Fully automated pelvic bone segmentation in multiparameteric MRI using a 3D convolutional neural network

Insights into Imaging

Xiang Liu¹  Yingpu Cui¹  Xiaoying Wang¹  Jingyun Wu¹  He Wang¹  Chao Han¹  Xiaodong Zhang¹ 

[1] Department of Radiology, Peking University First Hospital, No.8 Xishiku Street, Xicheng District, 100034, Beijing, China;

关键词: Pelvic bones;    Segmentation;    Multiparametric magnetic resonance imaging;    Convolutional neural network;    Deep learning;   

DOI  :  10.1186/s13244-021-01044-z

来源: Springer

【 摘 要 】

BackgroundAccurate segmentation of pelvic bones is an initial step to achieve accurate detection and localisation of pelvic bone metastases. This study presents a deep learning-based approach for automated segmentation of normal pelvic bony structures in multiparametric magnetic resonance imaging (mpMRI) using a 3D convolutional neural network (CNN).MethodsThis retrospective study included 264 pelvic mpMRI data obtained between 2018 and 2019. The manual annotations of pelvic bony structures (which included lumbar vertebra, sacrococcyx, ilium, acetabulum, femoral head, femoral neck, ischium, and pubis) on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images were used to create reference standards. A 3D U-Net CNN was employed for automatic pelvic bone segmentation. Additionally, 60 mpMRI data from 2020 were included and used to evaluate the model externally.ResultsThe CNN achieved a high Dice similarity coefficient (DSC) average in both testing (0.80 [DWI images] and 0.85 [ADC images]) and external (0.79 [DWI images] and 0.84 [ADC images]) validation sets. Pelvic bone volumes measured with manual and CNN-predicted segmentations were highly correlated (R2 value of 0.84–0.97) and in close agreement (mean bias of 2.6–4.5 cm3). A SCORE system was designed to qualitatively evaluate the model for which both testing and external validation sets achieved high scores in terms of both qualitative evaluation and concordance between two readers (ICC = 0.904; 95% confidence interval: 0.871–0.929).ConclusionsA deep learning-based method can achieve automated pelvic bone segmentation on DWI and ADC images with suitable quantitative and qualitative performance.

【 授权许可】

CC BY