Recurrence risk stratification for locally advanced cervical cancer using multi-modality transformer network

Jian Wang; Yixiao Mao; Xinna Gao; Yu Zhang

doi:10.3389/fonc.2023.1100087

Recurrence risk stratification for locally advanced cervical cancer using multi-modality transformer network

Front Oncol. 2023 Feb 16:13:1100087. doi: 10.3389/fonc.2023.1100087. eCollection 2023.

Authors

Jian Wang^{1

2}, Yixiao Mao^{1

2}, Xinna Gao³, Yu Zhang^{1

2}

Affiliations

¹ School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong, China.
² Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, Guangdong, China.
³ Department of Radiation Oncology, Southern Medical University Nanfang Hospital, Guangzhou, Guangdong, China.

Abstract

Objectives: Recurrence risk evaluation is clinically significant for patients with locally advanced cervical cancer (LACC). We investigated the ability of transformer network in recurrence risk stratification of LACC based on computed tomography (CT) and magnetic resonance (MR) images.

Methods: A total of 104 patients with pathologically diagnosed LACC between July 2017 and December 2021 were enrolled in this study. All patients underwent CT and MR scanning, and their recurrence status was identified by the biopsy. We randomly divided patients into training cohort (48 cases, non-recurrence: recurrence = 37: 11), validation cohort (21 cases, non-recurrence: recurrence = 16: 5), and testing cohort (35 cases, non-recurrence: recurrence = 27: 8), upon which we extracted 1989, 882 and 315 patches for model's development, validation and evaluation, respectively. The transformer network consisted of three modality fusion modules to extract multi-modality and multi-scale information, and a fully-connected module to perform recurrence risk prediction. The model's prediction performance was assessed by six metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, f1-score, sensitivity, specificity and precision. Univariate analysis with F-test and T-test were conducted for statistical analysis.

Results: The proposed transformer network is superior to conventional radiomics methods and other deep learning networks in both training, validation and testing cohorts. Particularly, in testing cohort, the transformer network achieved the highest AUC of 0.819 ± 0.038, while four conventional radiomics methods and two deep learning networks got the AUCs of 0.680 ± 0.050, 0.720 ± 0.068, 0.777 ± 0.048, 0.691 ± 0.103, 0.743 ± 0.022 and 0.733 ± 0.027, respectively.

Conclusions: The multi-modality transformer network showed promising performance in recurrence risk stratification of LACC and may be used as an effective tool to help clinicians make clinical decisions.

Keywords: cervical cancer; deep learning; multi-modality data; recurrence risk stratification; transformer network.

Grants and funding

This work was supported in part by the National Natural Science Foundation of China under Grant 61971213 and Grant 61671230, in part by the Basic and Applied Basic Research Foundation of Guangdong Province under Grant 2019A1515010417, and in part by the Guangdong Provincial Key Laboratory of Medical Image Processing under Grant No. 2020B1212060039.