History of Changes for Study: NCT04838756

Mammography Screening With Artificial Intelligence (MASAI) (MASAI)

A study version is represented by a row in the table.
Select two study versions to compare. One each from columns A and B.
Choose either the "Merged" or "Side-by-Side" comparison format to specify how the two study versions are to be displayed. The Side-by-Side format only applies to the Protocol section of the study.
Click "Compare" to do the comparison and show the differences.
Select a version's Submitted Date link to see a rendering of the study for that version.
The yellow A/B choices in the table indicate the study versions currently compared below. A yellow table row indicates the study version currently being viewed.
Hover over the "Recruitment Status" to see how the study's recruitment status changed.
Study edits or deletions are displayed in red.
Study additions are displayed in green.

Study Record Versions

Version	Submitted Date	Changes
1	April 8, 2021	None (earliest Version on record)
2	April 14, 2021	Recruitment Status, Study Status and Contacts/Locations
3	April 26, 2022	Study Status
4	December 12, 2022	Recruitment Status, Study Status and Study Design
5	March 8, 2024	Study Status

Comparison Format:

Merged
Side-by-Side

Study Identification


Unique Protocol ID:	2020-04936
Brief Title:	Mammography Screening With Artificial Intelligence (MASAI) (MASAI)
Official Title:	A Randomized, Single-blinded, Controlled Trial on the Efficacy of Mammography Screening With Artificial Intelligence - the MASAI Study
Secondary IDs:

Study Status


Record Verification:	April 2021
Overall Status:	Not yet recruiting
Study Start:	April 12, 2021
Primary Completion:	November 12, 2024 [Anticipated]
Study Completion:	April 12, 2025 [Anticipated]

First Submitted:	April 6, 2021
First Submitted that Met QC Criteria:	April 8, 2021
First Posted:	April 9, 2021 [Actual]

Last Update Submitted that Met QC Criteria:	April 8, 2021
Last Update Posted:	April 9, 2021 [Actual]

Sponsor/Collaborators


Sponsor:	Region Skane
Responsible Party:	Sponsor
Collaborators:	Unilabs Cancer Registry of Norway

Oversight


U.S. FDA-regulated Drug:	No
U.S. FDA-regulated Device:	No
Data Monitoring:	No

Study Description

Brief Summary:

The purpose of this randomized controlled trial is to assess whether AI can improve the efficacy of mammography screening, by adapting single and double reading based on AI derived cancer-risk scores and to use AI as a decision support in the screen reading, compared with conventional mammography screening (double reading without AI).

Detailed Description:

European guidelines recommend that mammography exams in breast cancer screening are read by two breast radiologists to ensure a high sensitivity. Double reading is, however, resource demanding and still results in missed cancers. Computer-aided detection based on AI has been shown to have similar accuracy as an average breast radiologist. AI can be used as decision support by highlighting suspicious findings in the image as well as a means to triage screen exams according to risk of malignancy.

Eligible women will be randomized (1:1) to the intervention (AI-integrated mammography screening) or control arm (conventional mammography screening). In the intervention arm, exams will be analysed with AI and triaged into two groups based on risk of malignancy. Low risk exams will be single read and high risk exams will be double read. The high risk group will contain appx. 10% of the screening population. Within the high-risk group, exams with the highest 1% risk will by default be recalled by the readers with the exception of obvious false positives. AI risk scores and Computer-Aided Detection (CAD)-marks of suspicious calcifications and masses are provided to the reader(s). In the control arm, screen exams are double read without AI (standard of care). Considering the interplay of number of interval cancers and workload, the study will be considered successful if the interval-cancer rate in the intervention arm is not more than 20% larger than in the control arm. If the interval-cancer rate is statistically and clinically significantly lower in the intervention arm than in the control arm, AI-integrated mammography screening will be considered superior to conventional mammography screening.

Conditions


Conditions:	Breast Cancer
Keywords:	Mammography Screening Artificial Intelligence

Study Design


Study Type:	Interventional
Primary Purpose:	Screening
Study Phase:	Not Applicable
Interventional Study Model:	Parallel Assignment
Number of Arms:	2
Masking:	Single (Participant)
Allocation:	Randomized
Enrollment:	100000 [Anticipated]

Arms and Interventions

Arms

Assigned Interventions

Experimental: Intervention arm

AI-integrated mammography screening

AI screening modality

Screen exam will be analysed with an AI system (Transpara, ScreenPoint, Nijmegen, The Netherlands) that assigns exams with a cancer-risk score from 1 to 10, as well as presenting CAD-marks at suspicious findings. Exams with risk score 1-9 will be single read and exam with score 10 will be double read. Risk scores and CAD-marks are provided to the reader(s). The reader(s) will decide whether to recall the woman for work-up or not (as per standard of care). In addition, exams with the highest 1% risk will by default be recalled with the exception of obvious false positives.

Experimental: Control arm

Conventional mammography screening (standard of care)

Conventional screening modality

Screen exams will be read by two radiologists without the support of AI.

Outcome Measures


Primary Outcome Measures:
1.	Interval-cancer rate [ Time Frame: 43 months ] Women with interval cancer per 1000 screens
Secondary Outcome Measures:
1.	Cancer-detection rate [ Time Frame: 15 months ] Women with screen-detected cancer per 1000 screens
2.	Recall rate [ Time Frame: 15 months ] Number of recalls per 1000 screens
3.	False-positive rate [ Time Frame: 15 months ] Women with false positive per 1000 screens
4.	Positive Predictive Value-1 [ Time Frame: 15 months ] Women with cancer for all recalls
5.	Sensitivity and specificity [ Time Frame: 43 months ] True and false-positive rate
6.	Cancer detection per cancer type [ Time Frame: 19 months ] Screen detection of cancer in relation to cancer type, size and stage
7.	Tumour biology of interval cancers [ Time Frame: 43 months ] Characterization of interval cancers per type, size and stage
8.	Screen-reading workload [ Time Frame: 19 months ] Number of screen-readings and number of consensus meetings
9.	Incremental cost-effectiveness ratio [ Time Frame: 43 months ] The incremental cost-effectiveness ratio for AI-integrated mammography screening versus standard of care

Eligibility


Minimum Age:	40 Years
Maximum Age:	74 Years
Sex:	Female
Gender Based:
Accepts Healthy Volunteers:	Yes
Criteria:	Inclusion Criteria: Women eligible for population-based mammography screening. Exclusion Criteria: None.

Contacts/Locations


Central Contact Person:	Kristina Lång, MD PhD Telephone: +4640338880 Email: kristina.lang@med.lu.se
Study Officials:	Kristina Lång, MD PhD Principal Investigator Region Skåne
Locations:

IPDSharing


Plan to Share IPD:	No IPD could be considered to be shared in future collaborations.

References


Citations:
Links:
Available IPD/Information: