GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification

Deep Learning in Medical Ultrasound Analysis: A Review

Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review.

Idiopathic generalized epilepsy (IGE) has been linked with disrupted intra-network connectivity of multiple resting-state networks (RSNs); however, whether impairment is present in inter-network interactions between RSNs, remains largely unclear. Here, 50 patients with IGE characterized by generalized tonic-clonic seizures (GTCS) and 50 demographically matched healthy controls underwent resting-state fMRI scans. A dynamic method was implemented to investigate functional network connectivity (FNC) in patients with IGE-GTCS. Specifically, independent component analysis was first carried out to extract RSNs, and then sliding window correlation approach was employed to obtain dynamic FNC patterns. Finally, k-mean clustering was performed to characterize six discrete functional connectivity states, and state analysis was conducted to explore the potential alterations in FNC and other dynamic metrics. Our results revealed that state-specific FNC disruptions were observed in IGE-GTCS and the majority of aberrant functional connectivity manifested itself in default mode network. In addition, temporal metrics derived from state transition vectors were altered in patients including the total number of transitions across states and the mean dwell time, the fraction of time spent and the number of subjects in specific FNC state. Furthermore, the alterations were significantly correlated with disease duration and seizure frequency. It was also found that dynamic FNC could distinguish patients with IGE-GTCS from controls with an accuracy of 77.91% (P < 0.001). Taken together, this study not only provided novel insights into the pathophysiological mechanisms of IGE-GTCS but also suggested that the dynamic FNC analysis was a promising avenue to deepen our understanding of this disease. Hum Brain Mapp 38:957-973, 2017. © 2016 Wiley Periodicals, Inc.

/pdf/dynamic-functional-network-connectivity-in-idiopathic-28bm8p050n.pdf

Dynamic functional network connectivity in idiopathic generalized epilepsy with generalized tonic–clonic seizure

A comparative review on sleep stage classification methods in patients and healthy individuals

Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

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.

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

Ultrasound imaging is a most common modality for tumor detection and diagnosis. Deep learning DL algorithms generally suffer from the small sample problem. The traditional texture feature extraction methods are still commonly used for small ultrasound image dataset. Deep polynomial network DPN is a newly proposed DL algorithm with excellent feature representation, which has the potential for small dataset. However, the simple concatenation of the learned hierarchical features from different layers in DPN limits its performance. Since the features from different layers in DPN can be regarded as heterogeneous features, they then can be effectively integrated by multiple kernel learning MKL methods. In this work, we propose a DPN and MKL based feature learning and classification framework DPN-MKL for tumor classification on small ultrasound image dataset. The experimental results show that DPN-MKL algorithm outperforms the commonly used DL algorithms for ultrasound image based tumor classification on small dataset.

Tumor Classification by Deep Polynomial Network and Multiple Kernel Learning on Small Ultrasound Image Dataset

The dimensionality reduction is an important step in ultrasound image based computer-aided diagnosis (CAD) for breast cancer. A newly proposed l2,1 regularized correntropy algorithm for robust feature selection (CRFS) has achieved good performance for noise corrupted data. Therefore, it has the potential to reduce the dimensions of ultrasound image features. However, in clinical practice, the collection of labeled instances is usually expensive and time costing, while it is relatively easy to acquire the unlabeled or undetermined instances. Therefore, the semi-supervised learning is very suitable for clinical CAD. The iterated Laplacian regularization (Iter-LR) is a new regularization method, which has been proved to outperform the traditional graph Laplacian regularization in semi-supervised classification and ranking. In this study, to augment the classification accuracy of the breast ultrasound CAD based on texture feature, we propose an Iter-LR-based semi-supervised CRFS (Iter-LR-CRFS) algorithm, and then apply it to reduce the feature dimensions of ultrasound images for breast CAD. We compared the Iter-LR-CRFS with LR-CRFS, original supervised CRFS, and principal component analysis. The experimental results indicate that the proposed Iter-LR-CRFS significantly outperforms all other algorithms.

Xiao Liu

Papers

Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

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

Tumor Classification by Deep Polynomial Network and Multiple Kernel Learning on Small Ultrasound Image Dataset

An iterated Laplacian based semi-supervised dimensionality reduction for classification of breast cancer on ultrasound images