ProFound AI®

The Complete Artificial Intelligence Solution for Breast Cancer Screening

2D Mammography, Tomosynthesis, Density & Risk

CE Marked

ProFound AI® for 2D Mammography and Digital Breast Tomosynthesis

A Precise, Powerful & Proven Technology

ProFound AI is a high-performance, deep-learning workflow solution trained to detect malignant soft-tissue densities and calcifications.  With thousands of installations around the world, ProFound AI offers multi-vendor compatibility and seamlessly integrates into the diagnostic process.

BrochureRequest a demoCase StudyPress ReleaseWhite Paper

NEW! ProFound AI 3rd generation performance1,2

Up to 10% improvement in specificity performanceUp to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 4% improvement in sensitivityUp to 40% faster processing Up to 40% faster processing

Benefits to the Patient

  • Assists in early cancer detection, which can lead to earlier treatment and improved outcomes
  • Fewer false positives/unnecessary recalls
  • Improves detection accuracy
  • Provides peace of mind

Benefits to the Facility

  • Enhances cancer detection and patient care
  • Improves workflow
  • Increases diagnostic confidence
  • Optimal integration in multi-vendor environments

ProFound AI for Digital Breast Tomosynthesis is clinically proven to improve radiologists’ performance and diagnostic confidence, while offering critical time-saving benefits.3

in sensitivity
-52.7%reduction in reading
time for radiologists
reduction in rate
of recalls

Clinical Evidence

ProFound AI for DBT Improves Accuracy and Efficiency3

  • + 8.0% in sensitivity
  • + 6.9% in specificity
  • - 52.2% in reading time for radiologists

Click on the video to see the evolution of the performance of each radiologist in the reader study. Each radiologist is represented by a circle.

How to use Case Scores

Case Scores are assigned to each case by the algorithm. These represent the algorithm's confidence that a case is malignant, on a scale between 0% to 100%.

The Case Score helps to:

  • Prioritize examinations and work-lists
  • Rapidly confirms normal cases
  • Allows radiologists to spend more time
      on challenging cases
  • Reduce screening mammography workload

How to use Certainty of Finding Scores

A Certainty of Finding score is assigned to each lesion identified by ProFound AI. From 0% to 100%, it represents the algorithm’s confidence that the lesion is malignant.

Examples with Certainty of Finding Scores for Soft Tissue Density Detections

85% Certainty of Finding48% Certainty of Finding

Examples with Certainty of Finding Scores for Calcification Detections

97% Certainty of Finding43% Certainty of Finding

The Certainty of Finding Score helps to:

  • Interpret the lesion
  • Determine if a suspicious finding needs further evaluation
  • Improve diagnostic performance
  • Enhance workflow

Clinical Evidence

ProFound AI for 2D Mammography offers superior sensitivity and may reduce interval breast cancer rates

  • Superior sensitivity
    With a sensitivity of 91.5 percent, the ProFound AI 2D algorithm offers a superior sensitivity compared to two radiologists without the support of AI4
  • Reduces interval breast cancer rates
    A retrospective analysis shows that ProFound AI for 2D Mammography could have helped detect 48% of interval cancers and 93% of subgroups that include false-negatives and minimal sign lesions5

Watch Dr Gräwingholt presenting his retrospective study on interval cancers in a screening population.

iCAD’s Breast Health Solutions Suite also includes:

New! ProFound AI® Risk

ProFound AI® Risk is the first and only clinical decision support tool that provides an accurate short-term breast cancer risk estimation that is truly personalized for each woman.

  • Unique tool based only on information readily available in a 2D or 3D mammogram
  • Offers a one, two or three-year risk estimation
  • Superior accuracy versus other risk models6

Learn More

Watch Prof. Per Hall explain how ProFound AI Risk can improve breast screening programs to detect breast cancer as early as possible.

PowerLook® Density Assessment

Automated Density Measurement

Calibrates the patient’s breast density to the appropriate density category corresponding to BI-RADS reporting system.

Learn More

Clinical Case Study

Axel Gräwingholt, MD, Head of the Mammography department at Radiologie am Theater used ProFound AI for 2D mammography, for tomosynthesis and ProFound AI Risk to retrospectively analyze a patient whose breast cancer could have been detected earlier if ProFound AI and ProFound AI Risk were available, applied, and used as a decision tool for supplemental screening.


ProFound AI for 2D mammography and Tomosynthesis runs on the industry-leading PowerLook® server platform with NVIDIA® Graphical Processing Units (GPU), the latest in powerful GPU technology. PowerLook is a flexible and reliable DICOM platform that easily integrates with image modalities, mammography review workstations, PACS, and image storage systems. Leveraging the latest in GPU technology, the algorithm can rapidly process a 4-view tomosynthesis case, ensuring results are available to radiologists in the most efficient manner.

Trust the proven leader in Breast AI.

Learn more about how ProFound AI can help you meet your goals.


  1. iCAD data on file. FDA filing: K203822. Standalone performance varies by vendor. FDA Cleared and CE Marked.
  2. Compared to previous versions of the software, the ProFound AI 3.0 algorithm offers up to a 10% improvement in specificity performance, up to 1% improvement in sensitivity with ProFound AI for Tomosynthesis and 4% improvement with ProFound AI for 2D mammography, and up to 40% faster processing on the new PowerLook platform.
  3. Conant, E et al. (2019). Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiology: Artificial Intelligence. 1 (4). Accessed via
  4. The value of 2D-AI-based CAD for second or third reading tested on 17,910 screening mammograms [RPS 702-4] by Sylvia H. HeyWang-Köbrunner MD, head of Referenzzentrum Mammographie München.
  5. Graewingholt A, Rossi PG. (2021). Retrospective analysis of the effect on interval cancer rate of adding an artificial intelligence algorithm to the reading process for two-dimensional full-field digital mammography. J Med Screen. 0(0) 1-3. Accessed via
  6. Eriksson M, Czene K, Strand F, et al. Identification of Women at High Risk of Breast Cancer Who Need Supplemental Screening. [published online ahead of print September 8, 2020]. Radiology. Accessed via

© iCAD Inc.  All rights reserved.  iCAD, the iCAD logo, PowerLook, ProFound AI, ProFound, Xoft, the Xoft logo, Axxent, Electronic Brachytherapy System and eBx are trademarks of iCAD, Inc. Reproduction of any of the material contained herein in any format or media without the express written permission of iCAD, Inc. is prohibited.

Facebook icon Twitter icon LinkedIn icon

Up to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 40% faster processing

PowerLook® Density Assessment

Up to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 40% faster processing

Up to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 40% faster processing

Up to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 40% faster processing

Up to 10% improvement in specificity performanceUp to 1% improvement in sensitivityUp to 40% faster processing