Using Deep Learning Methods to Analyze Automated Breast Ultrasound and Hand-held Ultrasound Images, to Establish a Diagnosis, Therapy Assessment and Prognosis Prediction Model of Breast Cancer.

• Sponsor: The First Affiliated Hospital of the Fourth Military Medical University (Other)
• Overall Status: Recruiting
• CT.gov ID: NCT04270032
• Collaborator: Seoul National University Bundang Hospital (Other), Xidian University (Other), Shenzhen University (Other)
• Enrollment: 10,000
• Location: 1
• Anticipated Duration (Months): 55
• Patients Per Site Per Month: 181.8

Study Details

Study Description

Brief Summary

The purpose of this study is using a deep learning method to analyze the automated breast ultrasound (ABUS) and hand-held ultrasound(HHUS) images, establish and evaluate a diagnosis, therapy assessment and prognosis prediction model of breast cancer. The model would provide important references for further early prevention, early diagnosis and personalized treatment.

Condition or Disease	Intervention/Treatment	Phase
Breast Cancer	Diagnostic Test: ABUS and HHUS

Detailed Description

1. Establishing a database By collecting ABUS, HHUS and comprehensive breast images data, essential information, clinical treatment information, prognosis, and curative effect information, a complete breast image database is constructed.

2. Marking ABUS images Three doctors use a semi-automatic method to frame the lesions on the image.

3. Building the model Using the deep learning method to preprocess, analyze and train the marked images, and finally get a model diagnosis, efficacy evaluation and prognosis prediction model of breast cancer.

4. Evaluating the model 1）Self-validation： Analyze the sensitivity, AUC of the breast cancer diagnosis model and the false-positive number on each ABUS volume.

1. Compared the sensitivity, AUC and the false-positive number with a commercial diagnosis model.

3)To test the screening and diagnostic efficacy of computer-aided diagnosis systems through prospective or retrospective studies.

4)By analyzing the size and characteristics of the lesions after neoadjuvant chemotherapy, and predicting the OS and DFS time, the therapy assessment and prognosis prediction model were evaluated.

Study Design

• Study Type: Observational
• Anticipated Enrollment: 10000 participants
• Observational Model: Other
• Time Perspective: Other
• Official Title: To Build and Evaluate a Precise Diagnosis, Therapy Assessment and Prognosis Prediction Model of Breast Cancer Based on Artificial Intelligence
• Actual Study Start Date: Feb 1, 2020
• Anticipated Primary Completion Date: Sep 1, 2024
• Anticipated Study Completion Date: Sep 1, 2024

Arms and Interventions

Arm	Intervention/Treatment
malignant group women with malignant lesions confirmed by pathology	Diagnostic Test: ABUS and HHUS; Using deep learning method to analyze and extract the features of automated breast ultrasound and hand-held ultrasound images
benign group women with benign lesions confirmed by pathology or stable in follow-up > 2 years	Diagnostic Test: ABUS and HHUS; Using deep learning method to analyze and extract the features of automated breast ultrasound and hand-held ultrasound images
normal group women have normal images with follow up > 2 years	Diagnostic Test: ABUS and HHUS; Using deep learning method to analyze and extract the features of automated breast ultrasound and hand-held ultrasound images

Outcome Measures

Primary Outcome Measures

1. sensitivity [4 years]

   Proportion of corrected-marked malignant lesions by the model

2. false-positive per volume [4 years]

   the number of uncorrected-marked malignant lesions by the model

3. area under curve [4 years]

   area under receiver operating characteristic (ROC) curve in percentage (%)

4. overall survival(OS) time [up to 10 years]

   It measures the time from the date of cancer diagnosis to any cause of death.

5. Disease-free survival (DFS) time [up to 5 years]

   The time that the patient is free of the signs and symptoms of a disease after treatment.

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years and Older
• Sexes Eligible for Study: Female
• Accepts Healthy Volunteers: Yes

Inclusion Criteria:

1. Female patients over 18 years old who come to the two centers for physical examination or treatment;

2. Complete basic information and image data

Exclusion Criteria:

1. There is no complete ABUS and HHUS images data;

2. The image quality is poor;

3. In multifocal breast cancer, the correlation between the tumor in the image and the postoperative pathological examination is uncertain.

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	The First Affiliated Hospital of Fourth Military Medical University	Xi'an	Shaanxi	China	710000

Sponsors and Collaborators

• The First Affiliated Hospital of the Fourth Military Medical University
• Seoul National University Bundang Hospital
• Xidian University
• Shenzhen University

Investigators

• Principal Investigator: Hongping Song, MD, Xijing hospital of The fourth military medical university

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Song Hongping, Principal Investigator, The First Affiliated Hospital of the Fourth Military Medical University
• ClinicalTrials.gov Identifier: NCT04270032
• Other Study ID Numbers: AI-Breast-US
• First Posted: Feb 17, 2020
• Last Update Posted: Jan 27, 2022
• Last Verified: Jan 1, 2022

• Individual Participant Data (IPD) Sharing Statement: Undecided
• Plan to Share IPD: Undecided
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: Yes
• Product Manufactured in and Exported from the U.S.: Yes
• Additional relevant MeSH terms: Breast Neoplasms

Study Results

No Results Posted as of Jan 27, 2022