Boundary-Weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation

Overview

Journal IEEE Trans Med Imaging

Date 2019 Aug 20

PMID 31425022

Citations 31

Authors

Qikui Zhu

Bo Du

Pingkun Yan

Affiliations

Soon will be listed here.

Abstract

Accurate segmentation of the prostate from magnetic resonance (MR) images provides useful information for prostate cancer diagnosis and treatment. However, automated prostate segmentation from 3D MR images faces several challenges. The lack of clear edge between the prostate and other anatomical structures makes it challenging to accurately extract the boundaries. The complex background texture and large variation in size, shape and intensity distribution of the prostate itself make segmentation even further complicated. Recently, as deep learning, especially convolutional neural networks (CNNs), emerging as the best performed methods for medical image segmentation, the difficulty in obtaining large number of annotated medical images for training CNNs has become much more pronounced than ever. Since large-scale dataset is one of the critical components for the success of deep learning, lack of sufficient training data makes it difficult to fully train complex CNNs. To tackle the above challenges, in this paper, we propose a boundary-weighted domain adaptive neural network (BOWDA-Net). To make the network more sensitive to the boundaries during segmentation, a boundary-weighted segmentation loss is proposed. Furthermore, an advanced boundary-weighted transfer leaning approach is introduced to address the problem of small medical imaging datasets. We evaluate our proposed model on three different MR prostate datasets. The experimental results demonstrate that the proposed model is more sensitive to object boundaries and outperformed other state-of-the-art methods.

Citing Articles

ETDformer: an effective transformer block for segmentation of intracranial hemorrhage.

Gong W, Luo Y, Yang F, Zhou H, Lin Z, Cai C Med Biol Eng Comput. 2025; .

PMID: 40019706 DOI: 10.1007/s11517-025-03333-x.

Domain adaptation using AdaBN and AdaIN for high-resolution IVD mesh reconstruction from clinical MRI.

Natarajan S, Humbert L, Ballester M Int J Comput Assist Radiol Surg. 2024; 19(10):2063-2068.

PMID: 39002098 DOI: 10.1007/s11548-024-03233-9.

Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation.

Xu Y, Xie S, Reynolds M, Ragoza M, Gong M, Batmanghelich K Med Image Comput Comput Assist Interv. 2024; 13437:671-681.

PMID: 38859913 PMC: 11164048. DOI: 10.1007/978-3-031-16449-1_64.

Catalyzing Precision Medicine: Artificial Intelligence Advancements in Prostate Cancer Diagnosis and Management.

Talyshinskii A, Hameed B, Ravinder P, Naik N, Randhawa P, Shah M Cancers (Basel). 2024; 16(10).

PMID: 38791888 PMC: 11119252. DOI: 10.3390/cancers16101809.

Deep Learning Prostate MRI Segmentation Accuracy and Robustness: A Systematic Review.

Fassia M, Balasubramanian A, Woo S, Vargas H, Hricak H, Konukoglu E Radiol Artif Intell. 2024; 6(4):e230138.

PMID: 38568094 PMC: 11294957. DOI: 10.1148/ryai.230138.

References

Guo Y, Gao Y, Shen D . Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching. IEEE Trans Med Imaging. 2015; 35(4):1077-89. PMC: 5002995. DOI: 10.1109/TMI.2015.2508280. View

Mahmood F, Chen R, Durr N . Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training. IEEE Trans Med Imaging. 2018; 37(12):2572-2581. DOI: 10.1109/TMI.2018.2842767. View

Gao Y, Sandhu R, Fichtinger G, Tannenbaum A . A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE Trans Med Imaging. 2010; 29(10):1781-94. PMC: 2988404. DOI: 10.1109/TMI.2010.2052065. View

Pinto P, Chung P, Rastinehad A, Baccala Jr A, Kruecker J, Benjamin C . Magnetic resonance imaging/ultrasound fusion guided prostate biopsy improves cancer detection following transrectal ultrasound biopsy and correlates with multiparametric magnetic resonance imaging. J Urol. 2011; 186(4):1281-5. PMC: 3193933. DOI: 10.1016/j.juro.2011.05.078. View

Goetz M, Weber C, Binczyk F, Polanska J, Tarnawski R, Bobek-Billewicz B . DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images. IEEE Trans Med Imaging. 2015; 35(1):184-96. DOI: 10.1109/TMI.2015.2463078. View

Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X . Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Trans Med Imaging. 2018; 37(6):1348-1357. PMC: 6021013. DOI: 10.1109/TMI.2018.2827462. View

Gao Z, Li Y, Sun Y, Yang J, Xiong H, Zhang H . Motion Tracking of the Carotid Artery Wall From Ultrasound Image Sequences: a Nonlinear State-Space Approach. IEEE Trans Med Imaging. 2017; 37(1):273-283. DOI: 10.1109/TMI.2017.2746879. View

Tian Z, Liu L, Zhang Z, Fei B . PSNet: prostate segmentation on MRI based on a convolutional neural network. J Med Imaging (Bellingham). 2018; 5(2):021208. PMC: 5771127. DOI: 10.1117/1.JMI.5.2.021208. View

Shen D, Zhan Y, Davatzikos C . Segmentation of prostate boundaries from ultrasound images using statistical shape model. IEEE Trans Med Imaging. 2003; 22(4):539-51. DOI: 10.1109/TMI.2003.809057. View

10.

Wang W, Shen J, Shao L . Video Salient Object Detection via Fully Convolutional Networks. IEEE Trans Image Process. 2017; 27(1):38-49. DOI: 10.1109/TIP.2017.2754941. View

11.

Azizi S, Bayat S, Yan P, Tahmasebi A, Kwak J, Xu S . Deep Recurrent Neural Networks for Prostate Cancer Detection: Analysis of Temporal Enhanced Ultrasound. IEEE Trans Med Imaging. 2018; 37(12):2695-2703. PMC: 7983161. DOI: 10.1109/TMI.2018.2849959. View

12.

Shin H, Roth H, Gao M, Lu L, Xu Z, Nogues I . Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging. 2016; 35(5):1285-98. PMC: 4890616. DOI: 10.1109/TMI.2016.2528162. View

13.

Jiang J, Hu Y, Tyagi N, Zhang P, Rimner A, Mageras G . Tumor-aware, Adversarial Domain Adaptation from CT to MRI for Lung Cancer Segmentation. Med Image Comput Comput Assist Interv. 2018; 11071:777-785. PMC: 6169798. DOI: 10.1007/978-3-030-00934-2_86. View

14.

Wang S, He K, Nie D, Zhou S, Gao Y, Shen D . CT male pelvic organ segmentation using fully convolutional networks with boundary sensitive representation. Med Image Anal. 2019; 54:168-178. PMC: 6506162. DOI: 10.1016/j.media.2019.03.003. View

15.

van Opbroek A, Ikram M, Vernooij M, De Bruijne M . Transfer learning improves supervised image segmentation across imaging protocols. IEEE Trans Med Imaging. 2014; 34(5):1018-30. DOI: 10.1109/TMI.2014.2366792. View

16.

Yan P, Cao Y, Yuan Y, Turkbey B, Choyke P . Label image constrained multiatlas selection. IEEE Trans Cybern. 2014; 45(6):1158-68. PMC: 8323590. DOI: 10.1109/TCYB.2014.2346394. View

17.

Tian Z, Liu L, Zhang Z, Fei B . Superpixel-Based Segmentation for 3D Prostate MR Images. IEEE Trans Med Imaging. 2015; 35(3):791-801. PMC: 4831070. DOI: 10.1109/TMI.2015.2496296. View

18.

Shan H, Zhang Y, Yang Q, Kruger U, Kalra M, Sun L . 3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network. IEEE Trans Med Imaging. 2018; 37(6):1522-1534. PMC: 6022756. DOI: 10.1109/TMI.2018.2832217. View

19.

Fedorov A, Schwier M, Clunie D, Herz C, Pieper S, Kikinis R . An annotated test-retest collection of prostate multiparametric MRI. Sci Data. 2018; 5:180281. PMC: 6278692. DOI: 10.1038/sdata.2018.281. View