Search

Collision-resistant, cryptographic hash (CRH) functions have long been an integral part of providing security and privacy in modern systems. Certain constructions of zero-knowledge proof (ZKP) protocols aim to utilize CRH functions to perform cryptographic hashing. Standard CRH functions, such as SHA2, are inefficient when employed in the ZKP domain, thus calling for ZK-friendly hashes, which are CRH functions built with ZKP efficiency in mind. The most mature ZK-friendly hash, MiMC, presents a block cipher and hash function with a simple algebraic structure that is well-suited, due to its achieved security and low complexity, for ZKP applications. Although ZK-friendly hashes have improved the performance of ZKP generation in software, the underlying computation of ZKPs, including CRH functions, must be optimized on hardware to enable practical applications. The challenge we address in this work is determining how to efficiently incorporate ZK-friendly hash functions, such as MiMC, into hardware accelerators, thus enabling more practical applications. In this work, we introduce AMAZE, a highly hardware-optimized open-source framework for computing the MiMC block cipher and hash function. Our solution has been primarily directed at resource-constrained edge devices; consequently, we provide several implementations of MiMC with varying power, resource, and latency profiles. Our extensive evaluations show that the AMAZE-powered implementation of MiMC outperforms standard CPU implementations by more than 13$\times$. In all settings, AMAZE enables efficient ZK-friendly hashing on resource-constrained devices. Finally, we highlight AMAZE's underlying open-source arithmetic backend as part of our end-to-end design, thus allowing developers to utilize the AMAZE framework for custom ZKP applications., Comment: Accepted to ICCAD 2024

Photon-counting computed tomography (PCCT) marks a significant advancement over conventional energy-integrating detector (EID) CT systems. This review highlights PCCT's superior spatial and contrast resolution, reduced radiation dose, and multi-energy imaging capabilities, which address key challenges in radiotherapy, such as accurate tumor delineation, precise dose calculation, and treatment response monitoring. PCCT's improved anatomical clarity enhances tumor targeting while minimizing damage to surrounding healthy tissues. Additionally, metal artifact reduction (MAR) and quantitative imaging capabilities optimize workflows, enabling adaptive radiotherapy and radiomics-driven personalized treatment. Emerging clinical applications in brachytherapy and radiopharmaceutical therapy (RPT) show promising outcomes, although challenges like high costs and limited software integration remain. With advancements in artificial intelligence (AI) and dedicated radiotherapy packages, PCCT is poised to transform precision, safety, and efficacy in cancer radiotherapy, marking it as a pivotal technology for future clinical practice.

Recent advances in deep learning structured state space models, especially the Mamba architecture, have demonstrated remarkable performance improvements while maintaining linear complexity. In this study, we introduce functional spatiotemporal Mamba (FST-Mamba), a Mamba-based model designed for discovering neurological biomarkers using functional magnetic resonance imaging (fMRI). We focus on dynamic functional network connectivity (dFNC) derived from fMRI and propose a hierarchical spatiotemporal Mamba-based network that processes spatial and temporal information separately using Mamba-based encoders. Leveraging the topological uniqueness of the FNC matrix, we introduce a component-wise varied-scale aggregation (CVA) mechanism to aggregate connectivity across individual components within brain networks, enabling the model to capture both inter-component and inter-network information. To better handle the FNC data, we develop a new component-specific scanning order. Additionally, we propose symmetric rotary position encoding (SymRope) to encode the relative positions of each functional connection while considering the symmetric nature of the FNC matrix. Experimental results demonstrate significant improvements in the proposed FST-Mamba model on various brain-based classification and regression tasks. Our work reveals the substantial potential of attention-free sequence modeling in brain discovery.

The phase diagram of the Gross-Neveu model in 1+1 dimensions is studied using Ginzburg-Landau expansion. It predicts several features of the exact phase diagram correctly even at low orders. It is shown that increasing the order of the expansion improves the accuracy of the crystal phase except for very small temperatures, where the expansion completely fails regardless of the order of the expansion. The source of this behaviour seems to be related to the Silver-Blaze phenomenon., Comment: 13 pages, 6 figures. arXiv admin note: text overlap with arXiv:1802.09095

Alzheimer's disease (AD) progresses from asymptomatic changes to clinical symptoms, emphasizing the importance of early detection for proper treatment. Functional magnetic resonance imaging (fMRI), particularly dynamic functional network connectivity (dFNC), has emerged as an important biomarker for AD. Nevertheless, studies probing at-risk subjects in the pre-symptomatic stage using dFNC are limited. To identify at-risk subjects and understand alterations of dFNC in different stages, we leverage deep learning advancements and introduce a transformer-convolution framework for predicting at-risk subjects based on dFNC, incorporating spatial-temporal self-attention to capture brain network dependencies and temporal dynamics. Our model significantly outperforms other popular machine learning methods. By analyzing individuals with diagnosed AD and mild cognitive impairment (MCI), we studied the AD progression and observed a higher similarity between MCI and asymptomatic AD. The interpretable analysis highlights the cognitive-control network's diagnostic importance, with the model focusing on intra-visual domain dFNC when predicting asymptomatic AD subjects., Comment: Accepted by EMBC 2024

DC microgrids are getting more and more applications due to simple converters, only voltage control and higher efficiencies compared to conventional AC grids. Droop control is a well know decentralized control strategy for power sharing among converter interfaced sources and loads in a DC microgrid. This work compares the stability assessment and control of four types of droops for boost converters using the concept of passivity. EN standard 50388-2 for railway systems provides a reference to ensure system stability in perspectives of converters and system integration. Low pass filter (LPF) in the feedback of the droop control is used to ensure converter passivity. Bus impedance is derived to ensure system passivity with less conservativeness. Analytical approach for design of passive controller for all four types of droops is verified through time domain simulations of a single boost converter based microgrid feeding a Constant Power Load (CPL).

Due to advancements in power electronics, new converter topologies are introduced day by day. It's hard to get an equivalent model from any manufacturer of any Commercial Off-The-Shelf (COTS) power electronics converters because of intellectual property (IP) and safety concerns. Most COTS products don't reveal the exact topology of the converter as well as the control architecture and corresponding control gains. Because of these reasons, it's very hard to implement an exact equivalent model of COTS converters. Hierarchical control is widely used in microgrid applications, where different control layers are decoupled on the timescale. This article gives a baseline approach to build an equivalent model of any droop controlled COTS converter to mimic its control performance. Bandwidths of the different control loops are estimated along with the control logic from experiments on COTS converter and then hierarchical control is followed to come up with the equivalent model. The approach is verified on COTS CE+T Stabiliti 30C3 converter with its equivalent model build in MATLAB Simulink.

Amyloid-$\beta$ (A$\beta$) plaques in conjunction with hyperphosphorylated tau proteins in the form of neurofibrillary tangles are the two neuropathological hallmarks of Alzheimer's disease. It is well-known that the identification of individuals with A$\beta$ positivity could enable early diagnosis. In this work, we aim at capturing the A$\beta$ positivity status in an unbalanced cohort enclosing subjects at different disease stages, exploiting the underlying structural and connectivity disease-induced modulations as revealed by structural, functional, and diffusion MRI. Of note, due to the unbalanced cohort, the outcomes may be guided by those factors rather than amyloid accumulation. The partial views provided by each modality are integrated in the model allowing to take full advantage of their complementarity in encoding the effects of the A$\beta$ accumulation, leading to an accuracy of $0.762\pm0.04$. The specificity of the information brought by each modality is assessed by \textit{post-hoc} explainability analysis (guided backpropagation), highlighting the underlying structural and functional changes. Noteworthy, well-established biomarker key regions related to A$\beta$ deposition could be identified by all modalities, including the hippocampus, thalamus, precuneus, and cingulate gyrus, witnessing in favor of the reliability of the method as well as its potential in shading light on modality-specific possibly unknown A$\beta$ deposition signatures., Comment: 16 pages, 3 figures, provisionally accepted to a journal

Alzheimer's disease (AD) is the most prevalent form of dementia with a progressive decline in cognitive abilities. The AD continuum encompasses a prodromal stage known as MCI, where patients may either progress to AD (MCIc) or remain stable (MCInc). Understanding AD mechanisms requires complementary analyses relying on different data sources, leading to the development of multimodal DL models. We leveraged structural and functional MRI to investigate the disease-induced GM and functional network connectivity changes. Moreover, considering AD's strong genetic component, we introduced SNPs as a third channel. Missing one or more modalities is a typical concern of multimodal methods. We hence propose a novel DL-based classification framework where a generative module employing Cycle GAN was adopted for imputing missing data in the latent space. Additionally, we adopted an XAI method, Integrated Gradients, to extract features' relevance, enhancing our understanding of the learned representations. Two tasks were addressed: AD detection and MCI conversion prediction. Experimental results showed that our framework reached the SOA in the classification of CN/AD with an average test accuracy of $0.926\pm0.02$. For the MCInc/MCIc task, we achieved an average prediction accuracy of $0.711\pm0.01$ using the pre-trained model for CN and AD. The interpretability analysis revealed that significant GM modulations led the classification performance in cortical and subcortical brain areas well known for their association with AD. Impairments in sensory-motor and visual functional network connectivity along AD, as well as mutations in SNPs defining biological processes linked to endocytosis, amyloid-beta, and cholesterol, were identified as contributors to the results. Overall, our integrative DL model shows promise for AD detection and MCI prediction, while shading light on important biological insights., Comment: 28 pages, 8 figures, submitted to a journal

Deep Learning has shown great success in reshaping medical imaging, yet it faces numerous challenges hindering widespread application. Issues like catastrophic forgetting and distribution shifts in the continuously evolving data stream increase the gap between research and applications. Continual Learning offers promise in addressing these hurdles by enabling the sequential acquisition of new knowledge without forgetting previous learnings in neural networks. In this survey, we comprehensively review the recent literature on continual learning in the medical domain, highlight recent trends, and point out the practical issues. Specifically, we survey the continual learning studies on classification, segmentation, detection, and other tasks in the medical domain. Furthermore, we develop a taxonomy for the reviewed studies, identify the challenges, and provide insights to overcome them. We also critically discuss the current state of continual learning in medical imaging, including identifying open problems and outlining promising future directions. We hope this survey will provide researchers with a useful overview of the developments in the field and will further increase interest in the community. To keep up with the fast-paced advancements in this field, we plan to routinely update the repository with the latest relevant papers at https://github.com/BioMedIA-MBZUAI/awesome-cl-in-medical ., Comment: 16 pages, 9 figures

Generative approaches for cross-modality transformation have recently gained significant attention in neuroimaging. While most previous work has focused on case-control data, the application of generative models to disorder-specific datasets and their ability to preserve diagnostic patterns remain relatively unexplored. Hence, in this study, we investigated the use of a generative adversarial network (GAN) in the context of Alzheimer's disease (AD) to generate functional network connectivity (FNC) and T1-weighted structural magnetic resonance imaging data from each other. We employed a cycle-GAN to synthesize data in an unpaired data transition and enhanced the transition by integrating weak supervision in cases where paired data were available. Our findings revealed that our model could offer remarkable capability, achieving a structural similarity index measure (SSIM) of $0.89 \pm 0.003$ for T1s and a correlation of $0.71 \pm 0.004$ for FNCs. Moreover, our qualitative analysis revealed similar patterns between generated and actual data when comparing AD to cognitively normal (CN) individuals. In particular, we observed significantly increased functional connectivity in cerebellar-sensory motor and cerebellar-visual networks and reduced connectivity in cerebellar-subcortical, auditory-sensory motor, sensory motor-visual, and cerebellar-cognitive control networks. Additionally, the T1 images generated by our model showed a similar pattern of atrophy in the hippocampal and other temporal regions of Alzheimer's patients.

Brain tumor segmentation is a fundamental step in assessing a patient's cancer progression. However, manual segmentation demands significant expert time to identify tumors in 3D multimodal brain MRI scans accurately. This reliance on manual segmentation makes the process prone to intra- and inter-observer variability. This work proposes a brain tumor segmentation method as part of the BraTS-GoAT challenge. The task is to segment tumors in brain MRI scans automatically from various populations, such as adults, pediatrics, and underserved sub-Saharan Africa. We employ a recent CNN architecture for medical image segmentation, namely MedNeXt, as our baseline, and we implement extensive model ensembling and postprocessing for inference. Our experiments show that our method performs well on the unseen validation set with an average DSC of 85.54% and HD95 of 27.88. The code is available on https://github.com/BioMedIA-MBZUAI/BraTS2024_BioMedIAMBZ.

This study highlights the importance of conducting comprehensive model inspection as part of comparative performance analyses. Here, we investigate the effect of modelling choices on the feature learning characteristics of graph neural networks applied to a brain shape classification task. Specifically, we analyse the effect of using parameter-efficient, shared graph convolutional submodels compared to structure-specific, non-shared submodels. Further, we assess the effect of mesh registration as part of the data harmonisation pipeline. We find substantial differences in the feature embeddings at different layers of the models. Our results highlight that test accuracy alone is insufficient to identify important model characteristics such as encoded biases related to data source or potentially non-discriminative features learned in submodels. Our model inspection framework offers a valuable tool for practitioners to better understand performance characteristics of deep learning models in medical imaging., Comment: International Symposium on Biomedical Imaging (ISBI)

Continual learning, the ability to acquire knowledge from new data while retaining previously learned information, is a fundamental challenge in machine learning. Various approaches, including memory replay, knowledge distillation, model regularization, and dynamic network expansion, have been proposed to address this issue. Thus far, dynamic network expansion methods have achieved state-of-the-art performance at the cost of incurring significant computational overhead. This is due to the need for additional model buffers, which makes it less feasible in resource-constrained settings, particularly in the medical domain. To overcome this challenge, we propose Dynamic Model Merging, DynaMMo, a method that merges multiple networks at different stages of model training to achieve better computational efficiency. Specifically, we employ lightweight learnable modules for each task and combine them into a unified model to minimize computational overhead. DynaMMo achieves this without compromising performance, offering a cost-effective solution for continual learning in medical applications. We evaluate DynaMMo on three publicly available datasets, demonstrating its effectiveness compared to existing approaches. DynaMMo offers around 10-fold reduction in GFLOPS with a small drop of 2.76 in average accuracy when compared to state-of-the-art dynamic-based approaches. The code implementation of this work will be available upon the acceptance of this work at https://github.com/BioMedIA-MBZUAI/DynaMMo.

Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the performance of explainability methods on these models is widening the gap between their development and safe deployment. In this work, we analyze the performance of various explainable AI methods on a vision-language model, MedCLIP, to demystify its inner workings. We also provide a simple methodology to overcome the shortcomings of these methods. Our work offers a different new perspective on the explainability of a recent well-known VLM in the medical domain and our assessment method is generalizable to other current and possible future VLMs.

The scarcity of well-annotated medical datasets requires leveraging transfer learning from broader datasets like ImageNet or pre-trained models like CLIP. Model soups averages multiple fine-tuned models aiming to improve performance on In-Domain (ID) tasks and enhance robustness against Out-of-Distribution (OOD) datasets. However, applying these methods to the medical imaging domain faces challenges and results in suboptimal performance. This is primarily due to differences in error surface characteristics that stem from data complexities such as heterogeneity, domain shift, class imbalance, and distributional shifts between training and testing phases. To address this issue, we propose a hierarchical merging approach that involves local and global aggregation of models at various levels based on models' hyperparameter configurations. Furthermore, to alleviate the need for training a large number of models in the hyperparameter search, we introduce a computationally efficient method using a cyclical learning rate scheduler to produce multiple models for aggregation in the weight space. Our method demonstrates significant improvements over the model souping approach across multiple datasets (around 6% gain in HAM10000 and CheXpert datasets) while maintaining low computational costs for model generation and selection. Moreover, we achieve better results on OOD datasets than model soups. The code is available at https://github.com/BioMedIA-MBZUAI/FissionFusion.

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible performance gains for deep learning models. Some advancements have been made in boosting the transfer learning performance gain by merging models starting from the same initialization. However, in the medical imaging analysis domain, there is an opportunity in merging models starting from different initialisations, thus combining the features learnt from different tasks. In this work, we propose MedMerge, a method whereby the weights of different models can be merged, and their features can be effectively utilized to boost performance on a new task. With MedMerge, we learn kernel-level weights that can later be used to merge the models into a single model, even when starting from different initializations. Testing on various medical imaging analysis tasks, we show that our merged model can achieve significant performance gains, with up to 3% improvement on the F1 score. The code implementation of this work will be available at www.github.com/BioMedIA-MBZUAI/MedMerge.

Automated segmentation proves to be a valuable tool in precisely detecting tumors within medical images. The accurate identification and segmentation of tumor types hold paramount importance in diagnosing, monitoring, and treating highly fatal brain tumors. The BraTS challenge serves as a platform for researchers to tackle this issue by participating in open challenges focused on tumor segmentation. This study outlines our methodology for segmenting tumors in the context of two distinct tasks from the BraTS 2023 challenge: Adult Glioma and Pediatric Tumors. Our approach leverages two encoder-decoder-based CNN models, namely SegResNet and MedNeXt, for segmenting three distinct subregions of tumors. We further introduce a set of robust postprocessing to improve the segmentation, especially for the newly introduced BraTS 2023 metrics. The specifics of our approach and comprehensive performance analyses are expounded upon in this work. Our proposed approach achieves third place in the BraTS 2023 Adult Glioma Segmentation Challenges with an average of 0.8313 and 36.38 Dice and HD95 scores on the test set, respectively.

Large-scale generative models have demonstrated impressive capabilities in producing visually compelling images, with increasing applications in medical imaging. However, they continue to grapple with hallucination challenges and the generation of anatomically inaccurate outputs. These limitations are mainly due to the reliance on textual inputs and lack of spatial control over the generated images, hindering the potential usefulness of such models in real-life settings. In this work, we present XReal, a novel controllable diffusion model for generating realistic chest X-ray images through precise anatomy and pathology location control. Our lightweight method comprises an Anatomy Controller and a Pathology Controller to introduce spatial control over anatomy and pathology in a pre-trained Text-to-Image Diffusion Model, respectively, without fine-tuning the model. XReal outperforms state-of-the-art X-ray diffusion models in quantitative metrics and radiologists' ratings, showing significant gains in anatomy and pathology realism. Our model holds promise for advancing generative models in medical imaging, offering greater precision and adaptability while inviting further exploration in this evolving field. The code and pre-trained model weights are publicly available at https://github.com/BioMedIA-MBZUAI/XReal.

Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes of the graphs. However, there is a disparity between the existing attribution methods, and it is unclear which attribution to trust. Therefore research has introduced evaluation experiments that assess them from different perspectives. In this work, we assess attribution methods from a perspective not previously explored in the graph domain: retraining. The core idea is to retrain the network on important (or not important) relationships as identified by the attributions and evaluate how networks can generalize based on these relationships. We reformulate the retraining framework to sidestep issues lurking in the previous formulation and propose guidelines for correct analysis. We run our analysis on four state-of-the-art GNN attribution methods and five synthetic and real-world graph classification datasets. The analysis reveals that attributions perform variably depending on the dataset and the network. Most importantly, we observe that the famous GNNExplainer performs similarly to an arbitrary designation of edge importance. The study concludes that the retraining evaluation cannot be used as a generalized benchmark and recommends it as a toolset to evaluate attributions on a specifically addressed network, dataset, and sparsity.

The Internet and social media have transformed news availability and accessibility, reshaping information consumption and production. However, they can also facilitate the rapid spread of misinformation, posing significant societal challenges. To combat misinformation effectively, it is crucial to understand the online information environment and news consumption patterns. Most existing research has primarily focused on single topics or individual countries, lacking cross-country comparisons. This study investigated information consumption in four European countries, analyzing three years of Twitter activity from news outlet accounts in France, Germany, Italy, and the UK and focusing on the role of misinformation sources. Our work offers a perspective on how topics of European significance are interpreted across various countries. Results indicate that reliable sources dominate the information landscape, although unreliable content is still present across all countries and topics. While most users engage with reliable sources, a small percentage consume questionable content. Interestingly, few users have a mixed information diet, bridging the gap between questionable and reliable news in the similarity network. Cross-country comparisons revealed differences in audience overlap of news sources, offering valuable guidance for policymakers and scholars in developing effective and tailored solutions to combat misinformation.

Electrochemistry ecosystems are promising for accelerating the design and discovery of electrochemical systems for energy storage and conversion, by automating significant parts of workflows that combine synthesis and characterization experiments with computations. They require the integration of flow controllers, solvent containers, pumps, fraction collectors, and potentiostats, all connected to an electrochemical cell. These are specialized instruments with custom software that is not originally designed for network integration. We developed network and software solutions for electrochemical workflows that adapt system and instrument settings in real-time for multiple rounds of experiments. We demonstrate this automated workflow by remotely operating the instruments and collecting their measurements to generate a voltammogram (I-V profile) of an electrolyte solution in an electrochemical cell. These measurements are made available at the remote computing system and used for subsequent analysis. In this paper, we focus on a novel, analytically validated machine learning (ML) method for an electrochemistry ecosystem to ensure that I-V measurements are consistent with the normal experimental conditions, and to detect abnormal conditions, such as disconnected electrodes or low cell content volume., Comment: published at eScience 2023

Alloys based on lanthanum phosphate (LaPO$_{4}$) are often employed as thermal barrier coatings, due to their low thermal conductivity and structural stability over a wide temperature range. To enhance the thermal-insulation performance of these alloys, it is essential to comprehensively understand the fundamental physics governing their heat conduction. Here, we employ the Wigner formulation of thermal transport in conjunction with first-principles calculations to elucidate how the interplay between anharmonicity and compositional disorder determines the thermal properties of La$_{1{-}x}$Gd$_{x}$PO$_{4}$ alloys, and discuss the fundamental physics underlying the emergence and coexistence of particle-like and wave-like heat-transport mechanisms. We also show how the Wigner transport equation describes correctly the thermodynamic limit of a compositionally disordered crystal, while the Boltzmann transport equation does not. Our predictions for microscopic vibrational properties (temperature-dependent Raman spectrum) and for macroscopic thermal conductivity are validated against experiments. Finally, we leverage these findings to devise strategies to optimize the performance of thermal barrier coatings., Comment: Main text: 11 pages, 9 figures. Appendix: 8 pages, 8 figures

The cross-modal synthesis between structural magnetic resonance imaging (sMRI) and functional network connectivity (FNC) is a relatively unexplored area in medical imaging, especially with respect to schizophrenia. This study employs conditional Vision Transformer Generative Adversarial Networks (cViT-GANs) to generate FNC data based on sMRI inputs. After training on a comprehensive dataset that included both individuals with schizophrenia and healthy control subjects, our cViT-GAN model effectively synthesized the FNC matrix for each subject, and then formed a group difference FNC matrix, obtaining a Pearson correlation of 0.73 with the actual FNC matrix. In addition, our FNC visualization results demonstrate significant correlations in particular subcortical brain regions, highlighting the model's capability of capturing detailed structural-functional associations. This performance distinguishes our model from conditional CNN-based GAN alternatives such as Pix2Pix. Our research is one of the first attempts to link sMRI and FNC synthesis, setting it apart from other cross-modal studies that concentrate on T1- and T2-weighted MR images or the fusion of MRI and CT scans.

The rise of ideological divides in public discourse has received considerable attention in recent years. However, much of this research has been concentrated on Western democratic nations, leaving other regions largely unexplored. Here, we delve into the political landscape of Pakistan, a nation marked by intricate political dynamics and persistent turbulence. Spanning from 2018 to 2022, our analysis of Twitter data allows us to capture pivotal shifts and developments in Pakistan's political arena. By examining interactions and content generated by politicians affiliated with major political parties, we reveal a consistent and active presence of politicians on Twitter, with opposition parties exhibiting particularly robust engagement. We explore the alignment of party audiences, highlighting a notable convergence among opposition factions over time. Our analysis also uncovers significant shifts in political affiliations, including the transition of politicians to the opposition alliance. Quantitatively, we assess evolving interaction patterns, showcasing the prevalence of homophilic connections while identifying a growing interconnection among audiences of opposition parties. Our study, by accurately reflecting shifts in the political landscape, underscores the reliability of our methodology and social media data as a valuable tool for monitoring political polarization and providing a nuanced understanding of macro-level trends and individual-level transformations.