Accession Number:



Development of Methods for Computer-Assisted Interpretation of Digital Mammograms for Early Breast Cancer Detection.

Descriptive Note:

Annual rept. 1 Mar 94-28 Feb 95,

Corporate Author:


Personal Author(s):

Report Date:


Pagination or Media Count:



The goal of tha research was to develop a computer-vision module as an aid to radiologists the specific aims 1 Further development of advanced computerized schemes for the detection and classification of masses and microcalcifications in digital mammograms, including quantitative analysis of the radiographic characteristics and the decision-making processes used by radiologists in making a decision with respect to the likelihood of malignancy and choosing the appropriate course of action. 2 Development of a dedicated intelligent modular system with man-machine interfaces and fast computation times appropriate for the effective use of the computer-vision schemes. 3 Evaluation of the efficacy and efficiency of the module using a large clinical database. The significance of this research is that if the detectability of cancers can be increased by employing a computer to aid the radiologists diagnosis, then the treatment of patients with cancer an be initiated earlier and their chance of survival improved. Systematic introduction of computer-vision tools to radiologists that is presented in this proposal requires minimal modification to the current reading habits of radiologists. When digital mammographic imaging units become commonplace, the computer-vision module can be interfaced to electronic, filmless medical imaging reading areas.

Subject Categories:

  • Medicine and Medical Research
  • Computer Programming and Software

Distribution Statement: