Auto-Segmentation Ultrasound-Based Radiomics Technology to Stratify Patient With Diabetic Kidney Disease: A Multi-Center Retrospective Study

Jifan Chen; Peile Jin; Yue Song; Liting Feng; Jiayue Lu; Hongjian Chen; Lei Xin; Fuqiang Qiu; Zhang Cong; Jiaxin Shen; Yanan Zhao; Wen Xu; Chenxi Cai; Yan Zhou; Jinfeng Yang; Chao Zhang; Qin Chen; Xiang Jing; Pintong Huang

doi:10.3389/fonc.2022.876967

Auto-Segmentation Ultrasound-Based Radiomics Technology to Stratify Patient With Diabetic Kidney Disease: A Multi-Center Retrospective Study

Front Oncol. 2022 Jul 4:12:876967. doi: 10.3389/fonc.2022.876967. eCollection 2022.

Authors

Jifan Chen¹, Peile Jin^{1

2}, Yue Song^{1

2}, Liting Feng³, Jiayue Lu⁴, Hongjian Chen^{1

2

5}, Lei Xin^{1

2}, Fuqiang Qiu^{1

2}, Zhang Cong^{1

2}, Jiaxin Shen^{1

2}, Yanan Zhao^{1

2}, Wen Xu^{1

2}, Chenxi Cai⁶, Yan Zhou⁷, Jinfeng Yang⁶, Chao Zhang^{1

2}, Qin Chen³, Xiang Jing⁷, Pintong Huang^{1

2

8}

Affiliations

¹ Department of Ultrasound in Medicine, The Second Affiliated Hospital of Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China.
² Ultrasound in Medicine and Biomedical Engineering Research Center, The Second Affiliated Hospital of Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China.
³ Department of Ultrasound, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu, China.
⁴ Department of Clinical Laboratory, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
⁵ Post-Doctoral Research Center, Hangzhou Supor South Ocean Pharmaceutical Co., Ltd, Hangzhou, China.
⁶ Department of Ultrasound, The People's Hospital of Yinshang, Anhui, China.
⁷ Department of Ultrasound, Tianjin Third Central Hospital, Tianjin, China.
⁸ Research Center for Life Science and Human Health, Binjiang Institute of Zhejiang University, Hangzhou, China.

Abstract

Background: An increasing proportion of patients with diabetic kidney disease (DKD) has been observed among incident hemodialysis patients in large cities, which is consistent with the continuous growth of diabetes in the past 20 years.

Purpose: In this multicenter retrospective study, we developed a deep learning (DL)-based automatic segmentation and radiomics technology to stratify patients with DKD and evaluate the possibility of clinical application across centers.

Materials and methods: The research participants were enrolled retrospectively and separated into three parts: training, validation, and independent test datasets for further analysis. DeepLabV3+ network, PyRadiomics package, and least absolute shrinkage and selection operator were used for segmentation, extraction of radiomics variables, and regression, respectively.

Results: A total of 499 patients from three centers were enrolled in this study including 246 patients with type II diabetes mellitus (T2DM) and 253 patients with DKD. The mean intersection-over-union (Miou) and mean pixel accuracy (mPA) of automatic segmentation of the data from the three medical centers were 0.812 ± 0.003, 0.781 ± 0.009, 0.805 ± 0.020 and 0.890 ± 0.004, 0.870 ± 0.002, 0.893 ± 0.007, respectively. The variables from the renal parenchyma and sinus provided different information for the diagnosis and follow-up of DKD. The area under the curve (AUC) of the radiomics model for differentiating between DKD and T2DM patients was 0.674 ± 0.074 and for differentiating between the high and low stages of DKD was 0.803 ± 0.037.

Conclusion: In this study, we developed a DL-based automatic segmentation, radiomics technology to stratify patients with DKD. The DL technology was proposed to achieve fast and accurate anatomical-level segmentation in the kidney, and an ultrasound-based radiomics model can achieve high diagnostic performance in the diagnosis and follow-up of patients with DKD.

Keywords: deep learning; diabetic kidney disease; multicenter; radiomics; ultrasound.