Currently,
breast biopsy serves as the key diagnostic tool in the
evaluation of breast masses for malignancy. Mammography is the
superior screening procedure with very high sensitivity, but its
lower specificity is well known. With emphasis on early
detection of breast cancer, it appears the effort to avoid
missing a malignant lesion has led to a low positive biopsy rate
for cancer, between 10-31%. Unfortunately, breast biopsy is
neither a benign nor an inexpensive process. Besides affecting
patients physically and emotionally, the procedure frequently
causes internal scarring, which obscures the results of future
mammograms. With approximately 1,700,000 women undergoing breast
biopsy per year, combined with a cost between $750-5000 per
procedure, the cost to the U.S. healthcare system is
significant. Ultrasound (US) is widely regarded as the adjunct
procedure of choice, especially for distinguishing cystic from
solid masses in which accuracy is 96-100%. However, earlier
studies, in which ultrasound was evaluated largely as a primary
screening tool, reported a wide variance in Positive Predictive
Value (PPV) and an unsettling range of False Negative (FN) rate
from 0.3-30%. These results led to many recommendations still
extant that ultrasound be used only to determine cyst from solid
and/or for needle guidance.
The
American College of Radiology has developed the
BI-RADS®
program for interpretation and reporting of breast
ultrasound exams and is detailing a program to accredit
the clinical practice of breast ultrasound. The American
Institute of Ultrasound in Medicine launched in 1998 a
program to accredit the breast ultrasound practices of
radiologists and sonographers. These steps by
professional organizations are designed to improve
quality and uniformity. Acceptance and utilization of
BI-RADS® for ultrasound is increasing but it has proven
difficult to teach the method and many authors have felt
uncomfortable with the number of benign and malignant
masses that overlap in appearance. The ACRIN research
protocol 6666 Breast Cancer: Ultrasound Screening is
examining many aspects of breast ultrasound
interpretation in a screening context that may
eventually lead to more uniform practice. If a lesion is
solid or indeterminate, biopsy is often recommended,
although current definitive estimates of the FN rate and
PPV for ultrasound are not available. Furthermore, even
with combined information from mammography and
ultrasound it is true that each radiologist may apply a
different decision threshold to biopsy a suspicious
mass. Operator variability and machine dependence is an
extremely important issue in breast ultrasound (US),
perhaps one of the most difficult medical imaging
procedures to perform. Despite improving imaging
technology with excellent near-field imaging and a
long-standing and increasing number of positive reports
that distinguish benign from malignant solid nodules
with sonography, it is likely that a majority of
radiologists in the U.S. recommend that US be used only
to determine whether a lesion is cystic or solid and/or
for needle guidance.
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. In
the future, development of the proposed system may advance the
application into the diagnostic area, for detection of
suspicious masses, for more accurate disease diagnosis following
interpretive guidelines and a validated clinical database, even
to other imaging problems.
This
site opens real time on-line access for individuals
or practitioners and institutions to the latest and
clinically validated breast ultrasound CAD tool.
