Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma.
Deep learning
Grad-CAM
Model explainability
OS prediction
PCNSL
Journal
International journal of computer assisted radiology and surgery
ISSN: 1861-6429
Titre abrégé: Int J Comput Assist Radiol Surg
Pays: Germany
ID NLM: 101499225
Informations de publication
Date de publication:
Oct 2023
Oct 2023
Historique:
received:
09
12
2022
accepted:
27
03
2023
medline:
13
9
2023
pubmed:
21
4
2023
entrez:
21
04
2023
Statut:
ppublish
Résumé
Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance is of utmost importance as it has the potential to aid clinical decision-making. Though radiomics-based machine learning (ML) has demonstrated the promising performance in PCNSL, it demands large amounts of manual feature extraction efforts from magnetic resonance images beforehand. deep learning (DL) overcomes this limitation. In this paper, we tailored the 3D ResNet to predict the OS of patients with PCNSL. To overcome the limitation of data sparsity, we introduced data augmentation and transfer learning, and we evaluated the results using r stratified k-fold cross-validation. To explain the results of our model, gradient-weighted class activation mapping was applied. We obtained the best performance (the standard error) on post-contrast T1-weighted (T1Gd)-area under curve [Formula: see text], accuracy [Formula: see text], precision [Formula: see text], recall [Formula: see text] and F1-score [Formula: see text], while compared with ML-based models on clinical data and radiomics data, respectively, further confirming the stability of our model. Also, we observed that PCNSL is a whole-brain disease and in the cases where the OS is less than 1 year, it is more difficult to distinguish the tumor boundary from the normal part of the brain, which is consistent with the clinical outcome. All these findings indicate that T1Gd can improve prognosis predictions of patients with PCNSL. To the best of our knowledge, this is the first time to use DL to explain model patterns in OS classification of patients with PCNSL. Future work would involve collecting more data of patients with PCNSL, or additional retrospective studies on different patient populations with rare diseases, to further promote the clinical role of our model.
Identifiants
pubmed: 37083973
doi: 10.1007/s11548-023-02886-2
pii: 10.1007/s11548-023-02886-2
pmc: PMC10497660
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1849-1856Informations de copyright
© 2023. The Author(s).
Références
Grommes C, DeAngelis LM (2017) Primary cns lymphoma. J Clin Oncol 35(21):2410
doi: 10.1200/JCO.2017.72.7602
pubmed: 28640701
pmcid: 5516483
Ferreri AJM (2017) Therapy of primary cns lymphoma: role of intensity, radiation, and novel agents. Hematol Am Soc Hematol Educ Program Book 2017(1):565–577
doi: 10.1182/asheducation-2017.1.565
Korfel A, Schlegel U (2013) Diagnosis and treatment of primary cns lymphoma. Nat Rev Neurol 9(6):317–327
doi: 10.1038/nrneurol.2013.83
pubmed: 23670107
Driscoll JJ, Rixe O (2009) Overall survival: still the gold standard: why overall survival remains the definitive end point in cancer clinical trials. Cancer J 15(5):401–405
doi: 10.1097/PPO.0b013e3181bdc2e0
pubmed: 19826360
Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563
doi: 10.1148/radiol.2015151169
pubmed: 26579733
Tomaszewski MR, Gillies RJ (2021) The biological meaning of radiomic features. Radiology 298(3):505
doi: 10.1148/radiol.2021202553
pubmed: 33399513
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Cai Y, Shaoju W, Zhao W, Li Z, Zheyang W, Ji S (2018) Concussion classification via deep learning using whole-brain white matter fiber strains. PLoS ONE 13(5):e0197992
doi: 10.1371/journal.pone.0197992
pubmed: 29795640
pmcid: 5967816
Vehtari A, Lampinen J (2002) Bayesian model assessment and comparison using cross-validation predictive densities. Neural Comput 14(10):2439–2468
doi: 10.1162/08997660260293292
pubmed: 12396570
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618–626
Zhang Y, Hong D, McClement D, Oladosu O, Pridham G, Slaney G (2021) Grad-cam helps interpret the deep learning models trained to classify multiple sclerosis types using clinical brain magnetic resonance imaging. J Neurosci Methods 353:109098
doi: 10.1016/j.jneumeth.2021.109098
pubmed: 33582174
Irie R, Otsuka Y, Hagiwara A, Kamagata K, Kamiya K, Suzuki M, Wada A, Maekawa T, Fujita S, Kato S (2020) A novel deep learning approach with a 3d convolutional ladder network for differential diagnosis of idiopathic normal pressure hydrocephalus and Alzheimer’s disease. Magn Resonan Med Sci mp–2019
Nguyen AV, Blears EE, Ross E, Lall RR, Ortega-Barnett J (2018) Machine learning applications for the differentiation of primary central nervous system lymphoma from glioblastoma on imaging: a systematic review and meta-analysis. Neurosurg Focus 45(5):E5
doi: 10.3171/2018.8.FOCUS18325
pubmed: 30453459
Suh CH, Kim HS, Jung SC, Park JE, Choi CG, Kim SJ (2019) Mri as a diagnostic biomarker for differentiating primary central nervous system lymphoma from glioblastoma: a systematic review and meta-analysis. J Magn Reson Imaging 50(2):560–572
doi: 10.1002/jmri.26602
pubmed: 30637843
Chen C, Zheng A, Ou X, Wang J, Ma X (2020) Comparison of radiomics-based machine-learning classifiers in diagnosis of glioblastoma from primary central nervous system lymphoma. Front Oncol 10:1151
doi: 10.3389/fonc.2020.01151
pubmed: 33042784
pmcid: 7522159
Weninger L, Haarburger C, Merhof D (2019) Robustness of radiomics for survival prediction of brain tumor patients depending on resection status. Front Comput Neurosci 13:73
doi: 10.3389/fncom.2019.00073
pubmed: 31780915
pmcid: 6857096
Liu S, Liu S, Cai W, Pujol S, Kikinis R, Feng D (2014) Early diagnosis of Alzheimer’s disease with deep learning. In: 2014 IEEE 11th international symposium on biomedical imaging (ISBI). IEEE, pp 1015–1018
Chen W, Liu B, Peng S, Sun J, Qiao X (2018) S3d-unet: separable 3d u-net for brain tumor segmentation. In: International MICCAI Brainlesion workshop. Springer, pp 358–368
He Yu, Ian P, Bingting B, Kasey H, Marcello C, Hui L, Shuping P, Sebro Ronnie A, Jing G, Thomas Y (2020) Deep learning-based classification of primary bone tumors on radiographs: a preliminary study. EBioMedicine 62:103121
doi: 10.1016/j.ebiom.2020.103121
pubmed: 33232868
pmcid: 7689511
Yoo TK, Choi JY, Kim HK, Ryu IH, Kim JK (2021) Adopting low-shot deep learning for the detection of conjunctival melanoma using ocular surface images. Comput Methods Programs Biomed 205:106086
doi: 10.1016/j.cmpb.2021.106086
pubmed: 33862570
https://www.slicer.org
Moradmand H, Aghamiri SMR, Ghaderi R (2020) Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J Appl Clin Med Phys 21(1):179–190
doi: 10.1002/acm2.12795
pubmed: 31880401
Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, Roth HR, Xu D (2022) Unetr: transformers for 3d medical image segmentation. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision pp 574–584
Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, Burren Y, Porz N, Slotboom J, Wiest R (2014) The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans Med Imaging 34(10):1993–2024
doi: 10.1109/TMI.2014.2377694
pubmed: 25494501
pmcid: 4833122
https://en.wikipedia.org/wiki/Student
Bonekamp D, Deike K, Wiestler B, Wick W, Bendszus M, Radbruch A, Heiland S (2015) Association of overall survival in patients with newly diagnosed glioblastoma with contrast-enhanced perfusion mri: comparison of intraindividually matched t1-and t2*-based bolus techniques. J Magn Reson Imaging 42(1):87–96
doi: 10.1002/jmri.24756
pubmed: 25244574
Chan H-W, Weng Y-T, Huang T-Y (2020) Automatic classification of brain tumor types with the MRI scans and histopathology images pp 353–359
Ma D, Gulani V, Seiberlich N, Liu K, Sunshine JL, Duerk JL, Griswold MA (2013) Magnetic resonance fingerprinting. Nature 495(7440):187–192
doi: 10.1038/nature11971
pubmed: 23486058
pmcid: 3602925
Lai R, Rosenblum MK, DeAngelis LM (2002) Primary cns lymphoma: a whole-brain disease? Neurology 59(10):1557–1562
doi: 10.1212/01.WNL.0000034256.20173.EA
pubmed: 12451197
Chen B, Wang H, Ge P, Zhao J, Li W, Huizi G, Wang G, Luo Y, Chen D (2012) Gross total resection of glioma with the intraoperative fluorescence-guidance of fluorescein sodium. Int J Med Sci 9(8):708
doi: 10.7150/ijms.4843
pubmed: 23091408
pmcid: 3477680
Yun J, Iwamoto FM, Sonabend AM (2016) Primary central nervous system lymphoma: a critical review of the role of surgery for resection. Arch Cancer Res 4(2):71
doi: 10.21767/2254-6081.100071
pubmed: 28239600
pmcid: 5321213