Ignite Creation Date:
2025-12-24 @ 9:56 PM
Ignite Modification Date:
2026-01-01 @ 8:48 AM
Study NCT ID:
NCT04270032
Status:
UNKNOWN
Last Update Posted:
2022-01-27
First Post:
2020-02-12
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
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:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D001943', 'term': 'Breast Neoplasms'}], 'ancestors': [{'id': 'D009371', 'term': 'Neoplasms by Site'}, {'id': 'D009369', 'term': 'Neoplasms'}, {'id': 'D001941', 'term': 'Breast Diseases'}, {'id': 'D012871', 'term': 'Skin Diseases'}, {'id': 'D017437', 'term': 'Skin and Connective Tissue Diseases'}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'OTHER', 'observationalModel': 'OTHER'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 10000}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'UNKNOWN', 'lastKnownStatus': 'RECRUITING', 'startDateStruct': {'date': '2020-02-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2022-01', 'completionDateStruct': {'date': '2024-09-01', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2022-01-12', 'studyFirstSubmitDate': '2020-02-12', 'studyFirstSubmitQcDate': '2020-02-13', 'lastUpdatePostDateStruct': {'date': '2022-01-27', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2020-02-17', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2024-09-01', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'sensitivity', 'timeFrame': '4 years', 'description': 'Proportion of corrected-marked malignant lesions by the model'}, {'measure': 'false-positive per volume', 'timeFrame': '4 years', 'description': 'the number of uncorrected-marked malignant lesions by the model'}, {'measure': 'area under curve', 'timeFrame': '4 years', 'description': 'area under receiver operating characteristic (ROC) curve in percentage (%)'}, {'measure': 'overall survival(OS) time', 'timeFrame': 'up to 10 years', 'description': 'It measures the time from the date of cancer diagnosis to any cause of death.'}, {'measure': 'Disease-free survival (DFS) time', 'timeFrame': 'up to 5 years', 'description': 'The time that the patient is free of the signs and symptoms of a disease after treatment.'}]}, 'oversightModule': {'isUsExport': True, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': True}, 'conditionsModule': {'conditions': ['Breast Cancer']}, 'descriptionModule': {'briefSummary': '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.', 'detailedDescription': '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.\n2. Marking ABUS images Three doctors use a semi-automatic method to frame the lesions on the image.\n3. 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.\n4. 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.\n\n2\\) Compared the sensitivity, AUC and the false-positive number with a commercial diagnosis model.\n\n3)To test the screening and diagnostic efficacy of computer-aided diagnosis systems through prospective or retrospective studies.\n\n4)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.'}, 'eligibilityModule': {'sex': 'FEMALE', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'PROBABILITY_SAMPLE', 'studyPopulation': 'Female patients over 18 years old from two countries (China and Korea).', 'healthyVolunteers': True, 'eligibilityCriteria': 'Inclusion Criteria:\n\n1. Female patients over 18 years old who come to the two centers for physical examination or treatment;\n2. Complete basic information and image data\n\nExclusion Criteria:\n\n1. There is no complete ABUS and HHUS images data;\n2. The image quality is poor;\n3. In multifocal breast cancer, the correlation between the tumor in the image and the postoperative pathological examination is uncertain.'}, 'identificationModule': {'nctId': 'NCT04270032', 'briefTitle': '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.', 'organization': {'class': 'OTHER', 'fullName': 'The First Affiliated Hospital of the Fourth Military Medical University'}, 'officialTitle': 'To Build and Evaluate a Precise Diagnosis, Therapy Assessment and Prognosis Prediction Model of Breast Cancer Based on Artificial Intelligence', 'orgStudyIdInfo': {'id': 'AI-Breast-US'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'malignant group', 'description': 'women with malignant lesions confirmed by pathology', 'interventionNames': ['Diagnostic Test: ABUS and HHUS']}, {'label': 'benign group', 'description': 'women with benign lesions confirmed by pathology or stable in follow-up \\> 2 years', 'interventionNames': ['Diagnostic Test: ABUS and HHUS']}, {'label': 'normal group', 'description': 'women have normal images with follow up \\> 2 years', 'interventionNames': ['Diagnostic Test: ABUS and HHUS']}], 'interventions': [{'name': 'ABUS and HHUS', 'type': 'DIAGNOSTIC_TEST', 'description': 'Using deep learning method to analyze and extract the features of automated breast ultrasound and hand-held ultrasound images', 'armGroupLabels': ['benign group', 'malignant group', 'normal group']}]}, 'contactsLocationsModule': {'locations': [{'zip': '710000', 'city': "Xi'an", 'state': 'Shaanxi', 'status': 'RECRUITING', 'country': 'China', 'contacts': [{'name': 'hongping song, Ph.D', 'role': 'CONTACT', 'email': 'Songhp@fmmu.edu.cn', 'phone': '+86-29-84771663'}, {'name': 'hongping song', 'role': 'PRINCIPAL_INVESTIGATOR'}], 'facility': 'The First Affiliated Hospital of Fourth Military Medical University', 'geoPoint': {'lat': 34.25833, 'lon': 108.92861}}], 'centralContacts': [{'name': 'Hongping Song, MD', 'role': 'CONTACT', 'email': 'song.hp@foxmail.com', 'phone': '86 029 84771663'}], 'overallOfficials': [{'name': 'Hongping Song, MD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'Xijing hospital of The fourth military medical university'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'UNDECIDED'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'The First Affiliated Hospital of the Fourth Military Medical University', 'class': 'OTHER'}, 'collaborators': [{'name': 'Seoul National University Bundang Hospital', 'class': 'OTHER'}, {'name': 'Xidian University', 'class': 'OTHER'}, {'name': 'Shenzhen University', 'class': 'OTHER'}], 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'Principal Investigator', 'investigatorFullName': 'Song Hongping', 'investigatorAffiliation': 'The First Affiliated Hospital of the Fourth Military Medical University'}}}}