Advertisement

Approaching automated applicator digitization from a new angle: Using sagittal images to improve deep learning accuracy and robustness in high-dose-rate prostate brachytherapy

      Abstract

      PURPOSE

      To automate the segmentation of treatment applicators on computed tomography (CT) images for high-dose-rate (HDR) brachytherapy prostate patients implanted with titanium needles with the goals of improving plan quality and reducing the patient's time under anesthesia.

      METHODS

      The investigation was performed using 57 retrospective, interstitial prostate treatments randomly assigned to training (n = 27), validation (n = 10), and testing (n = 20). Unique to this work, the CT image set was reformatted into 2D sagittal slices instead of the default axial orientation. A deep learning-based segmentation was performed using a 2D U-Net architecture followed by a density-based linkage clustering algorithm to classify individual catheters in 3D. Potential confounders, such as gold seeds and conjoined applicators with intersecting needle geometries, were corrected using a customized polynomial fitting algorithm. The geometric agreement of the automated digitization was evaluated against the clinically treated manual digitization to measure tip and shaft errors in the reconstruction.

      RESULTS

      The proposed algorithm achieved tip and shaft agreements of -0.1 ± 0.6 mm (range -1.8 mm to 1.4 mm) and 0.13 ± 0.09 mm (maximum 0.96 mm), respectively on a data set with 20 patients and 353 total needles. Our method was able to separate all intersecting applicators reliably. The time to generate the automated applicator digitization averaged approximately 1 min.

      CONCLUSIONS

      Using sagittal instead of axial images for 2D segmentation of interstitial brachytherapy applicators produced submillimeter agreement with manual segmentation. The automated digitization of interstitial applicators in prostate brachytherapy has the potential to improve quality and consistency while reducing the patient's time under anesthesia.

      Keywords

      Abbreviations:

      CT (computed tomorgraphy), HDR (high-dose rate), US (ultrasound), MR (magnetic resonance), DICOM (digital imaging communication in medicine)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Brachytherapy
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Siegel Rebecca L.
        • Miller Kimberly D.
        • Ahmedin Jemal
        Cancer statistics, 2020.
        CA Cancer J Clin. 2020; 70: 7-30
        • Kari Tanderup
        • Taran Paulsen Hellebust
        • Stefan Lang
        • et al.
        Consequences of random and systematic reconstruction uncertainties in 3D image based brachytherapy in cervical cancer.
        Radiother Oncol. 2008; 89: 156-163
        • Hai Hu
        • Yang Shao
        • Shijie Hu
        A review of the application of deep learning in brachytherapy.
        OALib. 2020; 07: 1-9
        • Kirisits Christian
        • Rivard Mark J.
        • Baltas Dimos
        • et al.
        Review of clinical brachytherapy uncertainties: Analysis guidelines of GEC-ESTRO and the AAPM.
        Radiother Oncol. 2014; 110: 199-212
        • May Whitaker
        • George Hruby
        • Aimee Lovett
        • et al.
        Prostate HDR brachytherapy catheter displacement between planning and treatment delivery.
        Radiother Oncol. 2011; 101: 490-494
        • Milickovic N.
        • Baltas D.
        • Giannouli S.
        • et al.
        A new algorithm for autoreconstruction of catheters in computed tomography-based brachytherapy treatment planning.
        IEEE Trans Biomed Eng. 2001; 48: 372-383
        • Yue Zhao
        • Christian Cachard
        • Hervé Liebgott
        Automatic needle detection and tracking in 3D ultrasound using an ROI-based RANSAC and Kalman method.
        Ultrasonic Imaging. 2013; 35: 283-306
        • Hyunuk Jung
        • Yesenia Gonzalez
        • Chenyang Shen
        • et al.
        Deep-learning–assisted automatic digitization of applicators in 3D CT image-based high-dose-rate brachytherapy of gynecological cancer.
        Brachytherapy. 2019; 18: 841-851
        • Christoffer Andersén
        • Tobias Rydén
        • Per Thunberg
        • et al.
        Deep learning-based digitization of prostate brachytherapy needles in ultrasound images.
        Med Phys. 2020; 47: 6414-6420
        • Zhang D.
        • Yang Z.
        • Jiang S.
        • et al.
        Automatic segmentation and applicator reconstruction for CT-based brachytherapy of cervical cancer using 3D convolutional neural networks.
        J Appl Clin Med Phys. 2020; 21: 158-169
        • Zhang Y.
        • He X.
        • Tian Z.
        • et al.
        Multi-needle detection in 3D ultrasound images using unsupervised order-graph regularized sparse dictionary learning.
        IEEE Trans Med Imaging. 2020; 39: 2302-2315
        • Zhang Y.
        • Lei Y.
        • Qiu R.L.J.
        • et al.
        Multi-needle localization with attention U-Net in US-guided HDR prostate brachytherapy.
        Med Phys. 2020; 47: 2735-2745
        • Yupei Zhang
        • Zhen Tian
        • Yang Lei
        • et al.
        Automatic multi-needle localization in ultrasound images using large margin mask RCNN for ultrasound-guided prostate brachytherapy.
        Phys Med Biol. 2020; 65205003
        • Mahdi Hashemi
        Enlarging smaller images before inputting into convolutional neural network: Zero-padding vs. interpolation.
        J Big Data. 2019; 6: 1-13
        • Olaf Ronneberger
        • Philipp Fischer
        • Thomas Brox
        U-Net: Convolutional networks for biomedical image segmentation.
        Lecture notes in computer science. Springer International Publishing, New York City2015: 234-241
        • Deufel Christopher L.
        • Tian Shulan
        • Yan Benjamin B.
        • et al.
        Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering.
        Brachytherapy. 2020; 19: 111-118
        • Leland McInnes
        • John Healy
        • Steve Astels
        hdbscan: Hierarchical density based clustering.
        J Open Source Software. 2017; 2: 205
        • Gillies Derek J.
        • Rodgers Jessica R.
        • Gyacskov Igor
        • et al.
        Deep learning segmentation of general interventional tools in two-dimensional ultrasound images.
        Med Phys. 2020; 47: 4956-4970
        • Xingjun Ma
        • Yuhao Niu
        • Lin Gu
        • et al.
        Understanding adversarial attacks on deep learning based medical image analysis systems.
        Pattern Recognit. 2021; 110107332
        • Albert Tiong
        • Sean Bydder
        • Martin Ebert
        • et al.
        A small tolerance for catheter displacement in high–dose rate prostate brachytherapy is necessary and feasible.
        Int J Radiat Oncol Biol Phys. 2010; 76: 1066-1072