Browsing by Author "Thompson, Eric M"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    An international study presenting a federated learning AI platform for pediatric brain tumors.
    (Nature communications, 2024-09) Lee, Edward H; Han, Michelle; Wright, Jason; Kuwabara, Michael; Mevorach, Jacob; Fu, Gang; Choudhury, Olivia; Ratan, Ujjwal; Zhang, Michael; Wagner, Matthias W; Goetti, Robert; Toescu, Sebastian; Perreault, Sebastien; Dogan, Hakan; Altinmakas, Emre; Mohammadzadeh, Maryam; Szymanski, Kathryn A; Campen, Cynthia J; Lai, Hollie; Eghbal, Azam; Radmanesh, Alireza; Mankad, Kshitij; Aquilina, Kristian; Said, Mourad; Vossough, Arastoo; Oztekin, Ozgur; Ertl-Wagner, Birgit; Poussaint, Tina; Thompson, Eric M; Ho, Chang Y; Jaju, Alok; Curran, John; Ramaswamy, Vijay; Cheshier, Samuel H; Grant, Gerald A; Wong, S Simon; Moseley, Michael E; Lober, Robert M; Wilms, Mattias; Forkert, Nils D; Vitanza, Nicholas A; Miller, Jeffrey H; Prolo, Laura M; Yeom, Kristen W
    While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.
  • Thumbnail Image
    ItemOpen Access
    Prognostic value of medulloblastoma extent of resection after accounting for molecular subgroup: a retrospective integrated clinical and molecular analysis.
    (The Lancet. Oncology, 2016-04) Thompson, Eric M; Hielscher, Thomas; Bouffet, Eric; Remke, Marc; Luu, Betty; Gururangan, Sridharan; McLendon, Roger E; Bigner, Darell D; Lipp, Eric S; Perreault, Sebastien; Cho, Yoon-Jae; Grant, Gerald; Kim, Seung-Ki; Lee, Ji Yeoun; Rao, Amulya A Nageswara; Giannini, Caterina; Li, Kay Ka Wai; Ng, Ho-Keung; Yao, Yu; Kumabe, Toshihiro; Tominaga, Teiji; Grajkowska, Wieslawa A; Perek-Polnik, Marta; Low, David CY; Seow, Wan Tew; Chang, Kenneth TE; Mora, Jaume; Pollack, Ian F; Hamilton, Ronald L; Leary, Sarah; Moore, Andrew S; Ingram, Wendy J; Hallahan, Andrew R; Jouvet, Anne; Fèvre-Montange, Michelle; Vasiljevic, Alexandre; Faure-Conter, Cecile; Shofuda, Tomoko; Kagawa, Naoki; Hashimoto, Naoya; Jabado, Nada; Weil, Alexander G; Gayden, Tenzin; Wataya, Takafumi; Shalaby, Tarek; Grotzer, Michael; Zitterbart, Karel; Sterba, Jaroslav; Kren, Leos; Hortobágyi, Tibor; Klekner, Almos; László, Bognár; Pócza, Tímea; Hauser, Peter; Schüller, Ulrich; Jung, Shin; Jang, Woo-Youl; French, Pim J; Kros, Johan M; van Veelen, Marie-Lise C; Massimi, Luca; Leonard, Jeffrey R; Rubin, Joshua B; Vibhakar, Rajeev; Chambless, Lola B; Cooper, Michael K; Thompson, Reid C; Faria, Claudia C; Carvalho, Alice; Nunes, Sofia; Pimentel, José; Fan, Xing; Muraszko, Karin M; López-Aguilar, Enrique; Lyden, David; Garzia, Livia; Shih, David JH; Kijima, Noriyuki; Schneider, Christian; Adamski, Jennifer; Northcott, Paul A; Kool, Marcel; Jones, David TW; Chan, Jennifer A; Nikolic, Ana; Garre, Maria Luisa; Van Meir, Erwin G; Osuka, Satoru; Olson, Jeffrey J; Jahangiri, Arman; Castro, Brandyn A; Gupta, Nalin; Weiss, William A; Moxon-Emre, Iska; Mabbott, Donald J; Lassaletta, Alvaro; Hawkins, Cynthia E; Tabori, Uri; Drake, James; Kulkarni, Abhaya; Dirks, Peter; Rutka, James T; Korshunov, Andrey; Pfister, Stefan M; Packer, Roger J; Ramaswamy, Vijay; Taylor, Michael D

    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.
  • Thumbnail Image
    ItemOpen Access
    Ratios of head circumference to ventricular size vary over time and predict eventual need for CSF diversion in intraventricular hemorrhage of prematurity.
    (Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery, 2024-03) Venkatraman, Vishal; Harward, Stephen C; Bhasin, Srijan; Calderon, Kylie; Atkins, Sage L; Liu, Beiyu; Lee, Hui-Jie; Chow, Shein-Chung; Fuchs, Herbert E; Thompson, Eric M

    Purpose

    Intraventricular hemorrhage (IVH) of prematurity can lead to hydrocephalus, sometimes necessitating permanent cerebrospinal fluid (CSF) diversion. We sought to characterize the relationship between head circumference (HC) and ventricular size in IVH over time to evaluate the clinical utility of serial HC measurements as a metric in determining the need for CSF diversion.

    Methods

    We included preterm infants with IVH born between January 2000 and May 2020. Three measures of ventricular size were obtained: ventricular index (VI), Evan's ratio (ER), and frontal occipital head ratio (FOHR). The Pearson correlations (r) between the initial (at birth) paired measurements of HC and ventricular size were reported. Multivariable longitudinal regression models were fit to examine the HC:ventricle size ratio, adjusting for the age of the infant, IVH grade (I/II vs. III/IV), need for CSF diversion, and sex.

    Results

    A total of 639 patients with an average gestational age of 27.5 weeks were included. IVH grade I/II and grade III/IV patients had a positive correlation between initial HC and VI (r = 0.47, p < 0.001 and r = 0.48, p < 0.001, respectively). In our longitudinal models, patients with a low-grade IVH (I/II) had an HC:VI ratio 0.52 higher than those with a high-grade IVH (p-value < 0.001). Patients with low-grade IVH had an HC:ER ratio 12.94 higher than those with high-grade IVH (p-value < 0.001). Patients with low-grade IVH had a HC:FOHR ratio 12.91 higher than those with high-grade IVH (p-value < 0.001). Infants who did not require CSF diversion had an HC:VI ratio 0.47 higher than those who eventually did (p < 0.001). Infants without CSF diversion had an HC:ER ratio 16.53 higher than those who received CSF diversion (p < 0.001). Infants without CSF diversion had an HC:FOHR ratio 15.45 higher than those who received CSF diversion (95% CI (11.34, 19.56), p < 0.001).

    Conclusions

    There is a significant difference in the ratio of HC:VI, HC:ER, and HC:FOHR size between patients with high-grade IVH and low-grade IVH. Likewise, there is a significant difference in HC:VI, HC:ER, and HC:FOHR between those who did and did not have CSF diversion. The routine assessments of both head circumference and ventricle size by ultrasound are important clinical tools in infants with IVH of prematurity.