Open-source, fully-automated hybrid cardiac substructure segmentation: development and optimisation.
Breast cancer
Cardiac substructures
Cardiotoxicity
Deep learning
Image segmentation
Lung cancer
Radiotherapy
Journal
Physical and engineering sciences in medicine
ISSN: 2662-4737
Titre abrégé: Phys Eng Sci Med
Pays: Switzerland
ID NLM: 101760671
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
received:
19
09
2022
accepted:
30
01
2023
pubmed:
14
2
2023
medline:
24
3
2023
entrez:
13
2
2023
Statut:
ppublish
Résumé
Radiotherapy for thoracic and breast tumours is associated with a range of cardiotoxicities. Emerging evidence suggests cardiac substructure doses may be more predictive of specific outcomes, however, quantitative data necessary to develop clinical planning constraints is lacking. Retrospective analysis of patient data is required, which relies on accurate segmentation of cardiac substructures. In this study, a novel model was designed to deliver reliable, accurate, and anatomically consistent segmentation of 18 cardiac substructures on computed tomography (CT) scans. Thirty manually contoured CT scans were included. The proposed multi-stage method leverages deep learning (DL), multi-atlas mapping, and geometric modelling to automatically segment the whole heart, cardiac chambers, great vessels, heart valves, coronary arteries, and conduction nodes. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), mean distance to agreement (MDA), Hausdorff distance (HD), and volume ratio. Performance was reliable, with no errors observed and acceptable variation in accuracy between cases, including in challenging cases with imaging artefacts and atypical patient anatomy. The median DSC range was 0.81-0.93 for whole heart and cardiac chambers, 0.43-0.76 for great vessels and conduction nodes, and 0.22-0.53 for heart valves. For all structures the median MDA was below 6 mm, median HD ranged 7.7-19.7 mm, and median volume ratio was close to one (0.95-1.49) for all structures except the left main coronary artery (2.07). The fully automatic algorithm takes between 9 and 23 min per case. The proposed fully-automatic method accurately delineates cardiac substructures on radiotherapy planning CT scans. Robust and anatomically consistent segmentations, particularly for smaller structures, represents a major advantage of the proposed segmentation approach. The open-source software will facilitate more precise evaluation of cardiac doses and risks from available clinical datasets.
Identifiants
pubmed: 36780065
doi: 10.1007/s13246-023-01231-w
pii: 10.1007/s13246-023-01231-w
pmc: PMC10030448
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
377-393Informations de copyright
© 2023. Crown.
Références
Finnegan R, Lorenzen EL, Dowling J, Jensen I, Berg M, Thomsen MMS et al (2020) Analysis of cardiac substructure dose in a large, multi-centre Danish breast cancer cohort (the DBCG HYPO trial): Trends and predictive modelling. Radiother Oncol 153:130–8. https://doi.org/10.1016/j.radonc.2020.09.004
doi: 10.1016/j.radonc.2020.09.004
pubmed: 32916238
Wang X, Palaskas NL, Yusuf SW, Abe J, Lopez-Mattei J, Banchs J et al (2020) Incidence and onset of severe cardiac events after radiotherapy for esophageal cancer. J Thorac Oncol 15:1682–90. https://doi.org/10.1016/j.jtho.2020.06.014
doi: 10.1016/j.jtho.2020.06.014
pubmed: 32599073
pmcid: 9398884
Iorio GC, Salvestrini V, Borghetti P, De Felice F, Greco C, Nardone V et al (2021) The impact of modern radiotherapy on radiation-induced late sequelae: focus on early-stage mediastinal classical Hodgkin Lymphoma. A critical review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (AIRO). Crit Rev Oncol 161:103326. https://doi.org/10.1016/j.critrevonc.2021.103326
doi: 10.1016/j.critrevonc.2021.103326
Meattini I, Poortmans PM, Aznar MC, Becherini C, Bonzano E, Cardinale D et al (2021) Association of breast cancer irradiation with cardiac toxic effects: a narrative review. JAMA Oncol 7:924–32. https://doi.org/10.1001/jamaoncol.2020.7468
doi: 10.1001/jamaoncol.2020.7468
pubmed: 33662107
Wei T, Cheng Y (2021) The cardiac toxicity of radiotherapy-a review of characteristics, mechanisms, diagnosis, and prevention. Int J Radiat Biol 97:1333–40. https://doi.org/10.1080/09553002.2021.1956007
doi: 10.1080/09553002.2021.1956007
pubmed: 34264176
van den Bogaard VA, Ta BD, van der Schaaf A, Bouma AB, Middag AM, Bantema-Joppe EJ et al (2017) Validation and modification of a prediction model for acute cardiac events in patients with breast cancer treated with radiotherapy based on three-dimensional dose distributions to cardiac substructures. J Clin Oncol 35:1171–8. https://doi.org/10.1200/JCO.2016.69.8480
doi: 10.1200/JCO.2016.69.8480
pubmed: 28095159
pmcid: 5455600
Stam B, Peulen H, Guckenberger M, Mantel F, Hope A, Werner-Wasik M et al (2017) Dose to heart substructures is associated with non-cancer death after SBRT in stage I–II NSCLC patients. Radiother Oncol 123:370–5
doi: 10.1016/j.radonc.2017.04.017
pubmed: 28476219
Piroth MD, Baumann R, Budach W, Dunst J, Feyer P, Fietkau R et al (2019) Heart toxicity from breast cancer radiotherapy. Strahl Onkol 195:1–12. https://doi.org/10.1007/s00066-018-1378-z
doi: 10.1007/s00066-018-1378-z
Atkins KM, Bitterman DS, Chaunzwa TL, Kozono DE, Baldini EH, Aerts HJ et al (2021) Mean heart dose is an inadequate surrogate for left anterior descending coronary artery dose and the risk of major adverse cardiac events in lung cancer radiation therapy. Int J Radiat Oncol Biol Phys 110:1473–9. https://doi.org/10.1016/j.ijrobp.2021.03.005
doi: 10.1016/j.ijrobp.2021.03.005
pubmed: 33713743
Banfill K, Giuliani M, Aznar M, Franks K, McWilliam A, Schmitt M et al (2021) Cardiac toxicity of thoracic radiotherapy: existing evidence and future directions. J Thorac Oncol 16:216–27. https://doi.org/10.1016/j.jtho.2020.11.002
doi: 10.1016/j.jtho.2020.11.002
pubmed: 33278607
pmcid: 7870458
Tohidinezhad F, Pennetta F, van Loon J, Dekker A, de Ruysscher D, Traverso A (2022) Prediction models for treatment-induced cardiac toxicity in patients with non-small-cell lung cancer: a systematic review and meta-analysis. Clin Transl Radiat Oncol 33:134–44. https://doi.org/10.1016/j.ctro.2022.02.007
doi: 10.1016/j.ctro.2022.02.007
pubmed: 35243024
pmcid: 8881199
Jacob S, Camilleri J, Derreumaux S, Walker V, Lairez O, Lapeyre M et al (2019) Is mean heart dose a relevant surrogate parameter of left ventricle and coronary arteries exposure during breast cancer radiotherapy: a dosimetric evaluation based on individually-determined radiation dose (BACCARAT study). Radiat Oncol 14:29. https://doi.org/10.1186/s13014-019-1234-z
doi: 10.1186/s13014-019-1234-z
pubmed: 30732640
pmcid: 6367844
Morris ED, Ghanem AI, Dong M, Pantelic MV, Walker EM, Glide-Hurst CK (2020) Cardiac substructure segmentation with deep learning for improved cardiac sparing. Med Phys 47:576–86. https://doi.org/10.1002/mp.13940
doi: 10.1002/mp.13940
pubmed: 31794054
Haq R, Hotca A, Apte A, Rimner A, Deasy JO, Thor M (2020) Cardio-pulmonary substructure segmentation of radiotherapy computed tomography images using convolutional neural networks for clinical outcomes analysis. Phys Imaging Radiat Oncol 14:61–66. https://doi.org/10.1016/j.phro.2020.05.009
doi: 10.1016/j.phro.2020.05.009
pubmed: 33458316
pmcid: 7807536
Chen X, Sun S, Bai N, Han K, Liu Q, Yao S et al (2021) A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol 160:175–84. https://doi.org/10.1016/j.radonc.2021.04.019
doi: 10.1016/j.radonc.2021.04.019
pubmed: 33961914
Harms J, Lei Y, Tian S, McCall NS, Higgins KA, Bradley JD et al (2021) Automatic delineation of cardiac substructures using a region-based fully convolutional network. Med Phys 48:2867–76. https://doi.org/10.1002/mp.14810
doi: 10.1002/mp.14810
pubmed: 33655548
van Velzen SG, Bruns S, Wolterink JM, Leiner T, Viergever MA, Verkooijen HM et al (2022) AI-based quantification of planned radiation therapy dose to cardiac structures and coronary arteries in patients with breast cancer. Int J Radiat Oncol Biol Phys 112:611–20. https://doi.org/10.1016/j.ijrobp.2021.09.009
doi: 10.1016/j.ijrobp.2021.09.009
pubmed: 34547373
Walls GM, Giacometti V, Apte A, Thor M, Mccann C, Hanna GG et al (2022) Validation of an established deep learning auto-segmentation tool for cardiac substructures in 4D radiotherapy planning scans. Phys Imaging Radiat Oncol 23:118–26. https://doi.org/10.1016/j.phro.2022.07.003
doi: 10.1016/j.phro.2022.07.003
pubmed: 35941861
pmcid: 9356270
van den Oever LB, Spoor DS, Crijns AP, Vliegenthart R, Oudkerk M, Veldhuis RN et al (2022) Automatic cardiac structure contouring for small datasets with cascaded deep learning models. J Med Syst. https://doi.org/10.1007/s10916-022-01810-6
doi: 10.1007/s10916-022-01810-6
pubmed: 35338425
pmcid: 8956542
Momin S, Lei Y, McCall NS, Zhang J, Roper J, Harms J et al (2022) Mutual enhancing learning-based automatic segmentation of CT cardiac substructure. Phys Med Biol. https://doi.org/10.1088/1361-6560/ac692d
doi: 10.1088/1361-6560/ac692d
pubmed: 35447610
Finnegan R, Dowling J, Koh ES, Tang S, Otton J, Delaney G et al (2019) Feasibility of multi-atlas cardiac segmentation from thoracic planning CT in a probabilistic framework. Phys Med Biol 64:085006. https://doi.org/10.1088/1361-6560/ab0ea6
doi: 10.1088/1361-6560/ab0ea6
pubmed: 30856618
Finnegan RN, Lorenzen E, Dowling JA, Holloway LC, Thwaites DI, Brink C (2020) Localised delineation uncertainty for iterative atlas selection in automatic cardiac segmentation. Phys Med Biol 65:035011. https://doi.org/10.1088/1361-6560/ab652a
doi: 10.1088/1361-6560/ab652a
pubmed: 31869823
Finnegan RN, Lorenzen EL, Dowling JA, Thwaites DI, Delaney G, Brink C et al (2021) Validation of a new open-source method for automatic delineation and dose assessment of the heart and LADCA in breast radiotherapy with simultaneous uncertainty estimation. Phys Med Biol. https://doi.org/10.1088/1361-6560/abcb1d
doi: 10.1088/1361-6560/abcb1d
pubmed: 33202389
Feng M, Moran JMJ, Koelling T, Chughtai A, Chan JL, Freedman L et al (2011) Development and validation of a heart atlas to study cardiac exposure to radiation following treatment for breast cancer. Int J Radiat Oncol Biol Phys 79:10–18. https://doi.org/10.1016/j.ijrobp.2009.10.058
doi: 10.1016/j.ijrobp.2009.10.058
pubmed: 20421148
Zhuang X (2013) Challenges and methodologies of fully automatic whole heart segmentation: a review. J Healthc Eng 4:371–408. https://doi.org/10.1260/2040-2295.4.3.371
doi: 10.1260/2040-2295.4.3.371
pubmed: 23965595
Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203–11. https://doi.org/10.1038/s41592-020-01008-z
doi: 10.1038/s41592-020-01008-z
pubmed: 33288961
Campello VM, Gkontra P, Izquierdo C, Martin-Isla C, Sojoudi A, Full PM et al (2021) Multi-centre, multi-vendor and multi-disease cardiac segmentation: the M &Ms challenge. IEEE Trans Med Imaging 20:1–1. https://doi.org/10.1109/tmi.2021.3090082
doi: 10.1109/tmi.2021.3090082
Finnegan RN, Reynolds HM, Ebert MA, Sun Y, Holloway L, Sykes JR et al (2022) A statistical, voxelised model of prostate cancer for biologically optimised radiotherapy. Phys Imaging Radiat Oncol 21:136–45. https://doi.org/10.1016/j.phro.2022.02.011
doi: 10.1016/j.phro.2022.02.011
pubmed: 35284663
pmcid: 8913349
Vercauteren T, Pennec X, Perchant A, Ayache N (2007) Diffeomorphic Demons Using ITK’s Finite Difference Solver Hierarchy. Insight J - ISC/NA MIC Worksh
Vercauteren T, Pennec X, Perchant A, and Ayache N (2008) Symmetric log-domain diffeomorphic registration: a demons-based approach. In: Lecture Notes in Computer Science. Vol. 5241. 1. Springer, Berlin, pp. 754-761. https://doi.org/10.1007/978-3-540-85988-8_90
Vercauteren T, Pennec X, Perchant A, Ayache N (2009) Diffeomorphic demons: efficient non-parametric image registration. NeuroImage 45:S61–S72. https://doi.org/10.1016/j.neuroimage.2008.10.040
doi: 10.1016/j.neuroimage.2008.10.040
pubmed: 19041946
Iglesias JE, Sabuncu MR, Eugenio J, Sabuncu MR, Iglesias JE, Sabuncu MR (2015) Multi-atlas segmentation of biomedical images: a survey. Med Image Anal 24:205–19. https://doi.org/10.1016/j.media.2015.06.012 . arXiv: 1412.3421
doi: 10.1016/j.media.2015.06.012
pubmed: 26201875
pmcid: 4532640
Socha J, Rygielska A, Uziȩbło-Życzkowska B, Chałubińska-Fendler J, Jurek A, Maciorowska M et al (2022) Contouring cardiac substructures on average intensity projection 4D-CT for lung cancer radiotherapy: a proposal of a heart valve contouring atlas. Radiother Oncol 167:261–8. https://doi.org/10.1016/j.radonc.2021.12.041
doi: 10.1016/j.radonc.2021.12.041
pubmed: 34990727
Duane F, Aznar MC, Bartlett F, Cutter DJ, Darby SC, Jagsi R et al (2017) A cardiac contouring atlas for radiotherapy. Radiother Oncol 122:416–22. https://doi.org/10.1016/j.radonc.2017.01.008
doi: 10.1016/j.radonc.2017.01.008
pubmed: 28233564
pmcid: 5356506
Loap P, Servois V, Dhonneur G, Kirov K, Fourquet A, Kirova Y (2021) A radiation therapy contouring atlas for cardiac conduction node delineation. Pract Radiat Oncol 11:e434–e437. https://doi.org/10.1016/j.prro.2021.02.002
doi: 10.1016/j.prro.2021.02.002
pubmed: 33561549
vanRossum G (1995) Python reference manual. Department of Computer Science [CS]
Lowekamp BC, Chen DT, Ibáñez L, Blezek D (2013) The design of SimpleITK. Front Neuroinf 7:45
doi: 10.3389/fninf.2013.00045
Išgum I, Staring M, Rutten A, Prokop M, Viergever MA, Van Ginneken B (2009) Multi-atlas-based segmentation with local decision fusion-application to cardiac and aortic segmentation in CT scans. IEEE Trans Med Imaging 28:1000–10. https://doi.org/10.1109/TMI.2008.2011480
doi: 10.1109/TMI.2008.2011480
pubmed: 19131298
Kirisli H, Schaap M, Klein S, Neefjes L, Weustink AC, van Walsum T et al (2010) Fully automatic cardiac segmentation from 3D CTA data: a multi-atlas based approach. Proc SPIE 7623:762305. https://doi.org/10.1117/12.838370
doi: 10.1117/12.838370
Zhuang X, Bai W, Song J, Zhan S, Qian X, Shi W et al (2015) Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection. Med Phys 42:3822–33. https://doi.org/10.1118/1.4921366
doi: 10.1118/1.4921366
pubmed: 26133584
Maffei N, Fiorini L, Aluisio G, D’Angelo E, Ferrazza P, Vanoni V et al (2020) Hierarchical clustering applied to automatic atlas based segmentation of 25 cardiac sub-structures. Phys Med 69:70–80. https://doi.org/10.1016/j.ejmp.2019.12.001
doi: 10.1016/j.ejmp.2019.12.001
pubmed: 31835189
Bruns S, Wolterink JM, Takx RA, van Hamersvelt RW, Suchá D, Viergever MA et al (2020) Deep learning from dual-energy information for whole-heart segmentation in dual-energy and single-energy non-contrast-enhanced cardiac CT. Med Phys 47:5048–60. https://doi.org/10.1002/mp.14451
doi: 10.1002/mp.14451
pubmed: 32786071
Loap P, De Marzi L, Kirov K, Servois V, Fourquet A, Khoubeyb A et al (2022) Development of simplified auto-segmentable functional cardiac atlas. Pract Radiat Oncol. https://doi.org/10.1016/j.prro.2022.02.004
doi: 10.1016/j.prro.2022.02.004
pubmed: 35192938
Jaworski C, Mariani JA, Wheeler G, Kaye DM (2013) Cardiac complications of thoracic irradiation. J Am College Cardiol 61:2319–28
doi: 10.1016/j.jacc.2013.01.090
Lorenzen EL, Taylor CW, Maraldo M, Nielsen MH, Offersen BV, Andersen MR et al (2013) Inter-observer variation in delineation of the heart and left anterior descending coronary artery in radiotherapy for breast cancer: a multi-centre study from Denmark and the UK. Radiother Oncol 108:254–8. https://doi.org/10.1016/j.radonc.2013.06.025
doi: 10.1016/j.radonc.2013.06.025
pubmed: 23891098
Zhou R, Liao Z, Pan T, Milgrom SA, Pinnix CC, Shi A et al (2017) Cardiac atlas development and validation for automatic segmentation of cardiac substructures. Radiother Oncol 122:66–71. https://doi.org/10.1016/j.radonc.2016.11.016
doi: 10.1016/j.radonc.2016.11.016
pubmed: 27939201
Milo MLH, Offersen BV, Bechmann T, Diederichsen ACP, Hansen CR, Holtved E et al (2020) Delineation of whole heart and substructures in thoracic radiation therapy: national guidelines and contouring atlas by the Danish Multidisciplinary Cancer Groups. Radiother Oncol 150:121–7. https://doi.org/10.1016/j.radonc.2020.06.015
doi: 10.1016/j.radonc.2020.06.015
pubmed: 32544606
Naimi Z, Moujahed R, Ghorbel S, Ben Rejeb M, Hamdoun A, Yahyaoui J, et al (2020) Inter-observer variation in delineating cardiac substructures and coronary arteries. In: Radiotherapy and Oncology. Vol. 152. Elsevier, East Park Shannon, Co. S1030–S1030
Jin X, Thomas MA, Dise J, Kavanaugh J, Hilliard J, Zoberi I et al (2021) Robustness of deep learning segmentation of cardiac substructures in noncontrast computed tomography for breast cancer radiotherapy. Med Phys 48:7172–88. https://doi.org/10.1002/mp.15237
doi: 10.1002/mp.15237
pubmed: 34545583
Garrett Fernandes M, Bussink J, Stam B, Wijsman R, Schinagl DA, Monshouwer R et al (2021) Deep learning model for automatic contouring of cardiovascular substructures on radiotherapy planning CT images: dosimetric validation and reader study based clinical acceptability testing. Radiother Oncol 165:52–59. https://doi.org/10.1016/j.radonc.2021.10.008
doi: 10.1016/j.radonc.2021.10.008
pubmed: 34688808
van den Bogaard VA, van Dijk LV, Vliegenthart R, Sijtsema NM, Langendijk JA, Maduro JH et al (2019) Development and evaluation of an auto-segmentation tool for the left anterior descending coronary artery of breast cancer patients based on anatomical landmarks. Radiother Oncol 136:15–20. https://doi.org/10.1016/j.radonc.2019.03.013
doi: 10.1016/j.radonc.2019.03.013
pubmed: 31015118
Loap P, Tkatchenko N, Nicolas E, Fourquet A, Kirova Y (2020) Optimization and auto-segmentation of a high risk cardiac zone for heart sparing in breast cancer radiotherapy. Radiother Oncol 153:146–54. https://doi.org/10.1016/j.radonc.2020.09.044
doi: 10.1016/j.radonc.2020.09.044
pubmed: 33007352
Tang S, Otton J, Holloway L, Delaney GP, Liney G, George A et al (2019) Quantification of cardiac subvolume dosimetry using a 17 segment model of the left ventricle in breast cancer patients receiving tangential beam radiotherapy. Radiother Oncol 132:257–65. https://doi.org/10.1016/j.radonc.2018.09.021
doi: 10.1016/j.radonc.2018.09.021
pubmed: 30446318
Nilsson G, Holmberg L, Garmo H, Duvernoy O, Sjogren I, Lagerqvist B et al (2012) Distribution of coronary artery stenosis after radiation for breast cancer. J Clin Oncol 30:380–6. https://doi.org/10.1200/JCO.2011.34.5900
doi: 10.1200/JCO.2011.34.5900
pubmed: 22203772
Morris ED, Aldridge K, Ghanem AI, Zhu S, Glide-Hurst CK (2020) Incorporating sensitive cardiac substructure sparing into radiation therapy planning. J Appl Clin Med Phys 21:195–204. https://doi.org/10.1002/acm2.13037
doi: 10.1002/acm2.13037
pubmed: 33073454
pmcid: 7701109
Bergom C, Bradley JA, Ng AK, Samson P, Robinson C, Lopez-Mattei J et al (2021) Past, present, and future of radiation-induced cardiotoxicity: refinements in targeting, surveillance, and risk stratification. JACC CardioOncol 3:343–59. https://doi.org/10.1016/j.jaccao.2021.06.007
doi: 10.1016/j.jaccao.2021.06.007
pubmed: 34604796
pmcid: 8463722
Kearney Keys M, Faivre-Finn C, Wang Z, Aznar MC, Duane F (2022) Exposure of the heart in lung cancer radiation therapy: a systematic review of heart doses published during (2013) to 2020. Radiother Oncol 2022(93):845–53. https://doi.org/10.1016/j.radonc.2022.05.007.12
doi: 10.1016/j.radonc.2022.05.007.12