B1162
Title: Deep Kronecker network
Authors: Long Feng - University of Hong Kong (Hong Kong) [presenting]
Abstract: Deep Kronecker Network (DKN) is proposed, a novel framework designed for analyzing medical imaging data, such as MRI, fMRI, CT, etc. Medical imaging data is different from general images in at least two aspects: i) sample size is usually much more limited, ii) model interpretation is more of a concern compared to outcome prediction. Due to its unique nature, general methods, such as the convolutional neural network (CNN), are difficult to be directly applied. As such, DKN is proposed, which is able to adapt to low sample size limitations and provide the desired model interpretation. DKN is general in the sense that it not only works for both matrix and (high-order) tensor represented image data but also could be applied to both discrete and continuous outcomes. DKN is built on a Kronecker product structure and implicitly imposes a piecewise smooth property on coefficients. Moreover, the Kronecker structure can be written into a convolutional form, so DKN also resembles a CNN, particularly a fully convolutional network (FCN). Interestingly, DKN is also highly connected to the tensor regression framework proposed in prior work, where a CANDECOMP/PARAFAC (CP) low-rank structure is imposed on tensor coefficients. Both classification and regression analyses are conducted using real MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to demonstrate the effectiveness of DKN.