Showing papers by "Qi Zhang published in 2016"

Multi-modality stacked deep polynomial network based feature learning for Alzheimer's disease diagnosis

Abstract: Feature representation is the critical factor for the computer-aided Alzheimer's disease (AD) diagnosis. Deep polynomial network (DPN) is a novel deep learning algorithm, which can effectively learn feature representation from small samples. In this work, a stacked DPN (S-DPN) algorithm is proposed to further improve feature representation. We then propose a multi-modality S-DPN (MM-S-DPN) algorithm to fuse multi-modality neuroimaging data and learn more discriminative and robust feature representation for AD classification. Experiments are performed on ADNI dataset with MRI and PET images as multi-modality data. The results indicate that S-DPN is superior to DPN and stacked auto-encoder algorithms. Moreover, MM-S-DPN achieves best performance compared with single-modality S-DPN and other multi-modality feature learning based algorithms.

Histopathological image classification using random binary hashing based PCANet and bilinear classifier

Abstract: The computer-aided histopathological image diagnosis has attracted considerable attention. Principal component analysis network (PCANet) is a novel deep learning algorithm with a simple network architecture and parameters. In this work, we propose a random binary hashing (RBH) based PCANet (RBH-PCANet), which can generate multiple randomly encoded binary codes to provide more information. Moreover, we rearrange the local features derived from PCANet to the matrix-form features in order to reduce feature dimensionality, and then we apply the low-rank bilinear classifier (LRBC) to perform effective classification for matrix features. The proposed classification framework using RBH-PCANet and LRBC (RBH-PCANet-LRBC) is adopted for histopathological image classification. The experimental results on both a hepatocellular carcinoma image dataset and a breast cancer image dataset show that the RBH-PCANet-LRBC algorithm achieves best performance compared with other unsupervised deep learning algorithms.

Improving Single-Modal Neuroimaging Based Diagnosis of Brain Disorders via Boosted Privileged Information Learning Framework

Abstract: In clinical practice, it is more prevalent to use only a single-modal neuroimaging for diagnosis of brain disorders, such as structural magnetic resonance imaging. A neuroimaging dataset generally suffers from the small-sample-size problem, which makes it difficult to train a robust and effective classifier. The learning using privileged information (LUPI) is a newly proposed paradigm, in which the privileged information is available only at the training phase to provide additional information about training samples, but unavailable in the testing phase. LUPI can effectively help construct a better predictive rule to promote classification performance. In this paper, we propose to apply LUPI for the single-modal neuroimaging based diagnosis of brain diseases along with multi-modal training data. Moreover, a boosted LUPI framework is developed, which performs LUPI-based random subspace learning and then ensembles all the LUPI classifiers with the multiple kernel boosting (MKB) algorithm. The experimental results on two neuroimaging datasets show that LUPI-based algorithms are superior to the traditional classifier models for single-modal neuroimaging based diagnosis of brain disorders, and the proposed boosted LUPI framework achieves best performance.

Learning Representation for Histopathological Image with Quaternion Grassmann Average Network

Abstract: Feature representation is a key step for the classification of histopathological images. The principal component analysis network (PCANet) offers a new unsupervised feature learning algorithm for images via a simple deep network architecture. However, PCA is sensitive to noise and outliers, which may depress the representation learning of PCANet. Grassmann averages (GA) is a newly proposed dimensionality reduction algorithm, which is more robust and effective than PCA. Therefore, in this paper, we propose a GA network (GANet) algorithm to improve the robustness of learned features from images. Moreover, since quaternion algebra provides a mathematically elegant tool to well handle color images, a quaternion representation based GANet (QGANet) is developed to fuse color information and learn a superior representation for color histopathological images. The experimental results on two histopathological image datasets show that GANet outperforms PCANet, while QGANet achieves the best performance for the classification of color histopathological images.

Histological grade and type classification of glioma using Magnetic Resonance Imaging

Abstract: Glioma is one of the most common brain tumors with high mortality and its histological grading and typing is important both in therapeutic decision and prognosis evaluation. This paper aims at using the high-throughput image feature analysis method to estimate the histological grade and type of a patient by using Magnetic Resonance Imaging (MRI) instead of histological examination. The proposed method consists of the initial label definition, the region-of-interest delineation, the self-adaptive feature extraction, the feature subset selection, and the multi-class voting classification. Hereinto, a novel feature extraction strategy is designed, which could avoid the MRI scan diversity so as to get the robust feature extraction result and make the proposed framework more stable and effective. This method was validated on a database of 124 patients with the grade II to IV of 78, 25, and 21, and with astrocytoma, oligodendroglioma, oligoastrocytoma of 86, 16, and 22, respectively. We show that by using the leave-one-out cross-validation, the multi-class classification accuracy and macro average could reach 88.71%, 0.8362 respectively for the grade classification, and 70.97%, 0.5692 respectively for the type classification. It can be concluded that the histological grade and subtype information could be estimated from the MRI image analysis.