Fully-Automatic Segmentation Of Kidneys In Clinical Ultrasound Images Using A Boundary Distance Regression Network

It remains challenging to automatically segment kidneys in clinical ultrasound images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we developed a novel boundary distance regression deep neural network to segment the kidneys, informed by the fact that the kidney boundaries are relatively consistent across images in terms of their appearance. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from ultrasound images, then these feature maps are used as input to learn kidney boundary distance maps using a boundary distance regression network, and finally the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixel classification network in an end-to-end learning fashion. Experimental results have demonstrated that our method could effectively improve the performance of automatic kidney segmentation, significantly better than deep learning based pixel classification networks.

[1]  D. Canning,et al.  Renal parenchymal area and risk of ESRD in boys with posterior urethral valves. , 2014, Clinical journal of the American Society of Nephrology : CJASN.

[2]  Hariharan Ravishankar,et al.  Learning and Incorporating Shape Models for Semantic Segmentation , 2017, MICCAI.

[3]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Wenyu Liu,et al.  DeepMitosis: Mitosis detection via deep detection, verification and segmentation networks , 2018, Medical Image Anal..

[5]  Nassir Navab,et al.  Semi-Automatic Segmentation of Autosomal Dominant Polycystic Kidneys using Random Forests , 2015, ArXiv.

[6]  Qiang Zheng,et al.  A dynamic graph-cuts method with integrated multiple feature maps for segmenting kidneys in ultrasound images , 2017, Academic radiology.

[7]  Marius George Linguraru,et al.  Segmentation of kidney in 3D-ultrasound images using Gabor-based appearance models , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[8]  Hariharan Ravishankar,et al.  Joint Deep Learning of Foreground, Background and Shape for Robust Contextual Segmentation , 2017, IPMI.

[9]  Tomas Kron,et al.  Deep Learning Renal Segmentation for Fully Automated Radiation Dose Estimation in Unsealed Source Therapy , 2018, Front. Oncol..

[10]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[11]  Yong Fan,et al.  A deep learning model integrating FCNNs and CRFs for brain tumor segmentation , 2017, Medical Image Anal..

[12]  Qiang Zheng,et al.  Transfer learning for diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[13]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Rémi Cuingnet,et al.  Fast kidney detection and segmentation with learned kernel convolution and model deformation in 3D ultrasound images , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[15]  Carlos S. Mendoza,et al.  Automatic Analysis of Pediatric Renal Ultrasound Using Shape, Anatomical and Image Acquisition Priors , 2013, MICCAI.

[16]  Yong Fan,et al.  3D Brain Tumor Segmentation Through Integrating Multiple 2D FCNNs , 2017, BrainLes@MICCAI.

[17]  Jun Xie,et al.  Segmentation of kidney from ultrasound images based on texture and shape priors , 2005, IEEE Transactions on Medical Imaging.

[18]  Marius George Linguraru,et al.  Renal Segmentation From 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes , 2016, IEEE Transactions on Medical Imaging.

[19]  Marcos Martín-Fernández,et al.  An approach for contour detection of human kidneys from ultrasound images using Markov random fields and active contours , 2005, Medical Image Anal..

[20]  Nassir Navab,et al.  Automatic Segmentation of Kidneys using Deep Learning for Total Kidney Volume Quantification in Autosomal Dominant Polycystic Kidney Disease , 2017, Scientific Reports.