Objectives:  Use digital image analysis and machine-learning to:
1) improve breast mass diagnosis based on fine needle aspirates
(FNA), and 2) improve breast cancer prognostic estimations.

Design: An interactive computer system evaluates, diagnoses, and
determines prognosis based on cytologic features derived directly
from a digital scan of FNA slides.  

Setting: The University of Wisconsin Departments of Computer
Science and Surgery.  

Patients:  569 consecutive patients (212 cancer, 357 benign)
provided the data for the diagnostic algorithm, and an additional
118 (31 malignant and 87 benign) consecutive, new patients tested
the algorithm.  190 of these patients with invasive cancer and
without distant metastases were used for prognosis.  

Interventions: All cancers and some benign masses were biopsied. 
The remaining cytologically benign masses were followed for a
year and were biopsied if they changed in size or character. 
Cancer patients received standard treatment.  

Outcome Measures: Cross validation was used to project the
accuracy of the diagnostic algorithm and to determine the 
importance of prognostic features.  Additionally, the mean errors
were calculated between the actual times of distant disease
occurrence and the times predicted using various prognostic
features. Statistical analyses were also done. 

Results: The predicted diagnostic accuracy was 97% and the actual
diagnostic accuracy on 118 new samples was 100%.  Tumor size and
lymph node status were weak prognosticators compared with nuclear
features, in particular those measuring nuclear size.  Compared
with the actual time for recurrence, the mean error of predicted
times for recurrence with the nuclear features was 17.9 months
and was 20.1 months with tumor size and lymph node status
(p=0.11). 

Conclusions: Computer technology will improve breast FNA accuracy
and prognostic estimations.