TY - JOUR
T1 - Multiscale connected chain topological modelling for microcalcification classification
AU - George, Minu
AU - Chen, Zhili
AU - Zwiggelaar, Reyer
N1 - Publisher Copyright:
© 2019
PY - 2019/11/1
Y1 - 2019/11/1
N2 - Computer-aided diagnosis (CAD) systems can be employed to help classify mammographic microcalcification clusters. In this paper, a novel method for the classification 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 surrounding tissue. The proposed approach used multiscale morphological relationship 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 accuracy 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 approach was appropriate for microcalcification cluster analysis and classification; topological connectivity and distribution can be linked to clinical understanding of microcalcification spatial distribution.
AB - Computer-aided diagnosis (CAD) systems can be employed to help classify mammographic microcalcification clusters. In this paper, a novel method for the classification 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 surrounding tissue. The proposed approach used multiscale morphological relationship 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 accuracy 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 approach was appropriate for microcalcification cluster analysis and classification; topological connectivity and distribution can be linked to clinical understanding of microcalcification spatial distribution.
KW - microcalcification
KW - topological modelling
KW - multiscale connected chains
KW - benign/malignant classification
KW - Benign/malignant classification
KW - Topological modelling
KW - Multiscale connected chains
KW - Breast Diseases/diagnostic imaging
KW - Breast/diagnostic imaging
KW - Humans
KW - Mammography/methods
KW - Algorithms
KW - Calcinosis/diagnostic imaging
KW - Female
KW - Radiographic Image Interpretation, Computer-Assisted/methods
UR - http://www.scopus.com/inward/record.url?scp=85072044454&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2019.103422
DO - 10.1016/j.compbiomed.2019.103422
M3 - Article
C2 - 31521895
SN - 0010-4825
VL - 114
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 103422
ER -