Abstract
Objectives
To develop and validate a deep learning model for predicting overall survival from whole-brain MRI without tumor segmentation in patients with diffuse gliomas.
Methods
In this multicenter retrospective study, two deep learning models were built for survival prediction from MRI, including a DeepRisk model built from whole-brain MRI, and an original ResNet model built from expert-segmented tumor images. Both models were developed using a training dataset (n = 935) and an internal tuning dataset (n = 156) and tested on two external test datasets (n = 194 and 150) and a TCIA dataset (n = 121). C-index, integrated Brier score (IBS), prediction error curves, and calibration curves were used to assess the model performance.
Results
In total, 1556 patients were enrolled (age, 49.0 ± 13.1 years; 830 male). The DeepRisk score was an independent predictor and can stratify patients in each test dataset into three risk subgroups. The IBS and C-index for DeepRisk were 0.14 and 0.83 in external test dataset 1, 0.15 and 0.80 in external dataset 2, and 0.16 and 0.77 in TCIA dataset, respectively, which were comparable with those for original ResNet. The AUCs at 6, 12, 24, 26, and 48 months for DeepRisk ranged between 0.77 and 0.94. Combining DeepRisk score with clinicomolecular factors resulted in a nomogram with a better calibration and classification accuracy (net reclassification improvement 0.69, p < 0.001) than the clinical nomogram.
Conclusions
DeepRisk that obviated the need of tumor segmentation can predict glioma survival from whole-brain MRI and offers incremental prognostic value.
Key Points
• DeepRisk can predict overall survival directly from whole-brain MRI without tumor segmentation.
• DeepRisk achieves comparable accuracy in survival prediction with deep learning model built using expert-segmented tumor images.
• DeepRisk has independent and incremental prognostic value over existing clinical parameters and IDH mutation status.
Similar content being viewed by others
Change history
19 May 2022
A Correction to this paper has been published: https://doi.org/10.1007/s00330-022-08847-8
Abbreviations
- AUC:
-
Area under the curve
- CNN:
-
Convolutional neural network
- GBM:
-
Glioblastoma
- IBS:
-
Integrated Brier score
- IDH:
-
Isocitrate dehydrogenase
- KPS:
-
Karnofsky performance status
- LrGG:
-
Lower-grade glioma
- NRI:
-
Net reclassification improvement
- ROC:
-
Receiver operating characteristics
- TCIA:
-
The Cancer Imaging Archive
References
Weller M, Wick W, Aldape K, Brada M, Berger M, Pfister SM (2015) Glioma. Nat Rev Dis Primers 1:1–18
Louis DN, Ohgaki H, Wiestler OD et al (2007) The 2007 WHO classification of tumours of the central nervous system. Int Agency for Res on Cancer 114:97–109
Eckel-Passow JE, Lachance DH, Molinaro AM et al (2015) Glioma groups based on 1p/19q, IDH, and TERT promoter mutations in tumors. N Engl J Med 372:2499–2508
Van den Bent MJ, Wefel JS, Schiff D et al (2011) Response assessment in Neuro-Oncol (a report of the RANO group): assessment of outcome in trials of diffuse low-grade gliomas. Lancet Oncol 12:583–593
Sottoriva A, Spiteri I, Piccirillo SGM et al (2013) Intratumor heterogeneity in human glioblastoma reflects cancer evolutionary dynamics. Proc Natl Acad Sci U S A 110:4009–4014
Louis DN, Perry A, Reifenberger G et al (2016) The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Int Agency for Res on Cancer 131:803–820
Louis DN, Perry A, Wesseling P et al (2021) The 2021 WHO classification of tumors of the central nervous system: a summary. [published online June 2, 2021]. Neuro-Oncol. https://doi.org/10.1093/neuonc/noab106
Gittleman H, Sloan AE, Barnholtz-Sloan JS (2020) An independently validated survival nomogram for lower-grade glioma. Neuro-Oncol 22:665–674
Gittleman H, Lim D, Kattan MW et al (2017) An independently validated nomogram for individualized estimation of survival among patients with newly diagnosed glioblastoma: NRG Oncology RTOG 0525 and 0825. Neuro-Oncol 19:669–677
Gittleman H, Cioffi G, Chunduru P et al (2019) An independently validated nomogram for isocitrate dehydrogenase-wild-type glioblastoma patient survival. Neuro-Oncol Adv 1:vdz007
Bae S, Choi YS, Ahn SS et al (2018) Radiomic MRI phenotyping of glioblastoma: improving survival prediction. Radiology 289:797–806
Kickingereder P, Neuberger U, Bonekamp D et al (2018) Radiomic subtyping improves disease stratification beyond key molecular, clinical, and standard imaging characteristics in patients with glioblastoma. Neuro-Oncol 20:848–857
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118
Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122–1131
Jiang Y, Liang X, Wang W et al (2021) Noninvasive prediction of occult peritoneal metastasis in gastric cancer using deep learning. JAMA Netw Open 4:e2032269
Kim H, Goo JM, Lee KH, Kim YT, Park CM (2020) Preoperative CT-based deep learning model for predicting disease-free survival in patients with lung adenocarcinomas. Radiology 296:216–224
Cheng N-M, Yao J, Cai J et al (2021) Deep learning for fully automated prediction of overall survival in patients with oropharyngeal cancer using FDG-PET imaging. [published online June 3, 2021]. Clin Cancer Res. https://doi.org/10.1158/1078-0432.CCR-20-4935
Jiang Y, Jin C, Yu H et al (2020) Development and validation of a deep learning CT signature to predict survival and chemotherapy benefit in gastric cancer: a multicenter, retrospective study. [published online January 6, 2020]. Ann Surg. https://doi.org/10.1097/SLA.0000000000003778
Tang Z, Xu Y, Jin L et al (2020) Deep learning of imaging phenotype and genotype for predicting overall survival time of glioblastoma patients. IEEE Trans Med Imaging 39:2100–2109
Lao J, Chen Y, Li Z-C et al (2017) A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme. Sci Rep 2017:7
Sahm F, Capper D, Jeibmann A et al (2012) Addressing diffuse glioma as a systemic brain disease with single-cell analysis. JAMA Neurol 69:523–526
Agarwal S, Sane R, Oberoi R, Ohlfest JR, Elmquist WF (2011) Delivery of molecularly targeted therapy to malignant glioma, a disease of the whole brain. Expert Rev Mol Med 13:e17
Osswald M, Jung E, Sahm F et al (2015) Brain tumour cells interconnect to a functional and resistant network. Nature 528:93–98
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR):770-778.
Camp RL, Dolled-Filhart M, Rimm DL (2004) X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res 10:7252–7259
Steyerberg EW, Vickers AJ, Cook NR et al (2010) Assessing the performance of prediction models: a framework for some traditional and novel measures. Epidemiology 21:128–138
Cordova JS, Shu H-KG, Liang Z et al (2016) Whole-brain spectroscopic MRI biomarkers identify infiltrating margins in glioblastoma patients. Neuro-Oncology 18:1180–1189
Li X, Strasser B, Jafari-Khouzani K et al (2020) Super-resolution whole-brain 3D MR spectroscopic imaging for mapping D-2-hydroxyglutarate and tumor metabolism in isocitrate dehydrogenase 1–mutated human gliomas. Radiology 294:589–597
Waldman AD, Jackson A, Price SJ et al (2009) Quantitative imaging biomarkers in neuro-oncology. Nat Rev Clin Oncol 6:445–454
Fang L, Wang C, Li S, Rabbani H, Chen X, Liu Z (2019) Attention to lesion: lesion-aware convolutional neural network for retinal optical coherence tomography image classification. IEEE Trans Med Imaging 38:1959–1970
Zhang J, Xie Y, Xia Y, Shen C (2019) Attention residual learning for skin lesion classification. IEEE Trans Med Imaging 38:2092–2103
Guo X, Yuan Y (2020) Semi-supervised WCE image classification with adaptive aggregated attention. Med Image Anal 64:101733
Wang H, Wang S, Qin Z, Zhang Y, Li R, Xia Y (2021) Triple attention learning for classification of 14 thoracic diseases using chest radiography. Med Image Anal 67:101846
Zhang Y, Li H, Du J et al (2021) 3D multi-attention guided multi-task learning network for automatic gastric tumor segmentation and lymph node classification. IEEE Trans Med Imaging 40:1618–1631
Truhn D, Schrading S, Haarburger C, Schneider H, Merhof D, Kuhl C (2019) Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast MRI. Radiology 290:290–297
Sun Q, Lin X, Zhao Y et al (2020) Deep learning vs. radiomics for predicting axillary lymph node metastasis of breast cancer using ultrasound images: don’t forget the peritumoral region. Front Oncol 10(53)
Lou B, Doken S, Zhuang T et al (2019) An image-based deep learning framework for individualising radiotherapy dose: a retrospective analysis of outcome prediction. Lancet Digital Health 1:e136–e147
Zhang B, Yan J, Chen W et al (2021) Machine learning classifier for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery. J Cancer 12:1604–1615
Sun Q, Chen Y, Liang C et al (2021) Biologic pathways underlying prognostic radiomics phenotypes from paired MRI and RNA sequencing in glioblastoma. Radiology 301:654–663
Yan J, Zhao Y, Chen Y et al (2021) Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities. EBioMedicine 72:103583
Gorlia T, Van den Bent M, Hegi ME et al (2008) Nomograms for predicting survival of patients with newly diagnosed glioblastoma: prognostic factor analysis of EORTC and NCIC trial 26981-22981/CE.3. Lancet Oncol 9:29–38
Yang T, Mao P, Chen X et al (2019) Inflammatory biomarkers in prognostic analysis for patients with glioma and the establishment of a nomogram. Oncol Lett 17:2516–2522
Funding
This study has received funding from the National Natural Science Foundation of China (No. U20A20171), Guangdong Basic and Applied Basic Research Foundation (2020B1515120046), Youth Innovation Promotion Association of the Chinese Academy of Sciences (2018364), and Guangdong Key Project (2018B030335001).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The guarantor of this publication is Zhi-Cheng Li.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors (Zhi-Cheng Li) has significant statistical expertise.
Informed consent
Written informed consent was waved by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained.
Methodology
• retrospective
• diagnostic or prognostic study
• multicenter study
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: the co-first authors Zhi-Cheng Li and Jing Yan were not referenced as equally contributing authors. Additionally, the captions to Figure 3, 4 and 6 were displayed incorrectly.
Supplementary Information
ESM 1
(DOCX 4047 kb)
Rights and permissions
About this article
Cite this article
Li, ZC., Yan, J., Zhang, S. et al. Glioma survival prediction from whole-brain MRI without tumor segmentation using deep attention network: a multicenter study. Eur Radiol 32, 5719–5729 (2022). https://doi.org/10.1007/s00330-022-08640-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-022-08640-7