Breast AI Research Portfolio

Rooted in Research. Optimized for Outcomes.

Redefining what breast cancer detection can be.

  • ScreenPoint Medical Research and Evidence in Breast AI

Recent research highlights

AITIC: "Autonomous AI" for low risk cases
AITIC_Promo1 (1)
Prospective Clinical Trial - Spain

AITIC: "Autonomous AI" for low risk cases

March 19, 2026

Researchers used Transpara Detection to safely reduce radiologist workload by over 60% by excluding low risk studies (including DM and DBT) from human review.

Read the study in Nature Medicine
MASAI: Interval cancer reduction
MASAI_Promo1 (1)
Randomised controlled trial - Sweden

MASAI: Interval cancer reduction

January 31, 2026

The first RCT in the field finds that Transpara increased cancer detection, improved radiologist workflow, and decreased the rate of interval cancers by 12%.

Read the study in The Lancet
From screening to stereotactic biopsy
Cancers_Promo1 (1)
Retrospective Study - USA

From screening to stereotactic biopsy

December 3, 2025

"Given its high sensitivity and high negative predictive value, AI may be used to guide radiologists in making biopsy or follow up recommendations."

Read the study in Cancers
Comparable performance to double reading
Lancet_Promo1 (1)
Retrospective Study - The Netherlands

Comparable performance to double reading

August 14, 2025

"AI detection of breast cancer in population-based mammography screening is comparable with double human reading."

Read the study in The Lancet Digital Health

Not all research is created equal

Born from the collaboration of two leading researchers in image processing, ScreenPoint’s origins in applied academia required us to be relentlessly focused on pushing frontiers in AI in breast imaging. Clinical research collaborations have been integral to our growth and our credibility.

Untitled
Workflow

Transpara saves practicing radiologists time - without compromising on clinical quality.

Workflow Transpara saves practicing radiologists time - without compromising on clinical quality.
Untitled
Confidence
Transpara’s unmarked studies have a 99.97% negative predictive value.
Confidence Transpara’s unmarked studies have a 99.97% negative predictive value.
Untitled
Results
Human sensitivity for breast cancer on mammograms can drop from around 80% in the least dense breast tissue to between 50-60% in the densest breasts.
Results Human sensitivity for breast cancer on mammograms can drop from around 80% in the least dense breast tissue to between 50-60% in the densest breasts.

With Transpara

1

Enhanced workflow

Whether you are reading DBT studies in a single reader screening environment like the United States, or identifying lower-risk studies for reducing reading burden in a double reading screening environment, Transpara saves practicing radiologists time – without compromising on clinical quality.

Enhanced workflow
2

Greater confidence

Reading faster has no value without confidence in the results. Transpara’s unmarked studies (70% of a typical screening population) have a 99.97% negative predictive value. These results save ~26% of reading time on DBT studies (Van Winkel, et al, 2021) or up to 44% of workload in a FFDM double-reading environment (Hernström, et al, 2025) while improving the cancer detection rate. Time saved can also save lives.

Greater confidence
3

Consistent results

One of the barriers to confident mammography reading is breast density. Human sensitivity for breast cancer on mammograms can drop from around 80% in the least dense breast tissue to between 50-60% in the densest breasts. Transpara analysis is not affected by the visual characteristics of density in the same way.

Consistent results

Research Portfolio

The Transpara Breast AI Suite is backed by the most substantive body of research and the first randomised controlled trial (search "MASAI") in Breast AI. Click a study to learn more or sort by journal.

For more information and the latest news, head to our Insights Page →

Schedule Demo