Area clustering of breast cancer tissues by electrical impedance tomography implemented with Poisson and Gaussian mixture models (EIT-PGMM)

Abstract In this study, areas of breast cancer tissues have been clustered by the newly-proposed electrical impedance tomography (EIT) implemented with Poisson and Gaussian mixture models (EIT-PGMM) for breast cancer identification. EIT-PGMM comprises two distinct methods for comparison: an EIT-Poisson mixture model (PMM) and an EIT-Gaussian mixture model (GMM). EIT-PGMM consists of two sections: (1) a reconstruction section by EIT to reconstruct conductivity distribution σ ∈ R F × N ( f : frequency 1 ⩽ f ⩽ F , n : spatial resolution 1 ⩽ n ⩽ N ) from impedance distribution Z ∈ R F × M ( m : measurement number 1 ⩽ m ⩽ M ) on injection current i between electrodes on the measurement boundary and measurement voltages v ; and (2) a clustering section by PGMM to cluster breast cancer area B with cluster assignment (one-hot vector) s ∈ R N × K ( k : cluster number 1 ⩽ k ⩽ K