About

Augmenting Mammography with Artificial Intelligence

Support the daily work at the breast unit by Artifical Intelligence

  • Artificial Intelligence mimicking doctor decisions.
  • Real time Feedback.
  • Automatic classifications according to BI-RADS ACR.
  • Image Quality classification according to PGMI.
  • High clinical accuracy.
  • Easily adaptable to each clinical site.
+ 1.5M
HIGH QUALITY DATA SETS
96%
CLINICAL ACCURACY
30%
FASTER
+ 40K
EVALUATED PATIENTS

The Problem

Early detection of breast cancer by mammography allows more treatment options and reduction in mortality. However, catching cancer is difficult in patients with a dense breast tissue and in poor quality images.

More Administration
Wasted Time
Higher Costs
Subjective Decisions

Our Solution

Empowered by Artifical Intelligence the b-box, supports the daily work of the radiologist and the technician.

Density

High breast density is one of the most important risk factors for breast cancer development. Moreover, the sensitivity of mammography for the detection of breast cancer dramatically drops from 98% for thin breasts to only 48% for dense breasts. For high breast density, additional ultrasound examination for breast cancer screening is recommended. The classification of the breast density is based on the visual rating of the doctor and thus extremely physician dependent. Poor reproducibility of the density determination results in potential misestimation of cancer risk and missed breast ultrasound examinations. Our software provides standardized, reproducible, and real-time classification of ACR BIRADS breast density with a proven accuracy over 93%.


Mockup

Quality

Our software provides real time information on the PGMI based quality assessment of mammographies. Using this solution, assessment of image quality can be carried out close to the mammography unit directly after image acquisition. The detailed feedback helps the technician correcting recurrent errors in the positioning of the patients in the mammography scanner. Moreover, as the obtained PGMI score can be linked to the technician performing the acquisition of the mammography, individual performance measurements including systematic errors as a quality control tool are feasible. The automation of the quality assurance allows for the first time tracking of the quality performance on the whole volume of data.


Mockup

Density

High breast density is one of the most important risk factors for breast cancer development. Moreover, the sensitivity of mammography for the detection of breast cancer dramatically drops from 98% for thin breasts to only 48% for dense breasts. For high breast density, additional ultrasound examination for breast cancer screening is recommended. The classification of the breast density is based on the visual rating of the doctor and thus extremely physician dependent. Poor reproducibility of the density determination results in potential misestimation of cancer risk and missed breast ultrasound examinations. Our software provides standardized, reproducible, and real-time classification of ACR BIRADS breast density with a proven accuracy over 93%.


Mockup

Quality

Our software provides real time information on the PGMI based quality assessment of mammographies. Using this solution, assessment of image quality can be carried out close to the mammography unit directly after image acquisition. The detailed feedback helps the technician correcting recurrent errors in the positioning of the patients in the mammography scanner. Moreover, as the obtained PGMI score can be linked to the technician performing the acquisition of the mammography, individual performance measurements including systematic errors as a quality control tool are feasible. The automation of the quality assurance allows for the first time tracking of the quality performance on the whole volume of data.


Mockup

What our Customers say...

Testimonial 1
"Automatized quality checks support my visual inspection. I have more time for my patients and better imaging data for diagnosis."
Testimonial 2
"An intelligent tool targeting a compelling need in mammography. The b-box meets our goal of providing excellent care to every patient."
Testimonial 3
"Real-time assessment of breast density and image quality substantially reduces examination time in the screening setting and in this way also costs."
Testimonial 4
"A work and educational support for the technical specialist on the front line."

Join the future of radiology

For the Patient
We allow accurate and standardized evaluation of medical imaging data for better breast cancer detectability. Our algorithms perform as good as experienced radiologists are fast, and robust. Technology is used at the service of patient care.
For the Institute
International standard of procedures requires traceability of quality performances in radiology. We provide institutions, for the first time, with the possibility of complying with international regulations in a sustainable way.
For the Radiologist
We provide the specialist with intelligent tools providing a second, standardized opinion for a faster a better daily care of patients. Our algorithms are trained according to international guidelines (ACR, BI-RADS, PGMI).
For the Technician
We support the daily work on the side of the technician. We allow specialists to constantly improve the quality of their performances.

Read our latest scientific publications

Accelerated diffusion-weighted imaging for lymph node assessment in the pelvis applying simultaneous multislice acquisition: A healthy volunteer study
Medicina ex Machina: Machine Learning in der Medizin
Intravoxel Incoherent Motion: Model-Free Determination of Tissue Type in Abdominal Organs Using Machine Learning
Fully automatic classification of breast MRI background parenchymal enhancement using a transfer learning approach
Classification of Mammographic Breast Microcalcifications Using a Deep Convolutional Neural Network: A BI-RADS-Based Approach
Determination of mammographic breast density using a deep convolutional neural network
Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning
Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study
Deep learning for the standardized classification of Ki-67 in vulva carcinoma: A feasibility study
Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making
Accelerated diffusion-weighted imaging for lymph node assessment in the pelvis applying simultaneous multislice acquisition: A healthy volunteer study
Medicina ex Machina: Machine Learning in der Medizin

Ready when You are

© 2022 b-rayZ AG

All rights reserved

Congresses

EUSOBI-2022