Hologic Genius AI® Detection Solution

Hologic’s 3D™ Genius AI Detection solution1 enables you to offer superior mammography screening* through accurate markings, fast triaging tools, and optimized point-of-care results.2,3

Monitor showing x-rays on a desk in an office setting.

    Overview

    Documents

    Training

    Giving you the Power to Find Additional Cancers

    Hologic Genius AI Detection solution is designed to locate lesions likely representing breast cancer with a meticulous search of each slice of the tomosynthesis image set with a high sensitivity of 94%.2,3 Suspicious areas are highlighted at radiologists’ workstations for concurrent reading to support smart, decisive interpretation.

    The Future of AI and Breast Cancer Detection

    AI Accuracy Sharpens Your Precision

    Introducing the new automated lesion correlation feature and over 70% reduction in false positive markings per case compared to Hologic's 2D ImageChecker® CAD.4

    Optimize your Workflow Starting with Results in the Exam Room

    Immediate access to results right on the acquisition workstation allows for point-of-care triaging and faster response to patients.

    Know What to Expect Before Reviewing a Study

    Reap the benefits of complete patient worklist integration with SecurView® 12.0 software, helping you quickly and efficiently prioritize cases to read.

    70%

    Reduction
    in false positive markings per case compared to ImageChecker CAD for an average of 0.9 false marking per case2,4

    +1

    Additional cancer
    +9% improvement in observed reading for approximately 1 additional cancer found for every 10 identified by a radiologist2

    94%

    Sensitivity
    High sensitivity2,3 reading solution to help radiologists review cases with efficiency and clarity

    X-ray images

    Breaking boundaries with the automated lesion correlation feature.

    Hologic Genius AI Detection 2.0 solution creates automated lesion correlation markings between CC and MLO views that can be viewed in the SecurView 12.0 software*. Marks can be displayed on individual tomosynthesis slices and overlaid on 3DQuorum SmartSlices, as well as, both FFDM and synthesized 2D images. There are advanced tools to provide quick navigation to relevant correlate lesion on a specific image slice. *Check your PACS vendor for feature availability

    Confident Cancer Detection

    Genius AI® Detection solution integrates seamlessly across the breast care continuum for key benefits in essential areas, with a reader study showing +9% improvement compared to radiologists not using Genius AI Detection solution in observed reader sensitivity for cancer cases. This equates to finding approximately one additional cancer for every 10 cancers correctly identified by a radiologist.2

    Operational Efficiency

    Hologic’s intimate understanding of customer workflow allows us to deliver AI solutions that help clinicians and administrators do their jobs better, faster, and more efficiently.

    Clinical Decision Support

    Clinical tools based on Genius AI® solutions provide insights to help direct the patient pathway and aid physicians in making the best decisions for every patient.

    data counter animation

    Aided Cancer Detection

    Tap into the benefits of Genius AI® Detection technology’s high sensitivity of 94%, plus a significant reduction in false positive marks per case (average of 0.9 false marks per case.) when applied to Hologic’s screening products.2,4

    graphic showing software data enlarged

    Beyond CAD. Redefining the Reading Process.

    Hologic’s leading edge Genius AI Detection solution was developed with the full picture in mind, designed to drive workflow efficiencies like point-of-care triaging in the exam room for both high-priority and no CAD findings cases. It allows radiologists to sort their patient work list, and read potentially easier or challenging cases based on Genius AI Detection solution results of knowing what to expect. 

    Helping Radiologists’ Diagnostic Performance

    "This technology is a whole new paradigm… We are reading cleaner and faster than ever before with Genius AI Detection technology because we can see and understand what is not important quickly and can extinguish the burden of mindless, droll, repetitive screening."
    James Schlund MD FACR, Tahoe Forest Hospital, Truckee, CA

    The AI-guided technology can help get me off the fence on whether to call someone back or not.

    "The AI-guided technology can help get me off the fence on whether to call someone back or not. It gives me it's opinion, and I can choose to listen or not."
    Chad Reihm, MD, Benefis Health System, Great Falls, MT

    Workflow Tools to Enhance Your Practice

    Fully integrated on the 3Dimensions and Selenia® Dimensions® platform.

    Case Score

    Case Score indicates the confidence, determined by Al, that a case contains a malignant lesion.

    Case Complexity Index

    Categorizes cases according to complexity, based on the number of suspicious markings and can be utilized to select which cases to review by the radiologist.

    Reading Priority Indicator

    Flags ~8-10% the most concerning cases at the time of the exam. Results are available in less than a minute to the technologist in the exam room and can be leveraged to prioritize cases for review.

    Read Time Indicator

    Provides an estimate of how much time radiologists would be expected to spend reading a case.

    Physician looking at x-rays

    Inside Hologic’s AI Solutions

    As a market leader with over 30 years at the forefront of developing software solutions for enhanced breast cancer detection, we are experts at harnessing the massive computational power of AI to aid radiologists in their mission of providing the best care to patients. Hologic's deep learning algorithm is fed by the accumulation of a large, diverse patient base, giving us the rich insight and intelligence necessary to develop the meticulous and dynamic algorithm powering our AI solutions.

      *compared to radiologists not using Genius AI Detection solution
      **compared to 2D alone
      1. FDA clearance K221449, K230096 2. U.S. Food and Drug Administration, Center for Device and Radiological Health. (2020, November 18). Genius AI Detection K201019 510(k) Summary. IN1FDA Clearance: K201019 *Based on analyses that do not control type I error and therefore cannot be generalized to specific comparisons outside this particular study. In this study: The average observed AUC was 0.825 (95% CI: 0.783, 0.867) with CAD and 0.794 (95% CI: 0.748, 0.840) without CAD. The difference in observed AUC was +0.031 (95% CI: 0.012, 0.051). The average observed reader sensitivity for cancer cases was 75.9% with CAD and 66.8% without CAD. The difference in observed sensitivity was +9.0% (99% CI: 6.0%, 12.1%). The average observed recall rate for non-cancer cases was 25.8% with CAD and 23.4% without CAD. The observed difference in negative recall rate was +2.4% (99% CI: 0.7%, 4.2%). The average observed case read-time was 52.0s with CAD and 46.3s without CAD. The observed difference in read-time was 5.7s (95% CI: 4.9s to 6.4s). www.accessdata.fda.gov/cdrh_docs/pdf20/K201019.pdf. FDA clearance K221449 Make #1 2 and add FDA 510(k) Clearance K230096. 3. U.S. Food and Drug Administration, Center for Device and Radiological Health. (2022, October 6). Genius AI Detection 2.0 K221449, K230096, 510(k) Summary. www.accessdata.fda.gov/cdrh_docs/pdf22/K221449.pdf. 4. Kshirsagar, A. (2023). Comparison between ImageChecker CAD and GAID algorithm on sequestered FDA database. Refer to Hologic document (DHM-14593).