Corruption depth: Analysis of DNN depth for misclassification.

Many large and complex deep neural networks have been shown to provide higher performance on various computer vision tasks. However, very little is known about the relationship between the complexity of the input data along with the type of noise and the depth needed for correct classification. Existing studies do not address the issue of common corruptions adequately, especially in understanding what impact these corruptions leave on the individual part of a deep neural network. Therefore, we can safely assume that the classification (or misclassification) might be happening at a particular layer(s) of a network that accumulates to draw a final correct or incorrect prediction. In this paper, we introduce a novel concept of corruption depth, which identifies the location of the network layer/depth until the misclassification persists. We assert that the identification of such layers will help in better designing the network by pruning certain layers in comparison to the purification of the entire network which is computationally heavy. Through our extensive experiments, we present a coherent study to understand the processing of examples through the network. Our approach also illustrates different philosophies of example memorization and a one-dimensional view of sample or query difficulty. We believe that the understanding of the corruption depth can open a new dimension of model explainability and model compression, where in place of just visualizing the attention map, the classification progress can be seen throughout the network.

Exploring the role of ChatGPT in patient care (diagnosis and treatment) and medical research: A systematic review.

Background: ChatGPT is an artificial intelligence based tool developed by OpenAI (California, USA). This systematic review examines the potential of ChatGPT in patient care and its role in medical research. Methods: The systematic review was done according to the PRISMA guidelines. Embase, Scopus, PubMed and Google Scholar data bases were searched. We also searched preprint data bases. Our search was aimed to identify all kinds of publications, without any restrictions, on ChatGPT and its application in medical research, medical publishing and patient care. We used search term "ChatGPT". We reviewed all kinds of publications including original articles, reviews, editorial/ commentaries, and even letter to the editor. Each selected records were analysed using ChatGPT and responses generated were compiled in a table. The word table was transformed in to a PDF and was further analysed using ChatPDF. Results: We reviewed full texts of 118 articles. ChatGPT can assist with patient enquiries, note writing, decision-making, trial enrolment, data management, decision support, research support, and patient education. But the solutions it offers are usually insufficient and contradictory, raising questions about their originality, privacy, correctness, bias, and legality. Due to its lack of human-like qualities, ChatGPT's legitimacy as an author is questioned when used for academic writing. ChatGPT generated contents have concerns with bias and possible plagiarism. Conclusion: Although it can help with patient treatment and research, there are issues with accuracy, authorship, and bias. ChatGPT can serve as a "clinical assistant" and be a help in research and scholarly writing.

Unveiling a rare radiological discovery: Interlobar pneumothorax in a young female patient.

Pneumothorax is a medical condition characterized by air in the space between the visceral and parietal pleural surfaces, with spontaneous and traumatic classifications. Spontaneous pneumothorax is further divided into primary and secondary groups based on the presence or absence of clinically apparent underlying lung disease. Here we present a case of a 23-year-old female with no past medical history who presented with chest pain and shortness of breath, ultimately diagnosed with primary spontaneous interlobar pneumothorax. Despite advancements in medical diagnosis techniques, spontaneous interlobar pneumothorax remains a rare presentation of pneumothoraces. Treatment strategies for clinically stable patients with a first episode of primary spontaneous pneumothorax include observation with or without supplemental oxygen, with further intervention only if the pneumothorax fails to improve or worsens.

Secondary electron count imaging in SEM.

Scanning electron microscopy (SEM) is a versatile technique used to image samples at the nanoscale. Conventional imaging by this technique relies on finding the average intensity of the signal generated on a detector by secondary electrons (SEs) emitted from the sample and is subject to noise due to variations in the voltage signal from the detector. This noise can result in degradation of the SEM image quality for a given imaging dose. SE count imaging, which uses the direct count of SEs detected from the sample instead of the average signal intensity, would overcome this limitation and lead to improvement in SEM image quality. In this paper, we implement an SE count imaging scheme by synchronously outcoupling the detector and beam scan signals from the microscope and using custom code to count detected SEs. We demonstrate a ∼30% increase in the image signal-to-noise-ratio due to SE counting compared to conventional imaging. The only external hardware requirement for this imaging scheme is an oscilloscope fast enough to accurately sample the detector signal for SE counting, making the scheme easily implementable on any SEM.

ggMOB: Elucidation of genomic conjugative features and associated cargo genes across bacterial genera using genus-genus mobilization networks.

Horizontal gene transfer mediated by conjugation is considered an important evolutionary mechanism of bacteria. It allows organisms to quickly evolve new phenotypic properties including antimicrobial resistance (AMR) and virulence. The frequency of conjugation-mediated cargo gene exchange has not yet been comprehensively studied within and between bacterial taxa. We developed a frequency-based network of genus-genus conjugation features and candidate cargo genes from whole-genome sequence data of over 180,000 bacterial genomes, representing 1,345 genera. Using our method, which we refer to as ggMOB, we revealed that over half of the bacterial genomes contained one or more known conjugation features that matched exactly to at least one other genome. Moreover, the proportion of genomes containing these conjugation features varied substantially by genus and conjugation feature. These results and the genus-level network structure can be viewed interactively in the ggMOB interface, which allows for user-defined filtering of conjugation features and candidate cargo genes. Using the network data, we observed that the ratio of AMR gene representation in conjugative versus non-conjugative genomes exceeded 5:1, confirming that conjugation is a critical force for AMR spread across genera. Finally, we demonstrated that clustering genomes by conjugation profile sometimes correlated well with classical phylogenetic structuring; but that in some cases the clustering was highly discordant, suggesting that the importance of the accessory genome in driving bacterial evolution may be highly variable across both time and taxonomy. These results can advance scientific understanding of bacterial evolution, and can be used as a starting point for probing genus-genus gene exchange within complex microbial communities that include unculturable bacteria. ggMOB is publicly available under the GNU licence at https://ruiz-hci-lab.github.io/ggMOB/.

Crafting Adversarial Perturbations via Transformed Image Component Swapping.

Adversarial attacks have been demonstrated to fool the deep classification networks. There are two key characteristics of these attacks: firstly, these perturbations are mostly additive noises carefully crafted from the deep neural network itself. Secondly, the noises are added to the whole image, not considering them as the combination of multiple components from which they are made. Motivated by these observations, in this research, we first study the role of various image components and the impact of these components on the classification of the images. These manipulations do not require the knowledge of the networks and external noise to function effectively and hence have the potential to be one of the most practical options for real-world attacks. Based on the significance of the particular image components, we also propose a transferable adversarial attack against unseen deep networks. The proposed attack utilizes the projected gradient descent strategy to add the adversarial perturbation to the manipulated component image. The experiments are conducted on a wide range of networks and four databases including ImageNet and CIFAR-100. The experiments show that the proposed attack achieved better transferability and hence gives an upper hand to an attacker. On the ImageNet database, the success rate of the proposed attack is up to 88.5%, while the current state-of-the-art attack success rate on the database is 53.8%. We have further tested the resiliency of the attack against one of the most successful defenses namely adversarial training to measure its strength. The comparison with several challenging attacks shows that: (i) the proposed attack has a higher transferability rate against multiple unseen networks and (ii) it is hard to mitigate its impact. We claim that based on the understanding of the image components, the proposed research has been able to identify a newer adversarial attack unseen so far and unsolvable using the current defense mechanisms.

Boosting Face Presentation Attack Detection in Multi-Spectral Videos Through Score Fusion of Wavelet Partition Images.

Presentation attack detection (PAD) algorithms have become an integral requirement for the secure usage of face recognition systems. As face recognition algorithms and applications increase from constrained to unconstrained environments and in multispectral scenarios, presentation attack detection algorithms must also increase their scope and effectiveness. It is important to realize that the PAD algorithms are not only effective for one environment or condition but rather be generalizable to a multitude of variabilities that are presented to a face recognition algorithm. With this motivation, as the first contribution, the article presents a unified PAD algorithm for different kinds of attacks such as printed photos, a replay of video, 3D masks, silicone masks, and wax faces. The proposed algorithm utilizes a combination of wavelet decomposed raw input images from sensor and face region data to detect whether the input image is bonafide or attacked. The second contribution of the article is the collection of a large presentation attack database in the NIR spectrum, containing images from individuals of two ethnicities. The database contains 500 print attack videos which comprise approximately 1,00,000 frames collectively in the NIR spectrum. Extensive evaluation of the algorithm on NIR images as well as visible spectrum images obtained from existing benchmark databases shows that the proposed algorithm yields state-of-the-art results and surpassed several complex and state-of-the-art algorithms. For instance, on benchmark datasets, namely CASIA-FASD, Replay-Attack, and MSU-MFSD, the proposed algorithm achieves a maximum error of 0.92% which is significantly lower than state-of-the-art attack detection algorithms.

Predicting Epitope Candidates for SARS-CoV-2.

Epitopes are short amino acid sequences that define the antigen signature to which an antibody or T cell receptor binds. In light of the current pandemic, epitope analysis and prediction are paramount to improving serological testing and developing vaccines. In this paper, known epitope sequences from SARS-CoV, SARS-CoV-2, and other Coronaviridae were leveraged to identify additional antigen regions in 62K SARS-CoV-2 genomes. Additionally, we present epitope distribution across SARS-CoV-2 genomes, locate the most commonly found epitopes, and discuss where epitopes are located on proteins and how epitopes can be grouped into classes. The mutation density of different protein regions is presented using a big data approach. It was observed that there are 112 B cell and 279 T cell conserved epitopes between SARS-CoV-2 and SARS-CoV, with more diverse sequences found in Nucleoprotein and Spike glycoprotein.

Functional Genomics Platform, A Cloud-Based Platform for Studying Microbial Life at Scale.

The rapid growth in biological sequence data is revolutionizing our understanding of genotypic diversity and challenging conventional approaches to informatics. With the increasing availability of genomic data, traditional bioinformatic tools require substantial computational time and the creation of ever-larger indices each time a researcher seeks to gain insight from the data. To address these challenges, we pre-computed important relationships between biological entities spanning the Central Dogma of Molecular Biology and captured this information in a relational database. The database can be queried across hundreds of millions of entities and returns results in a fraction of the time required by traditional methods. In this paper, we describe Functional Genomics Platform (formerly known as OMXWare), a comprehensive database relating genotype to phenotype for bacterial life. Continually updated, the Functional Genomics Platform today contains data derived from 200,000 curated, self-consistently assembled genomes. The database stores functional data for over 68 million genes, 52 million proteins, and 239 million domains with associated biological activity annotations from Gene Ontology, KEGG, MetaCyc, and Reactome. The Functional Genomics Platform maps all of the many-to-many connections between each biological entity including the originating genome, gene, protein, and protein domain. Various microbial studies, from infectious disease to environmental health, can benefit from the rich data and connections. We describe the data selection, the pipeline to create and update the Functional Genomics Platform, and the developer tools (Python SDK and REST APIs)which allow researchers to efficiently study microbial life at scale.

DAMAD: Database, Attack, and Model Agnostic Adversarial Perturbation Detector.

Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms to adversarial attacks. Existing adversary detection algorithms attempt to detect the singularities; however, they are in general, loss-function, database, or model dependent. To mitigate this limitation, we propose DAMAD-a generalized perturbation detection algorithm which is agnostic to model architecture, training data set, and loss function used during training. The proposed adversarial perturbation detection algorithm is based on the fusion of autoencoder embedding and statistical texture features extracted from convolutional neural networks. The performance of DAMAD is evaluated on the challenging scenarios of cross-database, cross-attack, and cross-architecture training and testing along with traditional evaluation of testing on the same database with known attack and model. Comparison with state-of-the-art perturbation detection algorithms showcase the effectiveness of the proposed algorithm on six databases: ImageNet, CIFAR-10, Multi-PIE, MEDS, point and shoot challenge (PaSC), and MNIST. Performance evaluation with nearly a quarter of a million adversarial and original images and comparison with recent algorithms show the effectiveness of the proposed algorithm.

Semi-Supervised Pipeline for Autonomous Annotation of SARS-CoV-2 Genomes.

SARS-CoV-2 genomic sequencing efforts have scaled dramatically to address the current global pandemic and aid public health. However, autonomous genome annotation of SARS-CoV-2 genes, proteins, and domains is not readily accomplished by existing methods and results in missing or incorrect sequences. To overcome this limitation, we developed a novel semi-supervised pipeline for automated gene, protein, and functional domain annotation of SARS-CoV-2 genomes that differentiates itself by not relying on the use of a single reference genome and by overcoming atypical genomic traits that challenge traditional bioinformatic methods. We analyzed an initial corpus of 66,000 SARS-CoV-2 genome sequences collected from labs across the world using our method and identified the comprehensive set of known proteins with 98.5% set membership accuracy and 99.1% accuracy in length prediction, compared to proteome references, including Replicase polyprotein 1ab (with its transcriptional slippage site). Compared to other published tools, such as Prokka (base) and VAPiD, we yielded a 6.4- and 1.8-fold increase in protein annotations. Our method generated 13,000,000 gene, protein, and domain sequences-some conserved across time and geography and others representing emerging variants. We observed 3362 non-redundant sequences per protein on average within this corpus and described key D614G and N501Y variants spatiotemporally in the initial genome corpus. For spike glycoprotein domains, we achieved greater than 97.9% sequence identity to references and characterized receptor binding domain variants. We further demonstrated the robustness and extensibility of our method on an additional 4000 variant diverse genomes containing all named variants of concern and interest as of August 2021. In this cohort, we successfully identified all keystone spike glycoprotein mutations in our predicted protein sequences with greater than 99% accuracy as well as demonstrating high accuracy of the protein and domain annotations. This work comprehensively presents the molecular targets to refine biomedical interventions for SARS-CoV-2 with a scalable, high-accuracy method to analyze newly sequenced infections as they arise.

MagNet: Detecting Digital Presentation Attacks on Face Recognition.

Presentation attacks on face recognition systems are classified into two categories: physical and digital. While much research has focused on physical attacks such as photo, replay, and mask attacks, digital attacks such as morphing have received limited attention. With the advancements in deep learning and computer vision algorithms, several easy-to-use applications are available where with few taps/clicks, an image can be easily and seamlessly altered. Moreover, generation of synthetic images or modifying images/videos (e.g. creating deepfakes) is relatively easy and highly effective due to the tremendous improvement in generative machine learning models. Many of these techniques can be used to attack the face recognition systems. To address this potential security risk, in this research, we present a novel algorithm for digital presentation attack detection, termed as MagNet, using a "Weighted Local Magnitude Pattern" (WLMP) feature descriptor. We also present a database, termed as ID Age nder, which consists of three different subsets of swapping/morphing and neural face transformation. In contrast to existing research, which utilizes sophisticated machine learning networks for attack generation, the databases in this research are prepared using social media platforms that are readily available to everyone with and without any malicious intent. Experiments on the proposed database, FaceForensic database, GAN generated images, and real-world images/videos show the stimulating performance of the proposed algorithm. Through the extensive experiments, it is observed that the proposed algorithm not only yields lower error rates, but also provides computational efficiency.

Analysis and forecasting of global real time RT-PCR primers and probes for SARS-CoV-2.

Rapid tests for active SARS-CoV-2 infections rely on reverse transcription polymerase chain reaction (RT-PCR). RT-PCR uses reverse transcription of RNA into complementary DNA (cDNA) and amplification of specific DNA (primer and probe) targets using polymerase chain reaction (PCR). The technology makes rapid and specific identification of the virus possible based on sequence homology of nucleic acid sequence and is much faster than tissue culture or animal cell models. However the technique can lose sensitivity over time as the virus evolves and the target sequences diverge from the selective primer sequences. Different primer sequences have been adopted in different geographic regions. As we rely on these existing RT-PCR primers to track and manage the spread of the Coronavirus, it is imperative to understand how SARS-CoV-2 mutations, over time and geographically, diverge from existing primers used today. In this study, we analyze the performance of the SARS-CoV-2 primers in use today by measuring the number of mismatches between primer sequence and genome targets over time and spatially. We find that there is a growing number of mismatches, an increase by 2% per month, as well as a high specificity of virus based on geographic location.

Image-histogram-based secondary electron counting to evaluate detective quantum efficiency in SEM.

Scanning electron microscopy is a powerful tool for nanoscale imaging of organic and inorganic materials. An important metric for characterizing the limits of performance of these microscopes is the Detective Quantum Efficiency (DQE), which measures the fraction of emitted secondary electrons (SEs) that are detected by the SE detector. However, common techniques for measuring DQE approximate the SE emission process to be Poisson distributed, which can lead to incorrect DQE values. In this paper, we introduce a technique for measuring DQE in which we directly count the mean number of secondary electrons detected from a sample using image histograms. This technique does not assume Poisson distribution of SEs and makes it possible to accurately measure DQE for a wider range of imaging conditions. As a demonstration of our technique, we map the variation of DQE as a function of working distance in the microscope.

Focused-helium-ion-beam blow forming of nanostructures: radiation damage and nanofabrication.

Targeted irradiation of nanostructures by a finely focused ion beam provides routes to improved control of material modification and understanding of the physics of interactions between ion beams and nanomaterials. Here, we studied radiation damage in crystalline diamond and silicon nanostructures using a focused helium ion beam, with the former exhibiting extremely long-range ion propagation and large plastic deformation in a process visibly analogous to blow forming. We report the dependence of damage morphology on material, geometry, and irradiation conditions (ion dose, ion energy, ion species, and location). We anticipate that our method and findings will not only improve the understanding of radiation damage in isolated nanostructures, but will also support the design of new engineering materials and devices for current and future applications in nanotechnology.

A general theoretical and experimental framework for nanoscale electromagnetism.

The macroscopic electromagnetic boundary conditions, which have been established for over a century1, are essential for the understanding of photonics at macroscopic length scales. Even state-of-the-art nanoplasmonic studies2-4, exemplars of extremely interface-localized fields, rely on their validity. This classical description, however, neglects the intrinsic electronic length scales (of the order of ångström) associated with interfaces, leading to considerable discrepancies between classical predictions and experimental observations in systems with deeply nanoscale feature sizes, which are typically evident below about 10 to 20 nanometres5-10. The onset of these discrepancies has a mesoscopic character: it lies between the granular microscopic (electronic-scale) and continuous macroscopic (wavelength-scale) domains. Existing top-down phenomenological approaches deal only with individual aspects of these omissions, such as nonlocality11-13 and local-response spill-out14,15. Alternatively, bottom-up first-principles approaches-for example, time-dependent density functional theory16,17-are severely constrained by computational demands and thus become impractical for multiscale problems. Consequently, a general and unified framework for nanoscale electromagnetism remains absent. Here we introduce and experimentally demonstrate such a framework-amenable to both analytics and numerics, and applicable to multiscale problems-that reintroduces the electronic length scale via surface-response functions known as Feibelman d parameters18,19. We establish an experimental procedure to measure these complex dispersive surface-response functions, using quasi-normal-mode perturbation theory and observations of pronounced nonclassical effects. We observe nonclassical spectral shifts in excess of 30 per cent and the breakdown of Kreibig-like broadening in a quintessential multiscale architecture: film-coupled nanoresonators, with feature sizes comparable to both the wavelength and the electronic length scale. Our results provide a general framework for modelling and understanding nanoscale (that is, all relevant length scales above about 1 nanometre) electromagnetic phenomena.

Exploring proximity effects and large depth of field in helium ion beam lithography: large-area dense patterns and tilted surface exposure.

Helium ion beam lithography (HIL) is an emerging nanofabrication technique. It benefits from a reduced interaction volume compared to that of an electron beam of similar energy, and hence reduced long-range scattering (proximity effect), higher resist sensitivity and potentially higher resolution. Furthermore, the small angular spread of the helium ion beam gives rise to a large depth of field. This should enable patterning on tilted and curved surfaces without the need of any additional adjustments, such as laser-auto focus. So far, most work on HIL has been focused on exploiting the reduced proximity effect to reach single-digit nanometer resolution, and has thus been concentrated on single-pixel exposures over small areas. Here we explore two new areas of application. Firstly, we investigate the proximity effect in large-area exposures and demonstrate HIL's capabilities in fabricating precise high-density gratings on large planar surfaces (100 µm × 100 µm, with pitch down to 35 nm) using an area dose for exposure. Secondly, we exploit the large depth of field by making the first HIL patterns on tilted surfaces (sample stage tilted 45°). We demonstrate a depth of field greater than 100 µm for a resolution of about 20 nm.

A nanofabricated, monolithic, path-separated electron interferometer.

Progress in nanofabrication technology has enabled the development of numerous electron optic elements for enhancing image contrast and manipulating electron wave functions. Here, we describe a modular, self-aligned, amplitude-division electron interferometer in a conventional transmission electron microscope. The interferometer consists of two 45-nm-thick silicon layers separated by 20 µm. This interferometer is fabricated from a single-crystal silicon cantilever on a transmission electron microscope grid by gallium focused-ion-beam milling. Using this interferometer, we obtain interference fringes in a Mach-Zehnder geometry in an unmodified 200 kV transmission electron microscope. The fringes have a period of 0.32 nm, which corresponds to the [1̄1̄1] lattice planes of silicon, and a maximum contrast of 15%. We use convergent-beam electron diffraction to quantify grating alignment and coherence. This design can potentially be scaled to millimeter-scale, and used in electron holography. It could also be applied to perform fundamental physics experiments, such as interaction-free measurement with electrons.