← Back to all signals
RESEARCH PAPER ANALYSIS

Deep Learning Blood Dosimetry Predicts Severe Lymphopenia and Survival After Craniospinal Irradiation.

AI interpretation is pending for this paper.

Open original publication →
PMID42031223
JournalInternational journal of radiation oncology, biology, physics
Publication Date2026-04-22
Ingested2026-08-02 12:06 AM
EXECUTIVE SUMMARY

What the AI sees

Not AI summarized yet.

WHY IT MATTERS

Research significance

Pending deeper interpretation.

ABSTRACT

Source abstract

PURPOSE: Craniospinal irradiation (CSI) is a standard treatment for pediatric brain tumors and is increasingly used for leptomeningeal metastases. Although effective, CSI often causes radiation-induced severe lymphopenia (RISL), which is associated with poor outcomes across various cancer types. We developed and validated a novel platform for personalized dosimetry of circulating blood cells (CBCs) and assessed its predictive value for RISL. METHODS AND MATERIALS: We combined a prospective pediatric CSI registry (initiated April 2018; n = 48) and retrospectively collected patients (January 2010-November 2024; n = 168). RISL was defined as grade 4 lymphopenia (<200/µL) during or within 1 week after CSI. The platform integrated deep learning-based whole-body segmentation, individualized blood volume modeling (HEDOS), patient-specific hemodynamics (cardiac output), and treatment delivery parameters to estimate CBC dose-volume histograms, which quantify the cumulative radiation dose distribution to circulating blood during CSI. CBC dose metrics were analyzed using LASSO, Random Forest, and XGBoost models, with and without cross-validation and Synthetic Minority Over-sampling Technique, to identify RISL predictors. RESULTS: Among 216 patients (median age 12 years; range, 2-68), proton beam therapy was used in 163 (75.5%). RISL occurred in 92 patients (42.6%). Among various CBC dosimetric parameters, CBC D5% consistently emerged as the most important predictor of RISL across all machine learning models. Stratification by CBC D5% with 3.0 GyE effectively differentiated overall survival and event-free survival outcomes (all P < .05). CONCLUSIONS: The current deep learning-based personalized blood dosimetry platform enables personalized CBC dosimetry during CSI. CBC D5% is associated with the development of RISL and survival outcomes. Personalized blood dosimetry may serve as a potential tool to identify patients at high risk for RISL, which may inform future efforts to optimize CSI planning.

SUPPORTING PAPER SET

32 more papers to review

Ranked by current scoring engine
1 A multidisciplinary team approach to a neonate with a rare primary mediastinal tumor: a case report. Folia medica 49.1 2 Isolated Lesser Trochanter Fractures in Adults: A Systematic Review of Malignant, Infectious, and Benign Etiologies. Cureus 73.9 3 Tuberculous Infection of a Posterior Mediastinal Neuroenteric Cyst Presenting as Secondary Autoimmune Hemolytic Anemia: A Case Report. Cureus 49.9 4 Organoids as brain tumour models: bridging the translational gap. Disease models & mechanisms 48.9 5 Establishing a Multicenter Personalized Medicine Program in Childhood, Adolescent, and Young Adult Cancer in Spain: The SEHOP-PENCIL Project. JCO precision oncology 56.0 6 Multiomic Characterization of a Rare Case of Pediatric Acute Leukemia With a Novel ANGPT1::HOXA10-AS Fusion. JCO precision oncology 47.5 7 Unmasking a Hidden Burden: Chemotherapy-Induced and Exacerbated Diabetes in Paediatric Cancer: A Report of Two Cases. Nigerian medical journal : journal of the Nigeria Medical Association 67.84 8 Clinical Characteristics and Surgical Outcomes of Paediatric Thyroid Disorders in a Nigerian Mission Hospital: A Nine-Year Review. Nigerian medical journal : journal of the Nigeria Medical Association 58.9 9 Peripheral nervous system involvement accompanies central nervous system involvement in anti-N-methyl-D-aspartate receptor encephalitis. Frontiers in immunology 72.6 10 Blinatumomab for Pediatric High-Risk B-Cell Precursor Acute Lymphoblastic Leukemia: Safety, MRD Response and Survival in a Single-Center Retrospective Cohort [Removal]. ImmunoTargets and therapy 58.24 11 Clinical features of MEN1 in children, adolescents, and young adults: a single-center study. Frontiers in endocrinology 61.9 12 Multidisciplinary Delphi consensus on malignancy screening in patients with common variable immunodeficiency. Frontiers in immunology 60.5 13 Prevalence and risk factors of Helicobacter pylori infection among children attending mercy pediatric hospital and royal hospital, Mogadishu, Somalia: a cross-sectional study. Frontiers in pediatrics 64.2 14 Mapping the de-implementation of traditional diagnostic tests in pediatric acute lymphoblastic leukemia. Frontiers in oncology 57.5 15 Early and sex-specific dynamic changes of the modified Glasgow Prognostic Score correlate with survival and immunotoxicities in patients undergoing allogeneic hematopoietic stem cell transplantation. Frontiers in immunology 66.22 16 Does the Initial Source of Recognition-Clinician versus Caregiver-Affect the Age at Orchidopexy for Undescended Testis? A Retrospective Comparative Analysis of 283 Cases. Journal of clinical practice and research 63.4 17 Diagnostic pitfalls in systemic juvenile idiopathic arthritis: insights from 6 misdiagnosed cases. Frontiers in pediatrics 58.7 18 Evaluation of HDAC8 as a Druggable Target in STAG2-Mutant Ewing Sarcoma. ACS chemical biology 56.16 19 Gluteal Calcifying Aponeurotic Fibroma: An Exceptional Location of a Rare Fibroblastic Tumour: A Case Report. Clinical, cosmetic and investigational dermatology 49.9 20 Clinical impact of Moraxella catarrhalis detection in respiratory illnesses: a comparative study of pediatric and adult populations in Taiwan. Journal of microbiology, immunology, and infection = Wei mian yu gan ran za zhi 64.0 21 Construction of nomogram for the clinical outcome for pediatric acute lymphoblastic leukemia patients. Medicine 64.0 22 Prevalence and determinants of anxiety and depression among children and adolescents undergoing cancer treatment at a tertiary hospital in a resource-limited setting: A cross-sectional study. Medicine 65.44 23 Bilateral advancement flaps in the treatment of divided nevus of the eyelid: A retrospective case series. Medicine 57.24 24 The global perspective on the evolution of nurse-related research in primary malignant bone tumors from 2004 to 2025: A bibliometric mapping and visual analysis study. Medicine 59.5 25 Size-specific dose estimation in pediatric computed tomography: From dose characterization to individualized optimization. World journal of radiology 57.62 26 Chemotherapy relative dose intensity and survival outcomes in pediatric and adolescent locoregionally advanced nasopharyngeal carcinoma: A retrospective cohort study. Therapeutic advances in medical oncology 76.78 27 T-rex: standardized analysis of germline variants in whole-exome sequencing trios. Scientific reports 57.0 28 Pregnancy outcomes in women conceiving after hematopoietic stem cell transplantation versus conventional chemotherapy for childhood or adolescent acute leukemia. Bone marrow transplantation 63.14 29 Tisagenlecleucel for post-transplant relapse in young acute lymphoblastic leukemia patients: European real-world determinants of outcome. Leukemia 65.42 30 A CAR-T Tonic Signaling Code Predicts Anti-Tumor Efficacy in Diffuse Midline Glioma. Neuro-oncology 78.6 31 Symptom Burden and Integrative Medicine Consultations Among Adolescents and Young Adults with Cancer: Experience from a Tertiary Care Center. Journal of adolescent and young adult oncology 56.0 32 Targeting of the oncogenic fusion EWSR1-FLI1 in Ewing Sarcoma by CRISPR/dCas9 silencers. Molecular therapy : the journal of the American Society of Gene Therapy 52.5
PATIENT-FRIENDLY SUMMARY

Deep Learning Blood Dosimetry Predicts Severe Lymphopenia and Survival After Craniospinal Irradiation.

For education only—not personal medical advice.

Pediatric cancer research intelligence graphic
PEDIATRIC CANCER VISUAL SYSTEM

Open the Research Intelligence Map

Explore the active pediatric oncology analysis view.

Expand Intelligence View →
Full Pediatric cancer research intelligence graphic