Neuro-oncology最新文献

{"title":"Hippocampal avoidance prophylactic cranial irradiation (HA-PCI) for small cell lung cancer better preserves white matter networks compared to conventional PCI.","authors":"R Colaes, J Blommaert, M Lambrecht, M B de Ruiter, P Pullens, D de Ruysscher, J Belderbos, S Sunaert, S B Schagen, S Deprez","doi":"10.1093/neuonc/noae271","DOIUrl":"https://doi.org/10.1093/neuonc/noae271","url":null,"abstract":"<p><strong>Background: </strong>Hippocampal avoidance during prophylactic cranial irradiation (HA-PCI) is proposed to reduce neurocognitive decline, while preserving the benefits of PCI. We evaluated whether (HA-)PCI induces changes in white matter (WM) microstructure and whether sparing the hippocampus has an impact on preserving brain network topology. Additionally, we evaluated associations between topological metrics with hippocampal volume and neuropsychological outcomes.</p><p><strong>Methods: </strong>In this multicenter randomized phase 3 trial (NCT01780675), small cell lung cancer (SCLC) patients underwent neuropsychological testing and diffusion tensor imaging (DTI) before, 4 months (33 PCI, 37 HA-PCI) and 1 year (19 PCI, 17 HA-PCI) after (HA-)PCI. Changes in WM microstructure were investigated using whole-brain voxel-based analysis of fractional anisotropy (FA) and mean diffusivity (MD). Both hippocampal and whole-brain graph measures were used to evaluate the topological organization of structural networks. Correlation analysis was performed to associate topological metrics with neuropsychological outcomes and hippocampal volume.</p><p><strong>Results: </strong>Both HA-PCI and PCI were associated with decreased FA in major WM tracts, such as the corpus callosum, at 4 months and 1 year post-treatment. While these FA decreases did not differ significantly between treatment groups, only PCI demonstrated increased MD over time. Additionally, PCI showed decreased global efficiency and increased characteristic path length over time when compared to HA-PCI. Significant correlations were found between whole-brain graph measures and neuropsychological outcomes.</p><p><strong>Conclusion: </strong>While both techniques induce important changes in the WM microstructure, HA-PCI might better preserve the topological organization of brain networks than PCI. The neuroprotective role of hippocampal sparing still needs further investigation.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142886102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Next step towards functional precision medicine in neuro-oncology.","authors":"Tobias Weiss, Sohyon Lee, Berend Snijder, Michael Weller","doi":"10.1093/neuonc/noae233","DOIUrl":"https://doi.org/10.1093/neuonc/noae233","url":null,"abstract":"","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142886103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"VGLL-fusions define a new class of intraparenchymal CNS schwannoma.","authors":"Simone Schmid, Kanish Mirchia, Anna Tietze, Ilon Liu, Christin Siewert, Jakob Nückles, Jens Schittenhelm, Felix Behling, Matija Snuderl, Christian Hartmann, Sebastian Brandner, Simon M L Paine, Andrey Korshunov, Martin Hasselblatt, Roland Coras, Sridhar Epari, Christine Stadelmann, Sabrina Zechel, Michèle Simon, Yelena Wilson, Francesca Gianno, G Lucas Calixto-Hope, Viktor Zherebitskiy, Vassil B Kaimaktchiev, Lorraina Robinson, Kenneth Aldape, Eelco W Hoving, Bastiaan B J Tops, Ashwyn Augustine Perera, Pauline Göller, Pablo Hernáiz Driever, Pieter Wesseling, Arend Koch, Arie Perry, Felix Sahm, David T W Jones, David Capper","doi":"10.1093/neuonc/noae269","DOIUrl":"https://doi.org/10.1093/neuonc/noae269","url":null,"abstract":"<p><strong>Background: </strong>Intracerebral schwannomas are rare tumors resembling their peripheral nerve sheath counterparts but localized in the CNS. They are not classified as a separate tumor type in the 2021 WHO classification. This study aimed to compile and characterize these rare neoplasms morphologically and molecularly.</p><p><strong>Methods: </strong>We analyzed 20 tumor samples by histology, RNA Next-Generation Sequencing, DNA-methylation profiling, copy number analyses, and single nucleus RNA sequencing (snRNA-seq). Clinical data, including age, sex, and disease progression, were collected. MRI series were included when available.</p><p><strong>Results: </strong>All cases with tissue available for histology review (n=13) were morphologically consistent with intracerebral schwannoma, but differed in their extent of GFAP staining. All (n=20) shared DNA-methylation profiles distinct from other CNS tumors, as well as from VGLL-altered peripheral nerve sheath tumors. Most cases (n=14/17) harbored fusions of either VGLL3 or VGLL1 (CHD7::VGLL3 (n=9/17) and EWSR1::VGLL1 (n=5/17)). In two cases the presence of a VGLL3 fusion was also confirmed by CNA analyses (n=2/17). MRI (n=4) showed well-defined, nodular tumors with strong, homogeneous enhancement and no diffusion restriction. Tumors were located throughout the neuroaxis [supratentorial (n=15), infratentorial (n=4), and spinal (n=1)]. snRNA-seq of a VGLL1-fused tumor indicated VGLL1 upregulation in 28.6% of tumor cells (n=1). During median follow-up of 1.8 years (range 3 months-9 years), none of the tumors recurred (n=10).</p><p><strong>Conclusions: </strong>We identify and define a new benign tumor class, designated VGLL-altered intraparenchymal CNS schwannomas. These tumors feature VGLL alterations and a specific DNA-methylation profile, with schwannoma-like histopathology and CNS localization, akin to previously classified intracerebral schwannomas.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142877550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Radiographic and visual response to the type II RAF inhibitor tovorafenib in children with relapsed/refractory optic pathway glioma in the FIREFLY-1 trial.","authors":"Karsten Nysom, Lindsay B Kilburn, Sarah E S Leary, Daniel B Landi, Evelien de Vos-Kerkhof, Sébastien Perreault, Olaf Witt, David S Ziegler, Pablo Hernáiz Driever, Andrea T Franson, Patricia A Baxter, Nicholas S Whipple, Cassie Kline, Devorah Segal, Nada Jabado, Simon Bailey, Geoffrey McCowage, Jordan R Hansford, Dong-Anh Khuong-Quang, Nicholas G Gottardo, Timothy Hassall, Jung Woo Han, Michal Yalon Oren, Susan N Chi, Jiaheng Qiu, Daniel Da Costa, Sandya Govinda Raju, Peter Manley, Darren Hargrave","doi":"10.1093/neuonc/noae274","DOIUrl":"https://doi.org/10.1093/neuonc/noae274","url":null,"abstract":"<p><strong>Background: </strong>Due to their anatomical locations, optic pathway gliomas (OPGs) can rarely be cured by resection. Given the importance of preserving visual function, we analyzed radiological and visual acuity (VA) outcomes for the type II RAF inhibitor tovorafenib in the OPG subgroup of the phase 2 FIREFLY-1 trial.</p><p><strong>Methods: </strong>FIREFLY-1 investigated the efficacy (arm 1, n=77), safety, and tolerability (arms 1/2) of tovorafenib (420 mg/m2 once weekly; 600 mg maximum) in patients with BRAF-altered relapsed/refractory pediatric low-grade glioma (pLGG). In this post hoc analysis, anti-tumor activity and VA were analyzed in arm 1 patients with OPG. Anti-tumor activity was independently assessed per Response Assessment in Neuro-Oncology high-grade glioma (RANO-HGG), Response Assessment in Pediatric Neuro-Oncology-LGG (RAPNO) and RANO-LGG criteria. The data cutoff was June 5, 2023.</p><p><strong>Results: </strong>Forty-two of 77 patients had OPGs; 35 of 42 had ≥2 VA assessments. The overall response rate in the OPG subgroup according to RANO-HGG, RAPNO and RANO-LGG criteria were 64%, 50%, and 55%, with clinical benefit rates 95%, 88%, and 90%, respectively. VA per patient was preserved for 80% of patients; 31% demonstrated improved VA; VA per eye was preserved in 87%, with 27% improving. The safety profile in the arm 1 OPG subgroup was similar to the overall FIREFLY-1 safety analysis set.</p><p><strong>Conclusions: </strong>Tovorafenib demonstrated anti-tumor activity in relapsed/refractory BRAF-altered OPG across radiological assessment criteria and was generally well tolerated. Importantly, vision remained stable or improved in most patients.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142864963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NCCN CNS Tumor Guidelines Update for 2024.","authors":"Louis Burt Nabors, Jona Hattangadi-Gluth, Craig Horbinski, Jana Portnow","doi":"10.1093/neuonc/noae267","DOIUrl":"https://doi.org/10.1093/neuonc/noae267","url":null,"abstract":"","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142854746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Molecular classification predicts response to surgery and radiotherapy.","authors":"Gelareh Zadeh, Farshad Nassiri","doi":"10.1093/neuonc/noae230","DOIUrl":"https://doi.org/10.1093/neuonc/noae230","url":null,"abstract":"","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142837690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast intraoperative detection of primary CNS lymphoma and differentiation from common CNS tumors using stimulated Raman histology and deep learning.","authors":"David Reinecke, Nader Maarouf, Andrew Smith, Daniel Alber, John Markert, Nicolas K Goff, Todd C Hollon, Asadur Chowdury, Cheng Jiang, Xinhai Hou, Anna-Katharina Meissner, Gina Fürtjes, Maximilian I Ruge, Daniel Ruess, Thomas Stehle, Abdulkader Al-Shughri, Lisa I Körner, Georg Widhalm, Thomas Roetzer-Pejrimovsky, John G Golfinos, Matija Snuderl, Volker Neuschmelting, Daniel A Orringer","doi":"10.1093/neuonc/noae270","DOIUrl":"10.1093/neuonc/noae270","url":null,"abstract":"<p><strong>Background: </strong>Accurate intraoperative diagnosis is crucial for differentiating between primary CNS lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge.</p><p><strong>Methods: </strong>We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within less than three minutes. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and two additional independent test cohorts. We trained on 54,000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS neoplastic/non-neoplastic lesions. Training and test data were collected from four tertiary international medical centers. The final histopathological diagnosis served as ground-truth.</p><p><strong>Results: </strong>In the prospective test cohort of PCNSL and non-PCNSL entities (n=160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ±0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 77.77%). The additional test cohorts (n=420, n=59) reached balanced accuracy rates of 95.44% ±0.74 and 95.57% ±2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma's capabilities to detect class-specific histomorphological key features.</p><p><strong>Conclusions: </strong>RapidLymphoma proves reliable and valid for intraoperative PCNSL detection and differentiation from other CNS entities. It provides visual feedback within three minutes, enabling fast clinical decision-making and subsequent treatment strategy planning.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel nuclear RNA HSD52 scaffolding NONO/SFPQ complex modulates DNA damage repair to facilitate temozolomide resistance.","authors":"Nan Sun, Qun Chen, Hao Chen, Penggang Sun, Yuxiang Liu, Dan Song, Daohan Yu, Pandeng Wang, Yu Song, Jie Qin, Kaifu Tian, Junzhe Zhong, Wenbin Ma, Hanwen Xuan, Da Qian, Ye Yuan, Tongzheng Chen, Xin Wang, Chuanlu Jiang, Jinquan Cai, Xiangqi Meng","doi":"10.1093/neuonc/noae272","DOIUrl":"https://doi.org/10.1093/neuonc/noae272","url":null,"abstract":"<p><strong>Background: </strong>Temozolomide (TMZ) is used in the treatment of glioblastoma (GBM). However, the primary obstacle remains the emergence of TMZ chemotherapy resistance. NONO and SFPQ are multifunctional nuclear proteins involved in genome stability and gene regulation. However, the specific role of NONO and SFPQ in TMZ resistance of GBM remains to be explored.</p><p><strong>Methods: </strong>RIP-chip and RNA microarray of TMZ-resistant and parental cells were performed for the gain of HSD52. The effects of HSD52 on TMZ resistance were investigated through in vitro assays, intracranial xenograft and GBM organoid models. The underlying mechanisms were explored by DNA methylation chip, RIP, RNA pulldown assays, among others. GBM clinical samples were rolled in to investigate the clinical significance of HSD52.</p><p><strong>Results: </strong>We identified a novel non-coding RNA, HSD52, that was highly expressed in TMZ-resistant GBM and facilitated the interaction between NONO and SFPQ. H3 ubiquitination attenuation and reduced DNMT1 recruitment increased HSD52 transcription via DNA hypo-methylation. HSD52 formed an RNA duplex with UFL1 mRNA, thereby promoting NONO/SFPQ complex binding to UFL1 mRNA and enhancing its stability, and then contributed to TMZ resistance through activating ATM signaling pathway. In vivo xenograft and GBM organoid models showed significant repression in tumor growth after HSD52 knockout with TMZ treatment. In GBM clinical samples, HSD52 was responsible for the malignant progression and TMZ resistance.</p><p><strong>Conclusions: </strong>Our results revealed that HSD52 could serve as a promising therapeutic target to overcome TMZ resistance, improving the clinical efficacy of TMZ chemotherapy in GBM.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"O-GlcNAcylation stabilized WTAP promotes GBM malignant progression in an N6-methyladenosine-dependent manner.","authors":"Jiawei Qiu, Rongrong Zhao, Caizhi Ma, Qingtong Wang, Boyan Li, Yanhua Qi, Ziwen Pan, Shulin Zhao, Shaobo Wang, Zijie Gao, Xiaofan Guo, Wei Qiu, Weijie Tang, Xing Guo, Lin Deng, Hao Xue, Gang Li","doi":"10.1093/neuonc/noae268","DOIUrl":"https://doi.org/10.1093/neuonc/noae268","url":null,"abstract":"<p><strong>Background: </strong>Interactions between mesenchymal glioblastoma stem cells (MES GSCs) and myeloid-derived macrophages (MDMs) shape the tumor-immunosuppressive microenvironment (TIME), promoting the progression of glioblastoma (GBM). N6-methyladenosine (m6A) plays important roles in the tumor progression. However, the mechanism of m6A in shaping the TIME of GBM remains elusive.</p><p><strong>Methods: </strong>Single-cell RNA sequencing and bulk RNA-seq datasets were employed to identify the critical role of WTAP in interactions between MES GBM and MDMs. The biological function of WTAP was confirmed both in vitro and in vivo. Mechanistically, mass spectrum, RNA immunoprecipitation (RIP), and co-immunoprecipitation assays were conducted.</p><p><strong>Results: </strong>Here, we identified that m6A methyltransferase Wilms' Tumor 1-Associated Protein (WTAP), whose protein stability could be synergistically enhanced via OGT-mediated O-GlcNAcylation and USP7-mediated de-ubiquitination, promoted LOXL2 m6A modification to enhance its mRNA stabilization in an IGF2BP2-dependent manner, upregulating secretion of LOXL2 protein (sLOXL2). sLOXL2 then interacted with integrin α5β1 on GSCs to activate FAK-ERK signaling, inducing mesenchymal transition of GSCs in an autocrine manner. Meanwhile, sLOXL2 also activated the integrin α5β1-FAK-ERK axis in MDMs, which promoted M2-like MDM phenotypes in a paracrine pathway, thereby contributing to T cell exhaustion to induce GBM immune escape. In translational medicine, combinations of the OGT inhibitor by targeting WTAP expression and the LOXL2 antagonist by disrupting MES GSC and MDM interactions showed favorable outcomes to the anti-PD1 immunotherapy.</p><p><strong>Conclusions: </strong>WTAP plays critical roles in mesenchymal transition of GSCs and formation of TIME, highlighting the therapeutic potential of targeting WTAP and its downstream effectors to enhance the efficacy of immunotherapy.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-based Prognostic Subgrouping of Glioblastoma: A Multi-center Study.","authors":"Hamed Akbari, Spyridon Bakas, Chiharu Sako, Anahita Fathi Kazerooni, Javier Villanueva-Meyer, Jose A Garcia, Elizabeth Mamourian, Fang Liu, Quy Cao, Russell T Shinohara, Ujjwal Baid, Alexander Getka, Sarthak Pati, Ashish Singh, Evan Calabrese, Susan Chang, Jeffrey Rudie, Aristeidis Sotiras, Pamela LaMontagne, Daniel S Marcus, Mikhail Milchenko, Arash Nazeri, Carmen Balana, Jaume Capellades, Josep Puig, Chaitra Badve, Jill S Barnholtz-Sloan, Andrew E Sloan, Vachan Vadmal, Kristin Waite, Murat Ak, Rivka R Colen, Yae Won Park, Sung Soo Ahn, Jong Hee Chang, Yoon Seong Choi, Seung-Koo Lee, Gregory S Alexander, Ayesha S Ali, Adam P Dicker, Adam E Flanders, Spencer Liem, Joseph Lombardo, Wenyin Shi, Gaurav Shukla, Brent Griffith, Laila M Poisson, Lisa R Rogers, Aikaterini Kotrotsou, Thomas C Booth, Rajan Jain, Matthew Lee, Abhishek Mahajan, Arnab Chakravarti, Joshua D Palmer, Dominic DiCostanzo, Hassan Fathallah-Shaykh, Santiago Cepeda, Orazio Santo Santonocito, Anna Luisa Di Stefano, Benedikt Wiestler, Elias R Melhem, Graeme F Woodworth, Pallavi Tiwari, Pablo Valdes, Yuji Matsumoto, Yoshihiro Otani, Ryoji Imoto, Mariam Aboian, Shinichiro Koizumi, Kazuhiko Kurozumi, Toru Kawakatsu, Kimberley Alexander, Laveniya Satgunaseelan, Aaron M Rulseh, Stephen J Bagley, Michel Bilello, Zev A Binder, Steven Brem, Arati S Desai, Robert A Lustig, Eileen Maloney, Timothy Prior, Nduka Amankulor, Mac Lean P Nasrallah, Donald M O'Rourke, Suyash Mohan, Christos Davatzikos","doi":"10.1093/neuonc/noae260","DOIUrl":"https://doi.org/10.1093/neuonc/noae260","url":null,"abstract":"<p><strong>Background: </strong>Glioblastoma is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification.</p><p><strong>Methods: </strong>We developed a highly reproducible, personalized prognostication and clinical subgrouping system using machine learning (ML) on routine clinical data, MRI, and molecular measures from 2,838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]).</p><p><strong>Results: </strong>The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95%CI: 1.43-1.84, p<0.001) and 3.48 (95%CI: 2.94-4.11, p<0.001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort.</p><p><strong>Conclusions: </strong>Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach for personalized patient management and clinical trial stratification in glioblastoma.</p>","PeriodicalId":19377,"journal":{"name":"Neuro-oncology","volume":" ","pages":""},"PeriodicalIF":16.4,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142813844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}