What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. 
Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of machine learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

An overview of deep learning in medical imaging focusing on MRI

In studying the performance of coded communications over memoryless channels (with or without fading), the results are given as upper bounds on the average bit error probability (BEP). In principle, there are three different approaches to arriving at these bounds, all of which employ obtaining the so-called pairwise error probability , or the probability of choosing one symbol sequence over another for a given pair of possible transmitted symbol sequences, followed by a weighted summation over all pairwise events. In this chapter, we will focus on the results obtained from the third approach since these provide the tightest upper bounds on the true performance. The first emphasis will be placed on evaluating the pairwise error probability with and without CSI, following which we shall discuss how the results of these evaluations can be used via the transfer bound approach to evaluate average BEP of coded modulation transmitted over the fading channel.

Coded Communication over Fading Channels

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

Deep learning has developed as an effective machine learning method that takes in numerous layers of features or representation of the data and provides state-of-the-art results. The application of deep learning has shown impressive performance in various application areas, particularly in image classification, segmentation and object detection. Recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we provide a detailed review of various deep architectures and model highlighting characteristics of particular model. Firstly, we described the functioning of CNN architectures and its components followed by detailed description of various CNN models starting with classical LeNet model to AlexNet, ZFNet, GoogleNet, VGGNet, ResNet, ResNeXt, SENet, DenseNet, Xception, PNAS/ENAS. We mainly focus on the application of deep learning architectures to three major applications, namely (i) wild animal detection, (ii) small arm detection and (iii) human being detection. A detailed review summary including the systems, database, application and accuracy claimed is also provided for each model to serve as guidelines for future work in the above application areas.

Convolutional neural network: a review of models, methodologies and applications to object detection

Super resolution problems are widely discussed in medical imaging Spatial resolution of medical images are not sufficient due to the constraints such as image acquisition time, low irradiation dose or hardware limits To address these problems, different super resolution methods have been proposed, such as optimization or learning-based approaches Recently, deep learning methods become a thriving technology and are developing at an exponential speed We think it is necessary to write a review to present the current situation of deep learning in medical imaging super resolution In this paper, we first briefly introduce deep learning methods, then present a number of important deep learning approaches to solve super resolution problems, different architectures as well as up-sampling operations will be introduced Afterwards, we focus on the applications of deep learning methods in medical imaging super resolution problems, the challenges to overcome will be presented as well

A Review of the Deep Learning Methods for Medical Images Super Resolution Problems

This letter analyzes the statistical properties of the root-mean-square (RMS) delay spread in a two-path distributed antenna system, where the received signal power from each path is subject to composite gamma fading and lognormal shadowing. The channel power delay profile considered consists of two delta functions with correlated power levels. We present analytical expressions for the probability density function of the RMS delay spread, as well as the cumulative distribution function, mean value and standard deviation. These analyses are validated through comparison with Monte-Carlo simulation results.

Delay Spread Statistics in a Two-Path Distributed Antenna System with Gamma-Lognormal Fading Channels

In this paper, we propose a novel framework of Foreign Object Debris (FOD) classification combining scale-invariant feature transform (SIFT) feature and color feature. This system contains FOD detection subsystem, image quality assessment, control center and FOD recognition subsystem. The system not only achieves the goal of FOD detection, but also fulfills the task of FOD classification. We propose a mixed feature method that combines SIFT feature and color feature to extract FOD feature and use Support vector machine (SVM) or nearest neighbor (NN) to classify FOD image. Experiment results show that the proposed framework is effective and accurate.

Fusion of low-level feature for FOD classification

Antenna selection (AS) and intelligent reflecting surface (IRS) are two promising technologies to reduce the hardware cost of multi-antenna systems. This letter intends to jointly design the users’ active transmit beamformers, the IRS’s passive beamformer, and the base station’s receive AS network in order to maximize the uplink sum rate of an IRS-aided multiuser multiple-input multiple-output (MU-MIMO) system. An efficient algorithm is proposed to solve the resultant non-convex problem via capitalizing on the block coordinate descent and fractional programming techniques. Numerical results show that compared with other baseline methods, the proposed algorithm can significantly improve the uplink sum rate.

Antenna Selection for IRS-Aided MU-MIMO

—This paper considers a lens antenna array-assisted millimeter wave (mmWave) multiuser multiple-input multiple- output (MU-MIMO) system. The base station’s beam selection matrix and user terminals’ phase-only beamformers are jointly designed with the aim of maximizing the uplink sum rate. In order to deal with the formulated mixed-integer optimization problem, a penalty dual decomposition (PDD)-based iterative algorithm is developed via capitalizing on the weighted minimum mean square error (WMMSE), block coordinate descent (BCD), and minorization-maximization (MM) techniques. Moreover, a low-complexity sequential optimization (SO)-based algorithm is proposed at the cost of a slight sum rate performance loss. Numerical results demonstrate that the proposed methods can achieve higher sum rates than state-of-the–art methods.

Lens Antenna Arrays-Assisted mmWave MU-MIMO Uplink Transmission: Joint Beam Selection and Phase-Only Beamforming Design

Foreign Object Debris (FOD) on the runways or taxiways may damage airplanes and injure personnel in the airport. There are two main types of commercial FOD detection systems, i.e. Fixed and mobile. Nowadays, only one of these two main types of FOD detection systems is deployed in some airports. In this paper, we propose a total solution to support both of FOD detection system types based on Shanghai Hongqiao International Airport FOD prevention's requirements, i.e. Mobile Ad-Hoc Network (MANET) based FOD detection system. In this paper, a novel FOD detection system architecture is proposed. Then we study the feasibility of MANET applied to the proposed FOD detection system. In this proposed MANET, Wi-Fi and IEEE 802.11 are introduced to physical and MAC layer of wireless node, OLSR is used to provide network routing function, in addition, a novel multi-path data fusion mechanism is proposed to decrease the packet loss ratio.

Haoyu Xu

Papers

Delay Spread Statistics in a Two-Path Distributed Antenna System with Gamma-Lognormal Fading Channels

Fusion of low-level feature for FOD classification

Antenna Selection for IRS-Aided MU-MIMO

Lens Antenna Arrays-Assisted mmWave MU-MIMO Uplink Transmission: Joint Beam Selection and Phase-Only Beamforming Design

A Study on the Feasibility of Mobile Ad-Hoc Networks Applied to Foreign Objective Debris Detection System