Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Nov 12;4(1):1286.
doi: 10.1038/s42003-021-02814-7.

Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans

Hwan-Ho Cho  1   2 , Ho Yun Lee  3   4 , Eunjin Kim  1   2 , Geewon Lee  5 , Jonghoon Kim  1 , Junmo Kwon  1   2 , Hyunjin Park  6   7
Affiliations

Radiomics-guided deep neural networks stratify lung adenocarcinoma prognosis from CT scans

Hwan-Ho Cho et al. Commun Biol. .

Abstract

Deep learning (DL) is a breakthrough technology for medical imaging with high sample size requirements and interpretability issues. Using a pretrained DL model through a radiomics-guided approach, we propose a methodology for stratifying the prognosis of lung adenocarcinomas based on pretreatment CT. Our approach allows us to apply DL with smaller sample size requirements and enhanced interpretability. Baseline radiomics and DL models for the prognosis of lung adenocarcinomas were developed and tested using local (n = 617) cohort. The DL models were further tested in an external validation (n = 70) cohort. The local cohort was divided into training and test cohorts. A radiomics risk score (RRS) was developed using Cox-LASSO. Three pretrained DL networks derived from natural images were used to extract the DL features. The features were further guided using radiomics by retaining those DL features whose correlations with the radiomics features were high and Bonferroni-corrected p-values were low. The retained DL features were subject to a Cox-LASSO when constructing DL risk scores (DRS). The risk groups stratified by the RRS and DRS showed a significant difference in training, testing, and validation cohorts. The DL features were interpreted using existing radiomics features, and the texture features explained the DL features well.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1. Overall workflow of the study.
(a) Three major procedures used in this study. (b) Graphical description of DL feature selection guided by radiomics used for prognosis.
Fig. 2
Fig. 2. Kaplan–Meier plots of the baseline radiomics model.
a Kaplan–Meier plot of training cohort, hazard ratio of 4.1384 (95% CI of 1.9140–8.9479), p-value of 0.0006, C-index of 0.7459. b Kaplan–Meier plot of test cohort, hazard ratio of 5.0566 (95% CI of 1.5379–16.6263), p-value of 0.0180, and C-index of 0.6837.
Fig. 3
Fig. 3. Kaplan–Meier plots of radiomics-guided DL (Yolo) model.
a Kaplan–Meier plot of training cohort, hazard ratio of 3.1728 (95% CI of 1.4675–6.8596), p-value of 0.0061, and C-index of 0.7994. b Kaplan–Meier plot of test cohort, hazard ratio of 7.6277 (95% CI of 2.2870–25.4399), p-value of 0.0027, and C-index of 0.7593. c Kaplan–Meier plot of validation cohort, hazard ratio of 6.5362 (95% CI of 2.1773–19.6213), p-value of 0.0022, and C-index of 0.7696.
Fig. 4
Fig. 4. Comparison of different proportions of radiomics features in five categories associated with the prognostic DL features for the three networks.
The five categories are shape (in blue), first-order (in orange), GLCM (in gray), GLSZM (in yellow), and margin (in light blue) categories. a Yolo network. b DenseNet. c VGG.
See this image and copyright information in PMC

References

    1. Travis WD, et al. International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society International Multidisciplinary Classification of Lung Adenocarcinoma. J. Thorac. Oncol. 2011;6:244–285. - PMC - PubMed
    1. Russell PA, et al. Does lung adenocarcinoma subtype predict patient survival?: A clinicopathologic study based on the new international association for the study of lung cancer/American thoracic society/European respiratory society international multidisciplinary lung adenocarcinoma classification. J. Thorac. Oncol. 2011;6:1496–1504. - PubMed
    1. Warth A, et al. The novel histologic International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society classification system of lung adenocarcinoma is a stage-independent predictor of survival. J. Clin. Oncol. 2012;30:1438–1446. - PubMed
    1. Yoshizawa A, et al. Impact of proposed IASLC/ATS/ERS classification of lung adenocarcinoma: Prognostic subgroups and implications for further revision of staging based on analysis of 514 stage i cases. Mod. Pathol. 2011;24:653–664. - PubMed
    1. Ito M, et al. Second predominant subtype predicts outcomes of intermediatemalignant invasive lung adenocarcinoma. Eur. J. Cardio-Thorac. Surg. 2017;51:218–222. - PubMed

Publication types