A survey on deep learning in medical image analysis

Rapid advances in hardware-based technologies during the past decades have opened up new possibilities for life scientists to gather multimodal data in various application domains, such as omics , bioimaging , medical imaging , and (brain/body)–machine interfaces . These have generated novel opportunities for development of dedicated data-intensive machine learning techniques. In particular, recent research in deep learning (DL), reinforcement learning (RL), and their combination (deep RL) promise to revolutionize the future of artificial intelligence. The growth in computational power accompanied by faster and increased data storage, and declining computing costs have already allowed scientists in various fields to apply these techniques on data sets that were previously intractable owing to their size and complexity. This paper provides a comprehensive survey on the application of DL, RL, and deep RL techniques in mining biological data. In addition, we compare the performances of DL techniques when applied to different data sets across various application domains. Finally, we outline open issues in this challenging research area and discuss future development perspectives.

/pdf/applications-of-deep-learning-and-reinforcement-learning-to-3l72kwyi7n.pdf

Applications of Deep Learning and Reinforcement Learning to Biological Data

Deep Learning in Medical Ultrasound Analysis: A Review

Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation.

Structural magnetic resonance imaging (sMRI) has been widely used for computer-aided diagnosis of neurodegenerative disorders, e.g., Alzheimer's disease (AD), due to its sensitivity to morphological changes caused by brain atrophy. Recently, a few deep learning methods (e.g., convolutional neural networks, CNNs) have been proposed to learn task-oriented features from sMRI for AD diagnosis, and achieved superior performance than the conventional learning-based methods using hand-crafted features. However, these existing CNN-based methods still require the pre-determination of informative locations in sMRI. That is, the stage of discriminative atrophy localization is isolated to the latter stages of feature extraction and classifier construction. In this paper, we propose a hierarchical fully convolutional network (H-FCN) to automatically identify discriminative local patches and regions in the whole brain sMRI, upon which multi-scale feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Our proposed H-FCN method was evaluated on a large cohort of subjects from two independent datasets (i.e., ADNI-1 and ADNI-2), demonstrating good performance on joint discriminative atrophy localization and brain disease diagnosis.

/pdf/hierarchical-fully-convolutional-network-for-joint-atrophy-4t54hfv8zj.pdf

Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI

The accurate diagnosis of Alzheimer's disease (AD) and its early stage, i.e., mild cognitive impairment, is essential for timely treatment and possible delay of AD. Fusion of multimodal neuroimaging data, such as magnetic resonance imaging (MRI) and positron emission tomography (PET), has shown its effectiveness for AD diagnosis. The deep polynomial networks (DPN) is a recently proposed deep learning algorithm, which performs well on both large-scale and small-size datasets. In this study, a multimodal stacked DPN (MM-SDPN) algorithm, which MM-SDPN consists of two-stage SDPNs, is proposed to fuse and learn feature representation from multimodal neuroimaging data for AD diagnosis. Specifically speaking, two SDPNs are first used to learn high-level features of MRI and PET, respectively, which are then fed to another SDPN to fuse multimodal neuroimaging information. The proposed MM-SDPN algorithm is applied to the ADNI dataset to conduct both binary classification and multiclass classification tasks. Experimental results indicate that MM-SDPN is superior over the state-of-the-art multimodal feature-learning-based algorithms for AD diagnosis.

Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease

OBJECTIVE With the fast development of artificial intelligence techniques, we proposed a novel two-stage multi-view learning framework for the contrast-enhanced ultrasound (CEUS) based computer-aided diagnosis for liver tumors, which adopted only three typical CEUS images selected from the arterial phase, portal venous phase and late phase. MATERIALS AND METHODS In the first stage, the deep canonical correlation analysis (DCCA) was performed on three image pairs between the arterial and portal venous phases, arterial and delayed phases, and portal venous and delayed phases respectively, which then generated total six-view features. While in the second stage, these multi-view features were then fed to a multiple kernel learning (MKL) based classifier to further promote the diagnosis result. Two MKL classification algorithms were evaluated in this MKL-based classification framework. We evaluated proposed DCCA-MKL framework on 93 lesions (47 malignant cancers vs. 46 benign tumors). RESULTS The proposed DCCA-MKL framework achieved the mean classification accuracy, sensitivity, specificity, Youden index, false positive rate, and false negative rate of 90.41 ± 5.80%, 93.56 ± 5.90%, 86.89 ± 9.38%, 79.44 ± 11.83%, 13.11 ± 9.38% and 6.44 ± 5.90%, respectively, by soft margin MKL classifier. CONCLUSION The experimental results indicate that the proposed DCCA-MKL framework achieves best performance for discriminating benign liver tumors from malignant liver cancers. Moreover, it is also proved that the three-phase CEUS image based CAD is feasible for liver tumors with the proposed DCCA-MKL framework.

A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images

The contrast-enhanced ultrasound (CEUS) has been a widely accepted imaging modality for diagnosis of liver cancers. In clinical practice, several typical images selected from enhancement patterns of the arterial, portal venous and late phases can provide reliable information basis for diagnosis. In this work, we propose to develop a CEUS-based computer-aided diagnosis (CAD) for liver cancers with only three typical CEUS images selected from three phases, which simulates the clinical diagnosis mode of radiologists. In the proposed CAD, the deep canonical correlation analysis (DCCA) is first performed on three CEUS pairs between arterial and portal venous phases, arterial and late phases, respectively, due to the effectiveness of multi-view fusion of DCCA. The generated six-view features are then fed to a multiple kernel learning (MKL) classifier to further promote the predictive diagnosis result. The experimental results indicate that the proposed DCCA-MKL algorithm achieves best performance for discriminating benign liver tumors from malignant liver cancers.

CEUS-based classification of liver tumors with deep canonical correlation analysis and multi-kernel learning

Quaternion Grassmann average network for learning representation of histopathological image

In clinical practice, the magnetic resonance imaging (MRI) is a prevalent neuroimaging technique for Alzheimer's disease (AD) diagnosis. As a learning using privileged information (LUPI) algorithm, SVM+ has shown its effectiveness on the classification of brain disorders, with single-modal neuroimaging samples for testing but multimodal neuroimaging samples for training. In this work, we propose to apply the multimodal restricted Boltzmann machines (RBM) as an LUPI algorithm for feature learning so as to form an RBM+ algorithm. Furthermore, an ensemble LUPI algorithm is developed, integrating SVM+ and RBM+ by the multiple kernel boosting based strategy. The experimental results demonstrate that the proposed RBM+ works well as an LUPI algorithm for feature learning, and the ensemble LUPI algorithm is superior to the traditional predictive models for the MRI-based AD diagnosis using the positron emission tomography as the privileged information.

Xiao Zheng

Papers

Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease

A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images

CEUS-based classification of liver tumors with deep canonical correlation analysis and multi-kernel learning

Quaternion Grassmann average network for learning representation of histopathological image

Improving MRI-based diagnosis of Alzheimer's disease via an ensemble privileged information learning algorithm