LDCT image biomarkers that matter most for the deep learning classification of indeterminate pulmonary nodules-Reference-Cited by-同舟云学术

LDCT image biomarkers that matter most for the deep learning classification of indeterminate pulmonary nodules

Published:2024-05-22 Issue: Volume: Page:1-10
ISSN:1875-8592
Container-title:Cancer Biomarkers
language:
Short-container-title:CBM

Author:

Masquelin Axel H.¹,Cheney Nick²,José Estépar Raúl San³,Bates Jason H.T.⁴,Kinsey C. Matthew⁵

Affiliation:

1. Electrical and Biomedical Engineering, University of Vermont, Burlington, VT, USA

2. Computer Science, University of Vermont, Burlington, VT, USA

3. Department of Radiology, Brigham and Women’s Hospital, Somerville, MA, USA

4. Department of Medicine, College of Medicine, University of Vermont, Burlington, VT, USA

5. Department of Medicine, Pulmonary and Critical Care, College of Medicine, University of Vermont, Burlington, VT, USA

Abstract

BACKGROUND: Continued improvement in deep learning methodologies has increased the rate at which deep neural networks are being evaluated for medical applications, including diagnosis of lung cancer. However, there has been limited exploration of the underlying radiological characteristics that the network relies on to identify lung cancer in computed tomography (CT) images. OBJECTIVE: In this study, we used a combination of image masking and saliency activation maps to systematically explore the contributions of both parenchymal and tumor regions in a CT image to the classification of indeterminate lung nodules. METHODS: We selected individuals from the National Lung Screening Trial (NLST) with solid pulmonary nodules 4–20 mm in diameter. Segmentation masks were used to generate three distinct datasets; 1) an Original Dataset containing the complete low-dose CT scans from the NLST, 2) a Parenchyma-Only Dataset in which the tumor regions were covered by a mask, and 3) a Tumor-Only Dataset in which only the tumor regions were included. RESULTS: The Original Dataset significantly outperformed the Parenchyma-Only Dataset and the Tumor-Only Dataset with an AUC of 80.80 ± 3.77% compared to 76.39 ± 3.16% and 78.11 ± 4.32%, respectively. Gradient-weighted class activation mapping (Grad-CAM) of the Original Dataset showed increased attention was being given to the nodule and the tumor-parenchyma boundary when nodules were classified as malignant. This pattern of attention remained unchanged in the case of the Parenchyma-Only Dataset. Nodule size and first-order statistical features of the nodules were significantly different with the average malignant and benign nodule maximum 3d diameter being 23 mm and 12 mm, respectively. CONCLUSION: We conclude that network performance is linked to textural features of nodules such as kurtosis, entropy and intensity, as well as morphological features such as sphericity and diameter. Furthermore, textural features are more positively associated with malignancy than morphological features.

Publisher

IOS Press

Reference41 articles.

1. Y. Wu et al., Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, ArXiv160908144 Cs (2016). http://arxiv.org/abs/1609.08144 (accessed November 2, 2021).

2. Deep Residual Learning for Image Recognition

3. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

4. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography;Ardila;Nat. Med.,2019

5. B. Kim et al., Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV), ArXiv171111279 Stat. (2018). http://arxiv.org/abs/1711.11279 (accessed May 13, 2021).