Radiomic- and dosiomic-based clustering development for radio-induced neurotoxicity in pediatric medulloblastoma.
Dosiomics
Neurotoxicity
Pediatric medulloblastoma
Radiomics
Small data
Journal
Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery
ISSN: 1433-0350
Titre abrégé: Childs Nerv Syst
Pays: Germany
ID NLM: 8503227
Informations de publication
Date de publication:
20 Apr 2024
20 Apr 2024
Historique:
received:
10
03
2024
accepted:
15
04
2024
medline:
20
4
2024
pubmed:
20
4
2024
entrez:
20
4
2024
Statut:
aheadofprint
Résumé
Texture analysis extracts many quantitative image features, offering a valuable, cost-effective, and non-invasive approach for individual medicine. Furthermore, multimodal machine learning could have a large impact for precision medicine, as texture biomarkers can underlie tissue microstructure. This study aims to investigate imaging-based biomarkers of radio-induced neurotoxicity in pediatric patients with metastatic medulloblastoma, using radiomic and dosiomic analysis. This single-center study retrospectively enrolled children diagnosed with metastatic medulloblastoma (MB) and treated with hyperfractionated craniospinal irradiation (CSI). Histological confirmation of medulloblastoma and baseline follow-up magnetic resonance imaging (MRI) were mandatory. Treatment involved helical tomotherapy (HT) delivering a dose of 39 Gray (Gy) to brain and spinal axis and a posterior fossa boost up to 60 Gy. Clinical outcomes, such as local and distant brain control and neurotoxicity, were recorded. Radiomic and dosiomic features were extracted from tumor regions on T1, T2, FLAIR (fluid-attenuated inversion recovery) MRI-maps, and radiotherapy dose distribution. Different machine learning feature selection and reduction approaches were performed for supervised and unsupervised clustering. Forty-eight metastatic medulloblastoma patients (29 males and 19 females) with a mean age of 12 ± 6 years were enrolled. For each patient, 332 features were extracted. Greater level of abstraction of input data by combining selection of most performing features and dimensionality reduction returns the best performance. The resulting one-component radiomic signature yielded an accuracy of 0.73 with sensitivity, specificity, and precision of 0.83, 0.64, and 0.68, respectively. Machine learning radiomic-dosiomic approach effectively stratified pediatric medulloblastoma patients who experienced radio-induced neurotoxicity. Strategy needs further validation in external dataset for its potential clinical use in ab initio management paradigms of medulloblastoma.
Sections du résumé
BACKGROUND
BACKGROUND
Texture analysis extracts many quantitative image features, offering a valuable, cost-effective, and non-invasive approach for individual medicine. Furthermore, multimodal machine learning could have a large impact for precision medicine, as texture biomarkers can underlie tissue microstructure. This study aims to investigate imaging-based biomarkers of radio-induced neurotoxicity in pediatric patients with metastatic medulloblastoma, using radiomic and dosiomic analysis.
METHODS
METHODS
This single-center study retrospectively enrolled children diagnosed with metastatic medulloblastoma (MB) and treated with hyperfractionated craniospinal irradiation (CSI). Histological confirmation of medulloblastoma and baseline follow-up magnetic resonance imaging (MRI) were mandatory. Treatment involved helical tomotherapy (HT) delivering a dose of 39 Gray (Gy) to brain and spinal axis and a posterior fossa boost up to 60 Gy. Clinical outcomes, such as local and distant brain control and neurotoxicity, were recorded. Radiomic and dosiomic features were extracted from tumor regions on T1, T2, FLAIR (fluid-attenuated inversion recovery) MRI-maps, and radiotherapy dose distribution. Different machine learning feature selection and reduction approaches were performed for supervised and unsupervised clustering.
RESULTS
RESULTS
Forty-eight metastatic medulloblastoma patients (29 males and 19 females) with a mean age of 12 ± 6 years were enrolled. For each patient, 332 features were extracted. Greater level of abstraction of input data by combining selection of most performing features and dimensionality reduction returns the best performance. The resulting one-component radiomic signature yielded an accuracy of 0.73 with sensitivity, specificity, and precision of 0.83, 0.64, and 0.68, respectively.
CONCLUSIONS
CONCLUSIONS
Machine learning radiomic-dosiomic approach effectively stratified pediatric medulloblastoma patients who experienced radio-induced neurotoxicity. Strategy needs further validation in external dataset for its potential clinical use in ab initio management paradigms of medulloblastoma.
Identifiants
pubmed: 38642113
doi: 10.1007/s00381-024-06416-6
pii: 10.1007/s00381-024-06416-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Von Bueren AO, Kortmann RD, Von Hoff K et al (2016) Treatment of children and adolescents with metastatic medulloblastoma and prognostic relevance of clinical and biologic parameters. J Clin Oncol 34:4151–4160. https://doi.org/10.1200/JCO.2016.67.2428
doi: 10.1200/JCO.2016.67.2428
Ramaswamy V, Taylor MD (2017) Medulloblastoma: from myth to molecular. J Clin Oncol 35:2355–2363. https://doi.org/10.1200/JCO.2017.72.7842
doi: 10.1200/JCO.2017.72.7842
pubmed: 28640708
Millard NE, De Braganca KC (2016) Medulloblastoma. J Child Neurol 31(12):1341–1353. https://doi.org/10.1177/0883073815600866
doi: 10.1177/0883073815600866
pubmed: 26336203
Archer TC, Mahoney EL, Pomeroy SL (2017) Medulloblastoma: molecular classification-based personal therapeutics. Neurotherapeutics 14:265–273. https://doi.org/10.1007/S13311-017-0526-Y/TABLES/1
doi: 10.1007/S13311-017-0526-Y/TABLES/1
pubmed: 28386677
pmcid: 5398996
Bouffet E (2021) Management of high-risk medulloblastoma. Neurochirurgie 67:61–68. https://doi.org/10.1016/J.NEUCHI.2019.05.007
doi: 10.1016/J.NEUCHI.2019.05.007
pubmed: 31229532
Parsons DW, Li M, Zhang X et al (2011) The genetic landscape of the childhood cancer medulloblastoma. Science 331:435–439. https://doi.org/10.1126/SCIENCE.1198056
doi: 10.1126/SCIENCE.1198056
pubmed: 21163964
Tamayo P, Cho YJ, Tsherniak A et al (2011) Predicting relapse in patients with medulloblastoma by integrating evidence from clinical and genomic features. J Clin Oncol 29:1415–1423. https://doi.org/10.1200/JCO.2010.28.1675
doi: 10.1200/JCO.2010.28.1675
pubmed: 21357789
pmcid: 3082982
Packer RJ, Zhou T, Holmes E et al (2013) Survival and secondary tumors in children with medulloblastoma receiving radiotherapy and adjuvant chemotherapy: results of Children’s Oncology Group trial A9961. Neuro Oncol 15:97–103. https://doi.org/10.1093/NEUONC/NOS267
doi: 10.1093/NEUONC/NOS267
pubmed: 23099653
Lorenzi M, McMillan AJ, Siegel LS et al (2009) Educational outcomes among survivors of childhood cancer in British Columbia, Canada: report of the Childhood/Adolescent/Young Adult Cancer Survivors (CAYACS) Program. Cancer 115:2234–2245. https://doi.org/10.1002/CNCR.24267
doi: 10.1002/CNCR.24267
pubmed: 19326396
Moxon-Emre I, Bouffet E, Taylor MD et al (2014) Impact of craniospinal dose, boost volume, and neurologic complications on intellectual outcome in patients with medulloblastoma. J Clin Oncol 32:1760–1768. https://doi.org/10.1200/JCO.2013.52.3290
doi: 10.1200/JCO.2013.52.3290
pubmed: 24516024
Seidel C, Heider S, Hau P et al (2021) Radiotherapy in medulloblastoma-evolution of treatment, current concepts and future perspectives. Cancers 13(23):5945. https://doi.org/10.3390/cancers13235945
doi: 10.3390/cancers13235945
pubmed: 34885055
pmcid: 8657317
Perreault S, Ramaswamy V, Achrol AS et al (2014) MRI surrogates for molecular subgroups of medulloblastoma. Am J Neuroradiol 35:1263–1269. https://doi.org/10.3174/ajnr.A3990
doi: 10.3174/ajnr.A3990
pubmed: 24831600
pmcid: 4819007
Nichelli L, Casagranda S (2021) Current emerging MRI tools for radionecrosis and pseudoprogression diagnosis. Curr Opin Oncol 33:597–607. https://doi.org/10.1097/CCO.0000000000000793
doi: 10.1097/CCO.0000000000000793
pubmed: 34534142
pmcid: 8528135
Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762. https://doi.org/10.1038/NRCLINONC.2017.141
doi: 10.1038/NRCLINONC.2017.141
pubmed: 28975929
Zhang S, Song G, Zang Y et al (2018) Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery. Eur Radiol 28:3692–3701. https://doi.org/10.1007/S00330-017-5180-6
doi: 10.1007/S00330-017-5180-6
pubmed: 29572634
Sun R, Limkin EJ, Vakalopoulou M et al (2018) A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol 19:1180–1191. https://doi.org/10.1016/S1470-2045(18)30413-3
doi: 10.1016/S1470-2045(18)30413-3
pubmed: 30120041
Kickingereder P, Götz M, Muschelli J et al (2016) Large-scale radiomic profiling of recurrent glioblastoma identifies an imaging predictor for stratifying anti-angiogenic treatment response. Clin Cancer Res 22:5765–5771. https://doi.org/10.1158/1078-0432.CCR-16-0702
doi: 10.1158/1078-0432.CCR-16-0702
pubmed: 27803067
pmcid: 5503450
Buizza G, Paganelli C, D’Ippolito E et al (2021) Radiomics and dosiomics for predicting local control after carbon-ion radiotherapy in skull-base chordoma. Cancers (Basel) 13:1–15. https://doi.org/10.3390/cancers13020339
doi: 10.3390/cancers13020339
Kinsella T, Deasy JO (1993) Tomotherapy: A new concept for the delivery of dynamic conformal radiotherapy. Med Phys 20:1709–1719. https://doi.org/10.1118/1.596958
doi: 10.1118/1.596958
pubmed: 8309444
Van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339
doi: 10.1158/0008-5472.CAN-17-0339
pubmed: 29092951
pmcid: 5672828
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97:273–324. https://doi.org/10.1016/s0004-3702(97)00043-x
doi: 10.1016/s0004-3702(97)00043-x
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 785–794. https://doi.org/10.1145/2939672.2939785
Rendón E, Abundez I, Arizmendi A, Quiroz EM (2011) Internal versus external cluster validation indexes. Int J Comput Commun 5:27–34
Liu ZM, Zhang H, Ge M et al (2022) Radiomics signature for the prediction of progression-free survival and radiotherapeutic benefits in pediatric medulloblastoma. Childs Nerv Syst 38:1085–1094. https://doi.org/10.1007/S00381-022-05507-6
doi: 10.1007/S00381-022-05507-6
pubmed: 35394210
Yan J, Zhang S, Li KKW et al (2020) Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma. EBioMedicine 61:103093. https://doi.org/10.1016/j.ebiom.2020.103093
doi: 10.1016/j.ebiom.2020.103093
pubmed: 33096488
pmcid: 7581926
Zheng H, Li J, Liu H et al (2021) Clinical-MRI radiomics enables the prediction of preoperative cerebral spinal fluid dissemination in children with medulloblastoma. World J Surg Oncol 19:134. https://doi.org/10.1186/s12957-021-02239-w
doi: 10.1186/s12957-021-02239-w
pubmed: 33888125
pmcid: 8063474
Zhou L, Peng H, Ji Q et al (2021) Radiomic signatures based on multiparametric MR images for predicting Ki-67 index expression in medulloblastoma. Ann Transl Med 9:1665–1665. https://doi.org/10.21037/ATM-21-5348
doi: 10.21037/ATM-21-5348
pubmed: 34988174
pmcid: 8667089
Zheng H, Li J, Liu H et al (2023) MRI radiomics signature of pediatric medulloblastoma improves risk stratification beyond clinical and conventional MR imaging features. J Magn Reson Imaging 58:236–246. https://doi.org/10.1002/jmri.28537
doi: 10.1002/jmri.28537
pubmed: 36412264
Chang FC, Wong TT, Wu KS et al (2021) Magnetic resonance radiomics features and prognosticators in different molecular subtypes of pediatric medulloblastoma. PLoS One 16(7):e0255500. https://doi.org/10.1371/journal.pone.0255500
doi: 10.1371/journal.pone.0255500
pubmed: 34324588
pmcid: 8321137
Larracy R, Phinyomark A, Scheme E (2021) Machine learning model validation for early stage studies with small sample sizes. Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Int Conf 2021:2314–2319. https://doi.org/10.1109/EMBC46164.2021.9629697
doi: 10.1109/EMBC46164.2021.9629697
An C, Park YW, Ahn SS et al (2021) Radiomics machine learning study with a small sample size: single random training-test set split may lead to unreliable results. PLoS ONE 16:e0256152. https://doi.org/10.1371/JOURNAL.PONE.0256152
doi: 10.1371/JOURNAL.PONE.0256152
pubmed: 34383858
pmcid: 8360533