Performance of the Diagnostic Value of Bone Age Assessment Software Based on Deep Learning in Chinese Children

High accuracy and precision bone age assessment is very important for the diagnosis and treatment monitoring of various pediatric diseases. The commonly used bone age assessment methods include GP atlas, TW3 score and Zhonghua 05. GP method is to compare wrist X-ray films with atlas reference X-ray films. Its main disadvantages are strong subjectivity and long atlas standard interval. Different from GP method, TW3 method is to grade and score each bone, add each epiphyseal score to calculate the total score of bone maturity, and obtain the corresponding final bone age value. Although TW3 scoring method is relatively accurate, it is complex and time-consuming, and there is great variability among evaluators. In order to evaluate bone age more efficiently and accurately, a method based on computer image automatic recognition technology can help to overcome these problems.

In this study, 1000 children aged 1-18 in 5 hospitals are selected as the research objects. After taking bone age films with bone age instrument, the film reading results and evaluation time of AI Group, artificial group and standard group are recorded. One month later, the artificial group re-analyzes 1000 films with the assistance of AI system, and the evaluation time is recorded. Finally, the accuracy and time difference of artificial group, AI Group, artificial combined AI Group and standard group are compared.

The purpose of this study is to use the most advanced artificial intelligence deep learning bone age evaluation software to explore the value of bone age instrument to improve the accuracy and diagnostic efficiency of bone age evaluation by pediatricians.

Study Overview

• Status: Recruiting
• Conditions: Endocrine Diseases
• Intervention / Treatment: Device: X-ray bone age instrument

Detailed Description

1. Study subjects: Radiographs of the left wrist of 1000 children aged 1-18 years who underwent bone age measurement at 5 hospitals were selected
2. Research methods:

2.1 general information: name, gender, actual age, height, weight, BMI, race, disease type 2.2 main instrument: artificial intelligence X-ray bone age instrument 2.3 scanning scheme: Left posterior and anterior radiographs 2.4 bone age evaluation method and group 2.4.1 the standard group：Tw3-RUS and TW3-CARPAL were used to evaluate the left hand bone age tablets by the 5 pediatric doctors designated in the TW3 system training. There was no time limit for reading the tablets. The mean value of the evaluation results of the 5 doctors was taken as the final reference standard.

2.4.2 Grouping of bone age assessment ① artificial group (5 assessors assess bone age separately) ② AI Group③ artificial + AI Group (artificial Group assesses bone age with the assistance of AI intelligent software assessment) After taking bone age films with bone age instrument, the film reading results and evaluation time of AI Group, artificial group and standard group are recorded. One month later, the artificial group re-analyzes 1000 films with the assistance of AI system, and the evaluation time is recorded. Finally, the accuracy and time difference of artificial group, AI Group, artificial combined AI Group and standard group are compared.

• Study Type: Observational
• Enrollment (Anticipated): 1000

Contacts and Locations

• Study Contact: Name: Xiaoping Luo, director; Phone Number: 13387522645; Email: xpluo@tjh.tjmu.edu.cn

Study Locations

• China
  • Hubei
    • Wuhan, Hubei, China
      • Recruiting
      • Tongji Hospital Tongji Medical College of HUST
      • Contact: Xiaoping Luo, director; Phone Number: 13387522645; Email: xpluo@tjh.tjmu.edu.cn
      • Principal Investigator: xiaoping luo, director

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 1 year to 18 years (Child, Adult)
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Children aged 1-18 who need bone age assessment

Description

Inclusion Criteria:

1. Children aged 1 to 18 years.
2. Clinical diagnosis of requiring bone age examination.

Exclusion Criteria:

1. There are obstructions or implants in the wrist bone, such as metal.
2. Poor resolution, which affects the observation of bone characteristics.
3. Poor shooting position of the wrist due to various reasons.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
bone age	The mean absolute error (MAE) and root mean square error (RSME) between the evaluation bone age results of different groups	one month

Collaborators and Investigators

• Sponsor: Tongji Hospital
• Collaborators: GeneScience Pharmaceuticals Co., Ltd.

Study record dates

Study Major Dates

• Study Start (Actual): February 21, 2022
• Primary Completion (Anticipated): December 31, 2024
• Study Completion (Anticipated): December 31, 2024

Study Registration Dates

• First Submitted: November 11, 2021
• First Submitted That Met QC Criteria: November 28, 2021
• First Posted (Actual): November 30, 2021

Study Record Updates

• Last Update Posted (Actual): April 20, 2023
• Last Update Submitted That Met QC Criteria: April 18, 2023
• Last Verified: April 1, 2023

More Information

Terms related to this study

• Keywords: bone age; TW3; AI
• Additional Relevant MeSH Terms: Endocrine System Diseases
• Other Study ID Numbers: GenSci-GD-21001

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No