Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
01 03 2022
01 03 2022
Historique:
pubmed:
16
10
2021
medline:
15
4
2022
entrez:
15
10
2021
Statut:
ppublish
Résumé
Although automated glioma segmentation holds promise for objective assessment of tumor biology and response, its routine clinical use is impaired by missing sequences, for example, due to motion artifacts. The aim of our study was to develop and validate a generative adversarial network for synthesizing missing sequences to allow for a robust automated segmentation. Our model was trained on data from The Cancer Imaging Archive (n = 238 WHO II-IV gliomas) to synthesize either missing FLAIR, T2-weighted, T1-weighted (T1w), or contrast-enhanced T1w images from available sequences, using a novel tumor-targeting loss to improve synthesis of tumor areas. We validated performance in a test set from both the REMBRANDT repository and our local institution (n = 68 WHO II-IV gliomas), using qualitative image appearance metrics, but also segmentation performance with state-of-the-art segmentation models. Segmentation of synthetic images was compared with 2 commonly used strategies for handling missing input data, entering a blank mask or copying an existing sequence. Across tumor areas and missing sequences, synthetic images generally outperformed both conventional approaches, in particular when FLAIR was missing. Here, for edema and whole tumor segmentation, we improved the Dice score, a common metric for evaluation of segmentation performance, by 12% and 11%, respectively, over the best conventional method. No method was able to reliably replace missing contrast-enhanced T1w images. Replacing missing nonenhanced magnetic resonance sequences via synthetic images significantly improves segmentation quality over most conventional approaches. This model is freely available and facilitates more widespread use of automated segmentation in routine clinical use, where missing sequences are common.
Identifiants
pubmed: 34652289
doi: 10.1097/RLI.0000000000000828
pii: 00004424-202203000-00007
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
187-193Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: The authors have no conflicts of interest to declare. F.K., B.M., and B.W. were supported by the DFG, SFB 824, project B12. F.K. was additionally supported by the DFG through TUM International Graduate School of Science and Engineering (IGSSE), GSC 81.
Références
Bakas S, Reyes M, Jakab A, et al. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. ArXiv181102629 Cs Stat . Available at: http://arxiv.org/abs/1811.02629 . Published online April 23, 2019. Accessed April 11, 2021.
Weltens C, Menten J, Feron M, et al. Interobserver variations in gross tumor volume delineation of brain tumors on computed tomography and impact of magnetic resonance imaging. Radiother Oncol . 2001;60:49–59.
Pereira S, Pinto A, Alves V, et al. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging . 2016;35:1240–1251. doi:10.1109/TMI.2016.2538465.
doi: 10.1109/TMI.2016.2538465
Ghaffari M, Sowmya A, Oliver R. Automated brain tumor segmentation using multimodal brain scans: a survey based on models submitted to the BraTS 2012-2018 challenges. IEEE Rev Biomed Eng . 2020;13:156–168. doi:10.1109/RBME.2019.2946868.
doi: 10.1109/RBME.2019.2946868
Kickingereder P, Isensee F, Tursunova I, et al. Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study. Lancet Oncol . 2019;20:728–740. doi:10.1016/S1470-2045(19)30098-1.
doi: 10.1016/S1470-2045(19)30098-1
Kofler F, Berger C, Waldmannstetter D, et al. BraTS toolkit: translating BraTS brain tumor segmentation algorithms into clinical and scientific practice. Front Neurosci . 2020;14:125. doi:10.3389/fnins.2020.00125.
doi: 10.3389/fnins.2020.00125
Conte GM, Weston AD, Vogelsang DC, et al. Generative adversarial networks to synthesize missing T1 and FLAIR MRI sequences for use in a multisequence brain tumor segmentation model. Radiology . 2021;300:E319 Published online 2021:203786.
Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Adv Neural Inf Process Syst . 2014. doi:10.1145/3422622.
doi: 10.1145/3422622
Finck T, Li H, Grundl L, et al. Deep-learning generated synthetic double inversion recovery images improve multiple sclerosis lesion detection. Invest Radiol . 2020;55:318–323.
Brou Boni KND, Klein J, Gulyban A, et al. Improving generalization in MR-to-CT synthesis in radiotherapy by using an augmented cycle generative adversarial network with unpaired data. Med Phys . 2021;48:3003–3010. Published online March 27, 2021. doi:10.1002/mp.14866.
doi: 10.1002/mp.14866
Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017 . IEEE Computer Society; 2017:5967–5976. doi:10.1109/CVPR.2017.632.
Bakas S, Akbari H, Sotiras A, et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data . 2017;4:170117. doi:10.1038/sdata.2017.117.
doi: 10.1038/sdata.2017.117
Rohlfing T, Zahr NM, Sullivan EV, et al. The SRI24 multichannel atlas of normal adult human brain structure. Hum Brain Mapp . 2010;31:798–819. doi:10.1002/hbm.20906.
doi: 10.1002/hbm.20906
Isensee F, Schell M, Pflueger I, et al. Automated brain extraction of multisequence MRI using artificial neural networks. Hum Brain Mapp . 2019;40:4952–4964. doi:10.1002/hbm.24750.
doi: 10.1002/hbm.24750
Yushkevich PA, Pashchinskiy A, Oguz I, et al. User-guided segmentation of multi-modality medical imaging datasets with ITK-SNAP. Neuroinformatics . 2019;17:83–102. doi:10.1007/s12021-018-9385-x.
doi: 10.1007/s12021-018-9385-x
Isensee F, Jaeger PF, Kohl SAA, et al. nnU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods . 2021;18:203–211. doi:10.1038/s41592-020-01008-z.
doi: 10.1038/s41592-020-01008-z
Mao X, Li Q, Xie H, Lau RYK, Wang Z, Smolley SP. Least squares generative adversarial networks. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017 . IEEE Computer Society; 2017:2813–2821. doi:10.1109/ICCV.2017.304.
Wang Z, Bovik AC, Sheikh HR, et al. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process . 2004;13:600–612. doi:10.1109/TIP.2003.819861.
doi: 10.1109/TIP.2003.819861
Eichinger P, Alberts E, Delbridge C, et al. Diffusion tensor image features predict IDH genotype in newly diagnosed WHO grade II/III gliomas. Sci Rep . 2017;7:13396. doi:10.1038/s41598-017-13679-4.
doi: 10.1038/s41598-017-13679-4
Kickingereder P, Sahm F, Radbruch A, et al. IDH mutation status is associated with a distinct hypoxia/angiogenesis transcriptome signature which is non-invasively predictable with rCBV imaging in human glioma. Sci Rep . 2015;5:16238. doi:10.1038/srep16238.
doi: 10.1038/srep16238
Kickingereder P, Neuberger U, Bonekamp D, et al. Radiomic subtyping improves disease stratification beyond key molecular, clinical, and standard imaging characteristics in patients with glioblastoma. Neuro-Oncol . 2018;20:848–857. doi:10.1093/neuonc/nox188.
doi: 10.1093/neuonc/nox188
Kleesiek J, Morshuis JN, Isensee F, et al. Can virtual contrast enhancement in brain MRI replace gadolinium?: a feasibility study. Invest Radiol . 2019;54:653–660. doi:10.1097/RLI.0000000000000583.
doi: 10.1097/RLI.0000000000000583
Ammari S, Bône A, Balleyguier C, et al. Can deep learning replace gadolinium in neuro-oncology?: a reader study. Invest Radiol . 2021. Published online July 28, 2021. doi:10.1097/RLI.0000000000000811.
doi: 10.1097/RLI.0000000000000811