Reducing uncertainty in cancer risk estimation for patients with indeterminate pulmonary nodules using an integrated deep learning model

Gao, Riqiang; Li, Thomas; Tang, Yucheng; Xu, Kaiwen; Khan, Mirza S.; Kammer, Michael N.; Antic, Sanja; Deppen, Steve; Huo, Yuankai; Lasko, Thomas A.; Sandler, Kim L.; Maldonado, Fabien; Landman, Bennett A.

doi:10.1016/j.compbiomed.2022.106113

Cited by 6 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of the MAYO clinic risk score with hs-Cyfra 21-1 and a radiomics risk score could for example reduce the number of participants requiring invasive procedures from 62.9% to 50.6% in a cohort (n = 456) recalibrated to a prevalence of LC of 0.33 [57]. Similar approaches of radiomics and blood-based biomarkers [58,59] or based on multiple proteins [60] are under development. These strategies have not directly been evaluated against image-based approaches such as volume doubling time (VDT) of pulmonary nodules.…”

Section: Combinations Of Blood-based Biomarkersmentioning

confidence: 99%

Screening approaches for lung cancer by blood-based biomarkers: Challenges and opportunities

Broek

Groen

2024

TUB

View full text Add to dashboard Cite

Lung cancer (LC) is one of the leading causes for cancer-related deaths in the world, accounting for 28% of all cancer deaths in Europe. Screening for lung cancer can enable earlier detection of LC and reduce lung cancer mortality as was demonstrated in several large image-based screening studies such as the NELSON and the NLST. Based on these studies, screening is recommended in the US and in the UK a targeted lung health check program was initiated. In Europe lung cancer screening (LCS) has not been implemented due to limited data on cost-effectiveness in the different health care systems and questions on for example the selection of high-risk individuals, adherence to screening, management of indeterminate nodules, and risk of overdiagnosis. Liquid biomarkers are considered to have a high potential to address these questions by supporting pre- and post- Low Dose CT (LDCT) risk-assessment thereby improving the overall efficacy of LCS. A wide variety of biomarkers, including cfDNA, miRNA, proteins and inflammatory markers have been studied in the context of LCS. Despite the available data, biomarkers are currently not implemented or evaluated in screening studies or screening programs. As a result, it remains an open question which biomarker will actually improve a LCS program and do this against acceptable costs. In this paper we discuss the current status of different promising biomarkers and the challenges and opportunities of blood-based biomarkers in the context of lung cancer screening.

show abstract

Section: Combinations Of Blood-based Biomarkersmentioning

confidence: 99%

Screening approaches for lung cancer by blood-based biomarkers: Challenges and opportunities

Broek

Groen

2024

TUB

View full text Add to dashboard Cite

show abstract

“…Additionally, many models exhibit poor generalization when dealing with datasets from different distributions, which is particularly evident in multicenter studies. These issues limit the application and effectiveness of deep learning methods in actual clinical environments [15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Accuracy Study on Deep Learning-Based CT Image Analysis for Lung Nodule Detection and Classification

Cheng,

Li,

et al. 2024

View full text Add to dashboard Cite

Early detection and accurate classification of lung nodules are crucial for the treatment of lung cancer. With the widespread application of deep learning technologies in medical imaging analysis, significant progress has been made in the automatic detection and classification of lung nodules from computed tomography (CT) images. However, existing deep learning approaches often face challenges with limited annotated data and generalization across diverse datasets. To address these challenges, this study introduces two innovative methods: a domain-adaptive adversarial network for joint segmentation of lung CT images to enhance model generalization, and an improved deep propagation generation network (DPGN) for few-shot classification of lung CT images to reduce reliance on extensive annotated data. Through these methods, this research aims to improve the accuracy of lung nodule detection and classification, providing more reliable support for clinical diagnosis.

show abstract

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis

Wulaningsih,

Villamaria,

Akram

et al. 2024

Lung

View full text Add to dashboard Cite

Background There has been growing interest in using artificial intelligence/deep learning (DL) to help diagnose prevalent diseases earlier. In this study we sought to survey the landscape of externally validated DL-based computer-aided diagnostic (CADx) models, and assess their diagnostic performance for predicting the risk of malignancy in computed tomography (CT)-detected pulmonary nodules. Methods An electronic search was performed in four databases (from inception to 10 August 2023). Studies were eligible if they were peer-reviewed experimental or observational articles comparing the diagnostic performance of externally validated DL-based CADx models with models widely used in clinical practice to predict the risk of malignancy. A bivariate random-effect approach for the meta-analysis on the included studies was used. Results Seventeen studies were included, comprising 8553 participants and 9884 nodules. Pooled analyses showed DL-based CADx models were 11.6% more sensitive than physician judgement alone, and 14.5% more than clinical risk models alone. They had a similar pooled specificity to physician judgement alone [0.77 (95% CI 0.68–0.84) v 0.81 (95% CI 0.71–0.88)], and were 7.4% more specific than clinical risk models alone. They had superior pooled areas under the receiver operating curve (AUC), with relative pooled AUCs of 1.03 (95% CI 1.00–1.07) and 1.10 (95% CI 1.07–1.13) versus physician judgement and clinical risk models alone, respectively. Conclusion DL-based models are already used in clinical practice in certain settings for nodule management. Our results show their diagnostic performance potentially justifies wider, more routine deployment alongside experienced physician readers to help inform multidisciplinary team decision-making.

show abstract

Reducing uncertainty in cancer risk estimation for patients with indeterminate pulmonary nodules using an integrated deep learning model

Cited by 6 publications

References 31 publications

Screening approaches for lung cancer by blood-based biomarkers: Challenges and opportunities

Screening approaches for lung cancer by blood-based biomarkers: Challenges and opportunities

Accuracy Study on Deep Learning-Based CT Image Analysis for Lung Nodule Detection and Classification

Deep Learning Models for Predicting Malignancy Risk in CT-Detected Pulmonary Nodules: A Systematic Review and Meta-analysis

Contact Info

Product

Resources

About