AIMS Norway: AI in Mammography Screening in Norway
In the research project "AI in Mammography Screening in Norway - a randomized controlled trial" - AIMS Norway in short - we investigate whether artificial intelligence in combination with radiologists is as good as or better at detecting breast cancer than the current standard procedure in BreastScreen Norway, where two radiologists evaluate the images.
Background
When you participate in BreastScreen Norway, your mammograms are evaluated by two radiologists, who both interpret the images without knowing what the other has concluded (independent double reading). This approach provides a high level of certainty, but since the vast majority of those screened do not have breast cancer, doctors end up spending a great deal of time evaluating normal images.
Artificial intelligence (AI) can help radiologists detect breast cancer while also reducing their workload. Studies show that AI can identify as many—or even more—cases of breast cancer than the current standard procedure in BreastScreen Norway, without increasing the number of “false alarms,” which means additional examinations where no breast cancer is found. At the same time, using AI can greatly reduce the number of screenings that need to be reviewed by two radiologists.
This study, called AIMS Norway (Artificial Intelligence in Mammography Screening in Norway) will test the use of the CE-marked AI program Transpara as a tool in evaluating screening mammograms in BreastScreen Norway. CE-marking means that the program meets European safety requirements for medical equipment.
Purpose
The purpose of the study is to find out whether the AI program, when used in a normal screening situation and in combination with one or two radiologists, is as good as or better at identifying breast cancers on mammograms than the standard procedure in BreastScreen Norway with independent double reading.
If AI can help maintain or improve the quality of screening interpretations, it could mean that the screening program may use medical resources more efficiently, without compromising the safety of those participating in the program.
Implementation
AIMS Norway is conducted as two sub-studies, AIMS 1 and AIMS 2, where AI will be used in slightly different ways in each. Both are carried out as randomized controlled trials. This means that in both sub-studies, half of the study participants will have their mammograms assessed by AI in combination with one or two radiologists (the study group), while the other half will have their images assessed by two radiologists following the standard procedure (the control group).
Assigning participants into the two groups is done by randomization, after signing a consent to participate. This means it is random whether a woman is assigned to the study or control group, and that neither the women, the radiographers at the screening unit nor the radiologists who assess the images can influence the distribution.
The screening examination and any follow-up tests or treatments are carried out as usual, regardless of whether you participate in the sub-studies or which group you may be assigned to.
AIMS 1
In this sub-study, the study group will have their mammograms assessed by one or two radiologists, depending on the AI program’s evaluation. Examinations that the AI classifies as low risk for breast cancer will be reviewed by one radiologist, while the remaining mammograms, classified as medium or high risk, will be reviewed by two radiologists (the standard procedure).
The radiologists will not have access to the AI results when they first assess the images. Only if they notice something suspicious will they see the AI results in a so-called “consensus meeting,” where at least two radiologists discuss the findings and decide whether the participants should be recalled for follow up.
In the control group, all mammograms are assessed by two radiologists according to the standard procedure. Here, too, the AI program will analyze the images, but the AI results will only be available after data collection has been completed. All results are registered in the Cancer Registry at the Norwegian Institute of Public Health (NIPH ) for later analysis in the study.
This sub-study is conducted at the breast centers in the Western, Central and Northern Norway Regional Health Authorities. All women attending screening in BreastScreen Noway at these centers will be asked to participate. Those who wish to participate must provide written consent, which will be requested when you attend the screening.
AIMS 2
In this sub-study, the mammograms in the study group will also be assessed by one or two radiologists, depending on the risk assessment from the AI program. The difference from AIMS 1 is that in this sub-study examinations classified by AI as low to medium risk for breast cancer will be reviewed by one radiologist, while those classified as high risk will be reviewed by two radiologists.
Additionally, the radiologists will have access to the AI results when they first assess the images and during the consensus meeting in this study.
In the control group, all examinations are assessed by two radiologists, according to the standard procedure.
This sub-study will be conducted in the South-East Norway Regional Health Authority, at the breast centers in Vestre Viken and Oslo. When the study begins, all women attending screening in BreastScreen Norway at these centers will be asked to participate. Those who wish to participate must provide written consent.
Data
The study will only include information about women who have consented to participate. In the study, the Cancer Registry of Norway at NIPH will register and use the information that the AI program provides about their mammograms. This includes a score indicating the probability of breast cancer being present in the mammogram.
In addition, the study will use information related to attendance and findings on the mammograms for all those who have provided written consent to participate in the study. This information is registered in the Cancer Registry of Norway according to the usual procedure in BreastScreen Norway. This includes information about the radiologists' assessments, including results of the screening examinations (screening information). The mammograms, which are stored in the hospitals patient records (in Norwegian: pasientjournal), will be used to ensure the quality of the study.
It will not be possible to identify individuals in any published results.
Organization
The Cancer Registry of Norway at the Norwegian Institute of Public Health (NIPH) is the coordinating institution with Solveig Hofvind as project manager. Both sub-studies are multi-center studies, and both the Cancer Registry at the NIPH and the cooperating health trusts are responsible research institutions in accordance with the Health Research Act. The parties have an independent responsibility for organizing and carrying out the part of the study performed in their own institution, and that this is done in accordance with relevant regulations and formal approvals.
The Cancer Registry at NIPH is data controller in both sub-studies. This entails responsibility for obtaining the necessary approvals, collecting data, monitoring the study, quality assurance and analysis of the data material, as well as publishing and reporting results from the study.
The study will be carried out at all breast centers in the Western, Central and Northern Norway Regional Health Authorities (AIMS 1) and at Vestre Viken and Oslo University Hospital in the South-East Norway Regional Health Authority. This includes 16 screening units in addition to mammography buses. The mammograms will be assessed by radiologists at the ten breast centers included. The IT departments in the four health regions will assist in the installation and setup of the AI program in collaboration with the Cancer Registry of Norway and the PACS supplier (program for displaying radiological images).
ScreenPoint Medical (Netherlands) is the company that has developed the AI program to be used in both sub-studies, Transpara. They will assist with installation and train the staff in how to use the system.
Status
AIMS 1
This sub-study started recruiting participants in the Western Norway Regional Health Authority in november 2024, and in the Central Norway Regional Health Authority in September 2025. The Northern Norway Regional Health Authority will be included subsequently.
Recruitment of study participants will continue until the study has reached a number that provides sufficient statistical power to show whether AI in combination with radiologists is as good as or better in assessing mammograms as radiologists alone. This number is about 140 000 women, which we hope to reach during 2026.
AIMS 2
This sub-study is currently being planned, and we are working to establish the technical workflow. Start-up is planned in first half of 2026. The goal is to include approximately 40,000 women.
About the project
Project leader: Solveig Hofvind
Project group at the Cancer Registry of Norway, NIPH: Åsne Holen, Marthe Larsen
Financing: This study is financed by the Pink Ribbon campaign and trough research grants from Western Norway Regional Health Authority of 2023, Central and Northern Norway Regional Health Authority research grants of 2024, and South-Eastern Norway Regional Health Authority research grants of 2025.
Duration: 1.1.2023-31.12.2033
Informed consent
- Information and informed consent
- All study participants will sign an informed consent (pdf)
- Information about data protection in the Cancer Registry of Norway (in Norwegian).
Ethical approvals: This project is approved by the Regional Committees for Medical and Health Research Ethics (REK), project number 366405.
Collaboration:
- Western Norway Regional Health Authority, including the health trusts of Helse Bergen, Helse Fonna, Helse Førde and Helse Stavanger
- Central Norway Regional Health Authority, including the health trusts of Helse Møre og Romsdal and St. Olavs hospital
- Northern Norway Regional Health Authority, including the health trusts of University Hospital of Northern Norway and Nordlandssykehuset
- South-Eastern Norway Regional Health Authority, including the health trusts of Vestre Viken and Oslo University Hospital
- ScreenPoint Medical, Nijmegen (the Netherlands)