Fully Automated Gross Tumor Volume Delineation From PET in Head and Neck Cancer Using Deep Learning Algorithms.
Journal
Clinical nuclear medicine
ISSN: 1536-0229
Titre abrégé: Clin Nucl Med
Pays: United States
ID NLM: 7611109
Informations de publication
Date de publication:
01 Nov 2021
01 Nov 2021
Historique:
pubmed:
10
7
2021
medline:
16
10
2021
entrez:
9
7
2021
Statut:
ppublish
Résumé
The availability of automated, accurate, and robust gross tumor volume (GTV) segmentation algorithms is critical for the management of head and neck cancer (HNC) patients. In this work, we evaluated 3 state-of-the-art deep learning algorithms combined with 8 different loss functions for PET image segmentation using a comprehensive training set and evaluated its performance on an external validation set of HNC patients. 18F-FDG PET/CT images of 470 patients presenting with HNC on which manually defined GTVs serving as standard of reference were used for training (340 patients), evaluation (30 patients), and testing (100 patients from different centers) of these algorithms. PET image intensity was converted to SUVs and normalized in the range (0-1) using the SUVmax of the whole data set. PET images were cropped to 12 × 12 × 12 cm3 subvolumes using isotropic voxel spacing of 3 × 3 × 3 mm3 containing the whole tumor and neighboring background including lymph nodes. We used different approaches for data augmentation, including rotation (-15 degrees, +15 degrees), scaling (-20%, 20%), random flipping (3 axes), and elastic deformation (sigma = 1 and proportion to deform = 0.7) to increase the number of training sets. Three state-of-the-art networks, including Dense-VNet, NN-UNet, and Res-Net, with 8 different loss functions, including Dice, generalized Wasserstein Dice loss, Dice plus XEnt loss, generalized Dice loss, cross-entropy, sensitivity-specificity, and Tversky, were used. Overall, 28 different networks were built. Standard image segmentation metrics, including Dice similarity, image-derived PET metrics, first-order, and shape radiomic features, were used for performance assessment of these algorithms. The best results in terms of Dice coefficient (mean ± SD) were achieved by cross-entropy for Res-Net (0.86 ± 0.05; 95% confidence interval [CI], 0.85-0.87), Dense-VNet (0.85 ± 0.058; 95% CI, 0.84-0.86), and Dice plus XEnt for NN-UNet (0.87 ± 0.05; 95% CI, 0.86-0.88). The difference between the 3 networks was not statistically significant (P > 0.05). The percent relative error (RE%) of SUVmax quantification was less than 5% in networks with a Dice coefficient more than 0.84, whereas a lower RE% (0.41%) was achieved by Res-Net with cross-entropy loss. For maximum 3-dimensional diameter and sphericity shape features, all networks achieved a RE ≤ 5% and ≤10%, respectively, reflecting a small variability. Deep learning algorithms exhibited promising performance for automated GTV delineation on HNC PET images. Different loss functions performed competitively when using different networks and cross-entropy for Res-Net, Dense-VNet, and Dice plus XEnt for NN-UNet emerged as reliable networks for GTV delineation. Caution should be exercised for clinical deployment owing to the occurrence of outliers in deep learning-based algorithms.
Identifiants
pubmed: 34238799
doi: 10.1097/RLU.0000000000003789
pii: 00003072-202111000-00002
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
872-883Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: This work was supported by the Swiss National Science Foundation under grants SNSF 320030_176052 and 320030_173091/1. None declared to all authors.
Références
Rohren EM, Turkington TG, Coleman RE. Clinical applications of PET in oncology. Radiology . 2004;231:305–332.
Lammertsma AA. Forward to the past: the case for quantitative PET imaging. J Nucl Med . 2017;58:1019–1024.
Zaidi H, Karakatsanis N. Towards enhanced PET quantification in clinical oncology. Br J Radiol . 2018;91:20170508.
Norouzi A, Rahim MSM, Altameem A, et al. Medical image segmentation methods, algorithms, and applications. IETE Technical Review . 2014;31:199–213.
Patil DD, Deore SG. Medical image segmentation: a review. Int J Comput Sci Mob Comput . 2013;2:22–27.
Xu Z, Gao M, Papadakis GZ, et al. Joint solution for PET image segmentation, denoising, and partial volume correction. Med Image Anal . 2018;46:229–243.
Foster B, Bagci U, Mansoor A, et al. A review on segmentation of positron emission tomography images. Comput Biol Med . 2014;50:76–96.
Day E, Betler J, Parda D, et al. A region growing method for tumor volume segmentation on PET images for rectal and anal cancer patients. Med Phys . 2009;36:4349–4358.
Hatt M, Lee JA, Schmidtlein CR, et al. Classification and evaluation strategies of auto-segmentation approaches for PET: report of AAPM task group no. 211. Med Phys . 2017;44:e1–e42.
Zaidi H, El Naqa I. PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques. Eur J Nucl Med Mol Imaging . 2010;37:2165–2187.
Drever L, Roa W, McEwan A, et al. Iterative threshold segmentation for PET target volume delineation. Med Phys . 2007;34:1253–1265.
Jentzen W, Freudenberg L, Eising EG, et al. Segmentation of PET volumes by iterative image thresholding. J Nucl Med . 2007;48:108–114.
Vees H, Senthamizhchelvan S, Miralbell R, et al. Assessment of various strategies for 18 F-FET PET-guided delineation of target volumes in high-grade glioma patients. Eur J Nucl Med Mol Imaging . 2009;36:182–193.
Brambilla M, Matheoud R, Basile C, et al. An adaptive thresholding method for BTV estimation incorporating PET reconstruction parameters: a multicenter study of the robustness and the reliability. Comput Math Methods Med . 2015;2015:571473.
Zhuang M, Dierckx RA, Zaidi H. Generic and robust method for automatic segmentation of PET images using an active contour model. Med Phys . 2016;43:4483–4494.
Abdoli M, Dierckx RA, Zaidi H. Contourlet-based active contour model for PET image segmentation. Med Phys . 2013;40:082507.
Blanc-Durand P, Van Der Gucht A, Verger A, et al. Voxel-based 18 F-FET PET segmentation and automatic clustering of tumor voxels: a significant association with IDH1 mutation status and survival in patients with gliomas. PLoS One . 2018;13:e0199379.
Belhassen S, Zaidi H. A novel fuzzy C-means algorithm for unsupervised heterogeneous tumor quantification in PET. Med Phys . 2010;37:1309–1324.
Hatt M, Cheze le Rest C, Turzo A, et al. A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET. IEEE Trans Med Imaging . 2009;28:881–893.
Stefano A, Vitabile S, Russo G, et al. An enhanced random walk algorithm for delineation of head and neck cancers in PET studies. Med Biol Eng Comput . 2017;55:897–908.
Geets X, Lee JA, Bol A, et al. A gradient-based method for segmenting FDG-PET images: methodology and validation. Eur J Nucl Med Mol Imaging . 2007;34:1427–1438.
Tylski P, Bonniaud G, Decenciere E, et al. 18 F-FDG PET images segmentation using morphological watershed: a phantom study. IEEE Nuclear Science Symposium Conference Record . 2006;4:2063–2067.
Song Q, Bai J, Han D, et al. Optimal co-segmentation of tumor in PET-CT images with context information. IEEE Trans Med Imaging . 2013;32:1685–1697.
Beichel RR, Van Tol M, Ulrich EJ, et al. Semiautomated segmentation of head and neck cancers in 18 F-FDG PET scans: a just-enough-interaction approach. Med Phys . 2016;43:2948–2964.
Yang J, Beadle BM, Garden AS, et al. A multimodality segmentation framework for automatic target delineation in head and neck radiotherapy. Med Phys . 2015;42:5310–5320.
Zeng Z, Wang J, Tiddeman B, et al. Unsupervised tumour segmentation in PET using local and global intensity-fitting active surface and alpha matting. Comput Biol Med . 2013;43:1530–1544.
Montgomery D, Amira A, Zaidi H. Fully automated segmentation of oncological PET volumes using a combined multiscale and statistical model. Med Phys . 2007;34:722–736.
Andrearczyk V, Oreiller V, Depeursinge A. Oropharynx detection in PET-CT for tumor segmentation. In: Proceedings of the 2020 Irish Machine Vision and Image Processing Conference (IMVIP 2020) . 2020:109–112.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature . 2015;521:436–444.
Arabi H, AkhavanAllaf A, Sanaat A, et al. The promise of artificial intelligence and deep learning in PET and SPECT imaging. Physica Medica . 2021;83:122–137.
Häggström I, Schmidtlein CR, Campanella G, et al. DeepPET: a deep encoder-decoder network for directly solving the PET image reconstruction inverse problem. Med Image Anal . 2019;54:253–262.
Shiri I, Arabi H, Geramifar P, et al. Deep-JASC: joint attenuation and scatter correction in whole-body (18)F-FDG PET using a deep residual network. Eur J Nucl Med Mol Imaging . 2020;47:2533–2548.
Cui J, Gong K, Guo N, et al. PET image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging . 2019;46:2780–2789.
Shiri I, AmirMozafari Sabet K, Arabi H, et al. Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks. J Nucl Cardiol . 2020.
Akhavanallaf A, Shiri I, Arabi H, et al. Whole-body voxel-based internal dosimetry using deep learning. Eur J Nucl Med Mol Imaging . 2021;48:670–682.
Moradi S, Oghli MG, Alizadehasl A, et al. MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography. Phys Med . 2019;67:58–69.
Isensee F, Kickingereder P, Wick W, et al. No new-net. In: International MICCAI Brainlesion Workshop . Granada, Spain: Springer; 2018:234–244.
Oktay O, Schlemper J, Folgoc LL, et al. Attention u-net: learning where to look for the pancreas. arXiv . 2018.
Zhou Z, Siddiquee MMR, Tajbakhsh N, et al. Unet++: A nested u-net architecture for medical image segmentation. arXiv . 2018;11045:3–11.
Yu H, Caldwell C, Mah K, et al. Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images. Int J Radiat Oncol Biol Phys . 2009;75:618–625.
Berthon B, Evans M, Marshall C, et al. Head and neck target delineation using a novel PET automatic segmentation algorithm. Radiother Oncol . 2017;122:242–247.
Kawata Y, Arimura H, Ikushima K, et al. Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy. Phys Med . 2017;42:141–149.
Grossiord E, Talbot H, Passat N, et al. Automated 3D lymphoma lesion segmentation from PET/CT characteristics. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) . 2017;174–178.
Leung KH, Marashdeh W, Wray R, et al. A physics-guided modular deep-learning based automated framework for tumor segmentation in PET. Phys Med Biol . 2020;65:245032.
Fu X, Bi L, Kumar A, et al. Multimodal spatial attention module for targeting multimodal PET-CT lung tumor segmentation. IEEE J Biomed Health Inform . 2021;PP. [Online ahead of print]. doi:10.1109/JBHI.2021.3059453.
doi: 10.1109/JBHI.2021.3059453
Zhong Z, Kim Y, Plichta K, et al. Simultaneous cosegmentation of tumors in PET-CT images using deep fully convolutional networks. Med Phys . 2019;46:619–633.
Chen L, Shen C, Zhou Z, et al. Automatic PET cervical tumor segmentation by combining deep learning and anatomic prior. Phys Med Biol . 2019;64:085019.
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;64:205015.
Jin D, Guo D, Ho T-Y, et al. Accurate esophageal gross tumor volume segmentation in PET/CT using two-stream chained 3D deep network fusion. arXiv . 2019;182–191.
Andrearczyk V, Oreiller V, Vallières M, et al. Automatic segmentation of head and neck tumors and nodal metastases in PET-CT scans. Proc Mach Learning Res . 2020;33–43.
Afshari S, BenTaieb A, Mirikharaji Z, et al. Weakly supervised fully convolutional network for PET lesion segmentation. Medical Imaging 2019: Image Processing, International Society for Optics and Photonics . 2019:109491K.
Huang B, Chen Z, Wu P-M, et al. Fully automated delineation of gross tumor volume for head and neck cancer on PET-CT using deep learning: a dual-center study. Contrast Media Mol Imaging . 2018;2018:1–12.
Berthon B, Spezi E, Galavis P, et al. Towards a standard for the evaluation of PET auto-segmentation methods: requirements and implementation. Med Phys . 2017;44:4098–4111.
Hatt M, Laurent B, Ouahabi A, et al. The first MICCAI challenge on PET tumor segmentation. Med Image Anal . 2018;44:177–195.
Prior FW, Clark K, Commean P, et al. TCIA: an information resource to enable open science. Int Conf IEEE Eng Med Biol Soc . 2013;2013:1282–1285.
Gevaert O, Xu J, Hoang CD, et al. Non–small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results. Radiology . 2012;264:387–396.
Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging . 2013;26:1045–1057.
Bakr S, Gevaert O, Echegaray S, et al. A radiogenomic dataset of non–small cell lung cancer. Sci Data . 2018;5:180202.
Vallières M, Kay-Rivest E, Perrin LJ, et al. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep . 2017;7:10117.
Rosset A, Spadola L, Ratib O. OsiriX: an open-source software for navigating in multidimensional DICOM images. J Digit Imaging . 2004;17:205–216.
Li W, Wang G, Fidon L, et al. On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. arXiv . 2017;348–360.
Gibson E, Giganti F, Hu Y, et al. Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Trans Med Imaging . 2018;37:1822–1834.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015 . Cham, Switzerland: Springer International Publishing. 2015;234–241.
Jadon S. A survey of loss functions for semantic segmentation. arXiv . 2020.
Zwanenburg A, Leger S, Vallières M, et al. Image biomarker standardisation initiative. arXiv . 2016.
van Griethuysen JJ, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res . 2017;77:e104–e107.
Brosch T, Yoo Y, Tang LY, et al. Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. IEEE Trans Med Imaging . 2015;3–11.
Mumford DB, Shah J. Optimal approximations by piecewise smooth functions and associated variational problems. Commun Pure Appl Mathematics . 1989;42:577–685.