Advertisement

Knowledge-based three-dimensional dose prediction for tandem-and-ovoid brachytherapy

      ABSTRACT

      PURPOSE

      The purpose of this work was to develop a knowledge-based dose prediction system using a convolution neural network (CNN) for cervical brachytherapy treatments with a tandem-and-ovoid applicator.

      METHODS

      A 3D U-NET CNN was utilized to make voxel-wise dose predictions based on organ-at-risk (OAR), high-risk clinical target volume (HRCTV), and possible source location geometry. The model comprised 395 previously treated cases: training (273), validation (61), test (61). To assess voxel prediction accuracy, we evaluated dose differences in all cohorts across the dose range of 20−130% of prescription, mean (SD) and standard deviation ( σ ) , as well as isodose dice similarity coefficients for clinical and/or predicted dose distributions. We examined discrete Dose-Volume Histogram (DVH) metrics utilized for brachytherapy plan quality assessment (HRCTV D90%; bladder, rectum, and sigmoid D2cc) with Δ D x = D x , a c t u a l D x , p r e d i c t e d mean, standard deviation, and Pearson correlation coefficient further quantifying model performance.

      RESULTS

      Ranges of voxel-wise dose difference accuracy ( δ D ¯ ± σ ) for 20−130% dose interval in training (test) sets ranged from [-0.5% ± 2.0% to +2.0% ± 14.0%] ([-0.1% ± 4.0% to +4.0% ± 26.0%]) in all voxels, [-1.7% ± 5.1% to -3.5% ± 12.8%] ([-2.9% ± 4.8% to -2.6% ± 18.9%]) in HRCTV, [-0.02% ± 2.40% to +3.2% ± 12.0%] ([-2.5% ± 3.6% to +0.8% ± 12.7%]) in bladder, [-0.7% ± 2.4% to +15.5% ± 11.0%] ([-0.9% ± 3.2% to +27.8% ± 11.6%]) in rectum, and [-0.7% ± 2.3% to +10.7% ± 15.0%] ([-0.4% ± 3.0% to +18.4% ± 11.4%]) in sigmoid. Isodose dice similarity coefficients ranged from [0.96,0.91] for training and [0.94,0.87] for test cohorts. Relative DVH metric prediction in the training (test) set were HRCTV Δ D ¯ 90 ± σ Δ D  = -0.19 ± 0.55Gy (-0.09 ± 0.67 Gy), bladder Δ D ¯ 2 c c ± σ Δ D = -0.06 ± 0.54Gy (-0.17 ± 0.67 Gy), rectum Δ D ¯ 2 c c ± σ Δ D = -0.03 ± 0.36Gy (-0.04 ± 0.46 Gy), and sigmoid Δ D ¯ 2 c c ± σ Δ D = -0.01 ± 0.34Gy (0.00 ± 0.44 Gy).

      CONCLUSIONS

      A 3D knowledge-based dose predictions provide voxel-level and DVH metric estimates that could be used for treatment plan quality control and data-driven plan guidance.

      Keywords

      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

        • Mayadev J.
        • Viswanathan A.
        • Liu Y.
        • et al.
        American Brachytherapy Task Group Report: a pooled analysis of clinical outcomes for high-dose-rate brachytherapy for cervical cancer.
        Brachytherapy. 2017; 16: 22-43
      1. Hanks GE, Herring DF, Kramer S.Patterns of Care Outcome Studies Results of the National Practice in Cancer of the Cervix. 2022.

        • Eifel P.J.
        • Moughan J.
        • Erickson B.
        • et al.
        Patterns of radiotherapy practice for patients with carcinoma of the uterine cervix: a patterns of care study.
        Internat J Radiation Oncol Biol Physics. 2004; 60: 1144-1153
        • Williamson C.W.
        • Liu H.C.
        • Mayadev J.
        • et al.
        Advances in external beam radiation therapy and brachytherapy for cervical cancer.
        Clin Oncol. 2021; 33: 567-578
        • Mayadev J.
        • Dieterich S.
        • Harse R.
        • et al.
        A failure modes and effects analysis study for gynecologic high-dose-rate brachytherapy.
        Brachytherapy. 2015; 14: 866-875
        • Mayadev J.
        • Qi L.
        • Lentz S.
        • et al.
        Implant time and process efficiency for CT-guided high-dose-rate brachytherapy for cervical cancer.
        Brachytherapy. 2014; 13: 233-239
        • Ma T.M.
        • Harkenrider M.M.
        • Yashar C.M.
        • et al.
        Understanding the underutilization of cervical brachytherapy for locally advanced cervical cancer.
        Brachytherapy. 2019; 18: 361-369
        • Pötter R.
        • Tanderup K.
        • Kirisits C.
        • et al.
        The EMBRACE II study: the outcome and prospect of two decades of evolution within the GEC-ESTRO GYN working group and the EMBRACE studies.
        Clin and Translational Rad Oncol. 2018; 9: 48-60
        • Tanderup K.
        • Ménard C.
        • Polgar C.
        • et al.
        Advancements in brachytherapy.
        Adv Drug Deliv Rev. 2017; 109: 15-25
        • Nelms B.E.
        • Tomé W.A.
        • Robinson G.
        • et al.
        Variations in the contouring of organs at risk: test case from a patient with oropharyngeal cancer.
        Internat J Radiation Oncol Biol Physics. 2012; 82: 368-378
        • Moore K.L.
        • Schmidt R.
        • Moiseenko V.
        • et al.
        Quantifying unnecessary normal tissue complication risks due to suboptimal planning: a secondary study of RTOG 0126.
        Internat J Radiation Oncol Biol Physics. 2015; 92: 228-235
        • Nelms B.E.
        • Robinson G.
        • Markham J.
        • et al.
        Variation in external beam treatment plan quality: an inter-institutional study of planners and planning systems.
        Pract Radiat Oncol. 2012; 2: 296-305
        • Wu B.
        • Ricchetti F.
        • Sanguineti G.
        • et al.
        Patient geometry-driven information retrieval for IMRT treatment plan quality control.
        Med Phys. 2009; 36: 5497-5505
        • Zhu X.
        • Ge Y.
        • Li T.
        • et al.
        A planning quality evaluation tool for prostate adaptive IMRT based on machine learning.
        Med Phys. 2011; 38: 719-726
        • Appenzoller L.M.
        • Michalski J.M.
        • Thorstad W.L.
        • et al.
        Predicting dose-volume histograms for organs-at-risk in IMRT planning.
        Med Phys. 2012; 39: 7446-7461
        • Moore K.L.
        • Brame R.S.
        • Low D.A.
        • et al.
        Experience-based quality control of clinical intensity-modulated radiotherapy planning.
        Internat J Radiation Oncol Biol Physics. 2011; 81: 545-551
        • Cornell M.
        • Kaderka R.
        • Hild S.J.
        • et al.
        Noninferiority study of automated knowledge-based planning versus human-driven optimization across multiple disease sites.
        Internat J Radiation Oncol Biol Physics. 2020; 106: 430-439
        • Yusufaly T.I.
        • Kallis K.
        • Simon A.
        • et al.
        A knowledge-based organ dose prediction tool for brachytherapy treatment planning of patients with cervical cancer.
        Brachytherapy. 2020; 19: 624-634
        • Kallis K.
        • Mayadev J.
        • Covele B.
        • et al.
        Evaluation of dose differences between intracavitary applicators for cervical brachytherapy using knowledge-based models.
        Brachytherapy. 2021; 20: 1323-1333
        • Kallis K.
        • Mayadev J.
        • Kisling K.
        • et al.
        Knowledge-based dose prediction models to inform gynecologic brachytherapy needle supplementation for locally advanced cervical cancer.
        Brachytherapy. 2021; 20: 1187-1199
        • Shiraishi S.
        • Moore K.L.
        Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy.
        Med Phys. 2016; 43: 378-387
        • McIntosh C.
        • Purdie T.G.
        Voxel-based dose prediction with multi-patient atlas selection for automated radiotherapy treatment planning.
        Phys Med Biol. 2017; 62: 415-431
        • McIntosh C.
        • Purdie T.G.
        Contextual atlas regression forests: multiple-atlas-based automated dose prediction in radiation therapy.
        IEEE Trans Med Imaging. 2016; 35: 1000-1012
        • Babier A.
        • Mahmood R.
        • McNiven A.L.
        • et al.
        Knowledge-based automated planning with three-dimensional generative adversarial networks.
        Med Phys. 2020; 47: 297-306
        • Mao X.
        • Pineau J.
        • Keyes R.
        • et al.
        RapidBrachyDL: rapid radiation dose calculations in brachytherapy via deep learning.
        Internat J Radiation Oncol Biol Physics. 2020; 108: 802-812
        • Viswanathan A.N.
        • Thomadsen B.
        American brachytherapy society cervical cancer recommendations committee, et al. American Brachytherapy Society consensus guidelines for locally advanced carcinoma of the cervix. Part I: general principles.
        Brachytherapy. 2012; 11: 33-46
      2. Apte AP. Walk-Through of CERR Capabilities CERR: computational Environment for Radiological Research. 2022.

      3. Yarpiz (2020). DBSCAN Clustering Algorithm. MATLAB Central File Exchange, Available at: https://www.mathworks.com/matlabcentral/fileexchange/52905-dbscan-clustering-algorithm (accessed 16 November 2020).

      4. Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: learning Dense Volumetric Segmentation from Sparse Annotation. 2022.

      5. Ronneberger O, Fischer P, Brox T. U-Net: convolutional Networks for Biomedical Image Segmentation. 2022.

        • Towns J.
        • Cockerill T.
        • Dahan M.
        • et al.
        XSEDE: accelerating Scientific Discovery.
        Comput Sci Eng. 2014; 16 (Epub ahead of print September)https://doi.org/10.1109/MCSE.2014.80
        • Nguyen D.
        • Long T.
        • Jia X.
        • et al.
        A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning.
        Sci Rep. 2019; 9: 1-10
        • Fields E.C.
        • Melvani R.
        • Hajdok G.
        • et al.
        A multi-institution, retrospective analysis of cervix intracavitary brachytherapy treatments. Part 1: is EQD2 good enough for reporting radiobiological effects?.
        Internat J Radiation Oncol Biol Physics. 2017; 99: 219-226