Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.

A review of medical image data augmentation techniques for deep learning applications.

A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects

Travelling Salesman Problem (TSP) is an Np-Hard problem, for which various solutions have been offered so far. Using the Harris Hawk Optimization (HHO) algorithm, this paper presented a new method that uses random-key encoding to generate a tour. This method helps maintain the main capabilities of the HHO algorithm, on the one hand, and to take advantage of the capabilities of active mechanisms in the continuous-valued problem space on the other hand. For the exploration phase, the DE/best/2 mutation mechanism employed in the exploitation phase, besides the main strategies in the HHO algorithm, was used. Ten neighborhood search operators are used, four of which are introduced. These operators were intelligently selected using the MCF. The Lin-Kernighan local search mechanism was utilized to improve the proposed algorithm's performance, and the Metropolis acceptance strategy was employed to escape the local optima trap. Besides, 80 datasets were evaluated in TSPLIB to demonstrate the performance and efficiency of the proposed algorithm. The results showed the excellent performance of the proposed algorithm.

An efficient harris hawk optimization algorithm for solving the travelling salesman problem

Application of modified pigeon-inspired optimization algorithm and constraint-objective sorting rule on multi-objective optimal power flow problem

Towards secure intrusion detection systems using deep learning techniques: Comprehensive analysis and review

The extensive acquisition and using of high-resolution remote sensing images have greatly promoted the development of airport detection. However, due to the complex shape, background and different scale of the airport location, the real-time and accuracy of airport detection are also facing major challenges. These factors can reduce the detection accuracy. To solve the above problems, we propose an improved faster region-based convolutional neural network (RCNN) detection method for airport detection in large scale remote sensing images. Multi-scale training is applied to faster RCNN to enhance the robustness of network for detecting airport with different sizes. Meanwhile, we adopt the modified multitask loss function to improve the accuracy of airport detection. Online hard example mining strategy is introduced to decrease the redundant negative samples in the training process. Then the non-maximum suppression method is used to remove the redundant boxes of the detected airport. Finally, we conduct sufficient experiments with the airport data obtained from Google Earth and make comparison with the state-of-the-art airport detection methods. The results show that the proposed method can accurately detect different airports under complex background with high detection rate, low false alarm rate and short running time.

Airport Detection Based on Improved Faster RCNN in Large Scale Remote Sensing Images

Hot region selection (HRS) is usually performed for larger scenes, especially in military target detection and battlefield situational awareness applications. Many state-of-the-art methods pay more attention on object detection. Although they can detect the region of interest in one image, these images are highly affected by illumination, rotation, and scale changes, which further increases the complexity of analysis compared to those obtained using standard remote sensing platforms. The study of HRS is of great importance in the analysis of remote sensing images. The current research focuses on the specific type of object area detection. A well-developed HRS needs to have three properties: uniform highlighting of the entire HRS, well-defined boundaries, and good robustness. Motivated by these requirements, a HRS method based on the selective search method and modified fuzzy c-means (FCM) in remote sensing images is proposed to address the detection of potential hot regions in large-scale remote sensing images. First, we create a Gaussian curvature filter to preprocess large scale remote sensing images. Second, a modified FCM segmentation method is utilized to segment the image. Third, an enhanced selective search method is adopted to establish well-defined boundaries for the HRS and to improve the immunity to noise. The geographic information is presented in this phase, which is conducive to improve the detection accuracy. In the experimental section, we compare our new method with four other extraction models on three data sets. The experimental results show that compared to the other competing models, the new model better defines the hot regions and obtains more entire boundaries in terms of Overlap and mA P.

/pdf/hot-region-selection-based-on-selective-search-and-modified-135283tect.pdf

Hot Region Selection Based on Selective Search and Modified Fuzzy C-Means in Remote Sensing Images

Medical image segmentation is one of the hot issues in the related area of image processing. Precise segmentation for medical images is a vital guarantee for follow-up treatment. At present, however, low gray contrast and blurred tissue boundaries are common in medical images, and the segmentation accuracy of medical images cannot be effectively improved. Especially, deep learning methods need more training samples, which lead to time-consuming process. Therefore, we propose a novelty model for medical image segmentation based on deep multiscale convolutional neural network (CNN) in this article. First, we extract the region of interest from the raw medical images. Then, data augmentation is operated to acquire more training datasets. Our proposed method contains three models: encoder, U-net, and decoder. Encoder is mainly responsible for feature extraction of 2D image slice. The U-net cascades the features of each block of the encoder with those obtained by deconvolution in the decoder under different scales. The decoding is mainly responsible for the upsampling of the feature graph after feature extraction of each group. Simulation results show that the new method can boost the segmentation accuracy. And, it has strong robustness compared with other segmentation methods.

/pdf/dmcnn-a-deep-multiscale-convolutional-neural-network-model-2zvcztj9n2.pdf

DMCNN: A Deep Multiscale Convolutional Neural Network Model for Medical Image Segmentation.

Currently, medical image segmentation has attracted more attention from researchers, which can assist in medical diagnosis. However, in the process of traditional medical image segmentation, it is sensitive to the initial contour and noise, which is difficult to deal with the weak edge image, complex iterative process. In this paper, we propose a new medical image segmentation method, which adopts density-oriented BIRCH (balanced iterative reducing and clustering using hierarchies) clustering method to modify active contour model and improve the robustness of noise. The BIRCH is a multi-stage clustering method using clustering feature tree. The improved model can effectively deal with the gray non-uniformity of real medical images. And we also introduce a new energy function in active contour model to make the contour curve approach to the edge, and finally stay at the edge of the image to complete the object segmentation. Experimental results show that this new model can overcome the influence of complex background on medical image segmentation and improve the speed and accuracy of medical segmentation results.

Active contour modal based on density-oriented BIRCH clustering method for medical image segmentation

Network intrusion detection (NID) is an important method for network system administrators to detect various security holes. The performance of traditional NID methods can be affected when unknown or new attacks are detected. Compared with other machine learning methods, the intrusion detection method based on convolutional neural network (CNN) can significantly improve the accuracy of classification, but the convergence speed and generalization ability of CNN are not ideal in model training process resulting in a low true rate and a high false alarm rate. To solve the above problems, this paper proposes a deep multi-scale convolutional neural network (DMCNN) for network intrusion detection. Different levels of features in a large number of high-dimensional unlabeled original data are extracted by different scales convolution kernel. And the learning rate of network structure is optimized by batch normalization method to obtain the optimal feature representation of the raw data. We use NSL-KDD dataset as the benchmark thus we can compare the performance of our proposed method with other existing works. This dataset includes two testing sets which are the first one is KDDTest+ while the second one is $$\text {KDDTest}^{-21}$$
 which is more difficult to be classified. The experimental results reveal that the AC and TPR are higher through our DMCNN model. Especially, in terms of DOS, the AC appropriately reaches to 98%. DMCNN has a high intrusion detection accuracy and a low false alarm rate, which overcomes the limitations of using the traditional detection methods and makes the new approach an attractive one for practical intrusion detection.

Hang Li

Papers

Airport Detection Based on Improved Faster RCNN in Large Scale Remote Sensing Images

Hot Region Selection Based on Selective Search and Modified Fuzzy C-Means in Remote Sensing Images

DMCNN: A Deep Multiscale Convolutional Neural Network Model for Medical Image Segmentation.

Active contour modal based on density-oriented BIRCH clustering method for medical image segmentation

A Network Intrusion Detection Method Based on Deep Multi-scale Convolutional Neural Network