Artificial Intelligence in Mammography Screening in Norway (AIMS Norway)

• ClinicalTrials.gov Identifier: NCT06032390
• Recruitment Status: Not yet recruiting
• First Posted: September 13, 2023
• Last Update Posted: September 13, 2023
• Sponsor: Cancer Registry of Norway
• Collaborators: Helse Vest; Helse Midt-Norge; Helse Nord; Norwegian Cancer Society
• Information provided by (Responsible Party): Cancer Registry of Norway

Study Description

Brief Summary:

The purpose of this randomized controlled trial is to compare the number of breast cancers detected among women who had their screening mammograms interpreted by artificial intelligence (AI) in combination with one or two breast radiologists to the number of breast cancers detected after standard independent double reading in BreastScreen Norway. The aims of the study is to prove that screening interpretation with AI in combination with one or two radiologists (the intervention) is non-inferior to standard interpretation procedure.

Condition or disease	Intervention/treatment	Phase
Breast Cancer	Other: AI assisted mammography screening interpretation; Other: Standard mammography screening interpretation	Not Applicable

Detailed Description:

Independent double reading with consensus is the recommended practice for breast cancer screening programs in Europe. This is a time-consuming process and more than 99% of examinations are determined to have a negative final outcome in BreastScreen Norway. However, radiologist still overlook cancers, and review-studies have shown 20-25% of screen-detected and interval cancers to be visible at prior screening mammograms. In Norway and other countries, there is also a shortage of breast radiologists.

Retrospective studies on AI in mammographic screening have shown promising results in the classification of cancer negative and cancer positive examinations. However, prospective studies are needed to elucidate questions concerning AI as a support or replacement for the radiologists in the interpretation process.

In this randomized controlled trial women attending screening and consenting to participate in the study, will be randomized (1:1 allocation) to an intervention or a control group. The screening examination will be performed as usual in both groups. The intervention in the trial is the interpretation procedure.

All examinations will be analyzed by AI. In the intervention group, examinations will be triaged according to risk of malignancy defined by an AI score. Examinations with a low AI score will have a single reading by one radiologist and examinations with a intermediate or high AI score will have an independent double reading by two radiologists. All examinations selected by either one or both radiologist will be discussed at consensus. Examinations with an AI raw score of 9.8 or above will be discussed at consensus independent of the radiologists' interpretation. The radiologists will be blinded to whether the mammograms are interpreted by one or two radiologists. AI risk scores and AI image marking of suspicious calcifications and masses are only provided to the radiologists at consensus, not during independent reading. In the control group, two independent radiologists will interpret all screening examinations according to standard procedure, independent double reading. AI results will not be available at either independent reading or consensus, only for comparison with the intervention group in final analyses.

Screen-detected cancers in the intervention and control arm will be analyzed in terms of non-inferiority.

Study Design

• Study Type: Interventional (Clinical Trial)
• Estimated Enrollment: 150000 participants
• Allocation: Randomized
• Intervention Model: Parallel Assignment
• Intervention Model Description: Participants will be randomized to an intervention or control arm. AI aided interpretation will be used in the intervention arm but not in the control arm.
• Masking: Double (Participant, Care Provider)
• Masking Description: Neither the participant nor the radiologic technician performing the mammography examination will know to what study arm the participant was allocated. Radiologists reading the screening examinations will be blinded to the intervention at initial reading but not at consensus.
• Primary Purpose: Screening
• Official Title: Artificial Intelligence in BreastScreen Norway - a Randomized Controlled Trial
• Estimated Study Start Date: January 2024
• Estimated Primary Completion Date: December 2026
• Estimated Study Completion Date: June 2033

Arms and Interventions

Arm	Intervention/treatment
Experimental: Intervention arm; AI assisted mammography screening interpretation	Other: AI assisted mammography screening interpretation; Screening examinations will be analyzed by the AI system (Transpara, ScreenPoint Medical, Nijmegen, The Netherlands) that assigns each examination a cancer risk score 1-10. Examinations with a score 1-7 will be single read and examinations with score 8-10 will be double read. Examinations selected by one or two readers will be discussed in consensus. Examinations with an AI score of 9.8 and above will be selected to consensus by default. Risk scores and AI image markings are provided to the readers only in consensus. The readers will decide whether to recall the woman for further assessment in consensus (standard procedure).
Active Comparator: Control arm; Standard mammography screening interpretation (standard procedure)	Other: Standard mammography screening interpretation; Screening examinations will be assessed according to standard of care: independently double read, examinations selected by one or two readers will be discussed in consensus, and the readers will decide whether to recall the woman for further assessment. Screening examinations will be analyzed by the AI system but the results will not be made available to the radiologist, only used for comparison to the intervention group in results analyses.

Outcome Measures

Primary Outcome Measures :

1. Screen-detected breast cancers [ Time Frame: 36 months from study start-up ]
   Number of breast cancers detected at screening per 1000 screening examinations.

Secondary Outcome Measures :

1. Consensus rate [ Time Frame: 24 months from study start-up ]
   Proportion of participant discussed in consensus among all participants (%).
2. Recall rate [ Time Frame: 24 months from study start-up ]
   Proportion of women recalled for further assessment among all participants (%).
3. Interval breast cancers [ Time Frame: 60 months from study start-up ]
   Number of interval breast cancers diagnosed per 1000 screening examinations.
4. Prognostic and predictive tumor characteristics of screen-detected breast cancer [ Time Frame: 36 months from study start-up ]
   Distribution of tumor characteristics among the participants with screen-detected breast cancer.
5. Prognostic and predictive tumor characteristics of interval breast cancer [ Time Frame: 60 months from study start-up ]
   Distribution of tumor characteristics among the participants with interval breast cancer.
6. Sensitivity [ Time Frame: 60 months from study start-up ]
   Proportion of true positives among true positive and false negatives (%).
7. Specificity [ Time Frame: 60 months from study start-up ]
   Proportion of true negatives among true negatives and false positives (%).
8. Mammographic features of screen-detected breast cancer [ Time Frame: 36 months from study start-up ]
   Distribution of characteristics of tumors observed on the mammograms of participants diagnosed with screen-detected breast cancer.
9. Time spent screen-reading [ Time Frame: 36 months from study start-up ]
   Time (minutes:seconds) spent by the individual radiologists interpreting screening mammograms

Eligibility Criteria

• Ages Eligible for Study: 50 Years to 69 Years (Adult, Older Adult)
• Sexes Eligible for Study: Female
• Accepts Healthy Volunteers: Yes

Criteria

Inclusion Criteria:

• Women attending the population-based mammography screening program BreastScreen Norway providing a signed, informed consent

Exclusion Criteria:

• Women attending the population-based mammography screening program BreastScreen Norway not providing a signed, informed consent, or with breast implants

Contacts and Locations

Contacts

Contact: Solveig Hofvind, PhD; 22928828 ext +47; sshh@kreftregisteret.no

Contact: Åsne S Holen, MSc; asho@kreftregisteret.no

Sponsors and Collaborators

Cancer Registry of Norway

Helse Vest

Helse Midt-Norge

Helse Nord

Norwegian Cancer Society

Investigators

• Principal Investigator: Solveig Hofvind, PhD; Cancer Registry of Norway

More Information

• Responsible Party: Cancer Registry of Norway
• ClinicalTrials.gov Identifier: NCT06032390
• Other Study ID Numbers: 366405
• First Posted: September 13, 2023
• Last Update Posted: September 13, 2023
• Last Verified: June 2023

Individual Participant Data (IPD) Sharing Statement:

• Plan to Share IPD: No
• Plan Description: Data will not be shared outside the project group.

• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Product Manufactured in and Exported from the U.S.: No

Keywords provided by Cancer Registry of Norway:

Breast Cancer Screening; Digital Mammography; Artificial Intelligence; Randomized Controlled Trial

Additional relevant MeSH terms:

Breast Neoplasms; Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases