Breast cancer cells are traditionally examined under a microscope by a human, who decides the degree of cancer present. People are inconsistent in these judgements from day to day and from person to person.
A BrainMaker neural network that classifies breast cancer cells has been developed. The system was developed by Andrea Dawson, MD of the University of Rochester Medical Center, Richard Austin, MD of the University of California at San Francisco, and David Weinberg, MD, PhD of the Brigham and Womens' Hospital and Harvard Medical School of Boston. Initial comparisons showed that BrainMaker is in good agreement with human observer cancer classifications.
Cancer cells are measured with the CAS-100 (Cell Analysis System, Elmhurst, IL). There are 17 inputs to the neural network which represent morphometric features such as density and texture. There are four network outputs representing nuclear grading. The cancerous nucleus is graded as being well, moderate, or poorly differentiated, or as benign. Correct grade assignments were made between 52% and 89% of the time on cases not seen during training. The lower success rate (for well differentiated) may have been due to the smaller percentage of this type in the training set. In addition, heterogeneity is much lower in well-differentiated tumors. Cancerous nuclei were classified within one grade of the correct grade.
object sum density
object average density
angular second moment
difference variance (Fisher)
information measure B
maximum correlation coefficient
second diagonal moment