Pelvic Multi-organ Segmentation on CBCT for Prostate Adaptive Radiotherapy.

BACKGROUND AND PURPOSE The purpose of this study is to develop a deep-learning based approach to simultaneously segment five pelvic organs including prostate, bladder, rectum, left and right femoral heads on cone-beam CT (CBCT), as required elements for prostate adaptive radiotherapy planning. METHODS AND MATERIALS We propose to utilize both CBCT and CBCT-based synthetic MRI (sMRI) for the segmentation of soft tissue and bony structures, as they provide complementary information for pelvic organs segmentation. CBCT images have superior bony structure contrast and sMRIs have superior soft tissue contrast. Prior to segmentation, sMRI was generated using a cycle-consistent adversarial networks (CycleGAN), which was trained using paired CBCT-MR images. To combine the advantages of both CBCT and sMRI, we developed a cross-modality attention pyramid network with late feature fusion. Our method processes CBCT and sMRI inputs separately to extract CBCT-specific and sMRI-specific features prior to combining them in a late fusion network for final segmentation. The network was trained and tested using 100 patients' datasets, with each dataset including the CBCT and manual physician contours. For comparison, we trained another two networks with different network inputs and architectures. The segmentation results were compared to manual contours for evaluations. RESULTS For the proposed method, Dice similarity coefficients (DSC) and mean surface distances (MSD) between the segmentation results and the ground truth were 0.96±0.03, 0.65±0.67mm; 0.91±0.08, 0.93±0.96mm; 0.93±0.04, 0.72±0.61mm; 0.95±0.05, 1.05±1.40mm; and 0.95±0.05, 1.08±1.48mm for bladder, prostate, rectum, left and right femoral heads, respectively. As compared to the other two competing methods, our method has shown superior performance in terms of the segmentation accuracy. CONCLUSION We developed a deep learning-based segmentation method to rapidly and accurately segment five pelvic organs simultaneously from daily CBCTs. The proposed method could be used in the clinic to support rapid target and organs-at-risk (OAR) contouring for prostate adaptive radiation therapy.

[1]  Di Yan,et al.  Adaptive radiation therapy for prostate cancer. , 2010, Seminars in radiation oncology.

[2]  J Castelli,et al.  Adaptive radiotherapy for head and neck cancer , 2018, Acta oncologica.

[3]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[4]  Xiangyang Tang,et al.  A patch-based CBCT scatter artifact correction using prior CT , 2017, Medical Imaging.

[5]  Jean-Philippe Thiran,et al.  Automatic prostate segmentation in cone-beam computed tomography images using rigid registration , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[6]  Arjan Bel,et al.  Automatic bladder segmentation on CBCT for multiple plan ART of bladder cancer using a patient-specific bladder model , 2012, Physics in medicine and biology.

[7]  Dwight E Heron,et al.  A cone beam CT-guided online plan modification technique to correct interfractional anatomic changes for prostate cancer IMRT treatment , 2009, Physics in medicine and biology.

[8]  Thomas Guerrero,et al.  A clinical 3D/4D CBCT‐based treatment dose monitoring system , 2018, Journal of applied clinical medical physics.

[9]  Yabo Fu,et al.  Deep Learning in Medical Image Registration: A Review , 2020, Physics in medicine and biology.

[10]  Diana Handrahan,et al.  Image-guided radiotherapy (IGRT) for prostate cancer comparing kV imaging of fiducial markers with cone beam computed tomography (CBCT). , 2009, International journal of radiation oncology, biology, physics.

[11]  Markus Stock,et al.  Feasibility of CBCT-based dose calculation: comparative analysis of HU adjustment techniques. , 2012, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[12]  Yang Lei,et al.  CBCT-guided Prostate Adaptive Radiotherapy with CBCT-based Synthetic MRI and CT , 2019, International Journal of Radiation Oncology*Biology*Physics.

[13]  Yang Lei,et al.  CT Prostate Segmentation Based on Synthetic MRI-aided Deep Attention Fully Convolution Network. , 2019, Medical physics.

[14]  Yang Lei,et al.  Male pelvic multi-organ segmentation aided by CBCT-based synthetic MRI , 2019, Physics in medicine and biology.

[15]  Vira Chankong,et al.  On-line re-optimization of prostate IMRT plans for adaptive radiation therapy , 2008, Physics in medicine and biology.

[16]  Nima Tajbakhsh,et al.  UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation , 2020, IEEE Transactions on Medical Imaging.

[17]  Fang-Fang Yin,et al.  On-Line Adaptive Radiation Therapy: Feasibility and Clinical Study , 2010, Journal of oncology.

[18]  Neeraj Sharma,et al.  Automated medical image segmentation techniques , 2010, Journal of medical physics.

[19]  Yang Lei,et al.  MRI-only based synthetic CT generation using dense cycle consistent generative adversarial networks. , 2019, Medical physics.

[20]  Yang Lei,et al.  Dosimetric study on learning-based cone-beam CT correction in adaptive radiation therapy. , 2019, Medical dosimetry : official journal of the American Association of Medical Dosimetrists.

[21]  T E Marchant,et al.  Accuracy of radiotherapy dose calculations based on cone-beam CT: comparison of deformable registration and image correction based methods , 2018, Physics in medicine and biology.

[22]  Steve B. Jiang,et al.  Ultrafast treatment plan optimization for volumetric modulated arc therapy (VMAT) , 2010, 1005.4396.

[23]  Turki Almatani,et al.  Automated algorithm for CBCT-based dose calculations of prostate radiotherapy with bilateral hip prostheses. , 2016, The British journal of radiology.

[24]  Mariana Guerrero,et al.  Deformable planning CT to cone-beam CT image registration in head-and-neck cancer. , 2011, Medical physics.

[25]  Christophe De Vleeschouwer,et al.  Using planning CTs to enhance CNN-based bladder segmentation on cone beam CT , 2019, Medical Imaging.

[26]  Tuathan O'Shea,et al.  Combined Ultrasound and Cone Beam CT Improves Target Segmentation for Image Guided Radiation Therapy in Uterine Cervix Cancer , 2019, International journal of radiation oncology, biology, physics.

[27]  Maria Thor,et al.  Deformable image registration for contour propagation from CT to cone-beam CT scans in radiotherapy of prostate cancer , 2011, Acta oncologica.

[28]  Yang Lei,et al.  CBCT-Based Synthetic MRI Generation for CBCT-Guided Adaptive Radiotherapy , 2019, AIRT@MICCAI.

[29]  Suqing Tian,et al.  Positioning accuracy during VMAT of gynecologic malignancies and the resulting dosimetric impact by a 6-degree-of-freedom couch in combination with daily kilovoltage cone beam computed tomography , 2015, Radiation oncology.

[30]  Jan-Jakob Sonke,et al.  Adaptive Radiotherapy for Anatomical Changes. , 2019, Seminars in radiation oncology.

[31]  Su Ruan,et al.  A review: Deep learning for medical image segmentation using multi-modality fusion , 2019, Array.

[32]  T Piotrowski,et al.  A review of cone-beam CT applications for adaptive radiotherapy of prostate cancer. , 2019, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[33]  S Wognum,et al.  Generic method for automatic bladder segmentation on cone beam CT using a patient-specific bladder shape model. , 2014, Medical physics.

[34]  Jan-Jakob Sonke,et al.  Adaptive radiotherapy for prostate cancer using kilovoltage cone-beam computed tomography: first clinical results. , 2008, International journal of radiation oncology, biology, physics.

[35]  Stefan Heldmann,et al.  Enhancing Label-Driven Deep Deformable Image Registration with Local Distance Metrics for State-of-the-Art Cardiac Motion Tracking , 2018, Bildverarbeitung für die Medizin.

[36]  Vira Chankong,et al.  Comparison of online IGRT techniques for prostate IMRT treatment: adaptive vs repositioning correction. , 2009, Medical physics.

[37]  Yaoqin Xie,et al.  Auto-propagation of contours for adaptive prostate radiation therapy , 2008, Physics in medicine and biology.

[38]  X. Gu,et al.  Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy , 2017, PloS one.

[39]  Deshan Yang,et al.  Automatic and hierarchical segmentation of the human skeleton in CT images , 2017, Physics in medicine and biology.

[40]  L. Xing,et al.  Feature-based rectal contour propagation from planning CT to cone beam CT. , 2008, Medical physics.

[41]  Richard Pötter,et al.  Feasibility of CBCT-based target and normal structure delineation in prostate cancer radiotherapy: multi-observer and image multi-modality study. , 2011, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[42]  Yabo Fu,et al.  Deep Learning in Multi-organ Segmentation , 2020, ArXiv.

[43]  Christina E. Agnew,et al.  Adaptive radiotherapy for head and neck cancer reduces the requirement for rescans during treatment due to spinal cord dose , 2019, Radiation Oncology.

[44]  Jin Hong Jung,et al.  Inter- and intra-observer variability in contouring of the prostate gland on planning computed tomography and cone beam computed tomography , 2011, Acta oncologica.