Automated classification of malignant and benign breast cancer lesions using neural networks on digitized mammograms

ASGOP: An aggregated similarity-based greedy-oriented approach for relational DDBSs design

In this paper, a proposed algorithm that dynamically changes the neural network structure is presented. The structure is changed based on some features in the cascade correlation algorithm. Cascade correlation is an important algorithm that is used to solve the actual problem by artificial neural networks as a new architecture and supervised learning algorithm. This process optimizes the architectures of the network which intends to accelerate the learning process and produce better performance in generalization. Many researchers have to date proposed several growing algorithms to optimize the feedforward neural network architectures. The proposed algorithm has been tested on various medical data sets. The results prove that the proposed algorithm is a better method to evaluate the accuracy and flexibility resulting from it. View Full-Text

Zero-watermarking methods provide promising solutions and impressive performance
for copyright protection of images without changing the original images. In this paper, a novel
zero-watermarking method for color images is envisioned. Our envisioned approach is based on
multi-channel orthogonal Legendre Fourier moments of fractional orders, referred to as MFrLFMs. In this
method, a highly precise Gaussian integration method is utilized to calculate MFrLFMs. Then, based
on the selected accurate MFrLFMs moments, a zero-watermark is constructed. Due to their accuracy,
geometric invariances, and numerical stability, the proposed MFrLFMs-based zero-watermarking method
shows excellent resistance against various attacks. Performed experiments using the proposed watermarking
method show the outperformance over existing watermarking algorithms.

The TCP SYN flooding (half-open connection) attack is a type of DDoS attack, which denies
the services by consuming the server resources. This attack prevents legitimate users
from using their desired service. The SYN flooding attack exploits the normal TCP three-way
handshake by sending stream of SYN packets to the server with spoofed IP addresses. The
detection of this attack is hard since the internet routing infrastructure cannot differenti-
ate between legitimate and spoofed SYN packets. In this paper we present a new detection
method for the SYN flooding attack based on Multifractal Detrended Fluctuation Analysis
(MFDFA) in addition to an adaptive threshold, thus we can detect the abnormal behavior in
the TCP protocol time series.

Watermarking of digital images is a well-known technique that is widely used for
securing image contents. A successful watermarking method must be accurate,
reversible, resilient, and robust against various attacks. In this paper, we propose a
reversible and robust color image watermarking method. A new set of multi-channel
fractional-order polar harmonic transforms and their geometric invariants have been
derived. These highly accurate and geometrically invariant features are used in the
watermarking process. The binary watermark’s bits were scrambled using a 1D chaotic
sine map to increase the security level. A set of experiments were performed
to evaluate the proposed watermarking method, and its performance was compared
with recent color image watermarking methods having similar colors. The obtained
results showed high visual imperceptibility and superior robustness against geometric
and signal processing attacks.

In the age of Information Technology, the day-life required transmitting millions of images
between users. Securing these images is essential. Digital image encryption is a well-known
technique used in securing image content. In image encryption techniques, digital images are
converted into noise images using secret keys, where restoring them to their originals required
the same keys. Most image encryption techniques depend on two steps: confusion and diffusion.
In this work, a new algorithm presented for image encryption using a hyperchaotic system and
Fibonacci Q-matrix. The original image is confused in this algorithm, utilizing randomly generated
numbers by the six-dimension hyperchaotic system. Then, the permutated image diffused using
the Fibonacci Q-matrix. The proposed image encryption algorithm tested using noise and data cut
attacks, histograms, keyspace, and sensitivity. Moreover, the proposed algorithm’s performance
compared with several existing algorithms using entropy, correlation coefficients, and robustness
against attack. The proposed algorithm achieved an excellent security level and outperformed the
existing image encryption algorithms.

Segmentation of brain images from Magnetic Resonance Images (MRI) is an indispensable step in clinical practice. Morphological changes of sub-cortical brain structures and quantification of brain lesions are considered biomarkers of neurological and neurodegenerative disorders and used for diagnosis, treatment planning, and monitoring disease progression. In recent years, deep learning methods showed an outstanding performance in medical image segmentation. However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images. The main objective of the study is to develop an automated deep learning segmentation approach that is accurate and robust to the variabilities in scanner and acquisition protocols. In this paper, we propose a transductive transfer learning approach for domain adaptation to reduce the domain-shift effect in brain MRI segmentation. The transductive scenario assumes that there are sets of images from two different domains: (1) source—images with manually annotated labels; and (2) target—images without expert annotations. Then, the network is jointly optimised integrating both source and target images into the transductive training process to segment the regions of interest and to minimise the domain-shift effect. We proposed to use a histogram loss in the feature level to carry out the latter optimisation problem. In order to demonstrate the benefit of the proposed approach, the method has been tested in two different brain MRI image segmentation problems using multi-centre and multi-scanner databases for: (1) sub-cortical brain structure segmentation; and (2) white matter hyperintensities segmentation. The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%. For the first segmentation problem it was possible to achieve a maximum improvement from 0.680 to 0.799 in average Dice Similarity Coefficient (DSC) metric and for the second problem the average DSC improved from 0.504 to 0.602. Moreover, the improvements after domain adaptation were on par or showed better performance compared to the commonly used traditional unsupervised segmentation methods (FIRST and LST), also achieving faster execution time. Taking this into account, this work presents one more step toward the practical implementation of deep learning algorithms into the clinical routine.