Baharak Ahmaderaghi

Bio: Baharak Ahmaderaghi is an academic researcher from Queen's University Belfast. The author has contributed to research in topics: Medicine & Classifier (UML). The author has an hindex of 2, co-authored 3 publications receiving 52 citations.

Blind Image Watermark Detection Algorithm Based on Discrete Shearlet Transform Using Statistical Decision Theory

Abstract: Blind watermarking targets the challenging recovery of the watermark when the host is not available during the detection stage. This paper proposes Discrete Shearlet Transform (DST) as a new embedding domain for blind image watermarking. Our novel DST blind watermark detection system uses a nonadditive scheme based on the statistical decision theory. It first computes the Probability Density Function (PDF) of the DST coefficients modeled as a Laplacian distribution. The resulting likelihood ratio is compared with a decision threshold calculated using Neyman–Pearson criterion to minimize the missed detection subject to a fixed false alarm probability. Our method is evaluated in terms of imperceptibility, robustness, and payload against different attacks (Gaussian noise, blurring, cropping, compression, and rotation) using 30 standard grayscale images covering different characteristics (smooth, more complex with a lot of edges, and high detail textured regions). The proposed method shows greater windowing flexibility with more sensitive to directional and anisotropic features when compared against discrete wavelet and contourlets.

Perceptual watermarking for Discrete Shearlet transform

Abstract: This paper presents a new perceptual watermarking model for Discrete Shearlet transform (DST). DST provides the optimal representation [10] of the image features based on multi-resolution and multi-directional analysis. This property can be exploited on for watermark embedding to achieve the watermarking imperceptibility by introducing the human visual system using Chou's model. In this model, a spatial JND profile is adapted to fit the sub-band structure. The combination of DST and the Just-Noticeable Distortion (JND) profile improves the levels of robustness against certain attacks while minimizing the distortion; by assigning a visibility threshold of distortion to each DST sub-band coefficient in the case of grey scale image watermarking.

Biological Misinterpretation of Transcriptional Signatures in Tumor Samples Can Unknowingly Undermine Mechanistic Understanding and Faithful Alignment with Preclinical Data

Abstract: Precise mechanism-based gene expression signatures (GESs) have been developed in appropriate in vitro and in vivo model systems, to identify important cancer-related signalling processes. However, some GESs originally developed to represent specific disease processes, primarily with an epithelial cell focus, are being applied to heterogeneous tumour samples where the expression of the genes in the signature may no longer be epithelial-specific. Therefore, unknowingly, even small changes in tumour stroma percentage can directly influence GESs, undermining the intended mechanistic signalling. Using colorectal cancer as an exemplar, we deployed numerous orthogonal profiling methodologies, including laser capture microdissection, flow cytometry, bulk and multiregional biopsy clinical samples, single cell RNAseq and finally spatial transcriptomics, to perform a comprehensive assessment of the potential for the most widely-used GESs to be influenced, or confounded, by stromal content in tumour tissue. To complement this work, we generated a freely-available resource, ConfoundR; https://confoundr.qub.ac.uk/, that enables users to test the extent of stromal influence on an unlimited number of the genes/signatures simultaneously across colorectal, breast, pancreatic, ovarian and prostate cancer datasets. Findings presented here demonstrate the clear potential for misinterpretation of the meaning of GESs, due to widespread stromal influences, which in-turn can undermine faithful alignment between clinical samples and preclinical data/models, particularly cell lines and organoids, or tumour models not fully recapitulating the stromal and immune microenvironment. As such, efforts to faithfully align preclinical models of disease using phenotypically-designed GESs must ensure that the signatures themselves remain representative of the same biology when applied to clinical samples.

Molecular Subtyping Resource: a user-friendly tool for rapid biological discovery from transcriptional data

Abstract: ABSTRACT Generation of transcriptional data has dramatically increased in the past decade, driving the development of analytical algorithms that enable interrogation of the biology underpinning the profiled samples. However, these resources require users to have expertise in data wrangling and analytics, reducing opportunities for biological discovery by ‘wet-lab’ users with a limited programming skillset. Although commercial solutions exist, costs for software access can be prohibitive for academic research groups. To address these challenges, we have developed an open source and user-friendly data analysis platform for on-the-fly bioinformatic interrogation of transcriptional data derived from human or mouse tissue, called Molecular Subtyping Resource (MouSR). This internet-accessible analytical tool, https://mousr.qub.ac.uk/, enables users to easily interrogate their data using an intuitive ‘point-and-click’ interface, which includes a suite of molecular characterisation options including quality control, differential gene expression, gene set enrichment and microenvironmental cell population analyses from RNA sequencing. The MouSR online tool provides a unique freely available option for users to perform rapid transcriptomic analyses and comprehensive interrogation of the signalling underpinning transcriptional datasets, which alleviates a major bottleneck for biological discovery. This article has an associated First Person interview with the first author of the paper.

MmCMS: mouse models’ consensus molecular subtypes of colorectal cancer

Abstract: Colorectal cancer (CRC) primary tumours are molecularly classified into four consensus molecular subtypes (CMS1-4). Genetically engineered mouse models aim to faithfully mimic the complexity of human cancers and, when appropriately aligned, represent ideal pre-clinical systems to test new drug treatments. Despite its importance, dual-species classification has been limited by the lack of a reliable approach. Here we utilise, develop and test a set of options for human-to-mouse CMS classifications of CRC tissue.Using transcriptional data from established collections of CRC tumours, including human (TCGA cohort; n = 577) and mouse (n = 57 across n = 8 genotypes) tumours with combinations of random forest and nearest template prediction algorithms, alongside gene ontology collections, we comprehensively assess the performance of a suite of new dual-species classifiers.We developed three approaches: MmCMS-A; a gene-level classifier, MmCMS-B; an ontology-level approach and MmCMS-C; a combined pathway system encompassing multiple biological and histological signalling cascades. Although all options could identify tumours associated with stromal-rich CMS4-like biology, MmCMS-A was unable to accurately classify the biology underpinning epithelial-like subtypes (CMS2/3) in mouse tumours.When applying human-based transcriptional classifiers to mouse tumour data, a pathway-level classifier, rather than an individual gene-level system, is optimal. Our R package enables researchers to select suitable mouse models of human CRC subtype for their experimental testing.

Blind Image Watermark Detection Algorithm Based on Discrete Shearlet Transform Using Statistical Decision Theory

Abstract: Blind watermarking targets the challenging recovery of the watermark when the host is not available during the detection stage. This paper proposes Discrete Shearlet Transform (DST) as a new embedding domain for blind image watermarking. Our novel DST blind watermark detection system uses a nonadditive scheme based on the statistical decision theory. It first computes the Probability Density Function (PDF) of the DST coefficients modeled as a Laplacian distribution. The resulting likelihood ratio is compared with a decision threshold calculated using Neyman–Pearson criterion to minimize the missed detection subject to a fixed false alarm probability. Our method is evaluated in terms of imperceptibility, robustness, and payload against different attacks (Gaussian noise, blurring, cropping, compression, and rotation) using 30 standard grayscale images covering different characteristics (smooth, more complex with a lot of edges, and high detail textured regions). The proposed method shows greater windowing flexibility with more sensitive to directional and anisotropic features when compared against discrete wavelet and contourlets.

GAN-Based Key Secret-Sharing Scheme in Blockchain

Abstract: In this article, we propose a key secret-sharing technology based on generative adversarial networks (GANs) to address three major problems in the blockchain: 1) low security; 2) hard recovery of lost keys; and 3) low communication efficiency. In our scheme, the proposed network plays the role of a dealer and treats the secret-sharing process as a classification issue. The key idea is to view the secret as an image during the secret-sharing process. If the user’s private key is text, we can covert the key text into an image called the original image. Specifically, we first divide the original image into original subimages by the image segmentation. Next, we encode each original subimage by DNA coding. Finally, we train the proposed network to find the key secret-sharing results. Our proposed scheme is not only a significant extension of the GANs but also a new direction for the key secret-sharing technology. The simulation results show that the scheme is secure, and both flexible and efficient in communication.

Robust transparent image watermarking with Shearlet transform and bidiagonal singular value decomposition

Abstract: Watermarking, means hiding data in digital medium such as image, is a good solution for copyright protection and authentication. Watermarking methods must have a good resistance again various attacks. Wavelet based techniques, due to their compatibility with the human visual system, have been used frequently in this area. In the field of mathematical analysis, several developments of wavelet transform have been proposed. Shearlet transform is a new extension of wavelet that is presented in the past few years. This transform is based on the analysis of multi-resolution and multi-directional and improves presentation of multidimensional data. The main characteristic of Shearlet is good edge presentation of image, so images with different textures can be modeled well using it. In this study, in addition to using Shearlet transform to gain high imperceptibility, bidiagonal singular value decomposition is exploited for robustness and security improvement. Experiments are carried out by various attacks on a wide range of host images with distinct texture characteristics. Results show that the proposed method has good transparency and high robustness against variety types of attacks. Hence, this method can be used in applications that other wavelet-based schemes are not effective enough.

Robust and blind watermarking algorithm based on DCT and SVD in the contourlet domain

Abstract: A blind watermarking algorithm in multiple transform domains is presented for copyright protection. This robust algorithm is designed by fusing contourlet transform (CT), discrete cosine transform (DCT) and singular value decomposition (SVD). The host image is first decomposed by one-level CT and its low frequency sub-band is partitioned into 8 × 8 non-overlapping blocks. Then, each block is transformed by DCT and several middle frequency DCT coefficients with good stability are selected to construct the carrier matrix. Finally, the watermark is embedded by modifying the largest singular values of two carrier matrices. Besides, the geometric distortion factor is estimated with the speed up robust features (SURF) algorithm. The proposed watermarking scheme is evaluated in terms of imperceptibility and robustness. Experimental results demonstrate that the proposed watermarking scheme preforms better in terms of invisibility and robustness than other related schemes.