Deep-learning-assisted automatic digitization of applicators in 3D CT image-based high-dose-rate brachytherapy of gynecological cancer.

PURPOSE Applicator digitization is one of the most critical steps in 3D high-dose-rate brachytherapy (HDRBT) treatment planning. Motivated by recent advances in deep-learning, we propose a deep-learning-assisted applicator digitization method for 3D CT image-based HDRBT. This study demonstrates its feasibility and potential in gynecological cancer HDRBT. METHODS AND MATERIALS Our method consisted of two steps. The first step used a U-net to segment applicator regions. We trained the U-net using two-dimensional CT images with a tandem-and-ovoid (T&O) applicator and corresponding applicator mask images. The second step applied a spectral clustering method and a polynomial curve fitting method to extract applicator central paths. We evaluated the accuracy, efficiency, and robustness of our method in different scenarios including other T&O cases that were not used in training, a T&O case scanned with cone-beam CT, and Y-tandem and cylinder-applicator cases. RESULTS In test cases with a T&O applicator, average 3D Dice similarity coefficient between automatic and manual segmented applicator regions was 0.93. Average distance between tip positions and average Hausdorff distance between applicator channels determined by our method and manually were 0.64 mm and 0.68 mm, respectively. Although trained only using CT images of T&O cases, our tool can also digitize Y-tandem, cylinder applicator, and T&O applicator scanned in cone-beam CT with error of tip position and Hausdorff distance <1 mm. Computation time was ∼15 s per case. CONCLUSIONS We have developed a deep-learning-assisted applicator digitization tool for 3D CT image-based HDRBT of gynecological cancer. The achieved accuracy, efficiency, and robustness made our tool clinically attractive.

[1]  J. Sarkaria,et al.  High-dose-rate versus low-dose-rate brachytherapy in the treatment of cervical cancer: analysis of tumor recurrence--the University of Wisconsin experience. , 1999, International journal of radiation oncology, biology, physics.

[2]  Joshua Scheuermann,et al.  Development and evaluation of an automatic interstitial catheter digitization tool for adaptive high-dose-rate brachytherapy. , 2015, Brachytherapy.

[3]  W. McDavid,et al.  Deriving Hounsfield units using grey levels in cone beam CT: a clinical application. , 2012, Dento maxillo facial radiology.

[4]  Xun Jia,et al.  Automated high-dose rate brachytherapy treatment planning for a single-channel vaginal cylinder applicator. , 2017, Physics in medicine and biology.

[5]  Vijayan K. Asari,et al.  Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation , 2018, ArXiv.

[6]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

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

[8]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[9]  Emmanuel Racine,et al.  Fast, automatic, and accurate catheter reconstruction in HDR brachytherapy using an electromagnetic 3D tracking system. , 2014, Medical physics.

[10]  J F Williamson,et al.  Code of practice for brachytherapy physics: report of the AAPM Radiation Therapy Committee Task Group No. 56. American Association of Physicists in Medicine. , 1997, Medical physics.

[11]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[12]  C. King.  LDR vs. HDR brachytherapy for localized prostate cancer: the view from radiobiological models. , 2002, Brachytherapy.

[13]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[15]  Kari Tanderup,et al.  Reconstruction of a ring applicator using CT imaging: impact of the reconstruction method and applicator orientation , 2007, Physics in medicine and biology.

[16]  S. Majumdar,et al.  Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry. , 2018, Radiology.

[17]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

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

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  Robert A Cormack,et al.  A system to use electromagnetic tracking for the quality assurance of brachytherapy catheter digitization. , 2014, Medical physics.

[21]  D. Downey,et al.  Brachytherapy needle deflection evaluation and correction. , 2005, Medical physics.

[22]  Naoya Murakami,et al.  Dose error from deviation of dwell time and source position for high dose-rate 192Ir in remote afterloading system , 2014, Journal of radiation research.

[23]  J. Palta,et al.  Comprehensive QA for radiation oncology: report of AAPM Radiation Therapy Committee Task Group 40. , 1994, Medical physics.

[24]  Andrew B. Kahng,et al.  New spectral methods for ratio cut partitioning and clustering , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[25]  G. Hellawell,et al.  High dose rate prostate brachytherapy: an overview of the rationale, experience and emerging applications in the treatment of prostate cancer. , 2012, The British journal of radiology.

[26]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.