Ultrasound
(US) is widely regarded as the adjunct procedure of
choice to mammography, especially for distinguishing
cystic from solid masses where accuracy is 96-100%.
Even with combined information from mammography and
ultrasound, each radiologist may apply a different
decision threshold to recommend biopsy of a
suspicious mass.
The
American College of Radiology (ACR) developed the
Breast Imaging Reporting and Data System (BI-RADS)
program to guide interpretation and reporting of
breast ultrasound exams. The ACR also manages a
program to accredit the clinical practice of breast
ultrasound. Similarly, in 1998 the American
Institute of Ultrasound in Medicine launched a
program to accredit the breast ultrasound practices
of radiologists and sonographers. These steps by
professional organizations are designed to improve
the quality and uniformity of care.
Acceptance
and utilization of BI-RADS for ultrasound is
increasing but the research literature, including
our own reports, shows it is difficult to uniformly
apply the method and there is considerable
variability of lesion description and assessment
between radiologists. Many authors report that some
radiologists remain uncomfortable with the number of
benign and malignant masses that overlap in
appearance.
Almen
Laboratories has developed a computer-aided tool for breast
ultrasound image analysis that operates with the physician in
the loop. The system compares a breast mass in question to a
database of patient lesion images with verified known findings,
displays those most similar to it and then computes CAD
assessment of the lesion in question following the American
College of Radiologists and FDA approved BI-RADS Lexicon,
Classification and method. The computed assessment
is based on confirmed findings of the retrieved
similar cases. Our approach
has considerable appeal and may be more readily acceptable to
radiologists because it does clearly show which factors have led
to the recommendation or classification. This allows the
radiologist the option to consider the findings with higher
confidence and to apply her/his own threshold for a decision.
Breast
Companion® (“BC”, “BC CADx”) is identical to BI-RADS
Companion™ (K072258) with an added optional scoring
function (Computer-aided Lesion Assessment, or “CLA”,
or “BC CLA”). It is an adjunctive tool to be used in
support of radiologists’ readings and is intended to
be used in the diagnostic breast work-up process.
This is an important distinction from computer-aided
detection devices for screening. CLA is intended to
be used by radiologist as decision stratification
tool.
The two packages are related as indicated in Figure
below.
Our approach
applies a database of verified known findings (Reference
Library) to which an
unknown may be compared and evaluated. Storage and retrieval of
these images is accomplished through identification of key
information content of the breast masses themselves (case-based
reasoning). We suggest that lesions of lower suspicion level
such as cysts may be ruled out as candidates for biopsy with
higher degree of confidence when image interpretation is made
with support of this computer-aided imaging tool.
The use of
the available Breast CAD is strictly subject to
Disclaimer
that specifically instruct on limitations and
research oriented intentions of
use. In order to start using the Breast Ultrasound CAD
the user needs to acknowledge agreement with all provisions and clause of the
Disclaimer and then
proceed to informational and service pages of this
web site.
In
the future, development of the system may advance this FDA
approved CADx software into other application areas
such as detection of
suspicious masses, for more accurate disease diagnosis following
interpretive guidelines and a validated clinical database, even
to other imaging problems.
Sponsor Breast Cancer Research (click here)
