Construction and Validation of an Intelligent Ultrasound Diagnostic System for the Spectrum of Neuroblastoma in Children

NCT07549425 | Active Not Recruiting

• 1 other identifier: 2026-IRB-0083-P-01
• Study Type: observational
• Target: 300
• Locations: 1 country
• Sites: 6

Brief Summary

The goal of this observational study is to build an intelligent ultrasound diagnostic system that integrates pathological typing, risk stratification and prognosis assessment. The main question it aims to answer is:

1. 1.Can the prediction model of neuroblastoma tumors (NTs) in children based on ultrasound images distinguish each pathological subtype?
2. 2.Can the multimodal fusion model established based on clinical and pathological features identify high-risk patients, predict bone marrow metastasis, and estimate the therapeutic effect?
3. 3.Can this ultrasound diagnostic system achieve a systematic and intelligent assessment of NTs patients to assist in clinical risk stratification and individualized treatment decisions?

Conditions

Neuroblastic Tumors

Keywords

neuroblastic tumors; radiomics; ultrasound; children

Outcome Measures

Primary Outcomes (4)

• F1 score

  F1 Score = 2 \* (Precision \* Recall) / (Precision + Recall)

  Within one week after the model training is completed, calculations are conducted respectively on the internal validation set and the independent external validation set.

• accuracy rate

  Draw multi-class ROC curves and calculate based on the ROC curves.

  Within one week after the model training is completed, performance tests are conducted respectively on the internal validation set and the independent external validation set.

• specificity

  specificity = (True negative cases / (True negative cases + False positive cases)) \* 100%

  Within one week after the model training is completed, calculations are conducted respectively on the internal validation set and the independent external validation set.

• sensitivity

  sensitivity= （True Positive / (True Positive + False Negative)）\*100%

  Within one week after the model training is completed, calculations are conducted respectively on the internal validation set and the independent external validation set.

Study Arms (3)

training set

The dataset from the Children's Hospital of Zhejiang University School of Medicine is planned to be randomly divided into a training set and an internal validation set in a ratio of 7:3.

internal validation set

The dataset from the Children's Hospital of Zhejiang University School of Medicine is planned to be randomly divided into a training set and an internal validation set in a ratio of 7:3.

independent external validation set

Data from the Children's Hospital Affiliated to Soochow University, Kunming Children's Hospital, and Anhui Provincial Children's Hospital were combined as an independent external validation set.

Eligibility Criteria

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

Study Population

Patients diagnosed with NTs at the Children's Hospital of Zhejiang University School of Medicine, the Children's Hospital Affiliated to Soochow University, the Children's Hospital of Kunming City, and Anhui Provincial Children's Hospital from January 2015 to February 2025.

You may qualify if:

• The diagnosis of NTs was confirmed by surgical resection or biopsy with histopathological examination, and the type was classified as NB, GNB or GN according to the INPC standard.
• Age ≤ 18 years old, with no gender restrictions.
• There are complete abdominal (or primary site) ultrasound images archived, in original DICOM or JPG format, with image quality meeting the analysis requirements.
• Complete clinical and pathological data relevant to the research purpose are available.

You may not qualify if:

• The patient has previously undergone surgical resection treatment in another hospital, but the tumor recurred or remained after the operation.
• Poor quality of ultrasound images: There are artifacts that seriously affect the identification of tumor contours or feature extraction, image blurring, or incomplete display of the lesion.
• Severe data deficiency: Key clinical pathological data or imaging data are missing, making it impossible to extract and analyze the required information.

Sponsors & Collaborators

• The Children's Hospital of Zhejiang University School of Medicine: lead

Study Sites (6)

Anhui Provincial Children's Hospital

Hefei, Anhui, 230041, China

Location

The Children's Hospital Affiliated to Soochow University

Suzhou, Jiangsu, 215008, China

Location

Kunming Children's Hospital

Kunming, Yunnan, 650100, China

Location

The Children's Hospital of Zhejiang University School of Medicine

Hangzhou, Zhejiang, 310000, China

Location

Zhejiang Cancer Hospital

Hangzhou, Zhejiang, 310000, China

Location

Wenling Institute of Medical Big Data and Artificial Intelligence

Wenling, Zhejiang, 317500, China

Location

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: associate chief physician

Study Record Dates

• First Submitted: April 1, 2026
• First Posted: April 24, 2026
• Study Start: January 1, 2026
• Primary Completion: April 30, 2026
• Study Completion (Estimated): September 30, 2026
• Last Updated: April 24, 2026

Record last verified: 2026-01

Data Sharing

• IPD Sharing: Will not share

Locations

CN (6)