Deep learning analysis to predict EGFR mutation status in lung adenocarcinoma manifesting as pure ground-glass opacity nodules on CT

Yoon, Haesung; Choi, J.; Kim, Eun Jin; Um, Sang‐Won; Kang, Noeul; Kim, Wook; Kim, Geena; Park, Hyunjin; Lee, Ho Yun

doi:10.3389/fonc.2022.951575

Cited by 6 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other similar studies have shown a similar utility of DL models with improvements in the AUC when combined with clinical parameters [ 25 , 26 , 27 , 28 ]. Further, a study on the PET/CT fusion algorithm using a dataset of 150 patients showed a prediction accuracy of EGFR and non-EGFR mutations of 86.25% in the training dataset and 81.92% in the validation set [ 29 ].…”

Section: Discussionmentioning

confidence: 63%

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging

Mahajan,

Kania,

Agarwal

et al. 2024

Cancers

View full text Add to dashboard Cite

Purpose: The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models and radiomic signatures to predict the EGFR mutation in patients with NSCLC, and to assess the semantic and clinical features that can contribute to detecting EGFR mutations. Methods: Using 990 patients from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses and nodules. Results: The combined radiomics and DLR model achieved an AUC of 0.88 ± 0.03 in predicting EGFR mutation status, outperforming individual models. Semantic features further improved the model’s accuracy, with an AUC of 0.88 ± 0.05. CT semantic features that were found to be significantly associated with EGFR mutations were pure solid tumours with no associated ground glass component (p < 0.03), the absence of peripheral emphysema (p < 0.03), the presence of pleural retraction (p = 0.004), the presence of fissure attachment (p = 0.001), the presence of metastatic nodules in both the tumour-containing lobe (p = 0.001) and the non-tumour-containing lobe (p = 0.001), the presence of ipsilateral pleural effusion (p = 0.04), and average enhancement of the tumour mass above 54 HU (p < 0.001). Conclusions: This AI-based radiomics and DLR model demonstrated high accuracy in predicting EGFR mutation, serving as a non-invasive and user-friendly imaging biomarker for EGFR mutation status prediction.

show abstract

Section: Discussionmentioning

confidence: 63%

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging

Mahajan,

Kania,

Agarwal

et al. 2024

Cancers

View full text Add to dashboard Cite

show abstract

“…They also suggested that deep learning models can assist radiologists in determining benign and malignant GGNs ( 89 ). Our group also investigated the possibility of deep learning analysis to predict EGFR mutation status in lung adenocarcinoma manifesting as pGGNs ( 92 ). In our study, the AUC of the clinical only and deep learning with clinical models to predict EGFR mutations were 0.50 and 0.85, respectively.…”

Section: Role Of Artificial Intelligence (Ai) Tools In Ssnsmentioning

confidence: 99%

A narrative review of the clinical approach to subsolid pulmonary nodules

Kim¹,

Um²

2023

Ann Transl Med

Self Cite

View full text Add to dashboard Cite

Background and Objective The widespread use of chest computed tomography (CT) for lung cancer screening has led to increased detection of subsolid pulmonary nodules. The management of subsolid nodules (SSNs) is challenging since they are likely to grow slowly and a long-term follow-up is needed. In this review, we discuss the characteristics, natural history, genetic features, surveillance, and management of SSNs. Methods PubMed and Google Scholar were searched to identify relevant articles published in English between January 1998 and December 2022 using the following keywords: “subsolid nodule”, “ground-glass nodule (GGN)”, and “part-solid nodule (PSN)”. Key Content and Findings The differential diagnosis of SSNs includes transient inflammatory lesions, focal fibrosis, and premalignant or malignant lesions. Long-term CT surveillance follow-up is needed to manage SSNs that persist for >3 months. Although most SSNs have an indolent clinical course, PSNs may have a more aggressive clinical course than pure GGNs. The proportion of growth and the time to grow is higher and shorter in PSN than pure GGN. In lung adenocarcinoma manifesting as SSNs, EGFR mutations were the major driver mutations. Guidelines are available for the management of incidentally detected and screening-detected SSNs. The size, solidity, location, and number of SSNs are important factors in determining the need for surveillance and surgical resection, as well as the interval of follow-up. Positron emission tomography/CT and brain magnetic resonance imaging (MRI) are not recommended for the diagnosis of SSNs, especially for pure GGNs. Periodic CT surveillance and lung-sparing surgery are the main strategies for the management of persistent SSNs. Nonsurgical treatment options for persistent SSNs include stereotactic body radiotherapy (SBRT) and radiofrequency ablation (RFA). For multifocal SSNs, the timing of repeated CT scans and the need for surgical treatment are decided based on the most dominant SSN(s). Conclusions The SSN is a heterogeneous disease and a personalized medicine approach is required in the future. Future studies of SSNs should focus on their natural history, optimal follow-up duration, genetic features, and surgical and nonsurgical treatments to improve the corresponding clinical management. All these efforts will lead to the personalized medicine approach for the SSNs.

show abstract

Deep learning in radiology for lung cancer diagnostics: A systematic review of classification, segmentation, and predictive modeling techniques

Atmakuru,

Chakraborty,

Faust

et al. 2024

Expert Systems with Applications

View full text Add to dashboard Cite

Deep learning analysis to predict EGFR mutation status in lung adenocarcinoma manifesting as pure ground-glass opacity nodules on CT

Cited by 6 publications

References 39 publications

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging

A narrative review of the clinical approach to subsolid pulmonary nodules

Deep learning in radiology for lung cancer diagnostics: A systematic review of classification, segmentation, and predictive modeling techniques

Contact Info

Product

Resources

About