scholarly journals Artificial Intelligence Tools for Refining Lung Cancer Screening

2020 ◽  
Vol 9 (12) ◽  
pp. 3860
Author(s):  
J. Luis Espinoza ◽  
Le Thanh Dong
Keyword(s):  
Artificial Intelligence ◽  
Lung Cancer ◽  
Cancer Screening ◽  
Computer Tomography ◽  
False Positive ◽  
False Positive Rate ◽  
Lung Cancer Screening ◽  
Disease Stage ◽  
Screening Programs ◽  
Positive Rate

Nearly one-quarter of all cancer deaths worldwide are due to lung cancer, making this disease the leading cause of cancer death among both men and women. The most important determinant of survival in lung cancer is the disease stage at diagnosis, thus developing an effective screening method for early diagnosis has been a long-term goal in lung cancer care. In the last decade, and based on the results of large clinical trials, lung cancer screening programs using low-dose computer tomography (LDCT) in high-risk individuals have been implemented in some clinical settings, however, this method has various limitations, especially a high false-positive rate which eventually results in a number of unnecessary diagnostic and therapeutic interventions among the screened subjects. By using complex algorithms and software, artificial intelligence (AI) is capable to emulate human cognition in the analysis, interpretation, and comprehension of complicated data and currently, it is being successfully applied in various healthcare settings. Taking advantage of the ability of AI to quantify information from images, and its superior capability in recognizing complex patterns in images compared to humans, AI has the potential to aid clinicians in the interpretation of LDCT images obtained in the setting of lung cancer screening. In the last decade, several AI models aimed to improve lung cancer detection have been reported. Some algorithms performed equal or even outperformed experienced radiologists in distinguishing benign from malign lung nodules and some of those models improved diagnostic accuracy and decreased the false-positive rate. Here, we discuss recent publications in which AI algorithms are utilized to assess chest computer tomography (CT) scans imaging obtaining in the setting of lung cancer screening.

scholarly journals Clinical Utility of a Plasma-Based miRNA Signature Classifier Within Computed Tomography Lung Cancer Screening: A Correlative MILD Trial Study

2014 ◽  
Vol 32 (8) ◽  
pp. 768-773 ◽  
Author(s):  
Gabriella Sozzi ◽  
Mattia Boeri ◽  
Marta Rossi ◽  
Carla Verri ◽  
Paola Suatoni ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Cancer Screening ◽  
Validation Study ◽  
False Positive ◽  
Diagnostic Performance ◽  
False Positive Rate ◽  
Lung Cancer Screening ◽  
Risk Groups ◽  
Positive Rate

Purpose Recent screening trial results indicate that low-dose computed tomography (LDCT) reduces lung cancer mortality in high-risk patients. However, high false-positive rates, costs, and potential harms highlight the need for complementary biomarkers. The diagnostic performance of a noninvasive plasma microRNA signature classifier (MSC) was retrospectively evaluated in samples prospectively collected from smokers within the randomized Multicenter Italian Lung Detection (MILD) trial. Patients and Methods Plasma samples from 939 participants, including 69 patients with lung cancer and 870 disease-free individuals (n = 652, LDCT arm; n = 287, observation arm) were analyzed by using a quantitative reverse transcriptase polymerase chain reaction–based assay for MSC. Diagnostic performance of MSC was evaluated in a blinded validation study that used prespecified risk groups. Results The diagnostic performance of MSC for lung cancer detection was 87% for sensitivity and 81% for specificity across both arms, and 88% and 80%, respectively, in the LDCT arm. For all patients, MSC had a negative predictive value of 99% and 99.86% for detection and death as a result of disease, respectively. LDCT had sensitivity of 79% and specificity of 81% with a false-positive rate of 19.4%. Diagnostic performance of MSC was confirmed by time dependency analysis. Combination of both MSC and LDCT resulted in a five-fold reduction of LDCT false-positive rate to 3.7%. MSC risk groups were significantly associated with survival (χ12 = 49.53; P < .001). Conclusion This large validation study indicates that MSC has predictive, diagnostic, and prognostic value and could reduce the false-positive rate of LDCT, thus improving the efficacy of lung cancer screening.

Performance of community-based lung cancer screening program in a region with a high rate of endemic histoplasmosis.

2018 ◽  
Vol 36 (30_suppl) ◽  
pp. 58-58
Author(s):  
Shruti Bhandari ◽  
Prashant Gyanendra Tripathi ◽  
Christina M Pinkston ◽  
Goetz H. Kloecker
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Screening Program ◽  
False Positive Rate ◽  
Lung Cancer Screening ◽  
Adherence Rate ◽  
Lung Cancers ◽  
Cancer Screening Program ◽  
Positive Rate ◽  
Lung Cancer Screening Program

58 Background: Lung cancer screening (LCS) with Low dose computed-tomography (LDCT) has been recommended by USPSTF for high-risk population since 2013 largely based on 20% relative reduction in lung cancer mortality shown in National Lung Screening Trial (NLST). The success of NLST was related to its high adherence rate and thorough ascertainment of lung cancers and deaths. This study evaluated performance of lung cancer screening program in Histoplasmosis endemic community. Methods: Demographic and clinical information was collected through retrospective review on all patients in the lung cancer screening program of a Kentucky health system comprising 21 centers from 2016 and 2017. A positive LDCT screen is defined as Lung-RADS version 1.0 assessment categories 3 or 4. Results: A total of 4500 LDCT screens were performed in 2016 (39%) and 2017 (61%) with 49% adherence rate to repeat annual screen in 2017. Mean age of patients was 64 years, majority being females (54%) and current smokers (69%) with average 52-pack year smoking history. The rate of positive LDCT was 13.3% (600) varying based on initial (14.6%) vs annual (9.5%) screen. A total of 70 lung cancers were diagnosed among all positive LDCT screens (11.7%) with a false positive rate of 12%. Conclusions: Comparing to NLST results updated with Lung-RADS categories, baseline positive screens in our community are similar (14.6% vs 13.6%, p = 0.15) despite being a Histoplasmosis endemic region. Our higher rate of annual positive screens (9.5% vs 6%, p < 0.001) and false positive rate (12% vs 8%, p < 0.001) may be explained by poor adherence to annual screens and an inability to thoroughly ascertain lung cancer diagnosis in all patients due to lost to follow up. In community setting with < 50% adherence to annual screens compared to 95% adherence in NLST, it is unclear if LCS mortality benefit still holds and needs intervention to increase adherence to LCS.

scholarly journals LDCT lung cancer screening in populations at different risk for lung cancer

2020 ◽  
Vol 7 (1) ◽  
pp. e000455
Author(s):  
Gustavo Borges da Silva Teles ◽  
Ana Carolina Sandoval Macedo ◽  
Rodrigo Caruso Chate ◽  
Viviane Arevalo Tabone Valente ◽  
Marcelo Buarque de Gusmao Funari ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
High Risk ◽  
Lung Cancer Risk ◽  
Risk Group ◽  
False Positive Rate ◽  
Lung Cancer Screening ◽  
Low Risk ◽  
Positive Rate ◽  
Risk Patients

IntroductionThe improvement of low-dose CT (LDCT) lung cancer screening selection criteria could help to include more individuals who have lung cancer, or in whom lung cancer will develop, while avoiding significant cost increase. We evaluated baseline results of LDCT lung cancer screening in a population with a heterogeneous risk profile for lung cancer.MethodsLDCT lung cancer screening was implemented alongside a preventive health programme in a private hospital in Brazil. Individuals older than 45 years, smokers and former smokers, regardless of tobacco exposure, were included. Patients were classified according to the National Lung Screening Trial (NLST) eligibility criteria and to PLCOm2012 6-year lung cancer risk. Patient characteristics, CT positivity rate, detection rate of lung cancer and false-positive rate were assessed.ResultsLDCT scans of 472 patients were evaluated and three lung adenocarcinomas were diagnosed. CT positivity rate (Lung-RADS 3/4) was significantly higher (p=0.019) in the NLST group (10.1% (95% CI, 5.9% to 16.9%)) than in the non-NLST group (3.6% (95% CI, 2.62% to 4.83%)) and in the PLCOm2012 high-risk group (14.3% (95% CI, 6.8% to 27.7%)) than in the PLCOm2012 low-risk group (3.7% (95% CI, 2.9% to 4.8%)) (p=0.016). Detection rate of lung cancer was also significantly higher (p=0.018) among PLCOm2012 high-risk patients (5.7% (95% CI, 2.5% to 12.6%)) than in the PLCOm2012 low-risk individuals (0.2% (95% CI, 0.1% to 1.1%)). The false-positive rate for NLST criteria (16.4% (95% CI, 13.2% to 20.1%)) was higher (p<0.001) than for PLCOm2012 criteria (7.6 (95% CI, 5.3% to 10.5%)).DiscussionOur study indicates a lower performance when screening low-risk individuals in comparison to screening patients meeting NLST criteria and PLCOm2012 high-risk patients. Also, incorporating PLCOm2012 6-year lung cancer risk ≥0.0151 as an eligibility criterion seems to increase lung cancer screening effectiveness.

scholarly journals Lung Cancer Screening, towards a Multidimensional Approach: Why and How?

Cancers ◽  
2019 ◽  
Vol 11 (2) ◽  
pp. 212 ◽  
Author(s):  
Jonathan Benzaquen ◽  
Jacques Boutros ◽  
Charles Marquette ◽  
Hervé Delingette ◽  
Paul Hofman
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
False Positive ◽  
Early Stage ◽  
False Positive Rate ◽  
Lung Cancer Screening ◽  
Target Population ◽  
High Rate ◽  
Multidisciplinary Teams ◽  
Surgical Interventions

Early-stage treatment improves prognosis of lung cancer and two large randomized controlled trials have shown that early detection with low-dose computed tomography (LDCT) reduces mortality. Despite this, lung cancer screening (LCS) remains challenging. In the context of a global shortage of radiologists, the high rate of false-positive LDCT results in overloading of existing lung cancer clinics and multidisciplinary teams. Thus, to provide patients with earlier access to life-saving surgical interventions, there is an urgent need to improve LDCT-based LCS and especially to reduce the false-positive rate that plagues the current detection technology. In this context, LCS can be improved in three ways: (1) by refining selection criteria (risk factor assessment), (2) by using Computer Aided Diagnosis (CAD) to make it easier to interpret chest CTs, and (3) by using biological blood signatures for early cancer detection, to both spot the optimal target population and help classify lung nodules. These three main ways of improving LCS are discussed in this review.

scholarly journals High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Yeshwant Reddy Chillakuru ◽  
Kyle Kranen ◽  
Vishnu Doppalapudi ◽  
Zhangyuan Xiong ◽  
Letian Fu ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Object Detection ◽  
High Precision ◽  
False Positive ◽  
False Positive Rate ◽  
Lung Nodule ◽  
Lung Cancer Screening ◽  
Radiology Reports ◽  
Axial Slice

Abstract Background Reidentification of prior nodules for temporal comparison is an important but time-consuming step in lung cancer screening. We develop and evaluate an automated nodule detector that utilizes the axial-slice number of nodules found in radiology reports to generate high precision nodule predictions. Methods 888 CTs from Lung Nodule Analysis were used to train a 2-dimensional (2D) object detection neural network. A pipeline of 2D object detection, 3D unsupervised clustering, false positive reduction, and axial-slice numbers were used to generate nodule candidates. 47 CTs from the National Lung Cancer Screening Trial (NLST) were used for model evaluation. Results Our nodule detector achieved a precision of 0.962 at a recall of 0.573 on the NLST test set for any nodule. When adjusting for unintended nodule predictions, we achieved a precision of 0.931 at a recall 0.561, which corresponds to 0.06 false positives per CT. Error analysis revealed better detection of nodules with soft tissue attenuation compared to ground glass and undeterminable attenuation. Nodule margins, size, location, and patient demographics did not differ between correct and incorrect predictions. Conclusions Utilization of axial-slice numbers from radiology reports allowed for development of a lung nodule detector with a low false positive rate compared to prior feature-engineering and machine learning approaches. This high precision nodule detector can reduce time spent on reidentification of prior nodules during lung cancer screening and can rapidly develop new institutional datasets to explore novel applications of computer vision in lung cancer imaging.

scholarly journals Cost-Effectiveness of Smoking Cessation Interventions in the Lung Cancer Screening Setting: A Simulation Study

2021 ◽  
Author(s):  
Christopher J Cadham ◽  
Pianpian Cao ◽  
Jinani Jayasekera ◽  
Kathryn L Taylor ◽  
David T Levy ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Smoking Cessation ◽  
Cost Effectiveness ◽  
Cancer Screening ◽  
Task Force ◽  
Lung Cancer Screening ◽  
Cancer Registries ◽  
Web Based ◽  
Screening Programs ◽  
Life Years

Abstract Background Guidelines recommend offering cessation interventions to smokers eligible for lung cancer screening, but there is little data comparing specific cessation approaches in this setting. We compared the benefits and costs of different smoking cessation interventions to help screening programs select specific cessation approaches. Methods We conducted a societal-perspective cost-effectiveness analysis using a Cancer Intervention and Surveillance Modeling Network model simulating individuals born in 1960 over their lifetimes. Model inputs were derived from Medicare, national cancer registries, published studies, and micro-costing of cessation interventions. We modeled annual lung cancer screening following 2014 US Preventive Services Task Force guidelines plus cessation interventions offered to current smokers at first screen, including pharmacotherapy only or pharmacotherapy with electronic and/or web-based, telephone, individual, or group counseling. Outcomes included lung cancer cases and deaths, life-years saved, quality-adjusted life-years (QALYs) saved, costs, and incremental cost-effectiveness ratios. Results Compared with screening alone, all cessation interventions decreased cases of and deaths from lung cancer. Compared incrementally, efficient cessation strategies included pharmacotherapy with either web-based cessation ($555 per QALY), telephone counseling ($7562 per QALY), or individual counseling ($35 531 per QALY). Cessation interventions continued to have costs per QALY well below accepted willingness to pay thresholds even with the lowest intervention effects and was more cost-effective in cohorts with higher smoking prevalence. Conclusion All smoking cessation interventions delivered with lung cancer screening are likely to provide benefits at reasonable costs. Because the differences between approaches were small, the choice of intervention should be guided by practical concerns such as staff training and availability.

Optimisation of volume-doubling time cutoff for fast-growing lung nodules in CT lung cancer screening reduces false-positive referrals

2013 ◽  
Vol 23 (7) ◽  
pp. 1836-1845 ◽  
Author(s):  
Marjolein A. Heuvelmans ◽  
Matthijs Oudkerk ◽  
Geertruida H. de Bock ◽  
Harry J. de Koning ◽  
Xueqian Xie ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
False Positive ◽  
Doubling Time ◽  
Lung Cancer Screening ◽  
Lung Nodules ◽  
Fast Growing ◽  
Volume Doubling Time ◽  
Volume Doubling

scholarly journals P2.11-21 Factors Predicting Attrition in Community-Based Healthcare Network Lung Cancer Screening Programs

2018 ◽  
Vol 13 (10) ◽  
pp. S786-S787
Author(s):  
K. Spiegel ◽  
J. Rayburn ◽  
C. Wilshire ◽  
E. Rauch ◽  
J. Handy ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Screening ◽  
Lung Cancer Screening ◽  
Community Based ◽  
Screening Programs ◽  
Healthcare Network
Sign in / Sign up

Export Citation Format

Share Document