Skip to content
Prof. Dr. Mustafa Özdoğan · Medical Oncologist

Artificial Intelligence Technology for Digital Breast Tomosynthesis Receives FDA Approval

Artificial Intelligence Technology for Digital Breast Tomosynthesis Receives FDA Approval
In this article

ProFound AI is a deep learning -based artificial intelligence (AI) software product approved for breast cancer diagnosis , commercial sale, and clinical use by the United States Food and Drug Administration (FDA). The announcement came from iCAD, the global medical technology company developing the software for digital breast tomosynthesis.

What Is Tomosynthesis?

Tomosynthesis is digital mammography producing 3-dimensional images. It examines breasts in 3 dimensions and 1 mm sections comprehensively, as an oncological imaging device. The breast is compressed less, and a machine moving around it sends low-dose X-rays, producing 3-dimensional images. It is a type of mammography; despite using more radiation than most standard mammograms, it shows problem areas more clearly. In 2011, FDA approved tomosynthesis as a cancer diagnosis test, but digital mammography remains standard for early screening.

Approval is based on positive results from a large study completed in early 2018 and presented on 25-30 November in Chicago at the 2018 Radiological Society of North America (RSNA) meeting. It involved 260 tomosynthesis cases read with and without iCAD’s ProFound AI by 24 radiologists.

Study Findings;

  • increased cancer detection,
  • reduced false positives, and
  • significantly reduced patient recalls and interpretation times.

The technology holds promise for helping radiologists detect cancers, reduce recalls for suspicious findings, and improve reading efficiency.

Clinical data show that with ProFound AI, average case-level sensitivity (cancer detection) increased by % 8, unnecessary patient recalls fell by an average % 7, and reading time fell significantly. Radiologists of different experience levels may benefit when reading large datasets.

Besides improving diagnostic and false-positive performance, ProFound AI reduced average reading time by more than 50 percent. Increased reading time has been a major challenge when moving from 2-dimensional to 3-dimensional mammography.

The software is currently available with digital breast tomosynthesis systems in the United States, Canada, and Europe.

About the Technology:

ProFound AI is a high-performance cancer detection and workflow solution using deep learning for digital breast tomosynthesis. It runs on the PowerLook server platform with NVIDIA Graphical Processing Units (GPU). PowerLook is a flexible, reliable DICOM platform integrating easily with imaging modules, mammography workstations, PACS, and image storage. Using the latest GPU technology, the algorithm rapidly processes cases to present results most efficiently to radiologists.

Sources

AI Technology for Digital Breast Tomosynthesis Receives FDA Clearance for Clinical Use.
By The ASCO Post, 25 December 2018
DROZDOGAN AI

Explore this article together

Ask about the article and read answers alongside published sources from our site.

DROZDOGAN AI

Drozdogan Assistant

Artificial Intelligence Technology for Digital Breast Tomosynthesis Receives FDA Approval

Ask about the article and read answers alongside published sources from our site.

Conversation and privacy information

Drozdogan Assistant answers this conversation. Authorized site administrators may review it for quality. Do not share personal information.

Replies use OpenAI infrastructure. Questions and replies are processed by that service; conversation records are stored on our site. Do not share identifying, contact or personal health information.

0 / 1000

For information only; no personal diagnosis or treatment advice.

Related articles

Explore other articles on this topic.

Stay informed

Receive new articles and scientific updates by email.

Google Analytics runs on public pages independently of this window and may use analytics cookies. Your choice here controls external services only.

Cookie policy