Literature DB >> 29766373

Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models.

Davood Karimi1, Golnoosh Samei2, Claudia Kesch3, Guy Nir4, Septimiu E Salcudean2.   

Abstract

PURPOSE: Most of the existing convolutional neural network (CNN)-based medical image segmentation methods are based on methods that have originally been developed for segmentation of natural images. Therefore, they largely ignore the differences between the two domains, such as the smaller degree of variability in the shape and appearance of the target volume and the smaller amounts of training data in medical applications. We propose a CNN-based method for prostate segmentation in MRI that employs statistical shape models to address these issues.
METHODS: Our CNN predicts the location of the prostate center and the parameters of the shape model, which determine the position of prostate surface keypoints. To train such a large model for segmentation of 3D images using small data (1) we adopt a stage-wise training strategy by first training the network to predict the prostate center and subsequently adding modules for predicting the parameters of the shape model and prostate rotation, (2) we propose a data augmentation method whereby the training images and their prostate surface keypoints are deformed according to the displacements computed based on the shape model, and (3) we employ various regularization techniques.
RESULTS: Our proposed method achieves a Dice score of 0.88, which is obtained by using both elastic-net and spectral dropout for regularization. Compared with a standard CNN-based method, our method shows significantly better segmentation performance on the prostate base and apex. Our experiments also show that data augmentation using the shape model significantly improves the segmentation results.
CONCLUSIONS: Prior knowledge about the shape of the target organ can improve the performance of CNN-based segmentation methods, especially where image features are not sufficient for a precise segmentation. Statistical shape models can also be employed to synthesize additional training data that can ease the training of large CNNs.

Entities:  

Keywords:  Convolutional neural networks; Deep learning; Medical image segmentation; Prostate segmentation; Statistical shape models

Mesh:

Year:  2018        PMID: 29766373     DOI: 10.1007/s11548-018-1785-8

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  9 in total

1.  Multifeature landmark-free active appearance models: application to prostate MRI segmentation.

Authors:  Robert Toth; Anant Madabhushi
Journal:  IEEE Trans Med Imaging       Date:  2012-05-30       Impact factor: 10.048

2.  Automated segmentation of the prostate in 3D MR images using a probabilistic atlas and a spatially constrained deformable model.

Authors:  Sébastien Martin; Jocelyne Troccaz; Vincent Daanenc
Journal:  Med Phys       Date:  2010-04       Impact factor: 4.071

3.  Point set registration: coherent point drift.

Authors:  Andriy Myronenko; Xubo Song
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2010-12       Impact factor: 6.226

4.  Prostate MRI segmentation using learned semantic knowledge and graph cuts.

Authors:  Dwarikanath Mahapatra; Joachim M Buhmann
Journal:  IEEE Trans Biomed Eng       Date:  2013-11-06       Impact factor: 4.538

5.  Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information.

Authors:  Stefan Klein; Uulke A van der Heide; Irene M Lips; Marco van Vulpen; Marius Staring; Josien P W Pluim
Journal:  Med Phys       Date:  2008-04       Impact factor: 4.071

Review 6.  Statistical shape models for 3D medical image segmentation: a review.

Authors:  Tobias Heimann; Hans-Peter Meinzer
Journal:  Med Image Anal       Date:  2009-05-27       Impact factor: 8.545

Review 7.  A survey on deep learning in medical image analysis.

Authors:  Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez
Journal:  Med Image Anal       Date:  2017-07-26       Impact factor: 8.545

8.  Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge.

Authors:  Geert Litjens; Robert Toth; Wendy van de Ven; Caroline Hoeks; Sjoerd Kerkstra; Bram van Ginneken; Graham Vincent; Gwenael Guillard; Neil Birbeck; Jindang Zhang; Robin Strand; Filip Malmberg; Yangming Ou; Christos Davatzikos; Matthias Kirschner; Florian Jung; Jing Yuan; Wu Qiu; Qinquan Gao; Philip Eddie Edwards; Bianca Maan; Ferdinand van der Heijden; Soumya Ghose; Jhimli Mitra; Jason Dowling; Dean Barratt; Henkjan Huisman; Anant Madabhushi
Journal:  Med Image Anal       Date:  2013-12-25       Impact factor: 8.545

9.  Brain tumor segmentation with Deep Neural Networks.

Authors:  Mohammad Havaei; Axel Davy; David Warde-Farley; Antoine Biard; Aaron Courville; Yoshua Bengio; Chris Pal; Pierre-Marc Jodoin; Hugo Larochelle
Journal:  Med Image Anal       Date:  2016-05-19       Impact factor: 8.545

  9 in total
  13 in total

1.  Segmentation of the Prostate Transition Zone and Peripheral Zone on MR Images with Deep Learning.

Authors:  Michelle Bardis; Roozbeh Houshyar; Chanon Chantaduly; Karen Tran-Harding; Alexander Ushinsky; Chantal Chahine; Mark Rupasinghe; Daniel Chow; Peter Chang
Journal:  Radiol Imaging Cancer       Date:  2021-05

2.  Automatic zonal segmentation of the prostate from 2D and 3D T2-weighted MRI and evaluation for clinical use.

Authors:  Dimitri Hamzaoui; Sarah Montagne; Raphaële Renard-Penna; Nicholas Ayache; Hervé Delingette
Journal:  J Med Imaging (Bellingham)       Date:  2022-03-14

3.  Integration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images.

Authors:  Massimo Salvi; Bruno De Santi; Bianca Pop; Martino Bosco; Valentina Giannini; Daniele Regge; Filippo Molinari; Kristen M Meiburger
Journal:  J Imaging       Date:  2022-05-11

4.  Transfer learning in medical image segmentation: New insights from analysis of the dynamics of model parameters and learned representations.

Authors:  Davood Karimi; Simon K Warfield; Ali Gholipour
Journal:  Artif Intell Med       Date:  2021-04-23       Impact factor: 7.011

5.  A systematic comparison of generative models for medical images.

Authors:  Hristina Uzunova; Matthias Wilms; Nils D Forkert; Heinz Handels; Jan Ehrhardt
Journal:  Int J Comput Assist Radiol Surg       Date:  2022-02-07       Impact factor: 3.421

Review 6.  Applications of Artificial Intelligence to Prostate Multiparametric MRI (mpMRI): Current and Emerging Trends.

Authors:  Michelle D Bardis; Roozbeh Houshyar; Peter D Chang; Alexander Ushinsky; Justin Glavis-Bloom; Chantal Chahine; Thanh-Lan Bui; Mark Rupasinghe; Christopher G Filippi; Daniel S Chow
Journal:  Cancers (Basel)       Date:  2020-05-11       Impact factor: 6.639

7.  Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology.

Authors:  Deepa Darshini Gunashekar; Lars Bielak; Leonard Hägele; Benedict Oerther; Matthias Benndorf; Anca-L Grosu; Thomas Brox; Constantinos Zamboglou; Michael Bock
Journal:  Radiat Oncol       Date:  2022-04-02       Impact factor: 4.309

8.  Variability in accuracy of prostate cancer segmentation among radiologists, urologists, and scientists.

Authors:  Michael Y Chen; Maria A Woodruff; Prokar Dasgupta; Nicholas J Rukin
Journal:  Cancer Med       Date:  2020-08-18       Impact factor: 4.452

9.  Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net.

Authors:  Nader Aldoj; Federico Biavati; Florian Michallek; Sebastian Stober; Marc Dewey
Journal:  Sci Rep       Date:  2020-08-31       Impact factor: 4.379

10.  Automatic contouring system for cervical cancer using convolutional neural networks.

Authors:  Dong Joo Rhee; Anuja Jhingran; Bastien Rigaud; Tucker Netherton; Carlos E Cardenas; Lifei Zhang; Sastry Vedam; Stephen Kry; Kristy K Brock; William Shaw; Frederika O'Reilly; Jeannette Parkes; Hester Burger; Nazia Fakie; Chris Trauernicht; Hannah Simonds; Laurence E Court
Journal:  Med Phys       Date:  2020-10-09       Impact factor: 4.071

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.