Hasil untuk "Pediatrics"

Mert Sonmezer, Serge Vasylechko, Duygu Atasoy et al.

Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured by overlapping anatomy or variable imaging views. Progress is further limited by the scarcity of large, well-annotated datasets for case-based medical image retrieval. We introduce WristMIR, a region-aware pediatric wrist radiograph retrieval framework that leverages dense radiology reports and bone-specific localization to learn fine-grained, clinically meaningful image representations without any manual image-level annotations. Using MedGemma-based structured report mining to generate both global and region-level captions, together with pre-processed wrist images and bone-specific crops of the distal radius, distal ulna, and ulnar styloid, WristMIR jointly trains global and local contrastive encoders and performs a two-stage retrieval process: (1) coarse global matching to identify candidate exams, followed by (2) region-conditioned reranking aligned to a predefined anatomical bone region. WristMIR improves retrieval performance over strong vision-language baselines, raising image-to-text Recall@5 from 0.82% to 9.35%. Its embeddings also yield stronger fracture classification (AUROC 0.949, AUPRC 0.953). In region-aware evaluation, the two-stage design markedly improves retrieval-based fracture diagnosis, increasing mean $F_1$ from 0.568 to 0.753, and radiologists rate its retrieved cases as more clinically relevant, with mean scores rising from 3.36 to 4.35. These findings highlight the potential of anatomically guided retrieval to enhance diagnostic reasoning and support clinical decision-making in pediatric musculoskeletal imaging. The source code is publicly available at https://github.com/quin-med-harvard-edu/WristMIR.

Neda Barbazi, Ji Youn Shin, Gurumurthy Hiremath et al.

Children with chronic conditions face evolving challenges in daily activities, peer relationships, and clinical care. Younger children often rely on parental support, while older ones seek independence. Prior studies on chronic conditions explored proxy-based, family-centered, and playful approaches to support children's health, but most technologies treat children as a homogeneous group rather than adapting to their developmental differences. To address this gap, we conducted four co-design workshops with 69 children with congenital heart disease (CHD) at a medically supported camp, spanning elementary, middle, and high school groups. Our analysis reveals distinct coping strategies: elementary children relied on comfort objects and reassurance, middle schoolers used mediated communication and selective disclosure, and high schoolers emphasized agency and direct engagement with peers and providers. Through child-centered participatory design, we contribute empirical insights into how children's management of chronic conditions evolves and propose design implications for pediatric health technologies that adapt across developmental trajectories.

Shruti Hegde, Mabon Manoj Ninan, Jonathan R. Dillman et al.

General-purpose clinical natural language processing (NLP) tools are increasingly used for the automatic labeling of clinical reports. However, independent evaluations for specific tasks, such as pediatric chest radiograph (CXR) report labeling, are limited. This study compares four commercial clinical NLP systems - Amazon Comprehend Medical (AWS), Google Healthcare NLP (GC), Azure Clinical NLP (AZ), and SparkNLP (SP) - for entity extraction and assertion detection in pediatric CXR reports. Additionally, CheXpert and CheXbert, two dedicated chest radiograph report labelers, were evaluated on the same task using CheXpert-defined labels. We analyzed 95,008 pediatric CXR reports from a large academic pediatric hospital. Entities and assertion statuses (positive, negative, uncertain) from the findings and impression sections were extracted by the NLP systems, with impression section entities mapped to 12 disease categories and a No Findings category. CheXpert and CheXbert extracted the same 13 categories. Outputs were compared using Fleiss Kappa and accuracy against a consensus pseudo-ground truth. Significant differences were found in the number of extracted entities and assertion distributions across NLP systems. SP extracted 49,688 unique entities, GC 16,477, AZ 31,543, and AWS 27,216. Assertion accuracy across models averaged around 62%, with SP highest (76%) and AWS lowest (50%). CheXpert and CheXbert achieved 56% accuracy. Considerable variability in performance highlights the need for careful validation and review before deploying NLP tools for clinical report labeling.

Maartje M. E. Hendrikse, André Goedegebure, Kars R. Tjepkema et al.

This study evaluated whether AutoSense Sky OS, an automatic classifier used in pediatric Advanced Bionics cochlear implants (CIs), improves speech intelligibility from the front without significantly impairing spatial awareness (i.e., sound detection and identification from all directions), with the main focus on the classroom situation. A double-blind crossover study was conducted with 12 pediatric CI users aged 7-16 years. Participants tested two settings: one with AutoSense Sky OS activated and the other with an omnidirectional microphone mode. Speech intelligibility from the front and spatial awareness were assessed in a virtual classroom environment using a Virtual Reality headset and a 12-loudspeaker array. Participants also rated the performance of each setting during a take-home period. A technical evaluation revealed that AutoSense Sky OS activated its directional microphone mode in the virtual classroom, and during the listening test this significantly improved speech intelligibility from the front while significantly reducing spatial awareness. While not all participants reported noticeable differences between settings in daily life, 8 out of 12 children preferred "AutoSense on", perceiving improved speech intelligibility in noisy environments. Conversely, some participants preferred "AutoSense off" due to poorer localization and speech intelligibility from behind with "AutoSense on". In conclusion, the automatic classifier provided improved speech understanding in noisy conditions such as a classroom, at the cost of a slightly reduced spatial awareness. The preference for AutoSense Sky OS among CI children and their parents appears to be a matter of individual trade-offs between improved speech intelligibility in noisy conditions and reduced spatial awareness.

Alya Almsouti, Ainur Khamitova, Darya Taratynova et al.

Assessing the severity of artifacts in pediatric brain Magnetic Resonance Imaging (MRI) is critical for diagnostic accuracy, especially in low-field systems where the signal-to-noise ratio is reduced. Manual quality assessment is time-consuming and subjective, motivating the need for robust automated solutions. In this work, we propose BRIQA (Balanced Reweighting in Image Quality Assessment), which addresses class imbalance in artifact severity levels. BRIQA uses gradient-based loss reweighting to dynamically adjust per-class contributions and employs a rotating batching scheme to ensure consistent exposure to underrepresented classes. Through experiments, no single architecture performs best across all artifact types, emphasizing the importance of architectural diversity. The rotating batching configuration improves performance across metrics by promoting balanced learning when combined with cross-entropy loss. BRIQA improves average macro F1 score from 0.659 to 0.706, with notable gains in Noise (0.430), Zipper (0.098), Positioning (0.097), Contrast (0.217), Motion (0.022), and Banding (0.012) artifact severity classification. The code is available at https://github.com/BioMedIA-MBZUAI/BRIQA.

Susanna Esposito, Valentina Fainardi, Maria Elena Capra et al.

<i>Background</i>: Respiratory syncytial virus (RSV) bronchiolitis remains a leading cause of hospitalization in infants, particularly those with risk factors such as prematurity or chronic diseases. Nirsevimab, a long-acting monoclonal antibody, has recently been approved for RSV prevention. However, parental acceptance of this novel immunoprophylaxis is crucial for effective implementation. The aim of this study was to investigate parental acceptance of nirsevimab prophylaxis for RSV among eligible neonates in Emilia-Romagna, Italy, and to identify factors influencing decision making. <i>Methods</i>: A prospective, multicenter observational study enrolled 1042 parents of neonates eligible for nirsevimab prophylaxis according to regional criteria. Parents completed a semi-structured questionnaire during pre-immunization counseling, exploring knowledge, attitudes, perceived risks, information sources, and willingness to accept prophylaxis. Statistical analysis assessed associations between parental characteristics and acceptance rates. <i>Results</i>: Among the 1042 respondents, 87.0% (n = 907) expressed willingness to administer nirsevimab to their child, while 2.2% (n = 23) refused and 8.8% (n = 92) were undecided. Higher acceptance was significantly associated with awareness of RSV risks (72.1% vs. 41.7%, <i>p</i> < 0.01), belief in nirsevimab’s high efficacy (46.2% vs. 18.3%, <i>p</i> < 0.01), and lower concern over side effects (10.6% vs. 27.8%, <i>p</i> < 0.01). Trust in primary care pediatricians and the healthcare system was also notably higher among accepting parents (<i>p</i> < 0.001). Willingness to pay declined with a hypothetical EUR 250 cost but remained higher among the acceptance group (71.0% vs. 50.4%, <i>p</i> < 0.001). <i>Conclusions</i>: Parental acceptance of nirsevimab in Emilia-Romagna was high, though significant gaps in knowledge and concerns about safety persist. Targeted educational strategies that clarify the nature, efficacy, and safety of nirsevimab—alongside maintaining cost-free access—are essential to support the successful implementation of RSV prophylaxis programs.

Hien Thanh Dao, Triet Hy Van, Tuyet Thi Bach Tran et al.

Introduction: Hereditary spherocytosis is a prevalent congenital hemolytic erythrocyte membranopathy. Laboratory diagnosis is traditionally based on erythrocyte morphology, yet 20% of cases may lack visible spherocytes, leading to misdiagnosis. The Eosin-5'-maleimide binding assay has emerged as a reliable diagnostic method. Objective: Evaluate the effectiveness of Eosin-5'-maleimide binding assay in diagnosing hereditary spherocytosis in pediatrics with negative-direct-antiglobulin-test-hemolytic anemia. Methods: A cross-sectional study was conducted with 66 negative-direct-antiglobulin-test-hemolytic-anemic patients and 44 healthy controls. The percentage of spherocytes was scored from peripheral blood smear observation; the percentage of decreased mean fluorescent intensity from Eosin-5'-maleimide binding assay was used to determine red cell membrane protein deficiency, and hereditary spherocytosis was finally confirmed by gene sequencing as a gold standard. Results: Eosin-5'-maleimide binding assay demonstrated high sensitivity (93.33%), specificity (100%), and accuracy (97.3%) in detecting hereditary spherocytosis, with an optimal cut-off value of 47.83% decreased mean fluorescent intensity. Conclusion: The Eosin-5'-maleimide binding assay is a highly accurate diagnostic tool that outperforms traditional blood smear analysis. It is precious for detecting hereditary spherocytosis in patients with mild clinical manifestations or coexisting hemolytic disorders. This assay should be considered a frontline test for diagnosing hereditary spherocytosis in patients with hemolytic anemia.

Leslee J Shaw, Todd C Villines, Francesco Giammarile et al.

Background Understanding pandemic-related reductions and subsequent recovery of cardiovascular testing in Asia is important for guiding regional public health efforts.Objectives This study sought to evaluate the recovery of cardiovascular testing in Asia 1 year into the COVID-19 pandemic.Methods In this subanalysis of a worldwide survey on the impact of COVID-19 on cardiovascular diagnostic care in April 2020 and April 2021, recovery of testing volume in Asia was compared among subregions, World Bank income groups and imaging modalities.Results Of 669 sites worldwide, 164 sites were in 33 Asian countries. Cardiovascular testing volumes in Asia decreased by 53% from March 2019 to April 2020, then recovered 96% of this decrease by April 2021, compared with 98% recovery in the rest of the world. Eastern Asia and Western and Central Asia reported recovery rates of 123% and 110%, compared with 50% and 80% recovery in Southern and South-eastern Asia. Testing volumes among high-income and upper-middle-income Asian countries recovered to 117% and 121% but remained depressed at 49% and 14% recovery in lower-middle and low-income countries, respectively. Stress ECG, stress echo and stress positron emission tomography studies experienced median reductions of 48%, 35% and 57% in testing volume between March 2019 and April 2021, while volumes of coronary artery calcium, coronary CT angiography and cardiac MR remained stable during this period.Conclusions The recovery of cardiovascular testing in Asia 1 year into the COVID-19 pandemic lagged in the Southern and South-eastern subregions, as well as in lower-income countries. Recovery favoured advanced cardiac imaging modalities over standard stress testing modalities.

Ammar Ahmed, Ali Shariq Imran, Zenun Kastrati et al.

Wrist pathologies, {particularly fractures common among children and adolescents}, present a critical diagnostic challenge. While X-ray imaging remains a prevalent diagnostic tool, the increasing misinterpretation rates highlight the need for more accurate analysis, especially considering the lack of specialized training among many surgeons and physicians. Recent advancements in deep convolutional neural networks offer promise in automating pathology detection in trauma X-rays. However, distinguishing subtle variations between {pediatric} wrist pathologies in X-rays remains challenging. Traditional manual annotation, though effective, is laborious, costly, and requires specialized expertise. {In this paper, we address the challenge of pediatric wrist pathology recognition with a fine-grained approach, aimed at automatically identifying discriminative regions in X-rays without manual intervention. We refine our fine-grained architecture through ablation analysis and the integration of LION.} Leveraging Grad-CAM, an explainable AI technique, we highlight these regions. Despite using limited data, reflective of real-world medical study constraints, our method consistently outperforms state-of-the-art image recognition models on both augmented and original (challenging) test sets. {Our proposed refined architecture achieves an increase in accuracy of 1.06% and 1.25% compared to the baseline method, resulting in accuracies of 86% and 84%, respectively. Moreover, our approach demonstrates the highest fracture sensitivity of 97%, highlighting its potential to enhance wrist pathology recognition. The implementation code can be found at https://github.com/ammarlodhi255/fine-grained-approach-to-wrist-pathology-recognition

Khashayar Namdar, Matthias W. Wagner, Cynthia Hawkins et al.

Pediatric Low-Grade Neuroepithelial Tumors (PLGNT) are the most common pediatric cancer type, accounting for 40% of brain tumors in children, and identifying PLGNT molecular subtype is crucial for treatment planning. However, the gold standard to determine the PLGNT subtype is biopsy, which can be impractical or dangerous for patients. This research improves the performance of Convolutional Neural Networks (CNNs) in classifying PLGNT subtypes through MRI scans by introducing a loss function that specifically improves the model's Area Under the Receiver Operating Characteristic (ROC) Curve (AUROC), offering a non-invasive diagnostic alternative. In this study, a retrospective dataset of 339 children with PLGNT (143 BRAF fusion, 71 with BRAF V600E mutation, and 125 non-BRAF) was curated. We employed a CNN model with Monte Carlo random data splitting. The baseline model was trained using binary cross entropy (BCE), and achieved an AUROC of 86.11% for differentiating BRAF fusion and BRAF V600E mutations, which was improved to 87.71% using our proposed AUROC loss function (p-value 0.045). With multiclass classification, the AUROC improved from 74.42% to 76. 59% (p-value 0.0016).

Andjela Dimitrijevic, Vincent Noblet, Benjamin De Leener

This study evaluates the performance of conventional SyN ANTs and learning-based registration methods in the context of pediatric neuroimaging, specifically focusing on intrasubject deformable registration. The comparison involves three approaches: without (NR), with rigid (RR), and with rigid and affine (RAR) initializations. In addition to initialization, performances are evaluated in terms of accuracy, speed, and the impact of age intervals and sex per pair. Data consists of the publicly available MRI scans from the Calgary Preschool dataset, which includes 63 children aged 2-7 years, allowing for 431 registration pairs. We implemented the unsupervised DL framework with a U-Net architecture using DeepReg and it was 5-fold cross-validated. Evaluation includes Dice scores for tissue segmentation from 18 smaller regions obtained by SynthSeg, analysis of log Jacobian determinants, and registration pro-rated training and inference times. Learning-based approaches, with or without linear initializations, exhibit slight superiority over SyN ANTs in terms of Dice scores. Indeed, DL-based implementations with RR and RAR initializations significantly outperform SyN ANTs. Both SyN ANTs and DL-based registration involve parameter optimization, but the choice between these methods depends on the scale of registration: network-based for broader coverage or SyN ANTs for specific structures. Both methods face challenges with larger age intervals due to greater growth changes. The main takeaway is that while DL-based methods show promise with faster and more accurate registrations, SyN ANTs remains robust and generalizable without the need for extensive training, highlighting the importance of method selection based on specific registration needs in the pediatric context. Our code is available at https://github.com/neuropoly/pediatric-DL-registration

Mianyong Ding, Matteo Maspero, Annemieke S Littooij et al.

Purposes: This study aimed to develop a computed tomography (CT)-based multi-organ segmentation model for delineating organs-at-risk (OARs) in pediatric upper abdominal tumors and evaluate its robustness across multiple datasets. Materials and methods: In-house postoperative CTs from pediatric patients with renal tumors and neuroblastoma (n=189) and a public dataset (n=189) with CTs covering thoracoabdominal regions were used. Seventeen OARs were delineated: nine by clinicians (Type 1) and eight using TotalSegmentator (Type 2). Auto-segmentation models were trained using in-house (ModelPMC-UMCU) and a combined dataset of public data (Model-Combined). Performance was assessed with Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and mean surface distance (MSD). Two clinicians rated clinical acceptability on a 5-point Likert scale across 15 patient contours. Model robustness was evaluated against sex, age, intravenous contrast, and tumor type. Results: Model-PMC-UMCU achieved mean DSC values above 0.95 for five of nine OARs, while spleen and heart ranged between 0.90 and 0.95. The stomach-bowel and pancreas exhibited DSC values below 0.90. Model-Combined demonstrated improved robustness across both datasets. Clinical evaluation revealed good usability, with both clinicians rating six of nine Type 1 OARs above four and six of eight Type 2 OARs above three. Significant performance 2 differences were only found across age groups in both datasets, specifically in the left lung and pancreas. The 0-2 age group showed the lowest performance. Conclusion: A multi-organ segmentation model was developed, showcasing enhanced robustness when trained on combined datasets. This model is suitable for various OARs and can be applied to multiple datasets in clinical settings.

Mehrnoosh Ayazi, Ipsita Sahin, Caio Mucchiani et al.

This paper presents a comprehensive analysis of the contact force profile of a single-cell bidirectional soft pneumatic actuator, specifically designed to aid in the abduction and adduction of the shoulder for pediatric exosuits. The actuator was embedded in an infant-scale test rig featuring two degrees of freedom: an actuated revolute joint supporting shoulder abduction/adduction and a passive (but lockable) revolute joint supporting elbow flexion/extension. Integrated load cells and an encoder within the rig were used to measure the force applied by the actuator and the shoulder joint angle, respectively. The actuator's performance was evaluated under various anchoring points and elbow joint angles. Experimental results demonstrate that optimal performance, characterized by maximum range of motion and minimal force applied on the torso and upper arm, can be achieved when the actuator is anchored at two-thirds the length of the upper arm, with the elbow joint positioned at a 90-degree angle. The force versus pressure and joint angle graphs reveal nonlinear and hysteresis behaviors. The findings of this study yield insights about optimal anchoring points and elbow angles to minimize exerted forces without reducing the range of motion.

Alexandra McMillin, Aviva Presser Aiden, Jules P. Sherman et al.

Background/Objectives: Kangaroo Care (KC) has been proven to enhance physiological stability, growth, and bonding in preterm, low-birthweight infants. Despite its benefits, KC is underutilized in Level IV Neonatal Intensive Care Units (NICUs) due to challenges in managing medical equipment. This study introduces the Kangarobe™, a novel garment designed to facilitate safe, comfortable, and efficient KC for medically fragile infants in high-acuity NICUs. Methods: From 2021 to 2023, a feasibility study was conducted involving 25 infant-parent dyads in a Level IV NICU. The Kangarobe™ was designed using human-centered design principles and tested on infants dependent on respiratory support. Surveys employing a 5-point Likert scale were administered to parents and nursing staff to assess safety, comfort, ease of use, and procedural access. Results: Survey results showed positive feedback from both parents and nursing staff, particularly in the areas of safety and comfort. For example, 72–80% of parents and nurses responded positively regarding ease and comfort. High level of agreement (76%) on the security of medical line management, with minimal negative feedback. In addition, parents using the Kangarobe™ held their infants for an average of 171 min per session, with a notable increase compared to the typical 75 min, indicating enhanced comfort and feasibility for extended KC sessions. The Kangarobe™ successfully enabled the secure management of medical lines and tubes, with the vertical access window improving procedural efficiency without interrupting KC. Conclusions: The Kangarobe™ demonstrates promise in addressing barriers to KC in high-acuity NICUs. By enhancing safety, comfort, and ease of use, it supports wider adoption of KC practices, potentially improving patient safety, staff efficiency, and family-centered care.

Fan-Sheng Kong, Fan-Sheng Kong, Zijing Lu et al.

BackgroundPolycystic ovary syndrome (PCOS) is a complex, multifactor disorder in women of reproductive age worldwide. Although RNA editing may contribute to a variety of diseases, its role in PCOS remains unclear.MethodsA discovery RNA-Seq dataset was obtained from the NCBI Gene Expression Omnibus database of granulosa cells from women with PCOS and women without PCOS (controls). A validation RNA-Seq dataset downloaded from the European Nucleotide Archive Databank was used to validate differential editing. Transcriptome-wide investigation was conducted to analyze adenosine-to-inosine (A-to-I) RNA editing in PCOS and control samples.ResultsA total of 17,395 high-confidence A-to-I RNA editing sites were identified in 3,644 genes in all GC samples. As for differential RNA editing, there were 545 differential RNA editing (DRE) sites in 259 genes with Nucleoporin 43 (NUP43), Retinoblastoma Binding Protein 4 (RBBP4), and leckstrin homology-like domain family A member 1 (PHLDA) showing the most significant three 3′-untranslated region (3′UTR) editing. Furthermore, we identified 20 DRE sites that demonstrated a significant correlation between editing levels and gene expression levels. Notably, MIR193b-365a Host Gene (MIR193BHG) and Hook Microtubule Tethering Protein 3 (HOOK3) exhibited significant differential expression between PCOS and controls. Functional enrichment analysis showed that these 259 differentially edited genes were mainly related to apoptosis and necroptosis pathways. RNA binding protein (RBP) analysis revealed that RNA Binding Motif Protein 45 (RBM45) was predicted as the most frequent RBP binding with RNA editing sites. Additionally, we observed a correlation between editing levels of differential editing sites and the expression level of the RNA editing enzyme Adenosine Deaminase RNA Specific B1 (ADARB1). Moreover, the existence of 55 common differentially edited genes and nine differential editing sites were confirmed in the validation dataset.ConclusionOur current study highlighted the potential role of RNA editing in the pathophysiology of PCOS as an epigenetic process. These findings could provide valuable insights into the development of more targeted and effective treatment options for PCOS.

Amar Taksande, Patel Zeeshan Jameel, Rupesh Rao et al.

Objectives: The exact prevalence of cardiac anomalies in diagnosed cases of echogenic foci is still unknown, as various studies have been carried out across multiple populations with different methodologies.  Objectives: The primary objective of this study was to determine the precise prevalence of cardiac anomalies found in cases with intracardiac echogenic foci.  Methods: The authors manually searched the electronic databases (Cochrane Library, PubMed, EMBASE, Scopus, Web of Science). Two reviewers independently did data extraction and quality control; a third reviewer resolved any raised conflicts. The data were analyzed by comprehensive meta-analysis software version 2. Risk of bias assessment and strobe checklist were used for quality assessment.  Results: Out of 531 articles identified, 32 studies met the inclusion criteria and were included in the meta-analysis with a total sample size of 7568. The pooled prevalence of cardiac anomalies in the fetuses with intracardiac echogenic foci was 4.8% (95% CI, 3.6%-6.4%). Subgroup analysis was done according to the geographical distribution of cases, maternal age, gestational age, year of publication, risk of bias, and ultrasonography operator.  Conclusions: The current study represents the first and only meta-analysis concerning the prevalence of cardiac anomaly in fetuses diagnosed with intracardiac echogenic focus (ICEF). This study supports a definitive relationship between ICEF and underlying congenital heart disease. We recommend increased training of individuals performing this ultrasonography to improve early detection, ultimately enhancing the care given to infants immediately post-birth.

Shintaro Terashita, Taketoshi Yoshida, Kenta Matsumura et al.

Abstract Caesarean section (CS) birth is widely reported to be a risk factor for childhood obesity. Although susceptibility to childhood obesity is influenced by race and ethnicity, it is unclear whether this risk of childhood obesity with CS birth also applies in the Japanese population. We investigated the impact of CS birth on obesity at 3 years of age in Japanese children. We obtained data from 60,769 mother–toddler pairs in the Japan Environment and Children’s Study, a large-scale birth cohort study. Obesity was determined by body mass index measured at 3 years of age. Analysis revealed that 11,241 toddlers (18.5%) had a CS birth and that 4912 toddlers (8.1%) were obese. The adjusted risk ratio for obesity at 3 years of age when born by CS compared with vaginal delivery, estimated using inverse probability of treatment weighting, was 1.16 (95% confidence interval 1.08–1.25). These results suggest that CS birth modestly increases the risk of obesity at 3 years of age in Japanese children.

Luca Paun, Alexandre Lavé, Gianpaolo Jannelli et al.

Posterior fossa atypical teratoid rhabdoid tumor (ATRT) is a rare childhood tumor usually associated with a dismal prognosis. Although upfront surgical gross total resection (GTR) has classically been the first line of treatment, new multimodal treatments, including two-stage surgery, are showing promising results in terms of overall survival (OS) and complication rate. We present a case of a 9-month-old child treated with two-staged surgery and chemotherapy. When deemed risky, multimodal treatments, including staged surgeries, can be a safe alternative to reduce surgical mortality and morbidity. At 23 months old, the patient had normal global development and no major impact on quality of life. We, therefore, discuss the most recent advancements from a treatment perspective, including molecular targeting.

Soleil Hernandez, Callistus Nguyen, Skylar Gay et al.

Purpose: Target delineation for radiation therapy is a time-consuming and complex task. Autocontouring gross tumor volumes (GTVs) has been shown to increase efficiency. However, there is limited literature on post-operative target delineation, particularly for CT-based studies. To this end, we trained a CT-based autocontouring model to contour the post-operative GTV of pediatric patients with medulloblastoma. Methods: 104 retrospective pediatric CT scans were used to train a GTV auto-contouring model. 80 patients were then preselected for contour visibility, continuity, and location to train an additional model. Each GTV was manually annotated with a visibility score based on the number of slices with a visible GTV (1 = <25%, 2 = 25%-50%, 3 = >50%-75%, and 4 = >75%-100%). Contrast and the contrast-to-noise ratio (CNR) were calculated for the GTV contour with respect to a cropped background image. Both models were tested on the original and pre-selected testing sets. The resulting surface and overlap metrics were calculated comparing the clinical and autocontoured GTVs and the corresponding clinical target volumes (CTVs). Results: 80 patients were pre-selected to have a continuous GTV within the posterior fossa. Of these, 7, 41, 21, and 11 were visibly scored as 4, 3, 2, and 1, respectively. The contrast and CNR removed an additional 11 and 20 patients from the dataset, respectively. The Dice similarity coefficients (DSC) were 0.61 +/- 0.29 and 0.67 +/- 0.22 on the models without pre-selected training data and 0.55 +/- 13.01 and 0.83 +/- 0.17 on the models with pre-selected data, respectively. The DSC on the CTV expansions were 0.90 +/- 0.13. Conclusion: We automatically contoured continuous GTVs within the posterior fossa on scans that had contrast >=10 HU. CT-Based auto-contouring algorithms have potential to positively impact centers with limited MRI access.

Min Chen, Min Chen, Min Chen et al.

Acute lymphoblastic leukemia (ALL) presenting with hypercalcemia and osteolytic lesions is rare and unusual in childhood. We report a case of a 13-year-old boy with ALL who presented with intermittent fever, nausea, vomiting, and increasing lower limb pain. Skeletal X-rays and CT scan showed severe osteolytic lesions of the skull and extremities. Physical examination revealed multiple inguinal lymph nodes. Laboratory tests demonstrated severe hypercalcemia (Ca &gt; 3.49 mmol/L), decreased parathyroid hormone (PTH), and vitamin D level. Despite a normal complete blood count and the absence of circulating blasts, bone marrow biopsy revealed B-precursor ALL. Hypercalcemia was initially treated with intravenous isotonic sodium chloride and furosemide but the serum calcium level was not normalized. It was successfully managed with calcitonin and pamidronate afterward. Later, the child responded well to chemotherapy and continued with consolidation treatment. The clinical condition was stable, and the bone marrow revealed complete remission. This case indicated that hypercalcemia alone or combined with osteolytic lesions can be the only presenting symptom of ALL in children. Diagnostic errors may occur especially when combined with the absence of circulating blasts in the peripheral blood smear. Bone marrow aspiration should be considered to confirm the diagnosis.