The complexity of EEG data presents significant challenges for accurate diagnosis in neurological conditions such as Alzheimer’s disease. In this paper, we introduce Explainable Orthogonal Attention Networks, a novel approach for EEG-based analysis that decouples spatial and temporal features to more effectively capture disease-related neural patterns. By leveraging orthogonal attention mechanisms, our model independently processes spatial relationships across EEG channels and temporal dynamics, enhancing both explainability and predictive performance. Our approach outperforms baselines, achieving superior performance in objective metrics, with a 14% relative improvement, while offering insights into the neural mechanisms underlying Alzheimer’s disease. Using attention maps and spectral analysis, we identified critical parietal and frontal contributions, along with EEG markers like elevated theta and reduced alpha power, commonly associated with Alzheimer’s disease. This method represents a significant step forward in developing explainable and high-performing EEG-based diagnostic tools. We will make the code and model’s weights publicly available upon publication at anonymized.

Predicting molecular impact on cellular function is a core challenge in therapeutic design. Phenomic experiments, designed to capture cellular morphology, utilize microscopy based techniques and demonstrate a high throughput solution for uncovering molecular impact on the cell. In this work, we learn a joint latent space between molecular structures and microscopy phenomic experiments, aligning paired samples with contrastive learning. Specifically, we study the problem of Contrastive PhenoMolecular Retrieval, which consists of zero-shot molecular structure identification conditioned on phenomic experiments. We assess challenges in multi-modal learning of phenomics and molecular modalities such as experimental batch effect, inactive molecule perturbations, and encoding perturbation concentration. We demonstrate improved multi-modal learner retrieval through (1) a uni-modal pre-trained phenomics model, (2) a novel inter sample similarity aware loss, and (3) models conditioned on a representation of molecular concentration. Following this recipe, we propose MolPhenix, a molecular phenomics model. MolPhenix leverages a pre-trained phenomics model to demonstrate significant performance gains across perturbation concentrations, molecular scaffolds, and activity thresholds. In particular, we demonstrate an 8.1 times improvement in zero shot molecular retrieval of active molecules over the previous state-of-the-art, reaching 77.33% in top-1% accuracy. These results open the door for machine learning to be applied in virtual phenomics screening, which can significantly benefit drug discovery applications.

Processing giga-pixel whole slide histopathology images (WSI) is a computationally expensive task. Multiple instance learning (MIL) has become the conventional approach to process WSIs, in which these images are split into smaller patches for further processing. However, MIL-based techniques ignore explicit information about the individual cells within a patch. In this paper, by defining the novel concept of shared-context processing, we designed a multi-modal Graph Transformer (AMIGO) that uses the cellular graph within the tissue to provide a single representation for a patient while taking advantage of the hierarchical structure of the tissue, enabling a dynamic focus between cell-level and tissue-level information. We benchmarked the performance of our model against multiple state-of-the-art methods in survival prediction and showed that ours can significantly outperform all of them including hierarchical Vision Transformer (ViT). More importantly, we show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data. Finally, in two different cancer datasets, we demonstrated that our model was able to stratify the patients into low-risk and high-risk groups while other state-of-the-art methods failed to achieve this goal. We also publish a large dataset of immunohistochemistry images (InUIT) containing 1,600 tissue microarray (TMA) cores from 188 patients along with their survival information, making it one of the largest publicly available datasets in this context.

Visual microscopic study of diseased tissue by pathologists has been the cornerstone for cancer diagnosis and prognostication for more than a century. Recently, deep learning methods have made significant advances in the analysis and classification of tissue images. However, there has been limited work on the utility of such models in generating histopathology images. These synthetic images have several applications in pathology including utilities in education, proficiency testing, privacy, and data sharing. Recently, diffusion probabilistic models were introduced to generate high quality images. Here, for the first time, we investigate the potential use of such models along with prioritized morphology weighting and color normalization to synthesize high quality histopathology images of brain cancer. Our detailed results show that diffusion probabilistic models are capable of synthesizing a wide range of histopathology images and have superior performance compared to generative adversarial networks.

Hyperspectral imaging provides rich information across many wavelengths of the captured scene, which is useful for many potential applications such as food quality inspection, medical diagnosis, material identification, artwork authentication, and crime scene analysis. However, hyperspectral imaging has not been widely deployed for such indoor applications. In this paper, we address one of the main challenges stifling this wide adoption, which is the strict illumination requirements for hyperspectral cameras. Hyperspectral cameras require a light source that radiates power across a wide range of the electromagnetic spectrum. Such light sources are expensive to setup and operate, and in some cases, they are not possible to use because they could damage important objects in the scene. We propose a data-driven method that enables indoor hyper-spectral imaging using cost-effective and widely available lighting sources such as LED and fluorescent. These common sources, however, introduce significant noise in the hyperspectral bands in the invisible range, which are the most important for the applications. Our proposed method restores the damaged bands using a carefully-designed supervised deep-learning model. We conduct an extensive experimental study to analyze the performance of the proposed method and compare it against the state-of-the-art using real hyperspectral datasets that we have collected. Our results show that the proposed method outperforms the state-of-the-art across all considered objective and subjective metrics, and it produces hyperspectral bands that are close to the ground truth bands captured under ideal illumination conditions.

Face-based authentication systems are among the most commonly used biometric systems, because of the ease of capturing face images at a distance and in non-intrusive way. These systems are, however, susceptible to various presentation attacks, including printed faces, artificial masks, and makeup attacks. In this paper, we propose a novel solution to address makeup attacks, which are the hardest to detect in such systems because makeup can substantially alter the facial features of a person, including making them appear older/younger by adding/hiding wrinkles, modifying the shape of eyebrows, beard, and moustache, and changing the color of lips and cheeks. In our solution, we design a generative adversarial network for removing the makeup from face images while retaining their essential facial features and then compare the face images before and after removing makeup. We collect a large dataset of various types of makeup, especially malicious makeup that can be used to break into remote unattended security systems. This dataset is quite different from existing makeup datasets that mostly focus on cosmetic aspects. We conduct an extensive experimental study to evaluate our method and compare it against the state-of-the art using standard objective metrics commonly used in biometric systems as well as subjective metrics collected through a user study. Our results show that the proposed solution produces high accuracy and substantially outperforms the closest works in the literature.

Network function virtualization (NFV) is referred to the technology in which softwarized network functions virtually run on commodity servers. Such functions are called virtual network functions (VNFs). A specific service is composed of a set of VNFs. This is a paradigm shift for service provisioning in telecom networks which introduces new design and implementation challenges. One of such challenges is to meet the reliability requirement of the requested services considering the reliability of the commodity servers. NFV placement which is the problem of assigning commodity servers to the VNFs becomes crucial under such circumstances. To address such an issue, in this paper, we employ Deep Reinforcement Learning (Deep-RL) to model NFV placement problem considering the reliability requirement of the services. The output of the introduced model determines optimal placement in each state. Numerical evaluations show that the introduced model can significantly improve the performance of the network operator.