NCT03080623

Ultrasound-based Diagnostic Model for Differentiating Malignant Breast Lesion From Benign Lesion

Completed Last updated 28 October 2020

What this trial tests

trial in Breast Cancer Female in 1,981 participants. Completed in 31 December 2019.

Timeline

8 September 2018

Primary endpoint
30 September 2019

31 December 2019

Quick facts

Lead sponsor	Peking University
Status	Completed
Study type	OBSERVATIONAL
Enrollment	1,981
Start date	8 September 2018
Primary completion	30 September 2019
Estimated completion	31 December 2019
Sites	4 locations across China

Conditions studied

• Breast Cancer Female — all drugs for Breast Cancer Female →
• Diagnoses Disease — all drugs for Diagnoses Disease →

Sponsor

Peking University

Who can join

Adults 18 to 80, female only, with Breast Cancer Female or Diagnoses Disease. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

This study proposed to construct an ultrasound-based diagnostic model for Differentiating Malignant Breast Lesion From Benign Lesion. This study contains both retrospective and prospective part, which are designed for model construction and independent validation, respectively.This study aims to construct an easy-to-use ultrasound-based model, prove the efficacy of the model for identifying malignant breast lesion from benign lesion, and finally promote the application of this diagnostic model in more clinics.

Publications & conference data

2 peer-reviewed publications reference this trial (live from Europe PMC):

1. Machine Learning Models to Improve the Differentiation Between Benign and Malignant Breast Lesions on Ultrasound: A Multicenter External Validation Study.
   Huo L, Tan Y, Wang S, Geng C, et al · · 2021 · cited 7× · PMID 33889025 · DOI 10.2147/cmar.s297794
2. Machine Learning Models for Breast Lesions Based on Ultrasound Imaging Features: A Observational Study
   Tan Y, Huo L, Wang S, Geng C, et al · · 2020 · DOI 10.21203/rs.3.rs-101184/v1