State-of-the-art DNN techniques for lung cancer diagnosis using chest CT scans

Lung cancer is the leading cause of the incidence and mortality of malignant tumors in our country, seriously endangering people's lives and health. The treatment of lung cancer has made great progress in the past 10 years, and the 5-year survival rate of lung cancer in China has also increased from 16.1% to 19.7%, but about 75% of patients are still in advanced stages of lung cancer at the time of diagnosis, missing the best time for radical surgery. Early diagnosis can significantly improve the prognosis and survival of lung cancer patients. From the 5-year survival rate of lung cancer patients, it can be seen that the 5-year survival rate of stage Ⅰ patients was 77%-92%, while that of stage ⅢA-ⅣA patients was only 10%-36%, and there was a significant difference in the 5-year survival rate. Studies have shown that early-diagnosed and completely resected lung adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) have 5-year disease-specific survival rates of 100% and 100%, respectively. Early diagnosis is the key to improving the prognosis of lung cancer. In order to further improve the level of early lung cancer diagnosis in China, especially the standardization in the diagnosis and evaluation of pulmonary nodules and early lung cancer, experts from the Lung Cancer Group of Chinese Thoracic Society formulated the "Chinese Expert Consensus on Diagnosis of Early Lung Cancer (2023 Edition)", on the basis of the actual situation in the field of diagnosis and treatment, with reference to the latest research data and relevant guidelines at home and abroad. Consensus on the application of artificial intelligence, big data and robotics, the Internet of Things and multidisciplinary cooperation in the diagnosis of early lung cancer, the management of pulmonary nodules and follow-up strategies for suspected early lung cancer, etc., were respectively recommended to provide references for clinicians in the diagnosis of early lung cancer, in order to further promote the early diagnosis of lung cancer in China.

Chapter 5 - Neural network for lung cancer diagnosis

Background: Lung cancer is the leading cause of death by cancer worldwide. Since 5-year survival rate increases significantly when lung cancer is diagnosed at early stages, the development of accurate non-invasive biomarkers for early lung cancer diagnosis is of utmost importance. Over the last years, several tumour biomarkers based on microRNAs (miRNAs) determined in exhaled breath condensate (EBC) have been evaluated and could be applied to early diagnosis of lung cancer. Rationale: miRNA signatures for surgical specimens of lung cancer have been determined providing a panel of differentially expressed miRNAs that were able to discriminate lung cancer patients from normal subjects. Using these miRNAs, we hypothesised that the miRNAs expression pattern is similar in lung cancer tissue and in EBC, indicating that EBC is a good surrogate of lung tissue and can be used for non-invasive diagnosis of lung cancer. Methods: Expression of miR-1, mir-200b, miR-21, miR-486, miR-375 was assessed in normal and tumour tissues and EBC obtained from 19 lung cancer patients and 18 healthy subjects. Results: Our results indicate that all miRNAs analysed were differentially expressed in normal and the corresponding lung cancer tissue. miR-1 and miR-486 were down-regulated in lung cancer tissues whereas miR-200b, miR-21 and miR-375 were significantly higher in lung cancer tissues. Interestingly, EBC miRNAs follow the same trend as that observed in the tissues. Conclusions: Our data indicate that a panel of miRNAs can be reliably determined in EBC, which could be considered as surrogate of lung cancer, indicating that these biomarkers could be useful in early diagnosis of lung cancer.

Implementation of lung screening (LS) programs is challenging even among health care organizations that have the motivation, the resources, and more importantly, the goal of providing for life-saving early detection, diagnosis, and treatment of lung cancer. We provide a case study of LS implementation in different healthcare systems, at the Mount Sinai Healthcare System (MSHS) in New York City, and at the Phoenix Veterans Affairs Health Care System (PVAHCS) in Phoenix, Arizona. This will illustrate the commonalities and differences of the LS implementation process in two very different health care systems in very different parts of the United States. Underlying the successful implementation of these LS programs was the use of a comprehensive management system, the Early Lung Cancer Action Program (ELCAP) Management SystemTM. The collaboration between MSHS and PVAHCS over the past decade led to the ELCAP Management SystemTM being gifted by the Early Diagnosis and Treatment Research Foundation to the PVAHCS, to develop a “VA-ELCAP” version. While there remain challenges and opportunities to continue improving LS and its implementation, there is an increasing realization that most patients who are diagnosed with lung cancer as a result of annual LS can be cured, and that of all the possible risks associated with LS, the greater risk of all is for heavy cigarette smokers not to be screened. We identified 10 critical components in implementing a LS program. We provided the details of each of these components for the two healthcare systems. Most importantly, is that continual re-evaluation of the screening program is needed based on the ongoing quality assurance program and database of the actual screenings. At minimum, there should be an annual review and updating. As early diagnosis of lung cancer must be followed by optimal treatment to be effective, treatment advances for small, early lung cancers diagnosed as a result of screening also need to be assessed and incorporated into the entire screening and treatment program.

Lung cancer is the leading cause of cancer-related death worldwide. The early detection of lung cancer is crucial for the diagnosis of this disease. Therefore, an effective and noninvasive method for the early diagnosis of lung cancer is urgently needed. To evaluate the diagnostic performance of circulating genetically abnormal cells (CACs) in early lung cancer, a total of 63 participants who completed CAC detection by Zhuhai SanMed Biotech Inc. and obtained pathological results from January to December 2020 were included in our study; 50 patients had lung cancer and 13 patients had benign lung disease. The levels of lung cancer-related markers in peripheral blood and the chest computed tomography (CT) imaging characteristics of these patients were collected before pathological acquisition. The positive rate of CAC was 90.0% in the lung cancer group and 23.1% in the benign lung disease group, and the difference was statistically significant (P < 0.01). The area under the receiver operating characteristic (ROC) curve of CAC was 0.837, the sensitivity was 90%, and the specificity was 76.9%. The area under the ROC curve and sensitivity were both higher than those of the combined or single serum tumor marker test. This study preliminarily concludes that the CAC test, as a noninvasive test, has high sensitivity and specificity for the early diagnosis of lung cancer. This test is expected to help with the early detection of disease in lung cancer patients.

Abstract. At present, the cancer that kills people the fastest worldwide is lung cancer, and many lung cancer patients are found or detected at the late stage of lung cancer, which is very bad for the prognosis of the disease, and makes the mortality rate of the patients increase greatly. Therefore, the development of techniques for the early diagnosis and detection of lung cancer is imperative. At the moment, lung cancer can be detected early due to biomarkers. This review primarily outlines the many kinds of biomarkers and the conventional techniques for detecting and diagnosing lung cancer. In addition, bodily fluids potential application as biomarker carriers in the detecting of cancer development and progression is mentioned in this review, the feasibility of non-invasive cancer diagnostic methods is analyzed, and the current status of the development of such diagnostic methods is summarized.

Lung cancer is the most frequently diagnosed cancer and the leading cause of cancer death worldwide. Early detection of lung cancer can lead to identification of the cancer at its initial treatable stages and improves survival. Low-dose CT scan (LDCT) is currently the gold standard for lung cancer screening in high-risk individuals. Despite the observed stage migration and consistently demonstrated disease-specific overall survival benefit, LDCT has inherent limitations, including false-positive results, radiation exposure, and low compliance. Recently, new techniques have been investigated for early detection of lung cancer. Several studies have shown that liquid biopsy biomarkers such as circulating cell-free DNA (cfDNA), microRNA molecules (miRNA), circulating tumor cells (CTCs), tumor-derived exosomes (TDEs), and tumor-educated platelets (TEPs), as well as volatile organic compounds (VOCs), have the power to distinguish lung cancer patients from healthy subjects, offering potential for minimally invasive and non-invasive means of early cancer detection. Furthermore, recent studies have shown that the integration of artificial intelligence (AI) with clinical, imaging, and laboratory data has provided significant advancements and can offer potential solutions to some challenges related to early detection of lung cancer. Adopting AI-based multimodality strategies, such as multi-omics liquid biopsy and/or VOCs’ detection, with LDCT augmented by advanced AI, could revolutionize early lung cancer screening by improving accuracy, efficiency, and personalization, especially when combined with patient clinical data. However, challenges remain in validating, standardizing, and integrating these approaches into clinical practice. In this review, we described these innovative milestones and methods, as well as their advantages and limitations in screening and early diagnosis of lung cancer.

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

e20614 Background: Lung 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. Methods: This 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 from The First Affiliated Hospital of Soochow University 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 (mRMR) 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. Results: We identified 7 DMRs corresponding to 7 differentially methylated genes (DMRs, including HOXB4, HOXA7, HOXD8, ITGA4, ZNF808, PTGER4, and B3GNTL1), highly associated with lung cancer by comparing the methylation profiles of lung cancer and benign nodule tissues. 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 0.966 (95%CI: 0.933-1.000)/0.961 (0.924-1.000), sensitivities of 0.887 (0.824-0.951)/0.922 (0.863-0.980), specificities of 0.938 (0.889-0.986)/1.000 (1.000-1.000), and accuracies of 0.896 (0.835-0.957)/0.938 (0.886-0.991) 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 0.935 (0.862-1.000), sensitivity of 0.808 (0.733-0.883), specificity of 0.975 (0.945-1.000), and accuracy of 0.934 (0.887-0.981). Conclusions: The 7 novel DMRs could be promising methylation biomarkers that merits further development as a noninvasive test for early detection of lung cancer.

11114 Background: Lipids play roles in membrane structure, energy storage, and signal transduction as well as lung cancer. Lipidomics, a new technology aims to measure all the lipids in a cell, has not been applied to diagnostic test development for a variety of cancer types. Here, we adopt lipidomics as a means to identify plasma lipid markers for the early detection of lung cancer and complement CT-based methods for lung cancer screening. Methods: Using mass spectrometry, we profiled 390 individual lipids in a training discovery cohort comprised of cohorts that were either at “high-risk” for lung cancer (n=22) and squamous cell carcinoma at early stages (n=22). Cases had a minimum of two years clinical follow-up and were matched in terms of race, sex, age and smoking status. Gain ratio feature selection and local weighted classification model were employed to find the best training classifier, which was further validated against an additional cohort, including high-risk individuals (n= 20) and squamous cell carcinoma patients (n=17). Results: In the training discovery stage, we found 20 distinct lipids that were significantly distributed between high-risk and cases of squamous cell carcinoma. We further defined a two lipid marker panel had a training accuracy at 95.5% sensitivity, 90.9% specificity and 95.2% AUC (Area under ROC curve). The validation accuracy against the additional cohort is 100.0% sensitivity, 90.0% specificity and 99.0% AUC (Table). The power for sample size we used in both discovery training and validation stages were over 90%. Conclusions: Using lipidomics we identified two lipid markers capable of discerning cases of squamous cell carcinoma from individuals at high risk for lung cancer, with a high sensitivity, specificity and accuracy. The markers maybe further developed as a quick, safe blood test for early diagnosis of squamous cell lung cancer and reduce unnecessary follow-up imaging or invasive procedures. [Table: see text]

Context: The early diagnosis and detection of lung cancer are crucial for reducing mortality and morbidity. Recently, the study of biomarkers for diagnosis and early detection has expanded significantly. Several volatile organic compounds (VOCs) found in exhaled breath may serve as valuable indicators for the early detection of lung cancer, which is influenced by pathological factors associated with cancer development. Aims: To create a profile of VOCs in lung cancer patients and healthy controls and to examine the differences in VOC levels among lung cancer patients based on histological type, stage, and therapy. Methods: A cross-sectional study was conducted involving lung cancer patients receiving treatment at Saiful Anwar General Hospital. A total of 40 lung cancer patients and 40 healthy controls who met the inclusion criteria were recruited through total sampling. VOC levels were measured using the Ubreath sensor array method. Statistical analysis of VOC variables was performed utilizing the Kruskal-Wallis and Mann-Whitney tests. Results: An analysis of three VOCs—ethanol, formaldehyde, and toluene—showed significantly higher levels in lung cancer patients compared to healthy controls (p&lt;0.05 for all three compounds). However, no significant differences in the levels of ethanol, formaldehyde, and toluene were observed based on histological type, stage, or therapy among lung cancer patients. Conclusions: Elevated concentrations of ethanol, formaldehyde, and toluene in exhaled breath suggest their potential as biomarkers for lung cancer detection.

ABSTRACTWe have previously identified a panel of autoantibodies (AABs), including p53, GAGE7, PGP9.5, CAGE, MAGEA1, SOX2 and GBU4-5, that was helpful in the early diagnosis of lung cancer. This large-scale, multicenter study was undertaken to validate the clinical value of this 7-AABs panel for early detection of lung cancer in a Chinese population. Two independent sets of plasma samples from 2308 participants were available for the assay of AABs (training set = 300; validation set = 2008). The concentrations of AABs were quantitated by enzyme-linked immunosorbent assay (ELISA), and the optimal cutoff value for each AAB was determined in the training set and then applied in the validation set. The value of the 7-AABs panel for the early detection of lung cancer was assessed in 540 patients who presented with ground-glass nodules (GGNs) and/or solid nodules. In the validation set, the sensitivity and specificity of the 7-AABs panel were 61% and 90%, respectively. For stage I and stage II non-small cell lung cancer (NSCLC), the sensitivity of the 7-AABs panel was 62% and 59%, respectively, and for limited stage small cell lung cancer (SCLC) it was 59%; these sensitivity values were considerably higher than for traditional biomarkers (including CEA, NSE and CYFRA21-1). Importantly, the combination of the 7-AABs panel and low-dose computed tomography (CT) scanning significantly improved the diagnostic yield in patients presenting with GGNs and/or solid nodules. In conclusion, our 7-AABs panel has clinical value for early detection of lung cancer, including early-stage lung cancer presenting as GGNs.

Lung cancer is the deadliest cancer worldwide. Early detection of lung cancer is a promising way to lower the risk of dying. Accurate pulmonary nodule detection in computed tomography (CT) images is crucial for early diagnosis of lung cancer. The development of computer-aided detection (CAD) system of pulmonary nodules contributes to making the CT analysis more accurate and with more efficiency. Recent studies from other groups have been focusing on lung cancer diagnosis CAD system by detecting medium to large nodules. However, to fully investigate the relevance between nodule features and cancer diagnosis, a CAD that is capable of detecting nodules with all sizes is needed. In this paper, we present a deep-learning based automatic all size pulmonary nodule detection system by cascading two artificial neural networks. We firstly use a U-net like 3D network to generate nodule candidates from CT images. Then, we use another 3D neural network to refine the locations of the nodule candidates generated from the previous subsystem. With the second sub-system, we bring the nodule candidates closer to the center of the ground truth nodule locations. We evaluate our system on a public CT dataset provided by the Lung Nodule Analysis (LUNA) 2016 grand challenge. The performance on the testing dataset shows that our system achieves 90% sensitivity with an average of 4 false positives per scan. This indicates that our system can be an aid for automatic nodule detection, which is beneficial for lung cancer diagnosis.

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

BackgroundLung cancer is typically diagnosed at a late stage. Early presentation and detection of lung cancer symptoms is critical to improving survival but can be clinically complicated and as yet a robust screening method for diagnosis is not available in routine practice. Accordingly, the barriers to help-seeking behaviour and diagnosis need to be considered. This review aimed to document the barriers to early presentation and diagnosis of lung cancer, based on patient and carer perspectives.MethodsA systematic review of databases was performed for original, English language articles discussing qualitative research on patient perceived barriers to early presentation and diagnosis of lung cancer. Three major databases were searched: Scopus, PubMed and EBSCOhost. References cited in the selected studies were searched for further relevant articles.ResultsFourteen studies met inclusion criteria for review. Barriers were grouped into three categories: healthcare provider and system factors, patient factors and disease factors.ConclusionsStudies showed that the most frequently reported barriers to early presentation and diagnosis of lung cancer reported by patients and carers related to poor relationships between GPs and patients, a lack of access to services and care for patients, and a lack of awareness of lung cancer symptoms and treatment. Addressing these barriers offers opportunities by which rates of early diagnosis of lung cancer may be improved.