UMIN-CTR Clinical Trial

Unique ID issued by UMIN UMIN000039009
Receipt number R000044471
Scientific Title A deep learning-based automated diagnostic system for classifying mammographic lesions
Date of disclosure of the study information 2019/12/26
Last modified on 2023/06/30 21:10:57

* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments


Basic information

Public title

A deep learning-based automated diagnostic system for classifying mammographic lesions

Acronym

DLADS

Scientific Title

A deep learning-based automated diagnostic system for classifying mammographic lesions

Scientific Title:Acronym

DLADS

Region

Japan


Condition

Condition

Breast cancer

Classification by specialty

Hematology and clinical oncology

Classification by malignancy

Malignancy

Genomic information

NO


Objectives

Narrative objectives1

The aim of this study is to construct a deep learning-based AI system to detect breast cancer on mammograms with high specificity, and to evaluate the performance of the AI system.

Basic objectives2

Efficacy

Basic objectives -Others


Trial characteristics_1


Trial characteristics_2


Developmental phase



Assessment

Primary outcomes

The sensitivity and specificity of the AI system to detect breast cancer with the test image set.

Key secondary outcomes



Base

Study type

Others,meta-analysis etc


Study design

Basic design


Randomization


Randomization unit


Blinding


Control


Stratification


Dynamic allocation


Institution consideration


Blocking


Concealment



Intervention

No. of arms


Purpose of intervention


Type of intervention


Interventions/Control_1


Interventions/Control_2


Interventions/Control_3


Interventions/Control_4


Interventions/Control_5


Interventions/Control_6


Interventions/Control_7


Interventions/Control_8


Interventions/Control_9


Interventions/Control_10



Eligibility

Age-lower limit

20 years-old <=

Age-upper limit


Not applicable

Gender

Female

Key inclusion criteria

Digital mammography images fulfilling all the following criteria are collected.
1.Taken after 2010
2.Images meeting either one of the following criteria
>Visible breast cancer or benign lesions on images
>Normal breast
3.If cancer or benign lesions are visible on images, their outlines can be traced manually
4.Images from patients aged 20 or older
5.Available mediolateral oblique (MLO) view with or without cranial-caudal view (CC)
6.No visible axillary lymph node metastasis from breast cancer
7.Images from patients with no previous history of chemotherapy, endocrine therapy or radiotherapy.
8.Images from patients who have not received any previous surgical breast procedure including partial resection, breast reconstruction, incisional biopsy, vacuum-assisted biopsy and mammoplasty
9.Read by readers ranked A according to the Japan Central Organization on Quality Assurance of Breast Cancer Screening
10.Benign lesions, breast cancer and normal breast on images are confirmed by the following criteria
(Benign lesions)
Meeting one of the following criteria
>Confirmed by histopathology
>Without malignancy development over at least 2 years of follow-up
>Findings clearly indicating a simple cyst by mammmography and other imaging modalities

(Breast cancer)
>Confirmed by histopathology

(Normal breast)
Meeting either one of the following criteria
>In addition to the findings of mammography, ultrasonography and MRI do not detect any lesions.
>Without malignancy development over at least 2 years of follow-up when no other imaging modalities except mammography are performed.

Key exclusion criteria

Digital mammography images fulfilling any of the following criteria are not collected.
1.Tomosynthesis and synthetic 2D mammographic images
2.Spot compression views
3.Poor image quality
4.Inappropriate images as judged by the local investigators

Target sample size

16000


Research contact person

Name of lead principal investigator

1st name Hirofumi
Middle name
Last name Mukai

Organization

National Cancer Center Hospital East

Division name

Division of Breast and Medical oncology

Zip code

277-8577

Address

6-5-1, Kashiwanoha, Kashiwa-shi, Chiba

TEL

04-7133-1111

Email

hrmukai@east.ncc.go.jp


Public contact

Name of contact person

1st name Hirofumi
Middle name
Last name Mukai

Organization

National Cancer Center Hospital East

Division name

Division of Breast and Medical oncology

Zip code

277-8577

Address

6-5-1, Kashiwanoha, Kashiwa-shi, Chiba

TEL

04-7133-1111

Homepage URL

http://cspor-bc.or.jp/

Email

hrmukai@east.ncc.go.jp


Sponsor or person

Institute

Comprehensive Support Project for Oncology Research for Breast Cancer (CSPOR-BC)

Institute

Department

Personal name



Funding Source

Organization

Comprehensive Support Project for Oncology Research for Breast Cancer (CSPOR-BC)

Organization

Division

Category of Funding Organization

Other

Nationality of Funding Organization



Other related organizations

Co-sponsor


Name of secondary funder(s)



IRB Contact (For public release)

Organization

National Cancer Center Hospital East Certified Review Board

Address

6-5-1 Kashiwanoha, Kashiwa-shiChiba-ken, 277-8577 Japan

Tel

04-7133-1111

Email

ncche-irb@east.ncc.go.jp


Secondary IDs

Secondary IDs

NO

Study ID_1


Org. issuing International ID_1


Study ID_2


Org. issuing International ID_2


IND to MHLW



Institutions

Institutions



Other administrative information

Date of disclosure of the study information

2019 Year 12 Month 26 Day


Related information

URL releasing protocol

https://journals.lww.com/md-journal/Fulltext/2020/07020/A_deep_learning_based_automated_diagnostic_s

Publication of results

Published


Result

URL related to results and publications

unpublished

Number of participants that the trial has enrolled

20000

Results

The constructed AI showed comparable ability to humans in reading mammograms.

Results date posted

2023 Year 06 Month 30 Day

Results Delayed


Results Delay Reason


Date of the first journal publication of results


Baseline Characteristics

Mammographic images of breast cancer, benign lesions and normal breasts were collected.

Participant flow

The images were collected from 63 institutions.

Adverse events

Not applicable.

Outcome measures

Both the sensitivity and specificity of the AI exceeded the target performance of 80%.

Plan to share IPD


IPD sharing Plan description



Progress

Recruitment status

Completed

Date of protocol fixation

2019 Year 05 Month 10 Day

Date of IRB

2019 Year 07 Month 04 Day

Anticipated trial start date

2019 Year 09 Month 01 Day

Last follow-up date

2021 Year 08 Month 31 Day

Date of closure to data entry


Date trial data considered complete


Date analysis concluded



Other

Other related information

The aim of this study is to construct a deep learning-based AI system to detect breast cancer on mammograms with high specificity, and to evaluate the performance of the AI system.


Management information

Registered date

2019 Year 12 Month 26 Day

Last modified on

2023 Year 06 Month 30 Day



Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000044471


Research Plan
Registered date File name

Research case data specifications
Registered date File name

Research case data
Registered date File name