Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy

Jing Li; Ying Song; Yongchang Wu; Lan Liang; Guangjun Li; Sen Bai

doi:10.3389/fonc.2023.1158315

Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy

Front Oncol. 2023 Sep 5:13:1158315. doi: 10.3389/fonc.2023.1158315. eCollection 2023.

Authors

Jing Li¹, Ying Song^{1

2}, Yongchang Wu¹, Lan Liang¹, Guangjun Li¹, Sen Bai¹

Affiliations

¹ Radiotherapy Physics & Technology Center, Cancer Center, West China Hospital, Sichuan University, Chengdu, China.
² Machine Intelligence Laboratory, College of Computer Science, Chengdu, China.

Abstract

Purpose: Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer.

Methods: Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Plan_ref and Plan_test. Pearson test was used to explore the correlation between geometric metrics and dose parameters.

Results: In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Plan_ref and Plan_test, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05).

Conclusions: CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

Keywords: CNN; automatic segmentation; deep learning; radiotherapy; rectal neoplasms.

Grants and funding

This work was supported by the National Natural Science Foundation of China, grant numbers 81972848; Cancer Precision Radiotherapy Spark Program of China International Medical Foundation, grant number 2019-N-11-04; Sichuan Province Science and Technology Support Program, grant number 2021YFS0143; Sichuan University Innovation Research Project, grant number 2022SCUH0021.