Comparison of computed tomography image features extracted by radiomics, self-supervised learning and end-to-end deep learning for outcome prediction of oropharyngeal cancer

Baoqiang Ma; Jiapan Guo; Hung Chu; Lisanne V van Dijk; Peter M A van Ooijen; Johannes A Langendijk; Stefan Both; Nanna M Sijtsema

doi:10.1016/j.phro.2023.100502

Comparison of computed tomography image features extracted by radiomics, self-supervised learning and end-to-end deep learning for outcome prediction of oropharyngeal cancer

Phys Imaging Radiat Oncol. 2023 Nov 7:28:100502. doi: 10.1016/j.phro.2023.100502. eCollection 2023 Oct.

Authors

Baoqiang Ma¹, Jiapan Guo^{1

2

3}, Hung Chu^{1

2

4}, Lisanne V van Dijk^{1

5}, Peter M A van Ooijen^{1

2}, Johannes A Langendijk¹, Stefan Both¹, Nanna M Sijtsema¹

Affiliations

¹ Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, Groningen, Netherlands.
² Machine Learning Lab, Data Science Center in Health (DASH), Groningen, Netherlands.
³ Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence , University of Groningen, Groningen, Netherlands.
⁴ Center for Information Technology, University of Groningen ,Groningen, Netherlands.
⁵ Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX USA.

Abstract

Background and purpose: To compare the prediction performance of image features of computed tomography (CT) images extracted by radiomics, self-supervised learning and end-to-end deep learning for local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), tumor-specific survival (TSS), overall survival (OS) and disease-free survival (DFS) of oropharyngeal squamous cell carcinoma (OPSCC) patients after (chemo)radiotherapy.

Methods and materials: The OPC-Radiomics dataset was used for model development and independent internal testing and the UMCG-OPC set for external testing. Image features were extracted from the Gross Tumor Volume contours of the primary tumor (GTVt) regions in CT scans when using radiomics or a self-supervised learning-based method (autoencoder). Clinical and combined (radiomics, autoencoder or end-to-end) models were built using multivariable Cox proportional-hazard analysis with clinical features only and both clinical and image features for LC, RC, LRC, DMFS, TSS, OS and DFS prediction, respectively.

Results: In the internal test set, combined autoencoder models performed better than clinical models and combined radiomics models for LC, RC, LRC, DMFS, TSS and DFS prediction (largest improvements in C-index: 0.91 vs. 0.76 in RC and 0.74 vs. 0.60 in DMFS). In the external test set, combined radiomics models performed better than clinical and combined autoencoder models for all endpoints (largest improvements in LC, 0.82 vs. 0.71). Furthermore, combined models performed better in risk stratification than clinical models and showed good calibration for most endpoints.

Conclusions: Image features extracted using self-supervised learning showed best internal prediction performance while radiomics features have better external generalizability.

Keywords: Deep learning; Oropharynx carcinoma; Prognostic modeling; Radiomics; Self-supervised learning.