Firm targets 1995 for commercial releaseThe rapid growth of digital mammography is spurring the developmentof computer-aided diagnosis (CAD) products to help mammographerslocate and analyze suspicious areas on mammograms. At this
The rapid growth of digital mammography is spurring the developmentof computer-aided diagnosis (CAD) products to help mammographerslocate and analyze suspicious areas on mammograms. At this month'sRadiological Society of North America meeting, a new company exhibitedwhat it hopes will be the first mammography CAD program on themarket.
Stereometrix of San Jose, CA, debuted Mammogram ViewStation 5000,a CAD system that it plans to begin selling next year. ViewStation5000 is a PC-based system that scans digitized mammograms to locatesuspicious masses and microcalcifications, which are then flaggedfor the radiologist's attention. Stereometrix points out thatits system is not designed to provide a diagnosis, but ratheris intended to aid radiologists in locating areas of suspicion.
The technology is based on analytical algorithms developed byStereometrix founder K.C. Saxena for the government of India forsatellite and aerial mapping. Saxena adapted the algorithms formedical applications, including the analysis of mammograms.
ViewStation 5000 converts mammogram interpretation criteria intomathematical algorithms, which the system uses to define the characteristicsthat indicate the presence of suspicious lesions. Stereometrixhas tested its system in over 400 biopsy cases and claims an averageaccuracy rate of over 95% and a false-positive rate of less thantwo per mammogram on mammograms in which suspicious areas areindicated.
Stereometrix plans to enter ViewStation 5000 into clinical trialsearly next year and hopes to have a 510(k) application on filewith the Food and Drug Administration several months later. Thecompany plans to market the system both directly and through distributors.It has not yet signed any OEM deals but is open to potential partners,according to president and CEO Robert Chapman.
Also moving to market is a competing CAD program being developedby University of Chicago researchers who have licensed marketingrights to R2 Technology of Mountain View, CA (SCAN 10/20/93).That program differs from the Stereometrix product in that itrelies on neural network technology to add an artificial intelligencecomponent to CAD. R2 has also contracted with Lockheed's PaloAlto Research Laboratories to conduct a feasibility study to determinewhether Lockheed's neural network technology can be integratedwith the University of Chicago software.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.
Is the Kaiser Score More Effective than BI-RADS for Assessing Contrast-Enhanced Mammography and MRI?
October 14th 2024For women with breast-enhanced masses, Kaiser scoring (KS) demonstrated a 20 percent higher AUC than BI-RADS classification for contrast-enhanced mammography (CEM) and was comparable to KS for breast MRI.
FDA Clears New Features in AI-Powered Mammography Software Suite
October 11th 2024Therapixel’s MammoScreen suite has received 510(k) FDA clearances for a breast density assessment feature and updated software that includes automated pre-reporting, which reportedly expedites reporting of mammography findings.