Advertisement
Original paper| Volume 65, P137-142, September 2019

Download started.

Ok

Using a neural network to predict deviations in mean heart dose during the treatment of left-sided deep inspiration breath hold patients

Published:August 26, 2019DOI:https://doi.org/10.1016/j.ejmp.2019.08.014

      Highlights

      • Predictions of the mean heart dose were made using a deep neural network.
      • Errors in prediction were small compared to other methods utilised in the literature.
      • Only parameters available at treatment planning were used for each prediction.
      • The optimal neural network was comprised of a single hidden layer of 30 neurons.
      • 94% of all prediction errors were below 0.2 Gy and 100% were below 0.5 Gy.

      Abstract

      Purpose

      We investigated if a neural network could be used to predict the change in mean heart dose when a patient's heart deviates from its planned position during radiotherapy treatment.

      Methods

      Predictions were made based on parameters available at the time of treatment planning. The dose prescription, deep inspiration breath-hold (DIBH) amplitude, heart volume, lung volume, V90% and mean heart dose were used to predict the increase in dose to the heart when a shift towards the treatment field was undertaken. The network was trained using 3 mm, 5 mm and 7 mm shifts in heart positions for 50 patients' giving 150 data points in total. The neural network architecture was also varied to find the most optimal network design. The final neural network was then tested using cross-validation to evaluate the model's ability to generalise to new data.

      Results

      The optimal neural network found was comprised of a single hidden layer of 30 neurons. Based on twenty train/test splits, 94% of all prediction errors were below 0.2 Gy, 97.3% were below 0.3 Gy and 100% were below 0.5 Gy. The average RMSE and maximum prediction error over all train/test splits were 0.13 Gy and 0.5 Gy respectively.

      Conclusions

      Our approach using a neural network provides a clinically acceptable estimate of the increase in Mean Heart Dose (MHD), without the need for further imaging, contouring or evaluation. The trained neural network gives clinicians the information and tools required to evaluate what shift in heart position would be acceptable and which scenarios require immediate action before treatment continues.

      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 Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Feng M.
        • Valdes G.
        • Dixit N.
        • Solberg T.D.
        Machine Learning in Radiation Oncology: Opportunities, Requirements, and Needs.
        Front Oncol. 2018; 8: 1-7https://doi.org/10.3389/fonc.2018.00110
        • Kang J.
        • Schwartz R.
        • Flickinger J.
        • Beriwal S.
        Machine learning approaches for predicting radiation therapy outcomes: a clinician’s perspective.
        Int J Radiat Oncol Biol Phys. 2015; 93: 1127-1135https://doi.org/10.1016/j.ijrobp.2015.07.2286
        • Kortesniemi M.
        • Tsapaki V.
        • Trianni A.
        • Russo P.
        • Maas A.
        • Källman H.E.
        • et al.
        The European Federation of Organisations for Medical Physics (EFOMP) White Paper: big data and deep learning in medical imaging and in relation to medical physics profession.
        Phys Medica. 2018; 56: 90-93https://doi.org/10.1016/j.ejmp.2018.11.005
        • Varfalvy N.
        • Piron O.
        • Cyr M.F.
        • Dagnault A.A.L.
        Classification of changes occurring in lung patient during radiotherapy using relative γ analysis and hidden Markov models.
        Int J Lab Hematol. 2016; 38: 42-49https://doi.org/10.1111/ijlh.12426
        • Oakden-Rayner L.
        • Carneiro G.
        • Bessen T.
        • Nascimento J.C.
        • Bradley A.P.
        • Palmer L.J.
        Precision Radiology: predicting longevity using feature engineering and deep learning methods in a radiomics framework.
        Sci Rep. 2017; 7: 1-13https://doi.org/10.1038/s41598-017-01931-w
        • Lao J.
        • Chen Y.
        • Li Z.C.
        • Li Q.
        • Zhang J.
        • Liu J.
        • et al.
        A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme.
        Sci Rep. 2017; 7: 1-8https://doi.org/10.1038/s41598-017-10649-8
        • Li Z.
        • Wang Y.
        • Yu J.
        • Guo Y.
        • Cao W.
        Deep Learning based Radiomics (DLR) and its usage in noninvasive IDH1 prediction for low grade glioma.
        Sci Rep. 2017; 7: 1-11https://doi.org/10.1038/s41598-017-05848-2
        • Cha K.H.
        • Hadjiiski L.
        • Chan H.P.
        • Weizer A.Z.
        • Alva A.
        • Cohan R.H.
        • et al.
        Bladder Cancer Treatment Response Assessment in CT using Radiomics with Deep-Learning.
        Sci Rep. 2017; 7: 1-12https://doi.org/10.1038/s41598-017-09315-w
        • Tseng H.H.
        • Luo Y.
        • Cui S.
        • Chien J.T.
        • Ten Haken R.K.
        • NI
        Deep Reinforcement Learning for Automated Radiation Adaptation in Lung Cancer Huan-Hsin.
        Int J Lab Hematol. 2016; 38: 42-49https://doi.org/10.1111/ijlh.12426
        • Sharp G.
        • Fritscher K.D.
        • Pekar V.
        • Peroni M.
        • Shusharina N.
        • Veeraraghavan H.
        • et al.
        Vision 20/20: perspectives on automated image segmentation for radiotherapy.
        Med Phys. 2014; 41: 1-13https://doi.org/10.1118/1.4871620
      1. Dai W, Dong N, Wang Z, Liang X, Zhang H, Xing EP. 2018. Scan: Structure correcting adversarial network for organ segmentation in chest x-rays. Lect Notes Comput Sci (Including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 11045 LNCS:263–73. doi:10.1007/978-3-030-00889-5_30.

        • Ibragimov B.
        • Xing L.
        Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks.
        Med Phys. 2017; 44: 547-557https://doi.org/10.1002/mp.12045
        • Korfiatis P.
        • Kline T.L.
        • Lachance D.H.
        • Parney I.F.
        • Buckner J.C.
        • Erickson B.J.
        Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.
        J Digit Imaging. 2017; 30: 622-628https://doi.org/10.1007/s10278-017-0009-z
        • Ruan D.
        • Keall P.
        Online prediction of respiratory motion: Multidimensional processing with low-dimensional feature learning.
        Phys Med Biol. 2010; 55: 3011-3025https://doi.org/10.1088/0031-9155/55/11/002
        • Isaksson M.
        • Jalden J.
        • Murphy M.J.
        On using an adaptive neural network to predict lung tumor motion during respiration for radiotherapy applications.
        Med Phys. 2005; 32: 3801-3809https://doi.org/10.1118/1.2134958
        • Mori S.
        Deep architecture neural network-based real-time image processing for image-guided radiotherapy.
        Phys Medica. 2017; 40: 79-87https://doi.org/10.1016/j.ejmp.2017.07.013
        • Li Q.
        • Chan M.F.
        Predictive time-series modeling using artificial neural networks for Linac beam symmetry: an empirical study.
        Ann N Y Acad Sci. 2017; 1387: 84-94https://doi.org/10.1111/nyas.13215
        • Valdes G.
        • Scheuermann R.
        • Hung C.Y.
        • Olszanski A.
        • Bellerive M.
        • Solberg T.D.
        A mathematical framework for virtual IMRT QA using machine learning.
        Med Phys. 2016; 43: 4323-4334https://doi.org/10.1118/1.4953835
        • Valdes G.
        • Chan M.F.
        • Lim S.B.
        • Scheuermann R.
        • Deasy J.O.
        • Solberg T.D.
        IMRT QA using machine learning: a multi-institutional validation.
        J Appl Clin Med Phys. 2017; 18: 279-284https://doi.org/10.1002/acm2.12161
        • El Naqa I.
        • Ruan D.
        • Valdes G.
        • Dekker A.
        • McNutt T.
        • Ge Y.
        • et al.
        Machine learning and modeling: data, validation, communication challenges.
        Med Phys. 2018; https://doi.org/10.1002/mp.12811
        • Ferlay J.
        • Soerjomataram I.
        • Ervik M.
        • Dikshit R.
        • Cancer Eser S MC
        • et al.
        Incidence and Mortality Worldwide: IARC CancerBase No. 11e.
        GLOBOCAN, 2012
        • Darby S.
        • McGale P.
        • Correa C.
        • Taylor C.
        • Arriagada R.
        • Clarke M.
        • et al.
        Effect of radiotherapy after breast-conserving surgery on 10-year recurrence and 15-year breast cancer death: meta-analysis of individual patient data for 10 801 women in 17 randomised trials.
        Lancet. 2011; 378: 1707-1716https://doi.org/10.1016/S0140-6736(11)61629-2
        • Abe O.
        • Abe R.
        • Enomoto K.
        • Kikuchi K.
        • Koyama H.
        • Masuda H.
        • et al.
        Effects of radiotherapy and of differences in the extent of surgery for early breast cancer on local recurrence and 15-year survival: an overview of the randomised trials.
        Lancet. 2005; 366: 2087-2106https://doi.org/10.1016/S0140-6736(05)67887-7
        • Ozyigit G.
        Current role of modern radiotherapy techniques in the management of breast cancer.
        World J Clin Oncol. 2014; 5: 425https://doi.org/10.5306/wjco.v5.i3.425
        • Syriopoulou E.
        • Bower H.
        • Andersson T.M.L.
        • Lambert P.C.
        • Rutherford M.J.
        Estimating the impact of a cancer diagnosis on life expectancy by socio-economic group for a range of cancer types in England.
        Br J Cancer. 2017; 117: 1419-1426https://doi.org/10.1038/bjc.2017.300
        • Hooning M.J.
        • Aleman B.M.P.
        • Van Rosmalen A.J.M.
        • Kuenen M.A.
        • Klijn J.G.M.
        • Van Leeuwen F.E.
        Cause-specific mortality in long-term survivors of breast cancer: a 25-year follow-up study.
        Int J Radiat Oncol Biol Phys. 2006; 64: 1081-1091https://doi.org/10.1016/j.ijrobp.2005.10.022
        • Taylor C.W.
        • McGale P.
        • Povall J.M.
        • Thomas E.
        • Kumar S.
        • Dodwell D.
        • et al.
        Estimating Cardiac Exposure From Breast Cancer Radiotherapy in Clinical Practice.
        Int J Radiat Oncol Biol Phys. 2009; 73: 1061-1068https://doi.org/10.1016/j.ijrobp.2008.05.066
        • Lorenzen E.L.
        • Brink C.
        • Taylor C.W.
        • Darby S.C.
        • Ewertz M.
        Uncertainties in estimating heart doses from 2D-tangential breast cancer radiotherapy.
        Radiother Oncol. 2016; 119: 71-76https://doi.org/10.1016/j.radonc.2016.02.017
        • Gagliardi Giovanna
        • Constine Louis S.
        • Moiseenko Vitali
        • Correa Candace
        • Pierce Lori J.
        • Allen Aaron M.
        • et al.
        Radiation Dose–Volume Effects In The Heart.
        Int J Radiat Oncol Biol Phys. 2010; 76: 77-85https://doi.org/10.1016/j.ijrobp.2009.05.070
        • Rudra Sonali
        • Al-Hallaq Hania A.
        • Feng Christine
        • Chmura Steven J.
        • Y, Hasan
        Effect of RTOG breast/chest wall guidelines on dose-volume histogram parameters.
        J Appl Clin Med Phys. 2014; 15: 4547https://doi.org/10.1111/j.1743-6109.2008.01122.x.Endothelial
        • Bergom C.
        • Currey A.
        • Desai N.
        • Tai A.
        • Strauss J.B.
        Deep Inspiration Breath Hold: Techniques and Advantages for Cardiac Sparing During Breast Cancer Irradiation.
        Front Oncol. 2018; 8: 1-10https://doi.org/10.3389/fonc.2018.00087
        • Royal College of Radiologists
        Postoperative radiotherapy for breast cancer.
        UK consensus statements. 2016;
        • Darby S.C.
        • Ewertz M.
        • McGale P.
        • Bennet A.M.
        • Blom-Goldman U.
        • Brønnum D.
        • et al.
        Risk of Ischemic Heart Disease in Women after Radiotherapy for Breast Cancer.
        N Engl J Med. 2013; 368: 987-998https://doi.org/10.1056/NEJMoa1209825
        • Huppert N.
        • Jozsef G.
        • DeWyngaert K.
        • Formenti S.C.
        The Role of a Prone Setup in Breast Radiation Therapy.
        Front Oncol. 2011; 1: 1-8https://doi.org/10.3389/fonc.2011.00031
        • Joseph K.
        • Warkentin H.
        • Ghosh S.
        • Polkosnik L.A.
        • Powell K.
        • Brennan M.
        • et al.
        Cardiac-sparing radiation therapy using positioning breast shell for patients with left-sided breast cancer who are ineligible for breath-hold techniques.
        Adv Radiat Oncol. 2017; 2: 532-539https://doi.org/10.1016/j.adro.2017.08.002
        • Kong F.M.
        • Klein E.E.
        • Bradley J.D.
        • Mansur D.B.
        • Taylor M.E.
        • Perez C.A.
        • et al.
        The impact of central lung distance, maximal heart distance, and radiation technique on the volumetric dose of the lung and heart for intact breast radiation.
        Int J Radiat Oncol Biol Phys. 2002; 54: 963-971https://doi.org/10.1016/S0360-3016(02)03741-0
        • Abadi M.
        • Agarwal A.
        • Barham P.
        • Brevdo E.
        • Chen Z.
        • Citro C.
        • et al.
        TensorFlow: Large-Scale Machine Learning on Heterogeneous.
        Distributed Systems. 2016; https://doi.org/10.1038/nn.3331
        • Abadi Martín
        • Barham Paul
        • Chen Jianmin
        • Chen Zhifeng
        • Davis Andy
        • Dean Jeffrey
        • et al.
        and Xiaoqiang Zheng GB. TensorFlow: A System for Large-Scale Machine Learning.
        Nat Neurosci. 2013; 16: 486-492https://doi.org/10.1038/nn.3331
        • Rampasek L.
        • Goldenberg A.
        TensorFlow: Biology’s Gateway to Deep Learning?.
        CellSyst. 2016; 2: 12-14https://doi.org/10.1016/j.cels.2016.01.009
        • Caruana R.
        • Lawrence S.
        • Giles L.
        Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping.
        13th Int Conf Neural Inf Process Syst. 2000; : 402-408https://doi.org/10.1109/IJCNN.2000.857823
        • Neelakantan A.
        • Vilnis L.
        • Le Q.V.
        • Sutskever I.
        • Kaiser L.
        • Kurach K.
        • et al.
        Adding Gradient Noise Improves Learning for Very Deep.
        Networks. 2015; : 1-11https://doi.org/10.21437/Interspeech.2016-491