scholarly journals LUNG CANCER DETECTION TECHNIQUE BASED ON SURF DESCRIPTOR AND KNN ALGORITHMS

2021 ◽  
Vol 9 (12) ◽  
pp. 64-80
Author(s):  
Karim Hussein ◽  
Dalia Shihab Ahmed
Keyword(s):  
Lung Cancer ◽  
Nearest Neighbor ◽  
Lung Cancer Screening ◽  
Diagnostic Techniques ◽  
K Nearest Neighbor ◽  
Mortality And Morbidity ◽  
System Sensitivity ◽  
Lung Cancer Patients ◽  
Technological Advances ◽  
Surf Features

In this century, lung cancer is undoubtedly one of the major serious health problems, and one of the leading causes of death for women and men worldwide. Despite advances in treating lung cancer with unprecedented products of pharmaceutical and technological advances, mortality and morbidity rates remain a major challenge for oncologists and cancer biologists. Thus, there is an urgent need to provide early, accurate, and effective diagnostic techniques to improve the survival rate and reduce morbidity and mortality related to lung cancer patients. Therefore, in this paper, an effective lung cancer screening technique is proposed for the early detection of risk factors for lung cancer. In this proposed technique, the powerful acceleration feature Speeded up robust feature (SURF) was used to extract the features. One of the machine learning methods was used to detect cancer by relying on the k nearest neighbor (KNN ) method, where the experimental results show an effective way to discover SURF features and tumor detection by relying on neighborhoods and calculating the distance using KNN. As a result, a high system sensitivity performance success rate of 96% and a system accuracy of 99% has been achieved.

scholarly journals Surgically treated lung cancer patients: do they all smoke and would they all have been detected with lung cancer screening?

2018 ◽  
Vol 4 (3) ◽  
pp. 00001-2018 ◽  
Author(s):  
Tanel Laisaar ◽  
Bruno Sarana ◽  
Indrek Benno ◽  
Kaja-Triin Laisaar
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Cancer Patients ◽  
Lung Cancer Screening ◽  
University Hospital ◽  
Smoking History ◽  
Inclusion Criteria ◽  
Lung Cancer Patients ◽  
Cancer Screening Trial ◽  
Lung Cancer Detection

Since publication of the National Lung Cancer Screening Trial (NLST) results early lung cancer detection has been widely studied, targeting individuals based on smoking history and age. However, over recent decades several changes in lung cancer epidemiology, including risk factors, have taken place. The aim of the current study was to explore smoking prevalence among lung cancer patients who had been treated surgically or undergone a diagnostic operation and whether these patients would have met the NLST inclusion criteria.All patients operated on for lung cancer in a university hospital in Estonia between 2009 and 2015 were included. Data were collected from hospital records.426 patients were operated on for lung cancer, with smoking history properly documented in 327 patients (87 females; median age 67 years). 170 (52%) patients were smokers, 97 (30%) patients were ex-smokers and 60 (18%) patients were nonsmokers. The proportion of females among smokers was 15%, among ex-smokers was 9% and among nonsmokers was 87%. 107 of our patients would not have met the NLST age criteria and 128 of our patients would not have met the NLST smoking criteria. In total, 183 patients (56% (79% of females and 48% of males)) would not have met the NLST inclusion criteria.Only half of surgically treated lung cancer patients were current smokers and more than half did not meet the NLST inclusion criteria.

scholarly journals Identification of a Blood-Based Protein Biomarker Panel for Lung Cancer Detection

Cancers ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1629 ◽  
Author(s):  
Victoria El-Khoury ◽  
Anna Schritz ◽  
Sang-Yoon Kim ◽  
Antoine Lesur ◽  
Katriina Sertamo ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Predictive Value ◽  
Characteristic Curve ◽  
Lung Cancer Screening ◽  
Disease Stage ◽  
Validation Dataset ◽  
Average Risk ◽  
Bootstrap Sampling ◽  
Lung Cancer Patients ◽  
Performance Area

Lung cancer is the deadliest cancer worldwide, mainly due to its advanced stage at the time of diagnosis. A non-invasive method for its early detection remains mandatory to improve patients’ survival. Plasma levels of 351 proteins were quantified by Liquid Chromatography-Parallel Reaction Monitoring (LC-PRM)-based mass spectrometry in 128 lung cancer patients and 93 healthy donors. Bootstrap sampling and least absolute shrinkage and selection operator (LASSO) penalization were used to find the best protein combination for outcome prediction. The PanelomiX platform was used to select the optimal biomarker thresholds. The panel was validated in 48 patients and 49 healthy volunteers. A 6-protein panel clearly distinguished lung cancer from healthy individuals. The panel displayed excellent performance: area under the receiver operating characteristic curve (AUC) = 0.999, positive predictive value (PPV) = 0.992, negative predictive value (NPV) = 0.989, specificity = 0.989 and sensitivity = 0.992. The panel detected lung cancer independently of the disease stage. The 6-protein panel and other sub-combinations displayed excellent results in the validation dataset. In conclusion, we identified a blood-based 6-protein panel as a diagnostic tool in lung cancer. Used as a routine test for high- and average-risk individuals, it may complement currently adopted techniques in lung cancer screening.

scholarly journals PROSPECTS FOR THE APPLICATION OF THE MOST MODERN METHODS OF DIAGNOSIS OF LUNG CANCER

2019 ◽  
pp. 3-7
Author(s):  
I. О. Vynnychenko ◽  
Yu. V. Moskalenko ◽  
O. І. Vynnychenko ◽  
M. Yu. Serdyuk ◽  
O. А. Ternovenko
Keyword(s):  
Lung Cancer ◽  
Lung Cancer Screening ◽  
Human Lung Cancer ◽  
Endobronchial Ultrasound ◽  
Lung Cancer Patients ◽  
Current State ◽  
Modern Methods ◽  
Screening Sensitivity ◽  
Diagnosis Of Lung Cancer

Lung cancer is one of the major causes of death from malignancies. That is why the article devoted to the issue early diagnosis of lung cancer. The objective of the work is to consider the features and prospects of using the most modern methods of diagnosis of lung cancer. The introduction of the latest technologies is essential for quality screening of lung cancer patients. Gradually, there is a growing interest in developing strategies around the world to better assess the risk of human lung cancer, increase screening sensitivity, and reduce costs. The methods of early detection of lung cancer are described in the article: determination of the concentration of volatile organic compounds (LuCID method), endobronchial ultrasound (EBUS method), FISH-marker method, basic principles of the Nano-Nose device. Despite some advances in our country in the diagnosis of lung cancer using common advanced methods of computed tomography and biopsy, the introduction of foreign experience in lung cancer screening is necessary, because the current state-of-the-art methods of diagnosis allow to detect cancer.

scholarly journals Risk Factors, Treatment and Prognosis of Patients with Lung Cancer after Heart Transplantation

Life ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1344
Author(s):  
Karsten M. Heil ◽  
Matthias Helmschrott ◽  
Fabrice F. Darche ◽  
Tom Bruckner ◽  
Philipp Ehlermann ◽  
...  
Keyword(s):  
Risk Factors ◽  
Lung Cancer ◽  
Heart Transplantation ◽  
Smoking Status ◽  
Lung Cancer Screening ◽  
Immunosuppressive Drugs ◽  
Term Survival ◽  
Lung Cancer Patients ◽  
Post Transplant ◽  
Diagnosis Of Lung Cancer

Long-term survival after heart transplantation (HTX) is impacted by adverse effects of immunosuppressive pharmacotherapy, and post-transplant lung cancer is a common occurrence. This study aimed to examine the risk factors, treatment, and prognosis of patients with post-transplant lung cancer. We included 625 adult patients who received HTX at Heidelberg Heart Center between 1989 and 2018. Patients were stratified by diagnosis and staging of lung cancer after HTX. Analysis comprised donor and recipient characteristics, medications including immunosuppressive drugs, and survival after diagnosis of lung cancer. A total of 41 patients (6.6%) were diagnosed with lung cancer after HTX, 13 patients received curative care and 28 patients had palliative care. Mean time from HTX until diagnosis of lung cancer was 8.6 ± 4.0 years and 1.8 ± 2.7 years from diagnosis of lung cancer until last follow-up. Twenty-four patients (58.5%) were switched to an mTOR-inhibitor after diagnosis of lung cancer. Multivariate analysis showed recipient age (HR: 1.05; CI: 1.01–1.10; p = 0.02), COPD (HR: 3.72; CI: 1.88–7.37; p < 0.01), and history of smoking (HR: 20.39; CI: 2.73–152.13; p < 0.01) as risk factors for post-transplant lung cancer. Patients in stages I and II had a significantly better 1-year (100.0% versus 3.6%), 2-year (69.2% versus 0.0%), and 5-year survival (53.8% versus 0.0%) than patients in stages III and IV (p < 0.01). Given the poor prognosis of late-stage post-transplant lung cancer, routine reassessment of current smoking status, providing smoking cessation support, and intensified lung cancer screening in high-risk HTX recipients are advisable.

scholarly journals Predicting Fine Particulate Matter (PM2.5) in the Greater London Area: An Ensemble Approach using Machine Learning Methods

2020 ◽  
Vol 12 (6) ◽  
pp. 914 ◽  
Author(s):  
Mahdieh Danesh Yazdi ◽  
Zheng Kuang ◽  
Konstantina Dimakopoulou ◽  
Benjamin Barratt ◽  
Esra Suel ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Nearest Neighbor ◽  
Meteorological Data ◽  
Fine Particulate Matter ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Technological Advances

Estimating air pollution exposure has long been a challenge for environmental health researchers. Technological advances and novel machine learning methods have allowed us to increase the geographic range and accuracy of exposure models, making them a valuable tool in conducting health studies and identifying hotspots of pollution. Here, we have created a prediction model for daily PM2.5 levels in the Greater London area from 1st January 2005 to 31st December 2013 using an ensemble machine learning approach incorporating satellite aerosol optical depth (AOD), land use, and meteorological data. The predictions were made on a 1 km × 1 km scale over 3960 grid cells. The ensemble included predictions from three different machine learners: a random forest (RF), a gradient boosting machine (GBM), and a k-nearest neighbor (KNN) approach. Our ensemble model performed very well, with a ten-fold cross-validated R2 of 0.828. Of the three machine learners, the random forest outperformed the GBM and KNN. Our model was particularly adept at predicting day-to-day changes in PM2.5 levels with an out-of-sample temporal R2 of 0.882. However, its ability to predict spatial variability was weaker, with a R2 of 0.396. We believe this to be due to the smaller spatial variation in pollutant levels in this area.

scholarly journals Serum Exosomes and Their miRNA Load—A Potential Biomarker of Lung Cancer

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1373
Author(s):  
Mateusz Smolarz ◽  
Piotr Widlak
Keyword(s):  
Lung Cancer ◽  
Cancer Progression ◽  
Lung Cancer Screening ◽  
Diagnostic Value ◽  
Lung Cancer Patients ◽  
Screening Programs ◽  
Potential Biomarker ◽  
Mirna Species ◽  
Molecular Components ◽  
Low Dose Computed Tomography

Early detection of lung cancer in screening programs is a rational way to reduce mortality associated with this malignancy. Low-dose computed tomography, a diagnostic tool used in lung cancer screening, generates a relatively large number of false-positive results, and its complementation with molecular biomarkers would greatly improve the effectiveness of such programs. Several biomarkers of lung cancer based on different components of blood, including miRNA signatures, were proposed. However, only a few of them have been positively validated in the context of early cancer detection yet, which imposes a constant need for new biomarker candidates. An emerging source of cancer biomarkers are exosomes and other types of extracellular vesicles circulating in body fluids. Hence, different molecular components of serum/plasma-derived exosomes were tested and showed different levels in lung cancer patients and healthy individuals. Several studies focused on the miRNA component of these vesicles. Proposed signatures of exosome miRNA had promising diagnostic value, though none of them have yet been clinically validated. These signatures involved a few dozen miRNA species overall, including a few species that recurred in different signatures. It is worth noting that all these miRNA species have cancer-related functions and have been associated with lung cancer progression. Moreover, a few of them, including known oncomirs miR-17, miR-19, miR-21, and miR-221, appeared in multiple miRNA signatures of lung cancer based on both the whole serum/plasma and serum/plasma-derived exosomes.

Assessing risk-based LDCT screening strategies versus the current USPSTF lung cancer screening recommendations at an institutional setting.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e13572-e13572
Author(s):  
Carol Velez Martinez ◽  
Aswani Thurlapati ◽  
Samina Hirani ◽  
Constance Larea Cole ◽  
Jade Abad ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
High Risk ◽  
Cancer Patients ◽  
Lung Cancer Screening ◽  
High Risk Group ◽  
Individual Risk ◽  
Screening Guidelines ◽  
Lung Cancer Patients ◽  
Individual Risk Assessment

e13572 Background: Lung cancer is the leading cause of cancer related deaths in men and women with 1.76 million deaths worldwide in 2018 [1]. Given its high prevalence and mortality, trials were developed to improve screening strategies. National-Lung-Screening-Trial showed a 20% relative-risk-reduction in mortality in people screened with annual low-dose-CT-scan [2] leading to the implementation of current USPSTF guidelines. We used USPSTF screening criteria to estimate the proportion of non-small cell lung cancer (NSCLC) patients that would have been screening-eligible at our institution.Upon chart review 33% of overall lung cancer patients at our institution did not meet the screening guidelines. We decided to investigate the need to modify the current screening guidelines of our institution based on individual risk assessment. Methods: We conducted a retrospective observational cohort study of the new diagnoses at Louisiana-State-University-Shreveport from 2011-2015. Patients were categorized into high-risk (groups 1 and 2), moderate risk, and low risk according to 2018 NCCN Lung Cancer Screening Guidelines Version 1.2020 [3]. To differentiate between high-risk group 2 and moderate risk, the Tammemagi lung cancer risk calculator was employed, considering 1.3% threshold of lung cancer risk over 6-year time frame [4]. According to NCCN, high-risk group 1 and 2 are eligible for annual low-dose-CT-scan. Results: 33% of overall lung cancer patients at our institution did not meet the screening guidelines criteria, among the 33% ineligible for screening, only 12.5% fell under the high-risk category based on the Tammemagi calculator. Conclusions: Despite using individual risk assessment based on Tammemagi calculator, 87.5% of lung cancer patients ineligible to current USPSTF guidelines are still missing the eligibility for screening at our institution. We believe more efficient risk prediction models have to be developed to improve selection of individuals for lung cancer screening.

scholarly journals Lung Cancer Screening

2015 ◽  
Vol 21 (4) ◽  
pp. 101
Author(s):  
Bronwyn Schar
Keyword(s):  
Lung Cancer ◽  
Lung Cancer Screening ◽  
Mortality And Morbidity ◽  
National Lung Screening Trial ◽  
Incurable Disease ◽  
Low Dose Computed Tomography ◽  
Global And Local ◽  
Lung Screening ◽  
Asymptomatic Disease ◽  
Related Mortality

<p>Lung cancer (LC) is the leading cause of cancer-related death worldwide. Its overall poor prognosis is attributable to the fact that most patients<br />remain asymptomatic until the disease is advanced and, therefore, present with late-stage incurable disease. e rationale for LC screening<br />is that early detection of asymptomatic disease oers the opportunity for earlier intervention, at a stage when denitive cure is still feasible,<br />which has the potential to reduce LC-related mortality and morbidity. e ndings of the National Lung Screening Trial provided the rst<br />strong evidence in support of this rationale. Since its publication, several professional organisations and societies have developed guidelines<br />recommending the implementation of LC screening with low-dose computed tomography in asymptomatic, high-risk individuals. Although<br />the benets of such screening programmes may be signicant, they must be carefully weighed against the potential harms to the relatively large<br />number of healthy individuals who would undergo screening. is review examines the available evidence and current recommendations for<br />LC screening, including benets, potentials harms and requirements for implementation of a high-quality, safe and eective programme. In<br />addition, the costs and availability of LC screening programmes in both the global and local settings are considered.</p>

Sign in / Sign up

Export Citation Format

Share Document