A Cross-Stitch Architecture for Joint Registration and Segmentation in Adaptive Radiotherapy

Recently, joint registration and segmentation has been formulated in a deep learning setting, by the definition of joint loss functions. In this work, we investigate joining these tasks at the architectural level. We propose a registration network that integrates segmentation propagation between images, and a segmentation network to predict the segmentation directly. These networks are connected into a single joint architecture via so-called cross-stitch units, allowing information to be exchanged between the tasks in a learnable manner. The proposed method is evaluated in the context of adaptive image-guided radiotherapy, using daily prostate CT imaging. Two datasets from different institutes and manufacturers were involved in the study. The first dataset was used for training (12 patients) and validation (6 patients), while the second dataset was used as an independent test set (14 patients). In terms of mean surface distance, our approach achieved $1.06 \pm 0.3$ mm, $0.91 \pm 0.4$ mm, $1.27 \pm 0.4$ mm, and $1.76 \pm 0.8$ mm on the validation set and $1.82 \pm 2.4$ mm, $2.45 \pm 2.4$ mm, $2.45 \pm 5.0$ mm, and $2.57 \pm 2.3$ mm on the test set for the prostate, bladder, seminal vesicles, and rectum, respectively. The proposed multi-task network outperformed single-task networks, as well as a network only joined through the loss function, thus demonstrating the capability to leverage the individual strengths of the segmentation and registration tasks. The obtained performance as well as the inference speed make this a promising candidate for daily re-contouring in adaptive radiotherapy, potentially reducing treatment-related side effects and improving quality-of-life after treatment.

[1]  Liyuan Liu,et al.  On the Variance of the Adaptive Learning Rate and Beyond , 2019, ICLR.

[2]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[3]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[4]  Dinggang Shen,et al.  BIRNet: Brain image registration using dual‐supervised fully convolutional networks , 2018, Medical Image Anal..

[5]  Martial Hebert,et al.  Cross-Stitch Networks for Multi-task Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[7]  Marius Staring,et al.  Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer , 2019, Medical physics.

[8]  Marc Niethammer,et al.  DeepAtlas: Joint Semi-Supervised Learning of Image Registration and Segmentation , 2019, MICCAI.

[9]  Yuchuan Qiao,et al.  Fast optimization methods for image registration in adaptive radiation therapy , 2017 .

[10]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[11]  Dwarikanath Mahapatra,et al.  Joint Registration And Segmentation Of Xray Images Using Generative Adversarial Networks , 2018, MLMI@MICCAI.

[12]  Marius Staring,et al.  Adversarial optimization for joint registration and segmentation in prostate CT radiotherapy , 2019, MICCAI.

[13]  W. Eric L. Grimson,et al.  A Bayesian model for joint segmentation and registration , 2006, NeuroImage.

[14]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[15]  Anthony J. Yezzi,et al.  A variational framework for integrating segmentation and registration through active contours , 2003, Medical Image Anal..