Deep learning-based automatic delineation of anal cancer gross tumour volume: a multimodality comparison of CT, PET and MRI

References

• Islami F, Ferlay J, Lortet-Tieulent J, et al. International trends in anal cancer incidence rates. Int J Epidemiol. 2017;46(3):924–938.
   PubMed Web of Science ®Google Scholar
• Rao S, Guren MG, Khan K, et al. Anal cancer: ESMO clinical practice guidelines for diagnosis, treatment and follow-up⋆. Ann Oncol. 2021;32(9):1087–1100.
   PubMed Web of Science ®Google Scholar
• Kachnic LA, Winter K, Myerson RJ, et al. RTOG 0529: a phase 2 evaluation of dose-painted intensity modulated radiation therapy in combination with 5-fluorouracil and mitomycin-C for the reduction of acute morbidity in carcinoma of the anal canal. Int J Radiat Oncol Biol Phys. 2013;86(1):27–33.
   PubMed Web of Science ®Google Scholar
• Segedin B, Petric P. Uncertainties in target volume delineation in radiotherapy – are they relevant and what can we do about them? Radiol Oncol. 2016;50(3):254–262.
   PubMed Web of Science ®Google Scholar
• Cox S, Cleves A, Clementel E, et al. Impact of deviations in target volume delineation – time for a new RTQA approach? Radiother Oncol. 2019;137:1–8.
   PubMed Web of Science ®Google Scholar
• Chang ATY, Tan LT, Duke S, et al. Challenges for quality assurance of target volume delineation in clinical trials. Front Oncol. 2017;7:221.
   PubMed Web of Science ®Google Scholar
• Vinod SK, Jameson MG, Min M, et al. Uncertainties in volume delineation in radiation oncology: a systematic review and recommendations for future studies. Radiother Oncol. 2016;121(2):169–179.
   PubMed Web of Science ®Google Scholar
• Ng M, Leong T, Chander S, et al. Australasian gastrointestinal trials group (AGITG) contouring atlas and planning guidelines for intensity-modulated radiotherapy in anal cancer. Int J Radiat Oncol Biol Phys. 2012;83(5):1455–1462.
   PubMed Web of Science ®Google Scholar
• Rusten E, Rekstad BL, Undseth C, et al. Target volume delineation of anal cancer based on magnetic resonance imaging or positron emission tomography. Radiat Oncol. 2017;12(1):147.
   PubMedGoogle Scholar
• Benson AB, Venoo AP, Al-Hawary MM, et al. Anal carcinoma, version 2.2018, NCCN clinical practice guidelines in Oncology. J Natl Compr Canc Netw. 2018;16(7):852–871.
   PubMed Web of Science ®Google Scholar
• Goh V, Gollub FK, Liaw J, et al. Magnetic resonance imaging assessment of squamous cell carcinoma of the anal canal before and after chemoradiation: can MRI predict for eventual clinical outcome? Int J Radiat Oncol Biol Phys. 2010;78(3):715–721.
   PubMed Web of Science ®Google Scholar
• Jones M, Hruby G, Solomon M, et al. The role of FDG-PET in the initial staging and response assessment of anal cancer: a systematic review and meta-analysis. Ann Surg Oncol. 2015;22(11):3574–3581.
   PubMed Web of Science ®Google Scholar
• Glynne-Jones R, Tan D, Hughes R, et al. Squamous-cell carcinoma of the anus: progress in radiotherapy treatment. Nat Rev Clin Oncol. 2016;13(7):447–459.
   PubMed Web of Science ®Google Scholar
• Cardenas CE, Yang J, Anderson BM, et al. Advances in auto-segmentation. Semin Radiat Oncol. 2019;29(3):185–197.
   PubMed Web of Science ®Google Scholar
• Lin L, Dou Q, Jin YM, et al. Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma. Radiology. 2019;291(3):677–686.
   PubMed Web of Science ®Google Scholar
• Guo Z, Li X, Huang H, et al. Deep learning-based image segmentation on multimodal medical imaging. IEEE Trans Radiat Plasma Med Sci. 2019;3(2):162–169.
   PubMed Web of Science ®Google Scholar
• Guo Z, Guo N, Gong K, et al. Gross tumor volume segmentation for head and neck cancer radiotherapy using deep dense multi-modality network. Phys Med Biol. 2019;64(20):205015.
   PubMed Web of Science ®Google Scholar
• Slørdahl KS, Klotz D, Olsen JÅ, et al. Treatment outcomes and prognostic factors after chemoradiotherapy for anal cancer. Acta Oncol. 2021;60(7):921–930.
   PubMed Web of Science ®Google Scholar
• Rusten E, Rekstad BL, Undseth C, et al. Anal cancer chemoradiotherapy outcome prediction using 18F-fluorodeoxyglucose positron emission tomography and clinicopathological factors. BJR. 2019;92(1097):20181006.
   Google Scholar
• Edge SB, Compton CC. The American Joint Committee on Cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM. Ann Surg Oncol. 2010;17(6):1471–1474.
   PubMed Web of Science ®Google Scholar
• Glynne-Jones R, Goh V, Aggarwal A, et al. Anal carcinoma. In: Grosu AL, Nieder C, editors. Target volume definition in radiation oncology. Berlin: Springer; 2015. p. 193–218.
   Google Scholar
• Maes F, Collignon A, Vandermeulen D, et al. Multimodality image registration by maximization of mutual information. IEEE Trans Med Imaging. 1997;16(2):187–198.
   PubMed Web of Science ®Google Scholar
• Freiman M, Voss SD, Mulkern RV, et al. In vivo assessment of optimal b-value range for perfusion-insensitive apparent diffusion coefficient imaging. Med Phys. 2012;39(8):4832–4839.
   PubMed Web of Science ®Google Scholar
• Ronneberger O, Fischer P, Brox T, et al. U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W,., editors. Medical image computing and Computer-Assisted intervention – MICCAI 2015. MICCAI 2015. Munich: Springer; 2015. p. 234–241.
   Google Scholar
• Milletari F, Mavab N, Ahmadi S. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D vision (3DV); 2016 Oct 25–28; Stanford (CA). IEEE; 2016. p. 565–571.
   Google Scholar
• Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203–211.
   PubMed Web of Science ®Google Scholar
• Kingma DP, Ba JL. ADAM: A Method for Stochastic Optimization. arXiv:1412.6980 [Preprint]. 2014 [cited 2021 June 9]: [15 p.]. Available from: https://arxiv.org/abs/1412.6980
   Google Scholar
• Lee J, Oh JE, Kim MJ, et al. Reducing the model variance of a rectal cancer segmentation network. IEEE Access. 2019;7:182725–182733.
   Web of Science ®Google Scholar
• Simard PY, Steinkraus D, Platt JC. Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition; 2003 Aug 6; Edinburgh. New York (NY): IEEE; 2003. p. 958–63.
   Google Scholar
• Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297–302.
   Web of Science ®Google Scholar
• Huttenlocher DP, Klanderman GA, Rucklidge WJ. Comparing images using the hausdorff distance. IEEE Trans Pattern Anal Machine Intell. 1993;15(9):850–863.
   Web of Science ®Google Scholar
• Friedman M. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc. 1937;32(200):675–701.
   Google Scholar
• Hollander M, Wolfe DA, Chicken E. Nonparametric statistical methods. 3rd ed. Hoboken (NJ): Wiley; 2014.
   Google Scholar
• Pohlert T. PMCMRplus: Calculate Pairwise Multiple Comparisons of Mean Rank Sums Extended [software]. R package version 1.9.0; 2021. [cited 2021 June 9]. Available from: https://CRAN.R-project.org/package=PMCMRplus
   Google Scholar
• Bird D, Nix MG, McCallum H, et al. Multicentre, deep learning, synthetic-CT generation for ano-rectal MR-only radiotherapy treatment planning. Radiother Oncol. 2021;156:23–28.
   PubMed Web of Science ®Google Scholar
• Jonsson J, Nyholm T, Söderkvist K. The rationale for MR-only treatment planning for external radiotherapy. Clin Transl Radiat Oncol. 2019;18:60–65.
   PubMed Web of Science ®Google Scholar
• Buijsen J, van den Bogaard J, Janssen MHM, et al. FDG-PET provides the best correlation with the tumor specimen compared to MRI and CT in rectal cancer. Radiother Oncol. 2011;98(2):270–276.
   PubMed Web of Science ®Google Scholar
• Rosa C, Delli Pizzi D, Augurio A, et al. Volume delineation in cervical cancer with T2 and diffusion-weighted MRI: agreement on volumes between observers. In Vivo. 2020;34(4):1981–1986.
   PubMed Web of Science ®Google Scholar
• Choudhury A, Theophanous S, Lønne PI, et al. Predicting outcomes in anal cancer patients using multi-centre data and distributed learning – a proof-of-concept study. Radiother Oncol. 2021;159:183–189.
   PubMed Web of Science ®Google Scholar
• Karimi D, Warfield SK, Gholipour A. Critical Assessment of Transfer Learning for Medical Image Segmentation with Fully Convolutional Neural Networks. arXiv:2006.00356v1 [Preprint]. 2020. [cited 2021 June 9]: [11 p.]. Available from: https://arxiv.org/abs/2006.00356v1
   Google Scholar
• Zhu S, Dai Z, Wen N. Two-Stage approach for segmenting gross tumor volume in head and neck cancer with CT and PET imaging. In: Andrearczyk V, Oreiller V, Depeursinge A, editors. Head and neck tumor segmentation. First Challenge, HECKTOR 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4, 2020, Proceedings. Cham: Springer; 2021. p. 22–27.
   Google Scholar
• Chen L, Shen C, Zhou Z, et al. Automatic PET cervical tumor segmentation by combining deep learning and anatomic prior. Phys Med Biol. 2019;64(8):085019.
   PubMed Web of Science ®Google Scholar
• Wang J, Lu J, Qin G, et al. Technical note: a deep learning-based autosegmentation of rectal tumors in MR images. Med Phys. 2018;45(6):2560–2564.
   PubMed Web of Science ®Google Scholar
• Wang M, Xie P, Ran Z, et al. Full convolutional network based multiple side-output fusion architecture for the segmentation of rectal tumors in magnetic resonance images: a multi-vendor study. Med Phys. 2019;46(6):2659–2668.
   PubMed Web of Science ®Google Scholar
• Kim J, Oh JE, Lee J, et al. Rectal cancer: toward fully automatic discrimination of T2 and T3 rectal cancers using deep convolutional neural network. Int J Imaging Syst Technol. 2019;29(3):247–259.
   Web of Science ®Google Scholar
• Soomro MH, Coppotelli M, Conforto S, et al. Automated segmentation of colorectal tumor in 3D MRI using 3D multiscale densely connected convolutional neural network. J Healthc Eng. 2019;2019:1075434.
   PubMed Web of Science ®Google Scholar
• Bnouni N, Islem R, Rhim MS, et al. Dynamic multi-scale CNN Forest learning for automatic cervical cancer segmentation. In: Shi Y, Suk HI, Liu M, editors. Machine learning in medical imaging. MLMI 2018. Granada: Springer; 2018. p. 19–27.
   Google Scholar
• Trebeschi S, van Griethuysen JJM, Lambregts DMJ, et al. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Sci Rep. 2017;7(1):5301.
   PubMed Web of Science ®Google Scholar
• Liu Z, Liu X, Xiao B, et al. Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network. Phys Med. 2020;69:184–191.
   PubMed Web of Science ®Google Scholar
• Prezzi D, Mandegaran R, Gourtsoyianni S, et al. The impact of MRI sequence on tumour staging and gross tumour volume delineation in squamous cell carcinoma of the anal canal. Eur Radiol. 2018;28(4):1512–1519.
   PubMed Web of Science ®Google Scholar
• Min LA, Vacher YJL, Dewit L, et al. Gross tumour volume delineation in anal cancer on T2-weighted and diffusion-weighted MRI – reproducibility between radiologists and radiation oncologists and impact of reader experience level and DWI image quality. Radiother Oncol. 2020;150:81–88.
   PubMed Web of Science ®Google Scholar