Accurate Diagnosis and Grading of Pediatric Solid Tumors Based on Pathological Large Models

NCT06822842 | Not Yet Recruiting

• 1 other identifier: XHEC-C-2025-015-1
• Study Type: observational
• Target: 2,000
• Locations: 0 countries
• Sites: N/A

Brief Summary

Pediatric malignancies are the second leading cause of death in the pediatric population, with solid tumors accounting for approximately 60% of all pediatric malignancies. The pathological diagnosis of pediatric solid tumors is highly complex and specialized, because of its diverse tissue morphology, rare tumor subtypes and lack of labeling data, the traditional pathological diagnosis relies on the experience of senior pathologists, but in actual clinical practice, due to the lack of expert resources and inconsistent diagnostic standards, more efficient and accurate auxiliary diagnostic tools are urgently needed. In this study, we aim to construct a multimodal dataset by collecting high-quality pathological images and pathological diagnosis results of pediatric solid tumors (neuroblastoma, medulloblastoma, Wilms tumor, hepatoblastoma, rhabdomyosarcoma, etc.), and introduce medical knowledge enhancement strategies on this basis, and improve the medical reasoning ability and adaptability to fine-grained pathological tasks by injecting domain knowledge (such as molecular characteristics of tumors, pathological grading standards, diagnostic rules, etc.) into the model. Through the model, the representation space of images and texts is unified, and diversified diagnostic tasks of pediatric solid tumors such as tumor region segmentation, cancer detection, and tumor subtype identification are realized, providing intelligent support for the accurate diagnosis and personalized treatment of pediatric solid tumors.

Conditions

Neuroblastoma; Medulloblastoma; Wilms Tumor; Hepatoblastoma; Rhabdomyosarcoma

Keywords

Machine learning; Diagnosis; Pathological classification

Outcome Measures

Primary Outcomes (1)

• Diagnostic accuracy of patients

  For the diagnostic model, we use both micro and macro area under the curve (AUC) metrics to evaluate the model in terms of sensitivity, specificity, accuracy, positive predictive value and negative predictive value at different classification thresholds

  immediately after surgery

Eligibility Criteria

• Age: 0 Years - 18 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

The clinical data and HE-stained sections of pathological tissues of children with solid tumors (including neuroblastoma, Wilms tumor, hepatoblastoma and medulloblastoma, etc.) diagnosed and treated by histopathology in Xinhua Hospital affiliated to Shanghai Jiao Tong University School of Medicine from January 2012 to January 2022 were retrospectively analyzed.

You may qualify if:

• Neuroblastoma (NB): For newly diagnosed patients with NB aged 0-18 years, the diagnosis criteria are one of the following two items: (1) the patient's tumor tissue has obtained a positive pathological diagnosis under the light microscope; (2) Bone marrow biopsy or aspiration revealed characteristic neuroblastoma cells, which were small round cells, arranged in a nested or chrysanthemum clump or positive staining for anti-GD2 antibodies, and accompanied by an increase in urinary vanillylmandelic acid (VMA) and an increase in blood neuron-specific enolase (NSE).
• Wilms tumor (nephroblastoma): patients aged 0-18 years old who have been diagnosed with Wilms tumor by histopathology.
• Hepatoblastoma (HB): Patients aged 0-18 years who have been diagnosed with hepatoblastoma by histopathology.
• Medulloblastoma (MB): Patients aged 0-18 years with a confirmed histopathological diagnosis of medulloblastoma.
• rhabdomyosarcoma (RMS): patients aged 0-18 years old who have been diagnosed with medulloblastoma by histopathology.

You may not qualify if:

• The patient's medical record and treatment follow-up information are incomplete; HE is not stained or faded
• Those who have 2 or more types of tumors at the same time;
• Those who do not meet the enrollment criteria.
• Tumor subtype with less than 3 WSI images

Sponsors & Collaborators

• Xinhua Hospital, Shanghai Jiao Tong University School of Medicine: lead

MeSH Terms

Conditions

Neuroblastoma; Medulloblastoma; Wilms Tumor; Hepatoblastoma; Rhabdomyosarcoma; Disease

Condition Hierarchy (Ancestors)

Neuroectodermal Tumors, Primitive, Peripheral; Neuroectodermal Tumors, Primitive; Neoplasms, Neuroepithelial; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Neoplasms, Nerve Tissue; Glioma; Neoplasms, Complex and Mixed; Kidney Neoplasms; Urologic Neoplasms; Urogenital Neoplasms; Neoplasms by Site; Neoplastic Syndromes, Hereditary; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Kidney Diseases; Urologic Diseases; Male Urogenital Diseases; Genetic Diseases, Inborn; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Myosarcoma; Neoplasms, Muscle Tissue; Neoplasms, Connective and Soft Tissue; Sarcoma; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

Kun Phd Sun

CONTACT

021-13601846338; drsunkun@xinhuamed.com.cn

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor of Department of Pediatric Cardiology

Study Record Dates

• First Submitted: January 24, 2025
• First Posted: February 12, 2025
• Study Start: February 1, 2025
• Primary Completion: April 30, 2025
• Study Completion: April 30, 2025
• Last Updated: February 12, 2025

Record last verified: 2025-01