A multi-kernel and multi-scale learning based deep ensemble model for predicting recurrence of non-small cell lung cancer

View article
PeerJ Computer Science

Main article text

 

Introduction

Materials and Methods

Preprocessing

Proposed ensemble prediction model

2D-convolutional neural network models

Multi-model ensemble based on deep learning

Implementation details

Performance metrics

Results

Performance of the 2D-CNN model for NSCLC recurrence prediction

Performance of the proposed multi-model ensemble network

Activation mapping of deep-learning networks

Benchmark study comparison

Discussion

Conclusions

Additional Information and Declarations

Competing Interests

The authors declare there are no competing interests.

Author Contributions

Gihyeon Kim conceived and designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.

Young Mi Park conceived and designed the experiments, authored or reviewed drafts of the article, and approved the final draft.

Hyun Jung Yoon conceived and designed the experiments, authored or reviewed drafts of the article, and approved the final draft.

Jang-Hwan Choi conceived and designed the experiments, authored or reviewed drafts of the article, and approved the final draft.

Ethics

The following information was supplied relating to ethical approvals (i.e., approving body and any reference numbers):

Clinical data and computed tomography (CT) images of NSCLC patients were collected from Veterans Health Service (VHS) Medical Center under an Institutional Review Board (IRB)-approved protocol (IRB No. BOHUN-2018-09-015). A written consent was obtained from all subjects.

Data Availability

The following information was supplied regarding data availability:

The clinical and CT image dataset is available at OSF: Choi, Jang-Hwan. 2022. “LDCT.” OSF. November 15. doi:10.17605/OSF.IO/TWK96.

The source code is available at GitHub and Zenodo:

https://github.com/gyyeon/NSCLC_prediction/.

gyyeon. (2023). gyyeon/NSCLC_prediction: v1.0 (v1.0). Zenodo. https://doi.org/10.5281/zenodo.7644809.

Funding

This research was supported by the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. RS-2022-00155966, Artificial Intelligence Convergence Innovation Human Resources Development (Ewha Womans University)), the BK21 FOUR (Fostering Outstanding Universities for Research) funded by the Ministry of Education (MOE, Korea) and National Research Foundation of Korea (NRF-5199990614253, Education Research Center for 4IR-Based Health Care), the National Research Foundation of Korea (NRF-2022R1A2C1092072), and by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711174276, RS-2020-KD000016). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

3 Citations 1,751 Views 54 Downloads