Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.
- MeSH
- big data * MeSH
- glioblastom * MeSH
- lidé MeSH
- šíření informací MeSH
- strojové učení MeSH
- vzácné nemoci MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- Research Support, N.I.H., Extramural MeSH
Medulloblastoma (MB) comprises a group of heterogeneous paediatric embryonal neoplasms of the hindbrain with strong links to early development of the hindbrain1-4. Mutations that activate Sonic hedgehog signalling lead to Sonic hedgehog MB in the upper rhombic lip (RL) granule cell lineage5-8. By contrast, mutations that activate WNT signalling lead to WNT MB in the lower RL9,10. However, little is known about the more commonly occurring group 4 (G4) MB, which is thought to arise in the unipolar brush cell lineage3,4. Here we demonstrate that somatic mutations that cause G4 MB converge on the core binding factor alpha (CBFA) complex and mutually exclusive alterations that affect CBFA2T2, CBFA2T3, PRDM6, UTX and OTX2. CBFA2T2 is expressed early in the progenitor cells of the cerebellar RL subventricular zone in Homo sapiens, and G4 MB transcriptionally resembles these progenitors but are stalled in developmental time. Knockdown of OTX2 in model systems relieves this differentiation blockade, which allows MB cells to spontaneously proceed along normal developmental differentiation trajectories. The specific nature of the split human RL, which is destined to generate most of the neurons in the human brain, and its high level of susceptible EOMES+KI67+ unipolar brush cell progenitor cells probably predisposes our species to the development of G4 MB.
- MeSH
- antigen Ki-67 metabolismus MeSH
- buněčná diferenciace * genetika MeSH
- buněčný rodokmen MeSH
- histondemethylasy MeSH
- lidé MeSH
- meduloblastom * klasifikace genetika patologie MeSH
- metencephalon * embryologie patologie MeSH
- mozeček embryologie patologie MeSH
- mutace MeSH
- nádory mozečku * klasifikace genetika patologie MeSH
- proteiny hedgehog metabolismus MeSH
- proteiny T-boxu metabolismus MeSH
- represorové proteiny MeSH
- svalové proteiny MeSH
- transkripční faktory Otx nedostatek genetika MeSH
- transkripční faktory PEBP2A genetika MeSH
- transkripční faktory MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Research Support, N.I.H., Extramural MeSH
Sonic hedgehog medulloblastoma encompasses a clinically and molecularly diverse group of cancers of the developing central nervous system. Here, we use unbiased sequencing of the transcriptome across a large cohort of 250 tumors to reveal differences among molecular subtypes of the disease, and demonstrate the previously unappreciated importance of non-coding RNA transcripts. We identify alterations within the cAMP dependent pathway (GNAS, PRKAR1A) which converge on GLI2 activity and show that 18% of tumors have a genetic event that directly targets the abundance and/or stability of MYCN. Furthermore, we discover an extensive network of fusions in focally amplified regions encompassing GLI2, and several loss-of-function fusions in tumor suppressor genes PTCH1, SUFU and NCOR1. Molecular convergence on a subset of genes by nucleotide variants, copy number aberrations, and gene fusions highlight the key roles of specific pathways in the pathogenesis of Sonic hedgehog medulloblastoma and open up opportunities for therapeutic intervention.
- MeSH
- dítě MeSH
- dospělí MeSH
- genetická variace MeSH
- genové regulační sítě MeSH
- kojenec MeSH
- lidé středního věku MeSH
- lidé MeSH
- meduloblastom genetika MeSH
- mladiství MeSH
- mladý dospělý MeSH
- nádory mozečku genetika MeSH
- předškolní dítě MeSH
- proteiny hedgehog genetika MeSH
- regulace genové exprese u nádorů * MeSH
- signální transdukce genetika MeSH
- transkriptom * MeSH
- Check Tag
- dítě MeSH
- dospělí MeSH
- kojenec MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- předškolní dítě MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Research Support, N.I.H., Extramural MeSH
While molecular subgrouping has revolutionized medulloblastoma classification, the extent of heterogeneity within subgroups is unknown. Similarity network fusion (SNF) applied to genome-wide DNA methylation and gene expression data across 763 primary samples identifies very homogeneous clusters of patients, supporting the presence of medulloblastoma subtypes. After integration of somatic copy-number alterations, and clinical features specific to each cluster, we identify 12 different subtypes of medulloblastoma. Integrative analysis using SNF further delineates group 3 from group 4 medulloblastoma, which is not as readily apparent through analyses of individual data types. Two clear subtypes of infants with Sonic Hedgehog medulloblastoma with disparate outcomes and biology are identified. Medulloblastoma subtypes identified through integrative clustering have important implications for stratification of future clinical trials.
- MeSH
- genomika MeSH
- individualizovaná medicína * MeSH
- kohortové studie MeSH
- lidé MeSH
- meduloblastom klasifikace genetika terapie MeSH
- metylace DNA MeSH
- shluková analýza MeSH
- stanovení celkové genové exprese MeSH
- variabilita počtu kopií segmentů DNA MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Patients with incomplete surgical resection of medulloblastoma are controversially regarded as having a marker of high-risk disease, which leads to patients undergoing aggressive surgical resections, so-called second-look surgeries, and intensified chemoradiotherapy. All previous studies assessing the clinical importance of extent of resection have not accounted for molecular subgroup. We analysed the prognostic value of extent of resection in a subgroup-specific manner. METHODS: We retrospectively identified patients who had a histological diagnosis of medulloblastoma and complete data about extent of resection and survival from centres participating in the Medulloblastoma Advanced Genomics International Consortium. We collected from resections done between April, 1997, and February, 2013, at 35 international institutions. We established medulloblastoma subgroup affiliation by gene expression profiling on frozen or formalin-fixed paraffin-embedded tissues. We classified extent of resection on the basis of postoperative imaging as gross total resection (no residual tumour), near-total resection (<1·5 cm(2) tumour remaining), or sub-total resection (≥1·5 cm(2) tumour remaining). We did multivariable analyses of overall survival and progression-free survival using the variables molecular subgroup (WNT, SHH, group 4, and group 3), age (<3 vs ≥3 years old), metastatic status (metastases vs no metastases), geographical location of therapy (North America/Australia vs rest of the world), receipt of chemotherapy (yes vs no) and receipt of craniospinal irradiation (<30 Gy or >30 Gy vs no craniospinal irradiation). The primary analysis outcome was the effect of extent of resection by molecular subgroup and the effects of other clinical variables on overall and progression-free survival. FINDINGS: We included 787 patients with medulloblastoma (86 with WNT tumours, 242 with SHH tumours, 163 with group 3 tumours, and 296 with group 4 tumours) in our multivariable Cox models of progression-free and overall survival. We found that the prognostic benefit of increased extent of resection for patients with medulloblastoma is attenuated after molecular subgroup affiliation is taken into account. We identified a progression-free survival benefit for gross total resection over sub-total resection (hazard ratio [HR] 1·45, 95% CI 1·07-1·96, p=0·16) but no overall survival benefit (HR 1·23, 0·87-1·72, p=0·24). We saw no progression-free survival or overall survival benefit for gross total resection compared with near-total resection (HR 1·05, 0·71-1·53, p=0·8158 for progression-free survival and HR 1·14, 0·75-1·72, p=0·55 for overall survival). No significant survival benefit existed for greater extent of resection for patients with WNT, SHH, or group 3 tumours (HR 1·03, 0·67-1·58, p=0·89 for sub-total resection vs gross total resection). For patients with group 4 tumours, gross total resection conferred a benefit to progression-free survival compared with sub-total resection (HR 1·97, 1·22-3·17, p=0·0056), especially for those with metastatic disease (HR 2·22, 1·00-4·93, p=0·050). However, gross total resection had no effect on overall survival compared with sub-total resection in patients with group 4 tumours (HR 1·67, 0·93-2·99, p=0·084). INTERPRETATION: The prognostic benefit of increased extent of resection for patients with medulloblastoma is attenuated after molecular subgroup affiliation is taken into account. Although maximum safe surgical resection should remain the standard of care, surgical removal of small residual portions of medulloblastoma is not recommended when the likelihood of neurological morbidity is high because there is no definitive benefit to gross total resection compared with near-total resection. FUNDING: Canadian Cancer Society Research Institute, Terry Fox Research Institute, Canadian Institutes of Health Research, National Institutes of Health, Pediatric Brain Tumor Foundation, and the Garron Family Chair in Childhood Cancer Research.
- MeSH
- dítě MeSH
- dospělí MeSH
- kojenec MeSH
- kombinovaná terapie MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- meduloblastom klasifikace genetika patologie chirurgie MeSH
- nádory mozku klasifikace genetika patologie chirurgie MeSH
- předškolní dítě MeSH
- přežití bez známek nemoci MeSH
- prognóza * MeSH
- progrese nemoci MeSH
- retrospektivní studie MeSH
- Check Tag
- dítě MeSH
- dospělí MeSH
- kojenec MeSH
- lidé MeSH
- mužské pohlaví MeSH
- předškolní dítě MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- Geografické názvy
- Kanada MeSH
PURPOSE: Medulloblastoma comprises four distinct molecular subgroups: WNT, SHH, Group 3, and Group 4. Current medulloblastoma protocols stratify patients based on clinical features: patient age, metastatic stage, extent of resection, and histologic variant. Stark prognostic and genetic differences among the four subgroups suggest that subgroup-specific molecular biomarkers could improve patient prognostication. PATIENTS AND METHODS: Molecular biomarkers were identified from a discovery set of 673 medulloblastomas from 43 cities around the world. Combined risk stratification models were designed based on clinical and cytogenetic biomarkers identified by multivariable Cox proportional hazards analyses. Identified biomarkers were tested using fluorescent in situ hybridization (FISH) on a nonoverlapping medulloblastoma tissue microarray (n = 453), with subsequent validation of the risk stratification models. RESULTS: Subgroup information improves the predictive accuracy of a multivariable survival model compared with clinical biomarkers alone. Most previously published cytogenetic biomarkers are only prognostic within a single medulloblastoma subgroup. Profiling six FISH biomarkers (GLI2, MYC, chromosome 11 [chr11], chr14, 17p, and 17q) on formalin-fixed paraffin-embedded tissues, we can reliably and reproducibly identify very low-risk and very high-risk patients within SHH, Group 3, and Group 4 medulloblastomas. CONCLUSION: Combining subgroup and cytogenetic biomarkers with established clinical biomarkers substantially improves patient prognostication, even in the context of heterogeneous clinical therapies. The prognostic significance of most molecular biomarkers is restricted to a specific subgroup. We have identified a small panel of cytogenetic biomarkers that reliably identifies very high-risk and very low-risk groups of patients, making it an excellent tool for selecting patients for therapy intensification and therapy de-escalation in future clinical trials.
- MeSH
- čipová analýza tkání MeSH
- cytogenetika MeSH
- dítě MeSH
- hodnocení rizik MeSH
- hybridizace in situ fluorescenční MeSH
- jaderné proteiny genetika MeSH
- kojenec MeSH
- lidé MeSH
- lidské chromozomy, pár 11 MeSH
- lidské chromozomy, pár 14 MeSH
- meduloblastom genetika mortalita patologie terapie MeSH
- mladiství MeSH
- mladý dospělý MeSH
- nádorové biomarkery genetika MeSH
- prediktivní hodnota testů MeSH
- předškolní dítě MeSH
- prognóza MeSH
- proporcionální rizikové modely MeSH
- proteiny hedgehog * genetika MeSH
- proteiny Wnt * genetika MeSH
- protoonkogenní proteiny c-myc genetika MeSH
- regulace genové exprese u nádorů MeSH
- reprodukovatelnost výsledků MeSH
- rizikové faktory MeSH
- stanovení celkové genové exprese MeSH
- transkripční faktory Krüppel-like genetika MeSH
- Check Tag
- dítě MeSH
- kojenec MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- předškolní dítě MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Research Support, N.I.H., Extramural MeSH
