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivity, specificity, and area under the curve (AUC) were used to evaluate the ability of AI-based imaging models to predict LNM in NSCLC patients. Sources of heterogeneity were investigated using meta-regression. Covariates, including country, sample size, imaging modality, model validation technique, and model algorithm, were examined in the subgroup analysis. The final meta-analysis comprised 11 retrospective studies of 6,088 NSCLC patients, of whom 1,483 had LNM. The pooled sensitivity, specificity, and AUC of the AI-based imaging model for predicting LNM in NSCLC patients were 0.87 [95% confidence interval (CI): 0.80-0.91], 0.85 (95% CI: 0.78-0.89), and 0.92 (95% CI: 0.90-0.94). Based on the QUADAS-2 results, a risk of bias was detected in the patient selection and diagnostic tests of the included articles. However, the quality of the included articles was generally acceptable. The pooled sensitivity and specificity were heterogeneous (I2>75%). The meta-regression and subgroup analyses showed that imaging modality [computed tomography (CT) or positron emission tomography (PET)/CT], and the neural network method model design significantly affected heterogeneity of this study. Models employing sample size data from a single center and the least absolute shrinkage and selection operator (LASSO) method had greater sensitivity than other techniques. Using the Deek' s funnel plot, no publishing bias was found. The results of the sensitivity analysis showed that deleting each article one by one did not change the findings. Imaging data models based on AI algorithms have good diagnostic accuracy in predicting LNM in patients with NSCLC and could be applied in clinical settings.

PurposeCurrently the screening for lung cancer for risk groups is based on Computed Tomography (CT) or low dose CT (LDCT); however, the lung cancer death rate has not decreased significantly with people undergoing LDCT. We aimed to develop a simple reliable blood test for early detection of all types of lung cancer based on the immunogenicity of aberrant forms of BARD1 that are specifically upregulated in lung cancer.MethodsELISA assays were performed with a panel of BARD1 epitopes to detect serum levels of antibodies against BARD1 epitopes. We tested 194 blood samples from healthy donors and lung cancer patients with a panel of 40 BARD1 antigens. Using fitted Lasso logistic regression we determined the optimal combination of BARD1 antigens to be used in ELISA for discriminating lung cancer from healthy controls. Random selection of samples for training sets or validations sets was applied to validate the accuracy of our test.ResultsFitted Lasso logistic regression models predict high accuracy of the BARD1 autoimmune antibody test with an AUC = 0.96. Validation in independent samples provided and AUC = 0.86 and identical AUCs were obtained for combined stages 1–3 and late stage 4 lung cancers. The BARD1 antibody test is highly specific for lung cancer and not breast or ovarian cancer.ConclusionThe BARD1 lung cancer test shows higher sensitivity and specificity than previously published blood tests for lung cancer detection and/or diagnosis or CT scans, and it could detect all types and all stages of lung cancer. This BARD1 lung cancer test could therefore be further developed as i) screening test for early detection of lung cancers in high-risk groups, and ii) diagnostic aid in complementing CT scan.

Lung cancer is the leading cause of cancer death worldwide and it would be essential to have effective tools to diagnose the disease in its early stages, to identify individuals at highest risk of developing the disease, and to set personalised therapies. The effectiveness of screening for lung cancer with low-dose CT (LDCT) in heavy smokers was demonstrated, in terms of reduction of cause-specific mortality, in recently published data by the study National Lung ScreeningTrial (NLST). In Europe, the introduction of LDCT as screening in individuals at risk is the object of a debate until the results of European randomized trials, expected in 2015-2016, are published. One problem is the high rate of calls for investigations when there is a noncalcified nodule, and it is therefore essential to be able to more accurately identify malignant nodules. The development of specific biomarkers appears to offer promising prospects. Recent advances in genetics and genomics have led to a series of studies aimed at the identification of molecular markers for the diagnosis, the assessment of the risk of developing lung cancer, the molecular characterisation of the different stages of the disease and the personalisation of therapy. Subjects enrolled in trials evaluating LCDT as a test for early detection of lung cancer represent the ideal population in which to study a combined bioinstrumental approach of screening (molecular test and LDCT). This paper reports on the state of knowledge on the possible use of biomarkers in the early detection of lung cancer and molecular analysis conducted within the project ITALUNG, a randomized controlled trial to assess the effect on tumour-specific mortality of LDCT, which provided a collection of biological materials from the subjects enrolled.

P1.03-007 Improvement in Performance of an Autoantibody Panel Test for Detection of Lung Cancer by Addition of a Single Novel Biomarker (EDB1)

Early detection of lung cancer is essential to reduce lung cancer-related morbidity and mortality. Despite significant efforts, current approaches suffer from high false-positive rates or limited sensitivity. There is a critical need for non-invasive, cost-effective technologies that detect the early changes in lung carcinogenesis with high sensitivity and specificity. Abnormal chromatin structure is one of the hallmarks of cancer cells and is independent of molecular pathways making it an attractive target for early cancer detection. In this study, we assessed the use of super-resolution stochastic optical reconstruction microscopy (STORM) to detect abnormal heterochromatin disruption in lung carcinogenesis. First, utilizing a mouse model of tobacco carcinogen (NNK)-induced lung adenocarcinoma, we analyzed heterochromatin structure in the lungs of NNK-treated mice at 8, 15 and 20 weeks post-NNK exposure together with non-treated control mice at the same time points. Super-resolution images of NNK-induced lung lesions at all time points showed significant disruption of condensed heterochromatin nanodomains compared to normal alveolar epithelial cells from the control mice, consistent with our data from other tumor types. Importantly, the normal-appearing bronchial epithelial cell nuclei from NNK-treated mice also showed significant heterochromatin disruption in NNK-treated mice at 15 and 20 weeks (P< 0.0001), demonstrating that this method can detect early changes. Next, we sought to confirm this in humans. Super-resolution imaging showed that, compared to normal alveolar and bronchial epithelial cells from control subjects without cancer, the heterochromatin structure was more disrupted in tumor cells from patients with lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC). We also observed significant disrupted heterochromatin structure in tumor-adjacent normal tissue at the tumor margin. Lastly, we performed a pilot study on bronchial epithelial cells isolated from sputum samples from 11 cigarette smokers with or without lung cancer. The heterochromatin structure in the bronchial epithelial cells collected from lung cancer patients at the time of diagnosis was significantly more disrupted than those from smokers without lung cancer (P= 0.004). Our results support disrupted heterochromatin structure as an early event in lung carcinogenesis and demonstrate the feasibility of utilizing super-resolution imaging of heterochromatin structure for early detection of lung cancer using sputum samples. Citation Format: Laura P. Stabile, Xuejiao Sun, Jianquan Xu, Beatriz Kanterewicz, David O. Wilson, Sanja Dacic, Lora H. Rigatti, Brenda Diergaarde, Yang Liu. Super-resolution imaging of heterochromatin structure detects early events in 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 777.

8553 Background: Lung cancer early detection improves survival, but risk-based low-dose CT screening (LDCT) only identifies a minority of patients. We implemented an ILNP in a community healthcare system, and evaluated its risks and benefits. Methods: Patients with lung lesions on routinely-performed radiologic studies were flagged by radiologists and triaged using evidence-based guidelines. We tracked demographics, clinical characteristics, procedures, complications, and health outcomes. We analyzed ILNP subjects’ eligibility for LDCT by National Lung Screening Trial (NLST), Center for Medicaid Services (CMS), NEderlands Leuvens Screening ONderzoek (NELSON), National Comprehensive Cancer Network (NCCN) Risk Groups 1 and 2 (screening recommended), NCCN Risk Group 3 (screening not currently recommended), and US Preventive Services Task Force (USPSTF) criteria from 2013 and 2020. Statistical analysis used the chi-square test and Kaplan Meier method. Results: From 2015-2020, 13,710 patients were evaluated in the ILNP program: median age, 64 years; 42% male; 65% White, 29% Black; 667 (4.9%) were diagnosed with lung cancer. Lung cancers diagnosed from ILNP were 39% adenocarcinoma / 20% Squamous Cell with clinical stage distribution 49% I, 8% II, 17% III, and 16% IV. 832 (6.1%) had invasive diagnostic testing- CT-guided biopsy (50%), bronchoscopy (30%), and/or EBUS (26%); 11% of the 832 had >1 invasive diagnostic test. The most common complications from invasive testing were pneumothorax and chest tube placement. Only 11%-20% of all ILNP patients would have been eligible for LDCT. In ILNP patients diagnosed with lung cancer, only 33% were eligible for screening by NLST criteria; the proportion increased substantially when USPSTF 2020 or NCCN Group 2 criteria were applied (Table). Compared to NLST, NCCN Group 2 criteria increased screening eligibility among cancer patients by 22% (from 33% to 55%), while only increasing screening eligibility by 6% (from 8% to 14%) in non-cancer patients. Aggregate 1-year and 3-year survival rates for lung cancer patient diagnosed through ILNP were 76% (95% CI: 73, 80) and 64% (95% CI: 59, 69). Conclusions: The ILNP identified early-stage lung cancer more frequently than most LDCT programs, with promising survival rates. The majority of subjects with lung cancer were not eligible for LDCT, we still need to optimize risk-based screening criteria. Even with new, expanded criteria for LDCT, structured ILNP is necessary to expand early detection of lung cancer.[Table: see text]

Lung cancer remains the leading cause of mortality from cancer. This chapter describes the evolution and results of screening studies using these techniques and the controversies that developed surrounding the results of these studies. It explores several emerging technologies for early lung cancer detection, with a special emphasis on low-dose spiral computed tomography (CT). Screening studies for lung cancer date to the 1950s and 1960s, when several studies were undertaken using a variety of screening protocols that combined chest radiography and sputum analysis. Low-dose spiral CT has been explored as a tool for detecting early lung cancer in asymptomatic individuals at risk for the disease, with encouraging preliminary results. The light-induced fluorescence endoscopy device, which was designed to capitalize on differences in autofluorescence properties in order to aid in the detection and localization of preinvasive lung cancer, has been approved by the FDA for the detection of early lung cancer.

The once-promising computed tomography (CT) lung cancer screening appears to result in high false positive rates. To tackle the common difficulties in diagnosing small lung cancer at an early stage, we developed a minimally invasive multimodality image-guided (MIMIG) interventional system for early detection and treatment of peripheral lung cancer. The system consists of new CT image segmentation for surgical planning, intervention guidance for targeting, and molecular imaging for diagnosis. Using advanced image segmentation technique the pulmonary vessels, airways, as well as nodules can be better visualized for surgical planning. These segmented results are then transformed onto the intra-procedural CT for interventional guidance using electromagnetic (EM) tracking. Diagnosis can be achieved at microscopic resolution using a fiber-optic microendoscopy. The system can also be used for fine needle aspiration biopsy to improve the accuracy and efficiency. Confirmed cancer could then be treated on-the-spot using radio-frequency ablation (RFA). The experiments on rabbits with VX2 lung cancer model show both accuracy and efficiency in localization and detecting lung cancer, as well as promising molecular imaging tumor detection.