AI solution for Mammography

Online Demo
  • 96%

    Detects breast cancer
    with 96-99%

  • 240,000

    Trained with a large-scale (more than 50,000 breast cancer cases), high-quality (biopsy-proven cases) training set.

  • 50%

    Reduces the chances of physicians
    overlooking breast cancer
    in the screening mammography by 50%

  • 2797

    Currently approved for
    commercial sales
    in Europe and Korea.

  • (*Without Density Analysis Feature)

  • Background
  • Product Description
  • Major Benefits
  • Example Cases
Free Online Demo


What if breast cancer can be found in
the early stages?

  • Improving mammography interpretation

    Lunit INSIGHT in Yonsei Severance Hospital, Yongin, Korea

  • Reducing the chances of missing breast cancer

  • 40% of breast cancer patients can be
    diagnosed earlier


    Lunit AI score


    Breast Cancer


    Lunit AI score


    Breast Cancer


    Lunit AI score

    Breast Cancer

  • When Detected
    Early by AI

    *5-year survival
    *Reference: AJCC 8th Edition

Product Description

all about breast cancer.

  • Accurately
    detects lesions suspicious of
    breast cancer in
    a mammogram.

    Developed using Lunit’s cutting-edge
    deep learning technology

  • Generated by

    • Detected Location

      The AI generates the location information of detected breast cancer in the form of heatmaps and outlines.

    • Abnormality Score

      The AI generates an abnormality score for each side of the breast, which reflects the AI’s calculation of the actual presence of the detected breast cancer.

    • Density Assessment

      The AI generates its assessment of breast density, categorized into four types.

Major Benefits

Reduce the risk of overlooking
breast cancer by 50%

  • Detect more
    breast cancers

    The combination of first-reader radiologists and Lunit AI detects more breast cancers, than not only the first-reader and second-reader radiologists but also the double reading by radiologists.¹

  • Fast triage of
    normal cases

    Triage up to 60% of the entire cases without human interpretation; reduce workload by more than half in mammogram interpretation.2

  • Improved reading performance of
    general radiologists

    General radiologists can improve their reading performance up to a breast-specialist-level.3

  • Early diagnosis of
    breast cancer

    Detect T1 and node-negative breast cancer with 91% and 87% accuracy, respectively.4

  • Support for decision-making on BI-RADS
    3 and 4 cases

    For difficult cases, compare with the AI results and decide with confidence for additional exams such as ultrasound and biopsy.

  • Improved diagnostic accuracy for
    dense breasts

    Improve diagnostic accuracy for dense and fatty breasts by up to 9% and 22%, respectively.5

Example Cases

Breast cancer
can be tricky to find.
Not with AI.

  • A mass in the right breast, diagnosed as invasive ductal carcinoma, is shown to be properly detected with a malignancy score of 98%.

    detected with a
    malignancy score of


    A lesion with microcalcifications in the right breast, diagnosed as ductal carcinoma in situ, is shown to be properly detected with a malignancy score of 58%.

    detected with a
    malignancy score of


  • Distributed in
    partnership with

  • Major Customers

Publications featuring

Our solutions

Watch and learn more about

Lunit YouTube


  • Background

    1Myers ER, Moorman P, Gierisch JM, et al. Benefits and harms of breast cancer screening: a systematic review. JAMA 2015;314:1615-34.

    2Thurfjell EL, Lernevall KA, Taube A. Benefit of independent double reading in a population-based mammography screening program. Radiology 1994;191:241-4.

    3Yankaskas BC, Klabunde CN, Ancelle-Park R, et al. International comparison of performance measures for screening mammography: can it be done? J Med Screen 2004;11:187-93.

    4Ciatto S, Ambrogetti D, Risso G, et al. The role of arbitration of discordant reports at double reading of screening mammograms. J Med Screen 2005;12:125-7.


  • Major Benefits

    1Mattie Salim, Erik Wåhlin, Karin Dembrower, et al., External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms, JAMA Oncology, 2020

    2Karin Dembrower, Erik Wåhlin, et al., Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study, THE LANCET Digital Health 2020

    3 4 5Hyo-Eun Kim, Hak Hee Kim, et al., Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study, THE LANCET Digital Health 2020