Ken Ferry, CEO
The collaboration between technology and medical science is advancing to protect and preserve life. According to Breastcancer.org, about one in eight U.S. women will develop invasive breast cancer during her lifetime. Two-thirds of women with breast cancer have the potential to be saved through early detection and progressive treatments.
Medical facilities worldwide are adopting Digital Breast Tomosynthesis (DBT) technology as their preferred method for screening and diagnostic mammography for detection of breast cancer. While there are many advantages with DBT such as improving the early detection of breast cancer, there are also some considerable challenges for radiologists. For example, a DBT exam now creates a much larger data set as compared to FFDM and is time consuming and somewhat daunting for radiologists.
A typical 2D digital mammography exam produces four images, while a 3D mammogram- or DBT produces more than a hundred images. With DBT, radiologists find they must spend significantly more time to review and interpret each exam. However, with innovative technologies available today, such as iCAD’s PowerLook Tomo Detection, a first-of-its-kind, concurrent-read cancer detection solution for breast tomosynthesis, radiologists can leverage Artificial Intelligence (AI) and deep learning tools that reduce their DBT interpretation time by an average of 29.2 percent and improve reading workflow.
The software uses a highly sensitive and unique algorithm to rapidly and precisely identify regions of interest in the tomosynthesis data set and blends those regions onto the GE synthetic image. This process results in a single enhanced image that highlights potentially cancerous lesions, creating an efficient and effective overview image and navigation tool for radiologists.
“Built on deep learning technology, PowerLook Tomo Detection is proven to optimize breast tomosynthesis reading efficiency, streamline workflow, and support cancer detection without increasing recalls,” says Ken Ferry, CEO, iCAD.
Built on deep learning technology, PowerLook Tomo Detection is proven to optimize breast tomosynthesis reading efficiency, streamline workflow, and support cancer detection without increasing recalls
Since its FDA-approval in March 2017, and CE and Health Canada in 2016, PowerLook Tomo Detection has been implemented by a number of leading breast health provider organizations worldwide. While currently only available with GE Healthcare’s DBT platforms as Enhanced V-Preview, iCAD is developing a multi-vendor solution expected to be available in 2018.
While early diagnosis is a defining element of successful treatment and survival outcomes, a study by Dr. Richard Benedikt et al. 2017 was conducted to evaluate the radiologist’s reading time, accuracy, and performance. The study found that iCAD’s concurrent DBT CAD solution decreased radiologist reading time by almost 30 percent without sacrificing performance.
Complementing PowerLook Tomo Detection is iCAD’s PowerLook Density Assessment, designed to standardize the assessment and reporting of breast density for FFDM exams, indicative of risk for developing breast cancer. In addition, iCAD’s PowerLook Mammo Detection serves as an interpretive cancer detection software for 2D mammography, providing a ‘second look’ at suspicious areas.
Furthermore, Xoft, a subsidiary of iCAD, provides Electronic Brachytherapy (eBx) radiation treatment for early-stage breast, endometrial, and skin cancer. Xoft may be provided as part of interoperative radiation therapy (IORT) that allows an early-stage breast cancer patient to undergo lumpectomy, get their dose of radiation, and forgo weeks of follow-up radiation therapy otherwise required.
iCAD intends to continue to develop innovative solutions to support imaging modalities through AI. “Backed by our expertise and investments over the last half a decade in AI, we believe we can extend our solutions beyond breast health into a number of other areas in the imaging space over the coming years,” concludes Ferry, with optimistic determination.