scholarly journals Improved Version of Graph-Cut Algorithm for CT Images of Lung Cancer With Clinical Property Condition

2020 ◽  
Vol 2 (4) ◽  
pp. 201-206
Author(s):  
Dr. Samuel Manoharan ◽  
Sathish
Keyword(s):  
Lung Cancer ◽  
Soft Tissues ◽  
Early Stage ◽  
Graph Cut ◽  
Lung Nodules ◽  
Lung Segmentation ◽  
Segmentation Methods ◽  
Diagnosis Of Lung Cancer ◽  
Property Condition ◽  
Task Segmentation

In a clinical evaluation, the detection of lung cancer is a challenging task. Segmentation methods are used to detect the extra growing nodule. Early diagnosis of lung cancer is significant in clinical research. The early stage of lung nodules is very soft tissues and tough to segment accurately. Generally, conservative graph cut methods are very weak to detect those soft edges in medical images. In this article, the proposed algorithm is improved to obtain the accuracy of the process to segment the edges than the conventional graph cut methods. This investigation is executed to shows the accuracy of lung segmentation.

scholarly journals Reducing False-Positives in Lung Nodules Detection Using Balanced Datasets

2021 ◽  
Vol 9 ◽  
Author(s):  
Jinglun Liang ◽  
Guoliang Ye ◽  
Jianwen Guo ◽  
Qifan Huang ◽  
Shaohui Zhang
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
False Positives ◽  
Classification Systems ◽  
Cad System ◽  
Nodule Detection ◽  
Diagnosis Of Lung Cancer ◽  
Lung Ct

Malignant pulmonary nodules are one of the main manifestations of lung cancer in early CT image screening. Since lung cancer may have no early obvious symptoms, it is important to develop a computer-aided detection (CAD) system to assist doctors to detect the malignant pulmonary nodules in the early stage of lung cancer CT diagnosis. Due to the recent successful applications of deep learning in image processing, more and more researchers have been trying to apply it to the diagnosis of pulmonary nodules. However, due to the ratio of nodules and non-nodules samples used in the training and testing datasets usually being different from the practical ratio of lung cancer, the CAD classification systems may easily produce higher false-positives while using this imbalanced dataset. This work introduces a filtering step to remove the irrelevant images from the dataset, and the results show that the false-positives can be reduced and the accuracy can be above 98%. There are two steps in nodule detection. Firstly, the images with pulmonary nodules are screened from the whole lung CT images of the patients. Secondly, the exact locations of pulmonary nodules will be detected using Faster R-CNN. Final results show that this method can effectively detect the pulmonary nodules in the CT images and hence potentially assist doctors in the early diagnosis of lung cancer.

Circulating Tumor Cell and Metabolites as Novel Biomarkers for Early-stage Lung Cancer Diagnosis

2020 ◽  
Author(s):  
Lingling Wan ◽  
Yutong He ◽  
Qingyi Liu ◽  
Di Liang ◽  
Yongdong Guo ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Early Diagnosis ◽  
Cancer Patients ◽  
Early Stage ◽  
Untargeted Metabolomics ◽  
Early Stage Lung Cancer ◽  
Lung Cancer Patients ◽  
Diagnosis Of Lung Cancer ◽  
Metabolomics Analysis ◽  
Stage Lung Cancer

Abstract Background: Lung cancer is a malignant tumor that has the highest morbidity and mortality rate among all cancers. Early diagnosis of lung cancer is a key factor in reducing mortality and improving prognosis. Methods: In this study, we performed CTC next-generation sequencing (NGS) in early-stage lung cancer patients to identify lung cancer-related gene mutations. Meanwhile, a serum liquid chromatography-tandem mass spectrometry (LC-MS) untargeted metabolomics analysis was performed in the CTC-positive patients, and the early diagnostic value of these assays in lung cancer was analyzed. Results: 62.5% (30/48) of lung cancer patients had ≥ 1 CTC. By CTC NGS, we found that > 50% of patients had 4 commonly mutated genes, namely, NOTCH1, IGF2, EGFR, and PTCH1. 47.37% (9/19) patients had ARIDH1 mutations. Additionally, 30 CTC-positive patients and 30 healthy volunteers were subjected to LC-MS untargeted metabolomics analysis. We found 100 different metabolites, and 10 different metabolites were identified through analysis, which may have potential clinical application value in the diagnosis of CTC-positive early-stage lung cancer (AUC > 0.9). Conclusions: Our results indicate that NGS of CTC and metabolomics may provide new tumor markers for the early diagnosis of lung cancer. This possibility requires more in-depth large-sample research for verification.

External validation of a panel of plasma microRNA biomarkers for lung cancer

2019 ◽  
Vol 13 (18) ◽  
pp. 1557-1564 ◽  
Author(s):  
Jin Li ◽  
HongBin Fang ◽  
Fang Jiang ◽  
Yang Ning
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
External Validation ◽  
Early Stage Lung Cancer ◽  
Combined Use ◽  
Diagnostic Values ◽  
Plasma Microrna ◽  
Diagnosis Of Lung Cancer ◽  
Lung Cancer Detection ◽  
Plasma Mirnas

Aim: We externally validate plasma miRNAs biomarkers for lung cancer in a large and retrospective sample set collected from a geographically distant population. Methods: Plasma samples are tested blindly to the clinical annotations by using PCR for quantitation of the four miRNAs in cohort 1 consisting of 232 lung cancer cases and 243 controls and cohort 2 comprising 239 cases and 246 controls. Results: Combined use of the four plasma miRNAs has 91% sensitivity and 95% specificity for diagnosis of lung cancer, and 85% sensitivity for early-stage lung cancer, while maintaining a specificity of 95%. Conclusion: The diagnostic values of the biomarkers are reproducibly confirmed in the independent and large sample sets, providing an assay for lung cancer detection.

Early non-invasive detection of stage Ia lung cancer using circulating tumor DNA methylation haplotypes (ctmDNA) in plasma.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e13159-e13159
Author(s):  
Kun Zhang ◽  
Zhoufeng Wang ◽  
Zhe Li ◽  
Jingyi Lu ◽  
Jun Min ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Low Dose ◽  
Early Stage ◽  
Lung Nodules ◽  
Screening Assay ◽  
Early Stage Lung Cancer ◽  
Test Set ◽  
Non Invasive ◽  
Stage Ia ◽  
Stage Lung Cancer

e13159 Background: Lung cancer is one of the most common forms of cancer and is responsible for approximately 1.8 million deaths per year worldwide. The current 5-year survival rate for lung cancer is only 18%; however, this improves to 56% if the cancer is detected early. While low-dose CT scans have shown promise as an early detection method, only 16% of lung cancer is currently detected at an early stage. We therefore set out to develop a non-invasive blood-based screening assay to identify lung cancer at an early stage using ctmDNA (circulating tumor methylated DNA haplotypes). Methods: Blood samples were prospectively collected from two partner hospitals from 325 healthy individuals and 116 individuals diagnosed with lung nodules by low-dose CT scan in EDTA or Streck BCT tubes and immediately separated into plasma. Patients with lung nodules that appeared cancerous then underwent surgical resection, and cancer diagnosis was confirmed via pathology. Patients were matched between healthy and cancer groups by age, sex, and smoking status. Plasma samples were processed using the Singlera Genomics LUNA assay, a targeted bisulfite sequencing method which identifies methylation haplotype patterns related to early-stage lung cancer. 241 samples were used to train a classification model based on pathology results, and 200 samples were used as a test set to validate the model. Results: In the independent test set, the LUNA assay was able to show a sensitivity of 91.9% to detect early-stage lung cancer with a specificity of 93.3% in healthy patients. Even patients with stage Ia lung cancer were readily detected by the LUNA assay (sensitivity of 91.7%). Conclusions: We have shown that ctmDNA can be utilized to non-invasively screen for early-stage lung cancer with high sensitivity and specificity, paving the way for a blood-based lung cancer early screening assay.

The utility of six serum tumor markers in early detection of lung cancer

2019 ◽  
Author(s):  
Qingwen Jiang ◽  
Xu Zheng ◽  
Yiting Li ◽  
Weina Huang ◽  
Xinjian Li ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Sensitivity And Specificity ◽  
Operating Characteristic ◽  
Early Stage ◽  
High Sensitivity ◽  
Roc Curves ◽  
Serum Levels ◽  
Benign Diseases ◽  
Significant Difference ◽  
Diagnosis Of Lung Cancer

Abstract Background: Lung cancer has become the leading cause of cancer-related death in China. However, most of patients were diagnosed at advanced stage. Thus, novel lung cancer diagnostic tests, which can be used to screen individuals in early stage, are required.Methods: A total of 208 patients involving 161 cases of lung cancer and 47 cases of benign diseases were enrolled. Serum concentration of GTM, CETM, PTM, CTM, ETM and HTM were analyzed by kits according to the manufacturer’s guidelines.Results: The results showed significant difference in serum concentrations of GTM, CETM, PTM, CTM, ETM, and HTM between patients with lung cancer and benign diseases. In addition, when compared with benign diseases, higher levels of those six markers were also observed in patient with SCC and SCLC, but not for ADC. Receiver operating characteristic (ROC) curves were further suggested a high sensitivity and specificity of six markers to identify lung cancer.Conclusion: The serum levels of GTM, CETM, PTM, CTM, ETM and HTM in lung cancer were significantly higher than those of benign diseases. Moreover, these six biomarkers showed a high sensitivity and specificity to identify a patient with malignant. These findings suggested that detection of those six biomarkers in serum might be helpful for differential diagnosis of lung cancer.

A Novel Approach of Lung Tumor Segmentation Using a 3D Deep Convolutional Neural Network

2022 ◽  
pp. 1-16
Author(s):  
Shweta Tyagi ◽  
Sanjay N. Talbar ◽  
Abhishek Mahajan
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Convolutional Neural Network ◽  
Lung Tumor ◽  
Early Stage ◽  
Tumor Segmentation ◽  
Lung Tumour ◽  
Dice Coefficient ◽  
Tumour Segmentation ◽  
Diagnosis Of Lung Cancer

Cancer is one of the most life-threatening diseases in the world, and lung cancer is the leading cause of death worldwide. If not detected at an early stage, the survival rate of lung cancer patients can be very low. To treat patients in later stages, one needs to analyze the tumour region. For accurate diagnosis of lung cancer, the first step is to detect and segment the tumor. In this chapter, an approach for segmentation of a lung tumour is presented. For pre-processing of lung CT images, simple image processing like morphological operations is used, and for tumour segmentation task, a 3D convolutional neural network (CNN) is used. The CNN architecture consists of a 3D encoder block followed by 3D decoder block just like U-Net but with deformable convolution blocks. For this study, two datasets have been used; one is the online-available NSCLC Radiomics dataset, and the other is collected from an Indian local hospital. The approach proposed in this chapter is evaluated in terms of dice coefficient. This approach is able to give significant results with a dice coefficient of 77.23%.

scholarly journals Liquid Biopsy: A New Diagnostic Strategy and Not Only for Lung Cancer?

2021 ◽  
Author(s):  
Stefania Scarpino ◽  
Umberto Malapelle
Keyword(s):  
Lung Cancer ◽  
Liquid Biopsy ◽  
Early Stage ◽  
Circulating Tumor Dna ◽  
Advanced Lung Cancer ◽  
Diagnostic Strategy ◽  
Improve Patient Survival ◽  
Molecular Therapies ◽  
Targeted Molecular Therapies ◽  
Diagnosis Of Lung Cancer

Targeted molecular therapies have significantly improved the therapeutic management of advanced lung cancer. The possibility of detecting lung cancer at an early stage is surely an important event in order to improve patient survival. Liquid biopsy has recently demonstrated its clinical utility in advanced non-small cell lung cancer (NSCLC) as a possible alternative to tissue biopsy for non-invasive evaluation of specific genomic alterations, thus providing prognostic and predictive information when the tissue is difficult to find or the material is not sufficient for the numerous investigations to be carried out. Several biosources from liquid biopsy, including free circulating tumor DNA (ctDNA) and RNA (ctRNA), circulating tumor cells (CTCs), exosomes and tumor-educated platelets (TEPs), have been extensively studied for their potential role in the diagnosis of lung cancer. This chapter proposes an overview of the circulating biomarkers assessed for the detention and monitoring of disease evolution with a particular focus on cell-free DNA, on the techniques developed to perform the evaluation and on the results of the most recent studies. The text will analyze in greater depth the liquid biopsy applied to the clinical practice of the management of NSCLC.

scholarly journals Circulating Tumor Cell and Metabolites as Novel Biomarkers for Early-Stage Lung Cancer Diagnosis

2021 ◽  
Vol 11 ◽  
Author(s):  
Lingling Wan ◽  
Qingyi Liu ◽  
Di Liang ◽  
Yongdong Guo ◽  
Guangjie Liu ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Early Diagnosis ◽  
Cancer Patients ◽  
Early Stage ◽  
Untargeted Metabolomics ◽  
Early Stage Lung Cancer ◽  
Lung Cancer Patients ◽  
Diagnosis Of Lung Cancer ◽  
Metabolomics Analysis ◽  
Stage Lung Cancer

BackgroundLung cancer is a malignant tumor that has the highest morbidity and mortality rate among all cancers. Early diagnosis of lung cancer is a key factor in reducing mortality and improving prognosis.MethodsIn this study, we performed CTC next-generation sequencing (NGS) in early-stage lung cancer patients to identify lung cancer-related gene mutations. Meanwhile, a serum liquid chromatography-tandem mass spectrometry (LC-MS) untargeted metabolomics analysis was performed in the CTC-positive patients. To screen potential diagnostic markers for early lung cancer.Results62.5% (30/48) of lung cancer patients had ≥1 CTC. By CTC NGS, we found that > 50% of patients had 4 commonly mutated genes, namely, NOTCH1, IGF2, EGFR, and PTCH1. 47.37% (9/19) patients had ARIDH1 mutations. Additionally, 30 CTC-positive patients and 30 healthy volunteers were subjected to LC-MS untargeted metabolomics analysis. We found 100 different metabolites, and 10 different metabolites were identified through analysis, which may have potential clinical application value in the diagnosis of CTC-positive early-stage lung cancer (AUC >0.9).ConclusionsOur results indicate that NGS of CTC and metabolomics may provide new tumor markers for the early diagnosis of lung cancer.

Sign in / Sign up

Export Citation Format

Share Document