News | Computer-Aided Detection Software | January 12, 2018

Transpara Deep Learning Software Matches Experienced Radiologists in Mammogram Reading

Study presented at RSNA examined performance of artificial intelligence software that combines findings of all available views into single cancer suspiciousness score

Transpara Deep Learning Software Matches Experienced Radiologists in Mammogram Reading

January 12, 2018 — Deep learning and artificial intelligence improves the efficiency and accuracy of reading mammograms, according to research presented at the 103rd Annual Radiological Society of North America (RSNA) meeting, Nov. 26-Dec. 1, 2017 in Chicago. Three studies demonstrated the performance of Transpara deep learning system developed by ScreenPoint Medical BV is approaching that of experienced breast radiologists.

Utilizing state-of-the-art image analysis and 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 computer-aided detection (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.

The study “Detecting Breast Cancer in Mammography: How Close Are Computers to Radiologists?,” was presented by Alejandro Rodriguez-Ruiz . In the study, researchers from Radboud University Medical Centre in Nijmegen, Netherlands, compared the performance of experienced radiologists to that of the deep learning computer detection system Transpara in detecting breast cancer on mammograms.

Researchers collected reader study data from multiple breast imaging centers across Europe to assess performance. In four different studies, more than 1,400 mammograms from three different vendors were retrospectively reviewed by groups of radiologists to measure their ability to detect breast cancer. The data included 336 exams with cancer, 430 with benign abnormalities and 669 normal mammograms. In total, 24 radiologists participated in these studies. Results showed no significant difference between automated reading with the Transpara software and reading by the radiologists. In two studies the radiologists had a higher appropriate use criteria (AUC) performance, while Transpara had a higher AUC in the two other studies.

In the session, “Development of Deep Learning Systems for Improving Breast Cancer Screening,” Prof. Nico Karssemeijer, Ph.D., CEO of ScreenPoint Medical, presented on how recent developments in machine learning offer unprecedented opportunities for researchers to develop fully automated systems for the reading of mammograms and breast tomosynthesis.

“The scope of these systems will be much wider than that of existing CAD systems for mammography. They will provide decision support to improve recall decisions and pre-screening of exams by computers will become a reality. This will lead to more efficient screening procedures where human readers rely on automation to select normal exams that they don't need to read. This will allow them to focus on making optimal decisions for women with potentially abnormal exams in which cancer is most likely,” said Karssemeijer.

The scientific exhibit, “Automated Pre-Selection of Mammograms without Abnormalities Using Deep learning,” was presented by Jonas Teuwen, MSc, Ph.D., in poster discussions.

For more information: www.screenpoint-medical.com

 

Related Content

Guerbet Partners With Imalogix on Dose Optimization With Artificial Intelligence
News | Radiation Dose Management | August 14, 2018
August 14, 2018 — Guerbet LLC USA announced a commercial partnership with Imalogix, a provider of...
Illinois Governor Approves State Breast Density Reporting Bill Into Law
News | Breast Density | August 13, 2018
Illinois Gov. Bruce Rauner approved the Illinois Breast Density Reporting Law (Public Act 100-0749) on Aug. 10, 2018...
Videos | Radiomics | August 09, 2018
A discussion with Martin Vallieres, Ph.D., post-doctoral fellow at McGill University, Montreal, Canada.
PET Tracer Identifies Estrogen Receptor Expression Differences in Breast Cancer Patients
News | PET Imaging | August 09, 2018
In metastatic breast cancer, prognosis and treatment is largely influenced by estrogen receptor (ER) expression of the...
Aidoc Receives FDA Clearance for AI Detection of Acute Intracranial Hemorrhage
Technology | Clinical Decision Support | August 08, 2018
Aidoc announced that it was granted U.S. Food and Drug Administration (FDA) clearance for the first product of its...
iCAD Receives FDA Clearance of PowerLook Density Assessment for Digital Breast Tomosynthesis
Technology | Breast Density | August 08, 2018
iCAD announced U.S. Food and Drug Administration (FDA) clearance of its latest artificial intelligence (AI) software...
Cardiac Imaging Reveals Roots of Preeclampsia Damage in Pregnant Women
News | Women's Health | August 07, 2018
Johns Hopkins researchers say a heart imaging study of scores of pregnant women with the most severe and dangerous form...
Metro Health-University of Michigan Health Partners With Eon to Improve Lung Cancer Care
News | Oncology Diagnostics | August 07, 2018
Metro Health-University of Michigan Health announced it is partnering with healthcare data company Eon to improve the...
Cardiac Monitoring a Higher Priority for High-Risk Breast Cancer Patients
News | Cardio-oncology | August 07, 2018
August 7, 2018 — While heart failure is an uncommon complication of...
Artificial Intelligence in Medical Imaging to Top $2 Billion by 2023
News | Artificial Intelligence | August 06, 2018
The world market for machine learning in medical imaging is set for a period of robust growth and is forecast to top $2...
Overlay Init