Characterisation of Architectural Distortion in Mammograms.

Date of Submission

December 2007

Date of Award

Winter 12-12-2008

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science


Electronics and Communication Sciences Unit (ECSU-Kolkata)


Chanda, Bhabatosh (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

Architectural Distortion is a very important finding in interpreting breast cancers as well as microcalcification and mass on digital mammograms. During screening mammography, architectural distortion is generally missed because of its subtlety; however architectural distortion has high potential for malignancy. Computer-aided diagnosis (CAD) techniques can improve the performance of radiologists in detecting masses and calcifications, however, most CAD systems have not been designed to detect architectural distortion.The objective of this work is to develop an automated image processing algorithm to detect architectural distortion in digital mammograms based on irregular concentration of mammary gland. Digital image of a breast in mammogram is modeled as a topographic image intensity surface whose contour map is used to find the linear structures of the mammary glands. The irregular concentration of these linear structures is indicative of architectural distortion being present in a mammogram.The proposed approach was tested on various mammograms from mini-MIAS database containing both normal and architectural distortion cases and the initial results are promising. The methodology needs to be rigorously tested on a larger database, so as to be of greater practical use.


ProQuest Collection ID:

Control Number


Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


This document is currently not available here.