Lung cancer screening: Computed tomography or chest radiographs?

Beek, Edwin Jacques Rudolph van; Mirsadraee, Saeed; Murchison, John T

doi:10.4329/wjr.v7.i8.189

Cited by 37 publications

(22 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lung cancer screening is performed by radiologists through the analysis of computer tomography (CT), chest X‐ray (CXR) or sputum cytology samples . Screening with low‐dose CT has better detection rate compared to screening with CXR .…”

Section: Introductionmentioning

confidence: 99%

“…For instance, the exposure to CT ionizing radiation may increase the risk of cancer in patients, and the usage of low‐dose CT has higher false‐positive rate than CXR screening. Therefore, it requires further investigation and also additional costs . On the other hand, lung cancer screening with CXR is cheaper, as previously mentioned.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, lung cancer screening with CXR is cheaper, as previously mentioned. Furthermore, screening with CXR can be improved when radiologists use computer‐aided detection (CAD) systems in clinical routine . Thus, the potential role of CXR on lung cancer screening motivates research efforts to improve the effectiveness of CAD systems in CXR, and to measure the impact of these systems on the performance of radiologists.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection and classification of lung nodules in chest X‐ray images using deep convolutional neural networks

Mendoza

Pedrini

2019

Computational Intelligence

View full text Add to dashboard Cite

Lung nodule classification is one of the main topics related to computer‐aided detection systems. Although convolutional neural networks (CNNs) have been demonstrated to perform well on many tasks, there are few explorations of their use for classifying lung nodules in chest X‐ray (CXR) images. In this work, we proposed and analyzed a pipeline for detecting lung nodules in CXR images that includes lung area segmentation, potential nodule localization, and nodule candidate classification. We presented a method for classifying nodule candidates with a CNN trained from the scratch. The effectiveness of our method relies on the selection of data augmentation parameters, the design of a specialized CNN architecture, the use of dropout regularization on the network, inclusive in convolutional layers, and addressing the lack of nodule samples compared to background samples balancing mini‐batches on each stochastic gradient descent iteration. All model selection decisions were taken using a CXR subset of the Lung Image Database Consortium and Image Database Resource Initiative dataset separately. Thus, we used all images with nodules in the Japanese Society of Radiological Technology dataset for evaluation. Our experiments showed that CNNs were capable of achieving competitive results when compared to state‐of‐the‐art methods. Our proposal obtained an area under the free‐response receiver operating characteristic curve of 7.76 considering 10 false positives per image (FPPI), and sensitivity values of 73.1% and 79.6% with 2 and 5 FPPI, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and classification of lung nodules in chest X‐ray images using deep convolutional neural networks

Mendoza

Pedrini

2019

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…In countries with scarce logistics and/or financial resources, low-dose CT screening referrals will be subject to available resources. 39 It should be taken into account that, when a patient undergoes chest CT, this might mean that there is a health concern, which is a motivator and an opportunity for smoking cessation. 40 …”

Section: Diagnostic Procedures That Can Be Useful For Smoking Cessatimentioning

confidence: 99%

Smoking control: challenges and achievements

Silva

Araújo

Queiroz³

et al. 2016

J. bras. pneumol.

View full text Add to dashboard Cite

Smoking is the most preventable and controllable health risk. Therefore, all health care professionals should give their utmost attention to and be more focused on the problem of smoking. Tobacco is a highly profitable product, because of its large-scale production and great number of consumers. Smoking control policies and treatment resources for smoking cessation have advanced in recent years, showing highly satisfactory results, particularly in Brazil. However, there is yet a long way to go before smoking can be considered a controlled disease from a public health standpoint. We can already perceive that the behavior of our society regarding smoking is changing, albeit slowly. Therefore, pulmonologists have a very promising area in which to work with their patients and the general population. We must act with greater impetus in support of health care policies and social living standards that directly contribute to improving health and quality of life. In this respect, pulmonologists can play a greater role as they get more involved in treating smokers, strengthening anti-smoking laws, and demanding health care policies related to lung diseases.

show abstract

“…Topics of trans-TUS are displayed in several handbooks[ 126 , 127 ], which are also available as e-books. The question of the possible use of TUS as a screening tool is the same question of lung CT[ 128 , 129 ] as a screening tool for lung cancer: Population and individuals at risk should be screened, but the use of TUS as a tool useful for addressing earlier more in depth CT controls is a matter of active current investigation[ 83 , 116 ].…”

Section: Chest Radiology and Ultrasound: What Who Where When Whymentioning

confidence: 99%

Thoracic ultrasound: An adjunctive and valuable imaging tool in emergency, resource-limited settings and for a sustainable monitoring of patients

Trovato¹,

Catalano²,

Trovato³

2016

WJR

View full text Add to dashboard Cite

Imaging workup of patients referred for elective assessment of chest disease requires an articulated approach: Imaging is asked for achieving timely diagnosis. The concurrent or subsequent use of thoracic ultrasound (TUS) with conventional (chest X-rays-) and more advanced imaging procedures (computed tomography and magnetic resonance imaging) implies advantages, limitations and actual problems. Indeed, despite TUS may provide useful imaging of pleura, lung and heart disease, emergency scenarios are currently the most warranted field of application of TUS: Pleural effusion, pneumothorax, lung consolidation. This stems from its role in limited resources subsets; actually, ultrasound is an excellent risk reducing tool, which acts by: (1) increasing diagnostic certainty; (2) shortening time to definitive therapy; and (3) decreasing problems from blind procedures that carry an inherent level of complications. In addition, paediatric and newborn disease are particularly suitable for TUS investigation, aimed at the detection of congenital or acquired chest disease avoiding, limiting or postponing radiological exposure. TUS improves the effectiveness of elective medical practice, in resource-limited settings, in small point of care facilities and particularly in poorer countries. Quality and information provided by the procedure are increased avoiding whenever possible artefacts that can prevent or mislead the achievement of the correct diagnosis. Reliable monitoring of patients is possible, taking into consideration that appropriate expertise, knowledge, skills, training, and even adequate equipment’s suitability are not always and everywhere affordable or accessible. TUS is complementary imaging procedure for the radiologist and an excellent basic diagnostic tool suitable to be shared with pneumologists, cardiologists and emergency physicians.

show abstract

Lung cancer screening: Computed tomography or chest radiographs?

Cited by 37 publications

References 39 publications

Detection and classification of lung nodules in chest X‐ray images using deep convolutional neural networks

Detection and classification of lung nodules in chest X‐ray images using deep convolutional neural networks

Smoking control: challenges and achievements

Thoracic ultrasound: An adjunctive and valuable imaging tool in emergency, resource-limited settings and for a sustainable monitoring of patients

Contact Info

Product

Resources

About