Slimmable transformer with hybrid axial-attention for medical image segmentation.

The transformer architecture has achieved remarkable success in medical image analysis owing to its powerful capability for capturing long-range dependencies. However, due to the lack of intrinsic inductive bias in modeling visual structural information, the transformer generally requires a large-scale pre-training schedule, limiting the clinical applications over expensive small-scale medical data. To this end, we propose a slimmable transformer to explore intrinsic inductive bias via position information for medical image segmentation. Specifically, we empirically investigate how different position encoding strategies affect the prediction quality of the region of interest (ROI) and observe that ROIs are sensitive to different position encoding strategies. Motivated by this, we present a novel Hybrid Axial-Attention (HAA) that can be equipped with pixel-level spatial structure and relative position information as inductive bias. Moreover, we introduce a gating mechanism to achieve efficient feature selection and further improve the representation quality over small-scale datasets. Experiments on LGG and COVID-19 datasets prove the superiority of our method over the baseline and previous works. Internal workflow visualization with interpretability is conducted to validate our success better; the proposed slimmable transformer has the potential to be further developed into a visual software tool for improving computer-aided lesion diagnosis and treatment planning.

In-Depth Retinal Sensitivity Assessment With the MP3 Type S Microperimeter: A Methods Study.

Purpose: Retinal sensitivity is frequently listed as an end point in clinical trials, often with long working practices. The purpose of this methods study was to provide a new workflow and reduced test time for in-depth characterization of retinal sensitivity. Methods: A workflow for the MP3-S microperimeter with detailed functional characterization of the retina under photopic, mesopic, and scotopic conditions was evaluated. Grids of 32 and 28 test positions for photopic/mesopic and scotopic, respectively, were tested in 12 healthy individuals and compared with an established 68-point grid for test time, mean sensitivity (MS), and bivariate contour ellipse area (BCEA). Results: The mean test time (range; ±SD) was 10.5 minutes (8.4-14.9; ±2.0) in the 68-point grid and 4.3 minutes (3.8-5.0; ±0.4) in the 32-point grid, which was significantly different (P < 0.0001). The mean of difference in test time (±SD; 95% confidence interval) was 6.1 minutes (±2.0; 4.6-7.6). MS and BCEA were significantly correlated between grids (r = 0.89 and 0.74; P = 0.0005 and 0.014, respectively). Mean test time of subjects who underwent the full protocol (n = 4) was 2.15 hours. Conclusions: The protocol suggested herein appears highly feasible with in-depth characterization of retinal function under different testing conditions and in a short test time. Translational Relevance: The protocol described herein allows for characterization of the retina under different testing conditions and in a short test time, which is relevant due to its potential for patient prognostication and follow-up in clinical settings and also given its increasing role as a clinical trial end point.

CITEViz: interactively classify cell populations in CITE-Seq via a flow cytometry-like gating workflow using R-Shiny.

BACKGROUND: The rapid advancement of new genomic sequencing technology has enabled the development of multi-omic single-cell sequencing assays. These assays profile multiple modalities in the same cell and can often yield new insights not revealed with a single modality. For example, Cellular Indexing of Transcriptomes and Epitopes by Sequencing (CITE-Seq) simultaneously profiles the RNA transcriptome and the surface protein expression. The surface protein markers in CITE-Seq can be used to identify cell populations similar to the iterative filtration process in flow cytometry, also called "gating", and is an essential step for downstream analyses and data interpretation. While several packages allow users to interactively gate cells, they often do not process multi-omic sequencing datasets and may require writing redundant code to specify gate boundaries. To streamline the gating process, we developed CITEViz which allows users to interactively gate cells in Seurat-processed CITE-Seq data. CITEViz can also visualize basic quality control (QC) metrics allowing for a rapid and holistic evaluation of CITE-Seq data. RESULTS: We applied CITEViz to a peripheral blood mononuclear cell CITE-Seq dataset and gated for several major blood cell populations (CD14 monocytes, CD4 T cells, CD8 T cells, NK cells, B cells, and platelets) using canonical surface protein markers. The visualization features of CITEViz were used to investigate cellular heterogeneity in CD14 and CD16-expressing monocytes and to detect differential numbers of detected antibodies per patient donor. These results highlight the utility of CITEViz to enable the robust classification of single cell populations. CONCLUSIONS: CITEViz is an R-Shiny app that standardizes the gating workflow in CITE-Seq data for efficient classification of cell populations. Its secondary function is to generate basic feature plots and QC figures specific to multi-omic data. The user interface and internal workflow of CITEViz uniquely work together to produce an organized workflow and sensible data structures for easy data retrieval. This package leverages the strengths of biologists and computational scientists to assess and analyze multi-omic single-cell datasets. In conclusion, CITEViz streamlines the flow cytometry gating workflow in CITE-Seq data to help facilitate novel hypothesis generation.

A Perspective on Crowdsourcing and Human-in-the-Loop Workflows in Precision Health.

Modern machine learning approaches have led to performant diagnostic models for a variety of health conditions. Several machine learning approaches, such as decision trees and deep neural networks, can, in principle, approximate any function. However, this power can be considered to be both a gift and a curse, as the propensity toward overfitting is magnified when the input data are heterogeneous and high dimensional and the output class is highly nonlinear. This issue can especially plague diagnostic systems that predict behavioral and psychiatric conditions that are diagnosed with subjective criteria. An emerging solution to this issue is crowdsourcing, where crowd workers are paid to annotate complex behavioral features in return for monetary compensation or a gamified experience. These labels can then be used to derive a diagnosis, either directly or by using the labels as inputs to a diagnostic machine learning model. This viewpoint describes existing work in this emerging field and discusses ongoing challenges and opportunities with crowd-powered diagnostic systems, a nascent field of study. With the correct considerations, the addition of crowdsourcing to human-in-the-loop machine learning workflows for the prediction of complex and nuanced health conditions can accelerate screening, diagnostics, and ultimately access to care.

Automating the Illumina DNA library preparation kit for whole genome sequencing applications on the flowbot ONE liquid handler robot.

Whole-genome sequencing (WGS) is currently making its transition from research tool into routine (clinical) diagnostic practice. The workflow for WGS includes the highly labor-intensive library preparations (LP), one of the most critical steps in the WGS procedure. Here, we describe the automation of the LP on the flowbot ONE robot to minimize the risk of human error and reduce hands-on time (HOT). For this, the robot was equipped, programmed, and optimized to perform the Illumina DNA Prep automatically. Results obtained from 16 LP that were performed both manually and automatically showed comparable library DNA yields (median of 1.5-fold difference), similar assembly quality values, and 100% concordance on the final core genome multilocus sequence typing results. In addition, reproducibility of results was confirmed by re-processing eight of the 16 LPs using the automated workflow. With the automated workflow, the HOT was reduced to 25 min compared to the 125 min needed when performing eight LPs using the manual workflow. The turn-around time was 170 and 200 min for the automated and manual workflow, respectively. In summary, the automated workflow on the flowbot ONE generates consistent results in terms of reliability and reproducibility, while significantly reducing HOT as compared to manual LP.

Effect of different fabrication workflows on the passive fit of screw-retained bar splinting two interforaminal implants: a parallel blinded randomised clinical trial.

BACKGROUND: To clinically compare the effect of the conventional and the digital workflows on the passive fit of a screw retained bar splinting two inter-foraminal implants. METHODS: The current study was designed to be a parallel triple blinded randomised clinical trial. Thirty six completely edentulous patients were selected and simply randomized into two groups; conventional group (CG) and digital group (DG). The participants, investigator and outcome assessor were blinded. In the group (CG), the bar was constructed following a conventional workflow in which an open top splinted impression and a lost wax casting technology were used. However, in group (DG), a digital workflow including a digital impression and a digital bar milling technology was adopted. Passive fit of each bar was then evaluated clinically by applying the screw resistance test using the "flag" technique in the passive and non passive situations. The screw resistance test parameter was also calculated. Unpaired t-test was used for intergroup comparison. P-value < 0.05 was the statistical significance level. The study protocol was reviewed by the Research Ethics Committee in the author's university (Rec IM051811). Registration of the clinical trial was made on clinical trials.gov ID NCT05770011. An informed consent was obtained from all participants. RESULTS: Non statistically significant difference was denoted between both groups in all situations. In the passive situation, the mean ± standard deviation values were 1789.8° ± 20.7 and1786.1° ± 30.7 for the groups (CG) and (DG) respectively. In the non passive situation, they were 1572.8° ± 54.2 and 1609.2° ± 96.9. Regarding the screw resistance test parameter, they were 217° ± 55.3 and 176° ± 98.8. CONCLUSION: Conventional and digital fabrication workflows had clinically comparable effect on the passive fit of screw retained bar attachments supported by two dental implants.

Deep learning workflow to support in-flight processing of digital aerial imagery for wildlife population surveys.

Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.

Standardised Versioning of Datasets: a FAIR-compliant Proposal.

This paper presents a standardised dataset versioning framework for improved reusability, recognition and data version tracking, facilitating comparisons and informed decision-making for data usability and workflow integration. The framework adopts a software engineering-like data versioning nomenclature ("major.minor.patch") and incorporates data schema principles to promote reproducibility and collaboration. To quantify changes in statistical properties over time, the concept of data drift metrics (d) is introduced. Three metrics (dP, dE,PCA, and dE,AE) based on unsupervised Machine Learning techniques (Principal Component Analysis and Autoencoders) are evaluated for dataset creation, update, and deletion. The optimal choice is the dE,PCA metric, combining PCA models with splines. It exhibits efficient computational time, with values below 50 for new dataset batches and values consistent with seasonal or trend variations. Major updates (i.e., values of 100) occur when scaling transformations are applied to over 30% of variables while efficiently handling information loss, yielding values close to 0. This metric achieved a favourable trade-off between interpretability, robustness against information loss, and computation time.

An Optimized Genotyping Workflow for Identifying Highly SCRaMbLEd Synthetic Yeasts.

Synthetic Sc2.0 yeast strains contain hundreds to thousands of loxPsym recombination sites that allow restructuring of the Saccharomyces cerevisiae genome by SCRaMbLE. Thus, a highly diverse yeast population can arise from a single genotype. The selection of genetically diverse candidates with rearranged synthetic chromosomes for downstream analysis requires an efficient and straightforward workflow. Here we present loxTags, a set of qPCR primers for genotyping across loxPsym sites to detect not only deletions but also inversions and translocations after SCRaMbLE. To cope with the large number of amplicons, we generated qTagGer, a qPCR genotyping primer prediction tool. Using loxTag-based genotyping and long-read sequencing, we show that light-inducible Cre recombinase L-SCRaMbLE can efficiently generate diverse recombination events when applied to Sc2.0 strains containing a linear or a circular version of synthetic chromosome III.

Serum micro-RNAs with mutation-targeted RNA modification: a potent cancer detection tool constructed using an optimized machine learning workflow.

RNA modifications affect fundamental biological processes and diseases and are a research hotspot. Several micro-RNAs (miRNAs) exhibit genetic variant-targeted RNA modifications that can greatly alter their biofunctions and influence their effect on cancer. Therefore, the potential role of these miRNAs in cancer can be implicated in new prevention and treatment strategies. In this study, we determined whether RMvar-related miRNAs were closely associated with tumorigenesis and identified cancer-specific signatures based on these miRNAs with variants targeting RNA modifications using an optimized machine learning workflow. An effective machine learning workflow, combining least absolute shrinkage and selection operator analyses, recursive feature elimination, and nine types of machine learning algorithms, was used to screen candidate miRNAs from 504 serum RMvar-related miRNAs and construct a diagnostic signature for cancer detection based on 43,047 clinical samples (with an area under the curve value of 0.998, specificity of 93.1%, and sensitivity of 99.3% in the validation cohort). This signature demonstrated a satisfactory diagnostic performance for certain cancers and different conditions, including distinguishing early-stage tumors. Our study revealed the close relationship between RMvar-related miRNAs and tumors and proposed an effective cancer screening tool.

3D printing vs traditional workflow for the fabrication of mandibular implant overdentures: study protocol for a mixed-methods cross-over RCT.

BACKGROUND: Complete tooth loss is a significant global oral health issue, particularly impacting older individuals with lower socioeconomic status. Computer-assisted technologies enhance oral healthcare access by the elderly. Despite promising in vitro reports on digital denture materials, evidence from randomized clinical trials (RCTs) is lacking to verify their performance. This cross-over RCT will investigate whether 3D-printed implant-retained mandibular overdentures (IMO) are more satisfactory for edentulous seniors than those made through traditional methods. METHODS/DESIGN: We will recruit 26 completely edentulous participants (any sex/gender) based on the following eligibility criteria: age ≥ 60 years, no tooth extraction in the past 12 months, two implants in the lower jaw, and need for new dentures in both jaws. Each participant will receive two denture pairs, either manufactured by 3D printing or traditionally, to be worn in a random order. A timeline of 3 months with each denture pair will be considered for outcome assessment (total: 6 months). Patient satisfaction with dentures will be measured by the McGill Denture Satisfaction Questionnaire. We will evaluate other patient-reported outcomes (including oral health-related quality of life) as well as clinician-assessed quality and cost. At the end of the trial, participants will choose which denture pair they wish to keep and interviewed about their experiences with the 3D-printed IMO. The quantitative and qualitative data will be incorporated through an explanatory mixed-methods strategy. A final quantitative assessment will happen after 12 months with the preferred IMO to assess the long-term performance and maintenance needs. DISCUSSION: This mixed-methods RCT will explore patient experiences with 3D-printed IMOs, aiming to assess the potential for altering clinical practice and dental public health policies. Our results will inform policies by showing whether 3D printing offers comparable outcomes at lower costs, facilitating greater access to oral care for the elderly. TRIAL REGISTRATION: ClinicalTrials.gov, NCT06155630, Registered on 04 December 2023. https://classic. CLINICALTRIALS: gov/ct2/show/NCT06155630.

A covid-19 e a reorganização do processo de trabalho do enfermeiro na atenção primária à saúde / Covid-19 and the reorganization of the nurse's work process in primary health care / Covid-19 y la reorganización del proceso de trabajo de la enfermería en la atención primaria de salud

Objetivo: descrever a experiência da reorganização do processo de trabalho de enfermeiros que atuam na Atenção Primária à Saúde no enfrentamento da covid-19, no município de João Pessoa - Paraíba. Métodos: Trata-se de um estudo descritivo com abordagem qualitativa, desenvolvido com um total de 15 enfermeiras atuantes no município de João Pessoa com idade entre 41 e 67 anos (média de 56 anos) e com tempo médio de 12 anos e 8 meses de atuação na Estratégia Saúde da Família. Resultados: foram evidenciados um campo amplo de alterações na dinâmica das Unidades Básicas de Saúde devido a pandemia, dentre elas, modificações no processo de trabalho da equipe, a estagnação das atividades coletivas, como também a implementação de ações destinadas para a covid-19. Conclusão: As experiências relatadas das participantes do estudo ressaltam o grande impacto que a pandemia trouxe para o cotidiano de uma equipe de Atenção Básica, sendo fundamental o fortalecimento da atenção primária à saúde, com recursos financeiros, incentivo e qualificação profissional, garantindo uma maior adequação da nova realidade vivida, a fim de garantir continuidade do cuidado. (AU)

Objective: to describe the experience of the reorganization of the work process of nurses who work in Primary Health Care in the face of covid-19, in the city of João Pessoa - Paraíba. Methods: This is a descriptive study with a qualitative approach, developed with a total of 15 nurses working in the city of João Pessoa aged between 41 and 67 years (average of 56 years) and with an average time of 12 years and 8 months of performance in the Family Health Strategy. Results: a wide field of changes in the dynamics of Basic Health Units due to the pandemic were evidenced, among them, changes in the team's work process, the stagnation of collective activities, as well as the implementation of actions aimed at covid-19. Conclusion: The reported experiences of the study participants highlight the great impact that the pandemic has brought to the daily life of a Primary Care team, making it essential to strengthen primary health care, with financial resources, incentives and professional qualification, ensuring greater adequacy. of the new lived reality, in order to guarantee continuity of care. (AU)

Objetivo: describir la experiencia de la reorganización del proceso de trabajo de los enfermeros que actúan en la Atención Primaria de Salud frente a la covid-19, en la ciudad de João Pessoa - Paraíba. Métodos: Se trata de un estudio descriptivo con enfoque cualitativo, desarrollado con un total de 15 enfermeros que actúan en la ciudad de João Pessoa con edades entre 41 y 67 años (promedio de 56 años) y con tiempo promedio de 12 años y 8 meses de vida. desempeño en la Estrategia de Salud de la Familia. Resultados: Se evidenció un amplio campo de cambios en la dinámica de las Unidades Básicas de Salud debido a la pandemia, entre ellos, cambios en el proceso de trabajo del equipo, el estancamiento de las actividades colectivas, así como la implementación de acciones dirigidas a la covid-19. Conclusión: Las experiencias relatadas por los participantes del estudio resaltan el gran impacto que la pandemia trajo para el cotidiano de un equipo de Atención Primaria, siendo imprescindible fortalecer la atención primaria de salud, con recursos económicos, incentivos y calificación profesional, asegurando una mayor adecuación. de la nueva realidad vivida, para garantizar la continuidad de la atención. (AU)

Workflow efficiencies for flexible cystoscopy: comparing single-use vs reusable cystoscopes.

BACKGROUND: Flexible cystoscopy is a common procedure to diagnose and treat lower urinary tract conditions. Single-use cystoscopes have been introduced to eliminate time-consuming reprocessing and costly repairs. We compared the hands-on labor time differences between flexible reusable cystoscopes versus Ambu's aScope™ 4 Cysto (aS4C) at a large urology Ambulatory Surgery Center (ASC). METHODS: Reusable and single-use cystoscopy procedures were shadowed for timestamp collection for setup and breakdown. A subset of reusable cystoscopes were followed through the reprocessing cycle. T-tests were calculated to measure the significance between groups. RESULTS: The average hands-on time necessary for reusable cystoscope preparation, breakdown, and pre-cleaning was 4'53″. Of this, 2'53″ were required for preparation, while 2'0″ were required for breakdown and pre-cleaning. The average hands-on time for reprocessing for reusable was 7'1" per cycle. The total time for single-use scopes was 2'22″. Of this, 1'36″ was needed for single-use preparation, and 45 s for breakdown. Compared to reusable cystoscopes, single-use cystoscopes significantly reduced pre and post-procedure hands-on labor time by 2'31", or 48%. When including reprocessing, total hands-on time was 80% greater for reusable than single-use cystoscopes. CONCLUSION: Single-use cystoscopes significantly reduced hands-on labor time compared to reusable cystoscopes. On average, the facility saw a reduction of 2'31″ per cystoscope for each procedure. This translates to 20 additional minutes gained per day, based on an 8 procedures per day. Utilizing single-use cystoscopes enabled the facility to reduce patient wait times, decrease turnaround times, and free up staff time.

Quantification of surgical workflow during robotic proctectomy.

BACKGROUND: Surgical workflow assessments offer insight regarding procedure variability. We utilised an objective method to evaluate workflow during robotic proctectomy (RP). METHODS: We annotated 31 RPs and used Spearman's correlation to measure the correlation of step time and step visit frequency with console time (CT) and total operative time (TOT). RESULTS: Strong correlations were seen with CT and step times for inferior mesenteric vein dissection and ligation (ρ = 0.60, ρ = 0.60), lateral-to-medial splenic flexure mobilisation (SFM) (ρ = 0.63), left rectal dissection (ρ = 0.64) and mesorectal division (ρ = 0.71). CT correlated strongly with medial-to-lateral (ρ = 0.75) and supracolic SFM visit frequency (ρ = 0.65). TOT correlated strongly with initial exposure time (ρ = 0.60), and medial-to-lateral (ρ = 0.67) and supracolic SFM visit frequency (ρ = 0.65). CONCLUSION: This study correlates surgical steps with CT and TOT through standardised annotation, providing an objective approach to quantify workflow.

Workflow interruptions in an era of instant messaging: A detailed analysis.

INTRODUCTION: The complex practice environment and responsibilities incumbent on diagnostic radiologists creates a workflow susceptible to disruption. While interruptions have been shown to contribute to medical errors in the healthcare delivery environment, the exact impact on highly subspecialized services such as diagnostic radiology is less certain. One potential source of workflow disruption is the use of a departmental instant messaging system (Webex), to facilitate communications between radiology faculty, residents, fellows, and technologists. A retrospective review was conducted to quantify the frequency of interruption experienced by our neuroradiology fellows. MATERIALS AND METHODS: Data logs were gathered comprising all instant messages sent and received within the designated group chats from July 5-December 31, 2021, during weekday shifts staffed by neuroradiology fellows. Interruptions per shift were calculated based on month, week, and day of the week. RESULTS: 14,424 messages were sent across 289 total shifts. The 6 fellows assigned to the main neuroradiology reading room sent 3258 messages and received 10,260 messages from technologists and other staff. There was an average of 50 interruptions per shift when examined by month (range 48-53), and 52 interruptions per shift when examined by day of the week (range 40-60). CONCLUSION: Neuroradiology fellows experience frequent interruptions from the departmental instant messaging system. These disruptions, when considered in conjunction with other non-interpretative tasks, may have negative implications for workflow efficiency, requiring iterative process improvements when incorporating new technology into the practice environment of diagnostic radiology.

AxoDetect: an automated nerve image segmentation and quantification workflow for computational nerve modeling.

Objective.Bioelectronic treatments targeting near-organ innervation have unprecedented clinical applications. Particularly in the spleen, the inhibition of the cholinergic inflammatory response by near-organ nerve stimulation has potential to replace pharmacological treatments in chronic and autoimmune diseases. A caveat is that the optimization of therapeutic stimulation parameters relies onin vivoexperimentation, which becomes challenging due to the small nerve diameters (2 µm), complex anatomy, and mixed axon type composition of the autonomic nerves. Effective development ofin silicomodels requires tools which allow for fast and efficient quantification of axonal composition of specific nerves. Current approaches to generate such information rely on manual image segmentation and quantification.Approach.We developed a combined image-segmentation and model-generation software called AxoDetect: a target- and format-agnostic computer vision algorithm which can segment myelin, endo/epineurium, and both myelinated and unmyelinated fibers from a nerve image without training.Main results.AxoDetect is over 10 times faster on average when compared with current automatic methods while maintaining flexibility through the use of tunable pixel threshold filters to detect different types of tissue. When compared to a distribution-based and a manually segmented model of the splenic nerve terminal branch 1, the model generated with AxoDetect had comparable threshold prediction and was able to accurately detect an increase in activation threshold caused by the addition of surrounding fat tissue to the modeled nerve.Significance.AxoDetect contributes to the acceleration of neuromodulation treatment development through faster model design and iteration without requiring training. Furthermore, the computer vision approach and tunable nature of the filters in our method allow for its use in a variety of histological applications. Our approach will impact not only the study of nerves but also the design of implantable neural interfaces to enhance bioelectronic therapeutic options.

On the pitfalls of Batch Normalization for end-to-end video learning: A study on surgical workflow analysis.

Batch Normalization's (BN) unique property of depending on other samples in a batch is known to cause problems in several tasks, including sequence modeling. Yet, BN-related issues are hardly studied for long video understanding, despite the ubiquitous use of BN in CNNs (Convolutional Neural Networks) for feature extraction. Especially in surgical workflow analysis, where the lack of pretrained feature extractors has led to complex, multi-stage training pipelines, limited awareness of BN issues may have hidden the benefits of training CNNs and temporal models end to end. In this paper, we analyze pitfalls of BN in video learning, including issues specific to online tasks such as a 'cheating' effect in anticipation. We observe that BN's properties create major obstacles for end-to-end learning. However, using BN-free backbones, even simple CNN-LSTMs beat the state of the art on three surgical workflow benchmarks by utilizing adequate end-to-end training strategies which maximize temporal context. We conclude that awareness of BN's pitfalls is crucial for effective end-to-end learning in surgical tasks. By reproducing results on natural-video datasets, we hope our insights will benefit other areas of video learning as well. Code is available at: https://gitlab.com/nct_tso_public/pitfalls_bn.

shinyMBA: a novel R shiny application for quality control of the multiplex bead assay for serosurveillance studies.

The multiplex bead assay (MBA) based on Luminex xMAP technology can be used as a tool to measure seroprevalence as part of population immunity evaluations to multiple antigens in large-scale serosurveys. However, multiplexing several antigens presents challenges for quality control (QC) assessments of the data because multiple parameters must be evaluated for each antigen. MBA QC parameters include monitoring bead counts and median fluorescence intensity (MFI) for each antigen in plate wells, and performance of assay controls included on each plate. Analyzing these large datasets to identify plates failing QC standards presents challenges for many laboratories. We developed a novel R Shiny application, shinyMBA, to expedite the MBA QC processes and reduce the risk of user error. The app allows users to rapidly merge multi-plate assay outputs to evaluate bead count, MFI, and performance of assay controls using statistical process control charts for all antigen targets simultaneously. The utility of the shinyMBA application and its various outputs are demonstrated using data from 32 synthetic xPONENT files with 3 multiplex antigens and two population serosurveillance studies that evaluated 1200 and 3871 samples, respectively, for 20 multiplexed antigens. The shinyMBA open-source code is available for download and modification at https://github.com/CDCgov/shinyMBA . Incorporation of shinyMBA into Luminex serosurveillance workflows can vastly improve the speed and accuracy of QC processes.

Data-Independent Acquisition Peptidomics.

In recent years, data-independent acquisition (DIA) has emerged as a powerful analysis method in biological mass spectrometry (MS). Compared to the previously predominant data-dependent acquisition (DDA), it offers a way to achieve greater reproducibility, sensitivity, and dynamic range in MS measurements. To make DIA accessible to non-expert users, a multifunctional, automated high-throughput pipeline DIAproteomics was implemented in the computational workflow framework "Nextflow" ( https://nextflow.io ). This allows high-throughput processing of proteomics and peptidomics DIA datasets on diverse computing infrastructures. This chapter provides a short summary and usage protocol guide for the most important modes of operation of this pipeline regarding the analysis of peptidomics datasets using the command line. In brief, DIAproteomics is a wrapper around the OpenSwathWorkflow and relies on either existing or ad-hoc generated spectral libraries from matching DDA runs. The OpenSwathWorkflow extracts chromatograms from the DIA runs and performs chromatographic peak-picking. Further downstream of the pipeline, these peaks are scored, aligned, and statistically evaluated for qualitative and quantitative differences across conditions depending on the user's interest. DIAproteomics is open-source and available under a permissive license. We encourage the scientific community to use or modify the pipeline to meet their specific requirements.