Multiscale connected chain topological modelling for microcalcification classification

Authors Organisations
Type Article
Original languageEnglish
Article number103422
JournalComputers in Biology and Medicine
Volume114
Early online date05 Sep 2019
DOI
Publication statusPublished - 01 Nov 2019
View graph of relations
Citation formats

Abstract

Computer-aided diagnosis (CAD) systems can be employed to help classify
mammographic microcalcification clusters. In this paper, a novel method for the
classication of the microcalcification clusters based on topology/connectivity
has been introduced. The proposed method is distinct from existing techniques
which concentrate on morphology and texture of microcalcifications and sur-
rounding tissue. The proposed approach used multiscale morphological relation
ship of connectivity between microcalcifications where connected chains between nearest microcalcifications were generated at each scale. Subsequently, graph connectivity features at each scale were extracted to estimate the topological connectivity structure of microcalcification clusters for benign versus malignant classification. The proposed approach was evaluated using publicly available digitized datasets: MIAS and DDSM, in addition to the digital OPTIMAM
dataset. The classification of features using KNN obtained a classification ac-
curacy of 86:47 +/- 1:30%, 90:0 +/- 0:00%, 82:5 +/- 2:63%, 76:75 +/- 0:66% for the DDSM, MIAS-manual, MIAS-auto and OPTIMAM datasets respectively. The
study showed that topological/connectivity modelling using a multiscale ap-
proach was appropriate for microcalcification cluster analysis and classification;
topological connectivity and distribution can be linked to clinical understanding
of microcalcification spatial distribution

Keywords

  • microcalcification, topological modelling, multiscale connected chains, benign/malignant classification

Documents

  • Multiscale connected chain topological modelling for microcalcification classification

    Accepted author manuscript, 2 MB, PDF

    Embargo ends: 05 Sep 2020

    Request copy