Training and Comparison of nnU-Net and DeepMedic Methods for Autosegmentation of Pediatric Brain Tumors.

BACKGROUND AND PURPOSE: Tumor segmentation is essential in surgical and treatment planning and response assessment and monitoring in pediatric brain tumors, the leading cause of cancer-related death among children. However, manual segmentation is time-consuming and has high interoperator variability, underscoring the need for more efficient methods. After training, we compared 2 deep-learning-based 3D segmentation models, DeepMedic and nnU-Net, with pediatric-specific multi-institutional brain tumor data based on multiparametric MR images. MATERIALS AND METHODS: Multiparametric preoperative MR imaging scans of 339 pediatric patients (n = 293 internal and n = 46 external cohorts) with a variety of tumor subtypes were preprocessed and manually segmented into 4 tumor subregions, ie, enhancing tumor, nonenhancing tumor, cystic components, and peritumoral edema. After training, performances of the 2 models on internal and external test sets were evaluated with reference to ground truth manual segmentations. Additionally, concordance was assessed by comparing the volume of the subregions as a percentage of the whole tumor between model predictions and ground truth segmentations using the Pearson or Spearman correlation coefficients and the Bland-Altman method. RESULTS: The mean Dice score for nnU-Net internal test set was 0.9 (SD, 0.07) (median, 0.94) for whole tumor; 0.77 (SD, 0.29) for enhancing tumor; 0.66 (SD, 0.32) for nonenhancing tumor; 0.71 (SD, 0.33) for cystic components, and 0.71 (SD, 0.40) for peritumoral edema, respectively. For DeepMedic, the mean Dice scores were 0.82 (SD, 0.16) for whole tumor; 0.66 (SD, 0.32) for enhancing tumor; 0.48 (SD, 0.27) for nonenhancing tumor; 0.48 (SD, 0.36) for cystic components, and 0.19 (SD, 0.33) for peritumoral edema, respectively. Dice scores were significantly higher for nnU-Net (P ≤ .01). Correlation coefficients for tumor subregion percentage volumes were higher (0.98 versus 0.91 for enhancing tumor, 0.97 versus 0.75 for nonenhancing tumor, 0.98 versus 0.80 for cystic components, 0.95 versus 0.33 for peritumoral edema in the internal test set). Bland-Altman plots were better for nnU-Net compared with DeepMedic. External validation of the trained nnU-Net model on the multi-institutional Brain Tumor Segmentation Challenge in Pediatrics (BraTS-PEDs) 2023 data set revealed high generalization capability in the segmentation of whole tumor, tumor core (a combination of enhancing tumor, nonenhancing tumor, and cystic components), and enhancing tumor with mean Dice scores of 0.87 (SD, 0.13) (median, 0.91), 0.83 (SD, 0.18) (median, 0.89), and 0.48 (SD, 0.38) (median, 0.58), respectively. CONCLUSIONS: The pediatric-specific data-trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.

Towards Consistency in Pediatric Brain Tumor Measurements: Challenges, Solutions, and the Role of AI-Based Segmentation.

MR imaging is central to the assessment of tumor burden and changes over time in neuro-oncology. Several response assessment guidelines have been set forth by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working groups in different tumor histologies; however, the visual delineation of tumor components using MRIs is not always straightforward, and complexities not currently addressed by these criteria can introduce inter- and intra-observer variability in manual assessments. Differentiation of non-enhancing tumor from peritumoral edema, mild enhancement from absence of enhancement, and various cystic components can be challenging; particularly given a lack of sufficient and uniform imaging protocols in clinical practice. Automated tumor segmentation with artificial intelligence (AI) may be able to provide more objective delineations, but rely on accurate and consistent training data created manually (ground truth). Herein, this paper reviews existing challenges and potential solutions to identifying and defining subregions of pediatric brain tumors (PBTs) that are not explicitly addressed by current guidelines. The goal is to assert the importance of defining and adopting criteria for addressing these challenges, as it will be critical to achieving standardized tumor measurements and reproducible response assessment in PBTs, ultimately leading to more precise outcome metrics and accurate comparisons among clinical studies.

A longitudinal single-cell and spatial multiomic atlas of pediatric high-grade glioma.

Pediatric high-grade glioma (pHGG) is an incurable central nervous system malignancy that is a leading cause of pediatric cancer death. While pHGG shares many similarities to adult glioma, it is increasingly recognized as a molecularly distinct, yet highly heterogeneous disease. In this study, we longitudinally profiled a molecularly diverse cohort of 16 pHGG patients before and after standard therapy through single-nucleus RNA and ATAC sequencing, whole-genome sequencing, and CODEX spatial proteomics to capture the evolution of the tumor microenvironment during progression following treatment. We found that the canonical neoplastic cell phenotypes of adult glioblastoma are insufficient to capture the range of tumor cell states in a pediatric cohort and observed differential tumor-myeloid interactions between malignant cell states. We identified key transcriptional regulators of pHGG cell states and did not observe the marked proneural to mesenchymal shift characteristic of adult glioblastoma. We showed that essential neuromodulators and the interferon response are upregulated post-therapy along with an increase in non-neoplastic oligodendrocytes. Through in vitro pharmacological perturbation, we demonstrated novel malignant cell-intrinsic targets. This multiomic atlas of longitudinal pHGG captures the key features of therapy response that support distinction from its adult counterpart and suggests therapeutic strategies which are targeted to pediatric gliomas.

Technical note: Traumatic atlanto-occipital dislocation and severe subaxial cervical distraction injury in an infant.

INTRODUCTION: Traumatic injuries of the spine requiring surgery are rare in infancy. Fusion procedures in the very young are not well-described at the atlanto-occipital junction or subaxial spine. Here we describe novel segmental posterior instrumentation in a severe spinal column disruption in an infant. CASE PRESENTATION: A 13-month-old male with atlanto-occipital dislocation and severe C6-7 distraction (ASIA impairment scale A) presented after a motor vehicle accident. He underwent instrumented fusion (occiput-C2 and C6-7) and halo placement. Postoperative imaging demonstrated reduction of the C6-7 vertebral bodies. Physical examination showed lower limb paraplegia and preserved upper extremity strength except for mild weakness in hand grip (3/5 on the MRC grading scale). Occiput-C2 instrumentation was performed using occipital keel and C2 pedicle screws with sublaminar C1 polyester tape. C6-7 reduction and fixation was performed with laminar hooks. Arthrodesis was promoted with lineage-committed cellular bone matrix allograft and suboccipital autograft. Anterior column stabilization was deferred secondary to a CSF leak. Intraoperative monitoring was performed throughout the procedure. Within 1 month after surgery the patient was able to manipulate objects against gravity. CT imaging revealed bony fusion and spontaneous reduction of C6-7. DISCUSSION: Spinal instrumentation is technically challenging in infants, regardless of injury mechanism, particularly in cases with complete spinal column disruption, but an anterior fusion may be avoided in infants and small children with posterior stabilization and halo placement.

Systematic review and cumulative analysis of clinical properties of BRAF V600E mutations in PLNTY histological samples.

PURPOSE: Polymorphous low-grade neuroepithelial tumors of the young (PLNTY) represent a rare pediatric-type tumor that most commonly presents as medically refractory epilepsy. PLNTY has only recently been recognized as a distinct clinical entity, having been first described in 2016 and added to the World Health Organization classification of CNS tumors in 2021. Molecular studies have determined that PLNTY is uniformly driven by aberrant MAPK pathway activation, with most tumors carrying either a BRAF V600E mutation or activating FGFR2 or FGFR3 fusion protein. Although it is known that these driver mutations are mutually exclusive, little is known about differences in clinical presentation or treatment outcomes between PLNTY cases driven by these distinct mutations. METHODS: We performed a systematic review and cumulative analysis of PLNTY cases to assess whether or not PLNTY tumors carrying the BRAF V600E mutation exhibit different clinical behaviors. By searching the literature for all cases of PLNTY wherein BRAF V600E status was characterized, we compiled a dataset of 62 unique patient instances. Using a logistic regression-based approach, we assessed a primary outcome of what factors of a clinical presentation were associated with BRAF V600E mutations and a secondary outcome of what factors predicted total seizure freedom post-surgical resection. RESULTS: PLNTY cases carrying BRAF V600E mutations in the literature were strongly positively associated with adult patients (p = 0.0055, OR = 6.556; 95% Conf. Int. = 1.737-24.742). BRAF V600E status was also positively associated with tumor involvement of the temporal lobe (p = 0.0046, OR = 11.036; 95% Conf. Int. = 2.100-58.006). Male sex was also positively associated with BRAF V600E status, but the result did not quite achieve statistical significance (p = 0.0731). BRAF V600E status was not found to be associated with post-operative seizure freedom. CONCLUSIONS: These findings indicate that BRAF V600E-positive PLNTY exhibit characteristic clinical presentations but are not necessarily different in treatment responsiveness. Non-BRAF V600E tumors are more commonly associated with young patients.

A multi-institutional pediatric dataset of clinical radiology MRIs by the Children's Brain Tumor Network.

Pediatric brain and spinal cancers remain the leading cause of cancer-related death in children. Advancements in clinical decision-support in pediatric neuro-oncology utilizing the wealth of radiology imaging data collected through standard care, however, has significantly lagged other domains. Such data is ripe for use with predictive analytics such as artificial intelligence (AI) methods, which require large datasets. To address this unmet need, we provide a multi-institutional, large-scale pediatric dataset of 23,101 multi-parametric MRI exams acquired through routine care for 1,526 brain tumor patients, as part of the Children's Brain Tumor Network. This includes longitudinal MRIs across various cancer diagnoses, with associated patient-level clinical information, digital pathology slides, as well as tissue genotype and omics data. To facilitate downstream analysis, treatment-naïve images for 370 subjects were processed and released through the NCI Childhood Cancer Data Initiative via the Cancer Data Service. Through ongoing efforts to continuously build these imaging repositories, our aim is to accelerate discovery and translational AI models with real-world data, to ultimately empower precision medicine for children.

Radio-pathomic approaches in pediatric neuro-oncology: Opportunities and challenges.

With medical software platforms moving to cloud environments with scalable storage and computing, the translation of predictive artificial intelligence (AI) models to aid in clinical decision-making and facilitate personalized medicine for cancer patients is becoming a reality. Medical imaging, namely radiologic and histologic images, has immense analytical potential in neuro-oncology, and models utilizing integrated radiomic and pathomic data may yield a synergistic effect and provide a new modality for precision medicine. At the same time, the ability to harness multi-modal data is met with challenges in aggregating data across medical departments and institutions, as well as significant complexity in modeling the phenotypic and genotypic heterogeneity of pediatric brain tumors. In this paper, we review recent pathomic and integrated pathomic, radiomic, and genomic studies with clinical applications. We discuss current challenges limiting translational research on pediatric brain tumors and outline technical and analytical solutions. Overall, we propose that to empower the potential residing in radio-pathomics, systemic changes in cross-discipline data management and end-to-end software platforms to handle multi-modal data sets are needed, in addition to embracing modern AI-powered approaches. These changes can improve the performance of predictive models, and ultimately the ability to advance brain cancer treatments and patient outcomes through the development of such models.

OpenPBTA: The Open Pediatric Brain Tumor Atlas.

Pediatric brain and spinal cancers are collectively the leading disease-related cause of death in children; thus, we urgently need curative therapeutic strategies for these tumors. To accelerate such discoveries, the Children's Brain Tumor Network (CBTN) and Pacific Pediatric Neuro-Oncology Consortium (PNOC) created a systematic process for tumor biobanking, model generation, and sequencing with immediate access to harmonized data. We leverage these data to establish OpenPBTA, an open collaborative project with over 40 scalable analysis modules that genomically characterize 1,074 pediatric brain tumors. Transcriptomic classification reveals universal TP53 dysregulation in mismatch repair-deficient hypermutant high-grade gliomas and TP53 loss as a significant marker for poor overall survival in ependymomas and H3 K28-mutant diffuse midline gliomas. Already being actively applied to other pediatric cancers and PNOC molecular tumor board decision-making, OpenPBTA is an invaluable resource to the pediatric oncology community.

Radiomics for characterization of the glioma immune microenvironment.

Increasing evidence suggests that besides mutational and molecular alterations, the immune component of the tumor microenvironment also substantially impacts tumor behavior and complicates treatment response, particularly to immunotherapies. Although the standard method for characterizing tumor immune profile is through performing integrated genomic analysis on tissue biopsies, the dynamic change in the immune composition of the tumor microenvironment makes this approach not feasible, especially for brain tumors. Radiomics is a rapidly growing field that uses advanced imaging techniques and computational algorithms to extract numerous quantitative features from medical images. Recent advances in machine learning methods are facilitating biological validation of radiomic signatures and allowing them to "mine" for a variety of significant correlates, including genetic, immunologic, and histologic data. Radiomics has the potential to be used as a non-invasive approach to predict the presence and density of immune cells within the microenvironment, as well as to assess the expression of immune-related genes and pathways. This information can be essential for patient stratification, informing treatment decisions and predicting patients' response to immunotherapies. This is particularly important for tumors with difficult surgical access such as gliomas. In this review, we provide an overview of the glioma microenvironment, describe novel approaches for clustering patients based on their tumor immune profile, and discuss the latest progress on utilization of radiomics for immune profiling of glioma based on current literature.

Diffuse leptomeningeal glioneuronal tumor in a child masquerading as an intramedullary spinal pilocytic astrocytoma.

Diffuse leptomeningeal glioneuronal tumor (DLGNT) occurs predominantly in children and is typically characterized by diffuse leptomeningeal lesions throughout the neuroaxis with focal segments of parenchymal involvement. Recent reports have identified cases without diffuse leptomeningeal involvement that retain classic glioneuronal features on histology. In this report, we present a case of a 4-year-old boy with a large cystic-solid intramedullary spinal cord lesion that on surgical biopsy revealed a biphasic astrocytic tumor with sparsely distributed eosinophilic granular bodies and Rosenthal fibers. Next-generation sequencing revealed a KIAA1549-BRAF fusion, 1p/19q codeletion, and lack of an IDH1 mutation. Methylation profiling demonstrated a calibrated class score of 0.98 for DLGNT and copy number loss of 1p. Despite the morphologic similarities to pilocytic astrocytoma and the lack of oligodendroglial/neuronal components or leptomeningeal dissemination, the molecular profile was definitive in classifying the tumor as DLGNT. This case highlights the importance of molecular and genetic testing in the characterization of pediatric central nervous system tumors.

A metagenomic analysis of the virome of inverted papilloma and squamous cell carcinoma.

INTRODUCTION: Inverted papilloma (IP) is a sinonasal tumor with a well-known potential for malignant transformation. The role of human papillomavirus (HPV) in its pathogenesis has been controversial. The purpose of this study was to determine the virome associated with IP, with progression to carcinoma in situ (CIS), and invasive carcinoma. METHODS: To determine the HPV-specific types, a metagenomics assay that contains 62,886 probes targeting viral genomes in a microarray format was used. The platform screens DNA and RNA from fixed tissues from eight controls, 16 IP without dysplasia, five IP with CIS, and 13 IP-associated squamous cell carcinoma (IPSCC). Paired with next-generation sequencing, 48 types of HPV with 857 region-specific probes were interrogated against the tumors. RESULTS: The prevalence of HPV-16 was 14%, 42%, 70%, and 73% in control tissue, IP without dysplasia, IP with CIS, and IPSCC, respectively. The prevalence of HPV-18 had a similar progressive increase in prevalence, with 14%, 27%, 67%, and 74%, respectively. The assay allowed region-specific analysis, which identified the only oncogenic HPV-18 E6 to be statistically significant when compared with control tissue. The prevalence of HPV-18 E6 was 0% in control tissue, 25% in IP without dysplasia, 60% in IP with CIS, and 77% in IPSCC. CONCLUSIONS: There are over 200 HPV types that infect human epithelial cells, of which only a few are known to be high-risk. Our study demonstrated a trend of increasing prevalence of HPV-18 E6 that correlated with histologic severity, which is novel and supports a potential role for HPV in the pathogenesis of IP.

Automated tumor segmentation and brain tissue extraction from multiparametric MRI of pediatric brain tumors: A multi-institutional study.

Background: Brain tumors are the most common solid tumors and the leading cause of cancer-related death among all childhood cancers. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high interoperator variability. We present a multi-institutional deep learning-based method for automated brain extraction and segmentation of pediatric brain tumors based on multi-parametric MRI scans. Methods: Multi-parametric scans (T1w, T1w-CE, T2, and T2-FLAIR) of 244 pediatric patients ( n = 215 internal and n = 29 external cohorts) with de novo brain tumors, including a variety of tumor subtypes, were preprocessed and manually segmented to identify the brain tissue and tumor subregions into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). The internal cohort was split into training ( n = 151), validation ( n = 43), and withheld internal test ( n = 21) subsets. DeepMedic, a three-dimensional convolutional neural network, was trained and the model parameters were tuned. Finally, the network was evaluated on the withheld internal and external test cohorts. Results: Dice similarity score (median ± SD) was 0.91 ± 0.10/0.88 ± 0.16 for the whole tumor, 0.73 ± 0.27/0.84 ± 0.29 for ET, 0.79 ± 19/0.74 ± 0.27 for union of all non-enhancing components (i.e., NET, CC, ED), and 0.98 ± 0.02 for brain tissue in both internal/external test sets. Conclusions: Our proposed automated brain extraction and tumor subregion segmentation models demonstrated accurate performance on segmentation of the brain tissue and whole tumor regions in pediatric brain tumors and can facilitate detection of abnormal regions for further clinical measurements.

Long-term quality of life after treatment in sinonasal malignancy: A prospective, multicenter study.

BACKGROUND: Quality of life (QOL) for individuals with sinonasal malignancy (SNM) is significantly under-studied, yet it is critical for counseling and may impact treatment. In this study we evaluated how patient, treatment, and disease factors impact sinonasal-specific and generalized QOL using validated metrics in a large cohort over a 5-year posttreatment time frame. METHODS: Patients with SNM who underwent definitive treatment with curative intent were enrolled in a prospective, multisite, longitudinal observational study. QOL was assessed using the 22-item Sino-Nasal Outcome Test (SNOT-22) and University of Washington Quality of Life Questionnaire (UWQOL) instruments at pretreatment baseline and multiple follow-ups through 5 years posttreatment. Multivariable modeling was used to determine demographic, disease, and treatment factors associated with disease-specific and generalized physical and social/emotional function QOL. RESULTS: One hundred ninety-four patients with SNM were analyzed. All QOL indices were impaired at pretreatment baseline and improved after treatment. SNOT-22 scores improved 3 months and UWQOL scores improved 6 to 9 months posttreatment. Patients who underwent open compared with endoscopic tumor resection had worse generalized QOL (p < 0.001), adjusted for factors including T stage. Pterygopalatine fossa (PPF) involvement was associated with worse QOL (SNOT-22, p < 0.001; UWQOL Physical dimension, p = 0.02). Adjuvant radiation was associated with worse disease-specific QOL (p = 0.03). Neck dissection was associated with worse generalized physical function QOL (p = 0.01). Positive margins were associated with worse generalized social/emotional function QOL (p = 0.01). CONCLUSION: Disease-specific and generalized QOL is impaired at baseline in patients with SNM and improves after treatment. Endoscopic resection is associated with better QOL. PPF involvement, adjuvant radiation, neck dissection, and positive margins were associated with worse QOL posttreatment.

Generation and multi-dimensional profiling of a childhood cancer cell line atlas defines new therapeutic opportunities.

Pediatric solid and central nervous system tumors are the leading cause of cancer-related death among children. Identifying new targeted therapies necessitates the use of pediatric cancer models that faithfully recapitulate the patient's disease. However, the generation and characterization of pediatric cancer models has significantly lagged behind adult cancers, underscoring the urgent need to develop pediatric-focused cell line resources. Herein, we establish a single-site collection of 261 cell lines, including 224 pediatric cell lines representing 18 distinct extracranial and brain childhood tumor types. We subjected 182 cell lines to multi-omics analyses (DNA sequencing, RNA sequencing, DNA methylation), and in parallel performed pharmacological and genetic CRISPR-Cas9 loss-of-function screens to identify pediatric-specific treatment opportunities and biomarkers. Our work provides insight into specific pathway vulnerabilities in molecularly defined pediatric tumor classes and uncovers biomarker-linked therapeutic opportunities of clinical relevance. Cell line data and resources are provided in an open access portal.

Magnetic resonance imaging-guided stereotactic laser ablation therapy for the treatment of pediatric epilepsy: a retrospective multiinstitutional study.

OBJECTIVE: The authors of this study evaluated the safety and efficacy of stereotactic laser ablation (SLA) for the treatment of drug-resistant epilepsy (DRE) in children. METHODS: Seventeen North American centers were enrolled in the study. Data for pediatric patients with DRE who had been treated with SLA between 2008 and 2018 were retrospectively reviewed. RESULTS: A total of 225 patients, mean age 12.8 ± 5.8 years, were identified. Target-of-interest (TOI) locations included extratemporal (44.4%), temporal neocortical (8.4%), mesiotemporal (23.1%), hypothalamic (14.2%), and callosal (9.8%). Visualase and NeuroBlate SLA systems were used in 199 and 26 cases, respectively. Procedure goals included ablation (149 cases), disconnection (63), or both (13). The mean follow-up was 27 ± 20.4 months. Improvement in targeted seizure type (TST) was seen in 179 (84.0%) patients. Engel classification was reported for 167 (74.2%) patients; excluding the palliative cases, 74 (49.7%), 35 (23.5%), 10 (6.7%), and 30 (20.1%) patients had Engel class I, II, III, and IV outcomes, respectively. For patients with a follow-up ≥ 12 months, 25 (51.0%), 18 (36.7%), 3 (6.1%), and 3 (6.1%) had Engel class I, II, III, and IV outcomes, respectively. Patients with a history of pre-SLA surgery related to the TOI, a pathology of malformation of cortical development, and 2+ trajectories per TOI were more likely to experience no improvement in seizure frequency and/or to have an unfavorable outcome. A greater number of smaller thermal lesions was associated with greater improvement in TST. Thirty (13.3%) patients experienced 51 short-term complications including malpositioned catheter (3 cases), intracranial hemorrhage (2), transient neurological deficit (19), permanent neurological deficit (3), symptomatic perilesional edema (6), hydrocephalus (1), CSF leakage (1), wound infection (2), unplanned ICU stay (5), and unplanned 30-day readmission (9). The relative incidence of complications was higher in the hypothalamic target location. Target volume, number of laser trajectories, number or size of thermal lesions, or use of perioperative steroids did not have a significant effect on short-term complications. CONCLUSIONS: SLA appears to be an effective and well-tolerated treatment option for children with DRE. Large-volume prospective studies are needed to better understand the indications for treatment and demonstrate the long-term efficacy of SLA in this population.

Intracranial Cannula Implantation for Serial Locoregional Chimeric Antigen Receptor (CAR) T Cell Infusions in Mice.

Pediatric CNS tumors are responsible for the majority of cancer-related deaths in children and have poor prognoses, despite advancements in chemotherapy and radiotherapy. As many tumors lack efficacious treatments, there is a crucial need to develop more promising therapeutic options, such as immunotherapies; the use of chimeric antigen receptor (CAR) T cell therapy directed against CNS tumors is of particular interest. Cell surface targets such as B7-H3, IL13RA2, and the disialoganglioside GD2 are highly expressed on the surface of several pediatric and adult CNS tumors, raising the opportunity to use CAR T cell therapy against these and other surface targets. To evaluate the repeated locoregional delivery of CAR T cells in preclinical murine models, an indwelling catheter system that recapitulates indwelling catheters currently being used in human clinical trials was established. Unlike stereotactic delivery, the indwelling catheter system allows for repeated dosing without the use of multiple surgeries. This protocol describes the intratumoral placement of a fixed guide cannula that has been used to successfully test serial CAR T cell infusions in orthotopic murine models of pediatric brain tumors. Following orthotopic injection and engraftment of the tumor cells in mice, intratumoral placement of a fixed guide cannula is completed on a stereotactic apparatus and secured with screws and acrylic resin. Treatment cannulas are then inserted through the fixed guide cannula for repeated CAR T cell delivery. Stereotactic placement of the guide cannula can be adjusted to deliver CAR T cells directly into the lateral ventricle or other locations in the brain. This platform offers a reliable mechanism for the preclinical testing of repeated intracranial infusions of CAR T cells and other novel therapeutics for these devastating pediatric tumors.

Retrospective dataset and survey analyses identify gaps in data collection for craniopharyngioma and priorities of patients and families affected by the disease.

INTRODUCTION: Craniopharyngioma is a rare, low-grade tumor located in the suprasellar region of the brain, near critical structures like the pituitary gland. Here, we concurrently investigate the status of clinical and genomic data in a retrospective craniopharyngioma cohort and survey-based data to better understand patient-relevant outcomes associated with existing therapies and provide a foundation to inform new treatment strategies. METHODS: Clinical, genomic, and outcome data for a retrospective cohort of patients with craniopharyngioma were collected and reviewed through the Children's Brain Tumor Network (CBTN) database. An anonymous survey was distributed to patients and families with a diagnosis of craniopharyngioma to understand their experiences throughout diagnosis and treatment. RESULTS: The CBTN repository revealed a large proportion of patients (40 - 70%) with specimens that are available for sequencing but lacked relevant quality of life (QoL) and functional outcomes. Frequencies of reported patient comorbidities ranged from 20-35%, which is significantly lower than historically reported. Survey results from 159 patients/families identified differences in treatment considerations at time of diagnosis versus time of recurrence. In retrospective review, patients and families identified preference for therapy that would improve QoL, rather than decrease risk of recurrence (mean 3.9 vs. 4.4 of 5) and identified endocrine issues as having the greatest impact on patients' lives. CONCLUSIONS: This work highlights the importance of prospective collection of QoL and functional metrics alongside robust clinical and molecular correlates in individuals with craniopharyngioma. Such comprehensive measures will facilitate biologically relevant therapeutic strategies that also prioritize patient needs.

Implementation of a Streamlined Care Pathway to Reduce Cost and Length of Stay for Patients Undergoing Endoscopic Transsphenoidal Pituitary Surgery.

BACKGROUND: We implemented a streamlined care pathway for patients undergoing endoscopic transsphenoidal (TSA) pituitary surgery. Select patients are recovered in the postanesthesia care unit and transferred to a step-down unit for intermediate neurologic care (INCU), with clinicians trained to manage cerebrospinal fluid leak, diabetes insipidus (DI), and other complications. METHODS: We evaluated all TSA surgeries performed at 1 academic medical center from 7th January, 2017 to 30th March, 2020, collecting patient factors, tumor characteristics, cost variables, and outcomes. The INCU pathway was implemented on 7th January 2018. Pathway patients were compared with nonpathway patients across the study period. Outcomes were assessed using multivariate regression, adjusting for patient and surgical characteristics, including intraoperative cerebrospinal fluid leak, postoperative DI, and tumor dimensions. RESULTS: One hundred eighty-seven patients were identified. Seventy-nine were on the INCU pathway. Mean age was 53.5 years. Most patients were male (66%), privately insured (62%), and white (66%). Mean total cost of admission was $27,276. Mean length of stay (LOS) was 3.97 days. Use of the INCU pathway was associated with total cost reduction of $6376.33 (P < 0.001, 95% confidence interval [CI]: $3698.21-$9054.45) and LOS reduction by 1.27 days (P = 0.008, 95% CI: 0.33-2.20). In-hospital costs were reduced across all domains, including $1964.87 in variable direct labor costs (P < 0.001, 95% CI: $1142.08-$2787.64) and $1206.52 in variable direct supply costs (P < 0.001, 95% CI: $762.54-$1650.51). Pathway patients were discharged earlier despite a higher rate of postoperative DI (25% vs. 11%, P = 0.011), with fewer readmissions (0% vs. 6%, P = 0.021). CONCLUSIONS: A streamlined care pathway following TSA surgery can reduce in-hospital costs and LOS without compromising patient outcomes.

Automated Tumor Segmentation and Brain Tissue Extraction from Multiparametric MRI of Pediatric Brain Tumors: A Multi-Institutional Study.

Background: Brain tumors are the most common solid tumors and the leading cause of cancer-related death among all childhood cancers. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high interoperator variability. We present a multi-institutional deep learning-based method for automated brain extraction and segmentation of pediatric brain tumors based on multi-parametric MRI scans. Methods: Multi-parametric scans (T1w, T1w-CE, T2, and T2-FLAIR) of 244 pediatric patients (n=215 internal and n=29 external cohorts) with de novo brain tumors, including a variety of tumor subtypes, were preprocessed and manually segmented to identify the brain tissue and tumor subregions into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). The internal cohort was split into training (n=151), validation (n=43), and withheld internal test (n=21) subsets. DeepMedic, a three-dimensional convolutional neural network, was trained and the model parameters were tuned. Finally, the network was evaluated on the withheld internal and external test cohorts. Results: Dice similarity score (median±SD) was 0.91±0.10/0.88±0.16 for the whole tumor, 0.73±0.27/0.84±0.29 for ET, 0.79±19/0.74±0.27 for union of all non-enhancing components (i.e., NET, CC, ED), and 0.98±0.02 for brain tissue in both internal/external test sets. Conclusions: Our proposed automated brain extraction and tumor subregion segmentation models demonstrated accurate performance on segmentation of the brain tissue and whole tumor regions in pediatric brain tumors and can facilitate detection of abnormal regions for further clinical measurements. Key Points: We proposed automated tumor segmentation and brain extraction on pediatric MRI.The volumetric measurements using our models agree with ground truth segmentations. Importance of the Study: The current response assessment in pediatric brain tumors (PBTs) is currently based on bidirectional or 2D measurements, which underestimate the size of non-spherical and complex PBTs in children compared to volumetric or 3D methods. There is a need for development of automated methods to reduce manual burden and intra- and inter-rater variability to segment tumor subregions and assess volumetric changes. Most currently available automated segmentation tools are developed on adult brain tumors, and therefore, do not generalize well to PBTs that have different radiological appearances. To address this, we propose a deep learning (DL) auto-segmentation method that shows promising results in PBTs, collected from a publicly available large-scale imaging dataset (Children's Brain Tumor Network; CBTN) that comprises multi-parametric MRI scans of multiple PBT types acquired across multiple institutions on different scanners and protocols. As a complementary to tumor segmentation, we propose an automated DL model for brain tissue extraction.