Tensor based multichannel reconstruction for breast tumours identification from DCE-MRIs

• Published in: PloS one Vol. 12; no. 3; p. e0172111
• Main Authors: Yin, X. -X., Hadjiloucas, S., Chen, J. -H., Zhang, Y., Wu, J. -L., Su, M. -Y.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 10.03.2017; Public Library of Science (PLoS)
• Subjects: Algorithms; Breast - diagnostic imaging; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Care and treatment; Clinical medicine; Cluster Analysis; Clustering; Comparative analysis; Computer science; Contrast Media - chemistry; Data mining; Datasets; Diagnosis; Digital imaging; Engineering schools; Feature extraction; Female; Humans; Image contrast; Image Enhancement; Image processing; Image Processing, Computer-Assisted; Image reconstruction; Image segmentation; Imaging, Three-Dimensional; Informatics; Knowledge discovery; Magnetic resonance; Magnetic Resonance Imaging; Mammography; Medicine and Health Sciences; Morphology; Multichannel; Neural networks; NMR; Nuclear magnetic resonance; Physical Sciences; Principal Component Analysis; Principal components analysis; Radiology; Research and Analysis Methods; Segmentation; Singular value decomposition; Spatial distribution; Studies; Systematic review; Temporal variations; Tumors; Ultrasonic imaging; Australia; United States; United Kingdom
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0172111

A new methodology based on tensor algebra that uses a higher order singular value decomposition to perform three-dimensional voxel reconstruction from a series of temporal images obtained using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is proposed. Principal component analysis (PCA) is used to robustly extract the spatial and temporal image features and simultaneously de-noise the datasets. Tumour segmentation on enhanced scaled (ES) images performed using a fuzzy C-means (FCM) cluster algorithm is compared with that achieved using the proposed tensorial framework. The proposed algorithm explores the correlations between spatial and temporal features in the tumours. The multi-channel reconstruction enables improved breast tumour identification through enhanced de-noising and improved intensity consistency. The reconstructed tumours have clear and continuous boundaries; furthermore the reconstruction shows better voxel clustering in tumour regions of interest. A more homogenous intensity distribution is also observed, enabling improved image contrast between tumours and background, especially in places where fatty tissue is imaged. The fidelity of reconstruction is further evaluated on the basis of five new qualitative metrics. Results confirm the superiority of the tensorial approach. The proposed reconstruction metrics should also find future applications in the assessment of other reconstruction algorithms.