Lung cancers and pulmonary nodules detected by computed tomography scan: a population-level analysis of screening cohorts

Li, Caichen; Liao, Jing; Cheng, Bo; Li, Jianfu; Liang, Hengrui; Jiang, Yu; Su, Zhan; Xiong, Shan; Zhu, Feng; Zhao, Yi; Zhong, Ran; Li, Feng; He, Jianxing; Liang, Wenhua

doi:10.21037/atm-20-5210

Cited by 4 publications

(3 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results agree with several previous studies reporting that lung cancer more commonly affects the upper lobes, especially the right upper lobe [ 35 ]. Nodule size is also a primary determinant of malignancy [ 36 ], and the guidelines specify that a suspicious nodule with a diameter larger than 6 mm has a risk of malignancy [ 4 ]. Therefore, the minimum size of nodules in our study was 7 mm, which was smaller than in previous studies.…”

Section: Discussionmentioning

confidence: 99%

A Novel Deep Learning Model to Distinguish Malignant Versus Benign Solid Lung Nodules

Wang

Zhou

et al. 2022

Med Sci Monit

View full text Add to dashboard Cite

Background In this study we aimed to establish a new transfer learning model based on noncontrast and thin-layer computed tomography (CT) scans to distinguish between malignant and benign solid lung nodules. Material/Methods CT images from 202 patients with 210 lesions (malignant: 127, benign: 83) manifesting as solid lung nodules from January 2016 to December 2020 from 3 institutions were retrospectively collected, and each nodule was histopathologically confirmed. Two experienced thoracic radiologists reviewed all images and determined the regions of interest (ROIs) in the three-dimensional (3D) images layer-by-layer. We divided the lesions and images into training and testing sets at a ratio of 7: 3. The Inception V3 model was pretrained by the training dataset. Five-fold cross-validation was used to choose the optimal model. Receiver operator characteristic curves (ROC curves) for methods to evaluate the performance of the models were drafted. Results In the validation set, the AUC, accuracy, sensitivity, and specificity of Inception V3 model (lesion-level) were 0.999, 0.989, 0.983, and 1.0, respectively, which is higher than the image-level (0.997, 0.933, 0.922, and 0.948, respectively). The Inception V3 model (lesion-level) performed better than the image-level but there was no significant difference between the models ( P >0.05). The ResNet50 model based on image level achieved AUC, accuracy, sensitivity, and specificity of 0.963, 0.926, 0.916, and 0.944, respectively, which is lower than that of Inception V3. Conclusions Our study developed a novel deep learning model based on noncontrast and thin-layer CT scans to classify benign vs malignant lung nodules, and the Inception V3 model greatly improved the differentiation accuracy and specificity.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Deep Learning Model to Distinguish Malignant Versus Benign Solid Lung Nodules

Wang

Zhou

et al. 2022

Med Sci Monit

View full text Add to dashboard Cite

show abstract

“…Treatment rates for cases of lung adenocarcinoma diagnosed through screening surveillance further determine the population effect of the intervention [43], and practices in rural areas report higher treatment rate data, reflecting to some extent the higher availability of early treatment services; at the same time, the reasons for nontreatment are influenced by the economic conditions, perceptions, and values of specific individual families, in addition to the availability of health care resources [44][45].…”

Section: Discussionmentioning

confidence: 99%

Accessibility of lung adenocarcinoma screening in the Chinese population: an exploratory analysis

Feng,

Peng

2024

JMMR

View full text Add to dashboard Cite

Objective: Systematic quantification of the accessibility of lung adenocarcinoma screening and surveillance services in the Chinese population, with particular reference to a series of indicators in the Availability dimension. Materials and methods: With reference to the specific contents and indicators involved in the evaluation of cancer screening accessibility by international authorities, including relevant local policy programmes, coverage rates, screening participation and adherence rates and influencing factors, acceptability, and treatment rates. A systematic review approach was adopted to systematically integrate and evaluate the indicators related to lung cancer screening and surveillance in the Chinese population. Results: The literature search resulted in the inclusion of 109 publications. The results of the analysis suggest that cancer screening services in China all have recommendations and practice evaluations of lung adenocarcinoma screening protocols for general risk groups in specific regions and age groups and clear surveillance protocol recommendations for different high-risk groups identified by screening. The annual coverage of primary screening for lung adenocarcinoma is approximately 0.09% nationally among people aged 20-70 years. The overall screening participation rate averaged 53.87; the surveillance adherence rate averaged 29.4%; and the subjective acceptance of methemoglobin testing combined with LDCT spiral lung cancer screening was 98.6% among the urban population at high risk of lung adenocarcinoma in China, as suggested by the analysis of a large national sample. The treatment rate for patients with lung adenocarcinoma detected by screening surveillance in rural populations was above 95%. Conclusion: There is still much room for improvement in the accessibility of lung cancer screening in China's public health services, and the accessibility of lung cancer screening in China's public health services should be continuously improved. At the same time, studies on the accessibility of lung cancer screening in China should continue to be improved.

show abstract

“…In addition, the higher proportion of smokers in our study (47.3 versus 38.9%) may explain the higher incidence of pulmonary pathologies. Since the probability of malignancy of pulmonary nodules increases after the age of 40 years, incidental findings should be more carefully followed over this age 11 .…”

Section: Discussionmentioning

confidence: 99%

Incidental lung findings in coronary computed tomography angiography

Eldeş

Kara

2021

Rev. Assoc. Med. Bras.

View full text Add to dashboard Cite

Lung cancers and pulmonary nodules detected by computed tomography scan: a population-level analysis of screening cohorts

Cited by 4 publications

References 69 publications

A Novel Deep Learning Model to Distinguish Malignant Versus Benign Solid Lung Nodules

A Novel Deep Learning Model to Distinguish Malignant Versus Benign Solid Lung Nodules

Accessibility of lung adenocarcinoma screening in the Chinese population: an exploratory analysis

Incidental lung findings in coronary computed tomography angiography

Contact Info

Product

Resources

About