ScreenPoint Medical Showcases Transpara™, its Machine Learning Software Application Designed to Improve Mammography Reading Efficiency and Accuracy, at RSNA
Studies Accepted for Presentation at RSNA Show that Transpara’s Use of AI and Deep Learning Results in Performance Comparable to Experienced Breast Radiologists
CHICAGO (PRWEB) November 21, 2017
ScreenPoint Medical will showcase Transpara™, software designed to assist radiologists with the reading of mammograms and digital breast tomosynthesis exams, at the upcoming 103rd Annual Radiological Society of North America (RSNA) meeting, November 26-December 1, 2017. (South Hall #3178). Exploiting Big Data, Deep Learning and the latest developments in Artificial Intelligence (AI), Transpara is based on innovative insights into how breast radiologists can best be supported to improve the efficiency and accuracy of reading mammograms.
Transpara has European regulatory approval (CE Mark) for use with Hologic, GE, Philips and Siemens digital mammography images, and is installed at leading centers throughout Europe. The system (investigational in the U.S.) will be shown at RSNA integrated within Sectra and Siemens breast imaging workstations.
Utilizing state of the art image analysis and revolutionary deep learning technology, Transpara automatically identifies soft-tissue and calcification lesions and combines the findings of all available views into a single cancer suspiciousness score. While calcifications are marked as in traditional CAD systems, only a small number of soft-tissue lesion marks are shown and are proven to have extremely low false positive rates. However, readers can probe any suspicious image region for decision support to help determine whether further investigation is needed.
Interactive decision support is a proven method to boost reading performance for soft tissue lesions and Transpara improves radiologists’ mammography reading accuracy and confidence in their assessment. This does not slow down workflow, as information is provided concurrent during reading and only when needed. In this way, readers are not confronted with distracting false positives on soft-tissue lesions. Intelligent software correlates MLO and CC views when abnormalities are visible in both views.
“Transpara was developed with the goal of making mammogram reading better and more efficient, recognizing the fact, that in breast cancer screening, radiologists need decision support and not just CAD marks to support the search for abnormalities,” said Prof. Nico Karssemeijer, PhD, CEO of ScreenPoint Medical. “The hope is that by using smart Artificial Intelligence techniques a ‘best achievable performance’ can be achieved by all readers, for the benefit of all women participating in screening.”
Transpara categorizes every mammogram on a 10-point scale based on calcification and soft tissue lesion findings. Using the Transpara Score, mammograms can be sorted according to the likelihood that breast cancer is present and detectable. If no potential abnormalities are found a low score is assigned. When there are suspicious findings a higher score is assigned. Practices can use Transpara to automatically pre-screen to identify, with high confidence, the cases that most likely have no cancer and help identify cases that need increased attention.
Studies accepted for presentation at RSNA demonstrate that the performance of Transpara is approaching that of experienced breast radiologists:
Development of Deep Learning Systems for Improving Breast Cancer Screening (SPSH40B)
Presenter: Prof. Nico Karssemeijer
Wednesday 7:15-8:15 AM, Room: E450A
Detecting Breast Cancer in Mammography: How Close Are Computers to Radiologists? (SSK02-02)
Presenter: Alejandro Rodriguez-Ruiz
Wednesday 10:30-12:00 PM, Room: E451A
About ScreenPoint Medical BV
ScreenPoint Medical develops image analysis technology for automated reading of mammograms and digital breast tomosynthesis exams, exploiting Big Data, Deep Learning and the latest developments in Artificial Intelligence. ScreenPoint Medical was founded in 2014 by Nico Karssemeijer and Michael Brady, two experts in breast imaging, machine learning, computer vision, and computer-aided detection. The main office is in Nijmegen, The Netherlands.
# # #
For the original version on PRWeb visit: http://www.prweb.com/releases/2017/11/prweb14937787.htm
