Workflow Optimization Research Articles

Abstract 6185: Generative AI for virtual HE-staining of whole slide images of unstained breast cancer tissue

Abstract Introduction Hematoxylin and eosin (HE) is the standard stain used in histology to make tissue visible to the human eye by highlighting certain cellular and tissue structures, and it is a technique that is widely used in the diagnosis of cancer and other pathologies. Chemical staining, however, is irreversible, making the tissue unusable for subsequent measurements, such as spatial transcriptomics. Here we utilize generative AI method based on pix2pix image-to-image translation to generate virtual HE-staining for whole slide images (WSIs) acquired of unstained tissue with brightfield microscopy and perform a thorough histological evaluation for the feasibility in breast cancer diagnostics. Materials and Methods We optimized sample preparation and imaging setup for virtual staining purposes, and developed a custom generative adversarial network architecture for learning the virtual staining from paires samples of unstained and H&E stained tissue. Here, we focus on the utility of virtual staining in breast cancer diagnostics, using a set of breast cancer samples for acquiring whole slide images from unstained tissue before H&E staining and from reference H&E stained tissue after chemical staining. Hold-out set of sample pairs are left for validation, allowing us to evaluate the virtual staining performance for a vast array of tissue components and to examine the potential shortcomings in staining reproduction. We use a comprehensive set of quantitative metrics both on pixel and object level to evaluate virtual staining quality. In addition, we perform thorough visual evaluation of histological feasibility by histology experts to examine the computational staining. Results We demonstrate that by careful optimization of both sample preparation and imaging workflow, as well as the computational methods, generative adversarial networks can be used for virtual staining of whole slide images of breast cancer tissue acquired from unstained tissue using regular bright field microscopy. We analyzed the virtual staining performance quantitatively and visually, and highlight the potential of the method through successful cases and demonstrate the applicability in breast cancer diagnostics, as well as discuss the challenges and shortcomings of virtual staining for clinical samples. Conclusions We demonstrate the potential of virtual HE staining for clinical histopathology of breast cancer tissue. Notably, our virtual staining based on generative AI shows promise towards more sustainable and streamlined sample processing and staining process in digital pathology. Citation Format: Leena Latonen, Umair Khan, Sonja Koivukoski, Johan Hartman, Pekka Ruusuvuori. Generative AI for virtual HE-staining of whole slide images of unstained breast cancer tissue [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6185.

Application of Machine Learning and Optimization of Oil Recovery and CO2 Sequestration in the Tight Oil Reservoir

Summary In recent years, shale and tight reservoirs have become an essential source of hydrocarbon production since advanced multistage and horizontal drilling techniques were developed. Tight oil reservoirs contain huge oil reserves but suffer from low recovery factors. For tight oil reservoirs, CO2-water alternating gas (CO2-WAG) is one of the preferred tertiary methods to enhance the overall cumulative oil production while also sequestering significant amounts of injected CO2. However, the evaluation of CO2-WAG is strongly dependent on the injection parameters, which renders numerical simulations computationally expensive. In this study, a novel approach has been developed that utilized machine learning (ML)-assisted computational workflow in optimizing a CO2-WAG project for a low-permeability oil reservoir considering both hydrocarbon recovery and CO2 storage efficacies. To make the predictive model more robust, two distinct proxy models—multilayered neural network (MLNN) models coupled with particle swarm optimization (PSO) and genetic algorithms (GAs)—were trained and optimized to forecast the cumulative oil production and CO2 storage. Later, the optimized results from the two algorithms were compared. The optimized workflow was used to maximize the predefined objective function. For this purpose, a field-scaled numerical simulation model of the Changqing Huang 3 tight oil reservoir was constructed. By December 2060, the base case predicts a cumulative oil production of 0.368 million barrels (MMbbl) of oil, while the MLNN-PSO and MLNN-GA forecast 0.389 MMbbl and 0.385 MMbbl, respectively. As compared with the base case (USD 150.5 million), MLNN-PSO and MLNN-GA predicted a further increase in the oil recovery factor by USD 159.2 million and USD 157.6 million, respectively. In addition, the base case predicts a CO2 storage amount of 1.09×105 tons, whereas the estimates from MLNN-PSO and MLNN-GA are 1.26×105 tons and 1.21×105 tons, respectively. Compared with the base case, CO2 storage for the MLNN-PSO and MLNN-GA increased by 15.5% and 11%, respectively. In terms of the performance analysis of the two algorithms, both showed remarkable performance. PSO-developed proxies were 16 times faster and GA proxies were 10 times faster as compared with the reservoir simulation in finding the optimal solution. The developed optimization workflow is extremely efficient and computationally robust. The experiences and lessons will provide valuable insights into the decision-making process and in optimizing the Changqing Huang 3 low-permeability oil reservoir.

Psychological and Social-Communication Aspects of HR Management Career in Wartime, Including Stress, Motivation, Will and Efficiency of Working Conditions

The initiation of a full-scale invasion of Ukraine by the Russian Federation, coupled with the imposition of martial law, has prompted a paradigm shift in the comprehension of psychological and socio-communication dimensions inherent in the management of human resources. This underscores the significance of the present work. The primary objective of this study is to conduct a thorough examination of stress, motivation, will, and the efficacy of working conditions as integral components constituting the psychological and socio-communication facets of HR management during wartime. The article employs methodological approaches such as analysis, synthesis, scientific generalization, and the formal logical method. The business landscape in Ukraine, under the constraints of martial law, is marked by diminished production volumes, logistical and supply chain challenges, and financial constraints. In this pivotal juncture, human resources (HR) management necessitates the systematic implementation of planning, organization, motivation, control, and regulation. Presently, structural adjustments in HR management encompass elements such as flexible management, decentralization, integration, privatization, heightened innovation, organizational workflow optimization, and enhancement of the quality of working life. Furthermore, there is a noticeable escalation in individuals' interest in self-management. Motivating personnel amid a military conflict poses inherent challenges, given that warfare induces stress, anxiety, and restlessness among employees. Stress, in a general sense, constitutes the body's defensive response to threats or tension, and its adverse impacts on HR management become particularly pronounced in the context of military conflicts, where these factors synergistically manifest.

The Future of Artificial Intelligence in Sports Medicine and Return to Play.

Artificial intelligence (AI) has shown tremendous growth over the last decade, with the more recent development of clinical applications in health care. The ability of AI to synthesize large amounts of complex data automatically allows health care providers to access previously unavailable metrics and thus enhance and personalize patient care. These innovations include AI-assisted diagnostic tools, prediction models for each treatment pathway, and various tools for workflow optimization. The extension of AI into sports medicine is still early, but numerous AI-driven algorithms, devices, and research initiatives have delved into predicting and preventing athlete injury, aiding in injury assessment, optimizing recovery plans, monitoring rehabilitation progress, and predicting return to play.

Surface-guided radiotherapy systems in locoregional deep inspiration breath hold radiotherapy for breast cancer - a multicenter study on the setup accuracy.

Daily image-guided radiotherapy (IGRT) and deep inspiration breath hold (DIBH) technique are recommended for locoregional RT of breast cancer. The optimal workflow for a combination of surface-guided RT (SGRT) with DIBH technique is of current clinical interest. The setup accuracy at three hospitals was evaluated using different SGRT workflows. A total of 150 patients (2269 image pairs) were analyzed in three groups: patient setup with the AlignRT® SGRT system in Tampere (Site 1, n = 50), the Catalyst™ SGRT system in Turku (Site 2, n = 50) and the Catalyst™ SGRT system in Jönköping (Site 3, n = 50). Each site used their routine workflow with SGRT-based setup and IGRT positioning. Residual errors of the bony chest wall, thoracic vertebra (Th 1) and humeral head were evaluated using IGRT images. Systematic residual errors in the cranio-caudal (CC) direction and in pitch were generally larger at Site 2 than those at Sites 1 and 3 (p = 0.01-0.7). With daily IGRT, only a small difference (p = 0.01-0.9) was observed in residual random errors of bony structures in other directions between sites. The introduction of SGRT and the use of daily IGRT lead to small residual errors when combining the best workflow practices from different hospitals. Our multicenter evaluation led to improved workflow by tightening the SGRT tolerances on Site 2 and fixation modification. Because of mainly small random errors, systematic posture errors in the images need to be corrected after posture correction with new setup surfaces. We recommend tight SGRT tolerances, good fixation and correction of systematic errors.

Asynchronous consult report generation for pharmacogenomic clinical support: Time and motion

As pharmacogenomic (PGx) testing becomes more commonplace in clinical practice, appropriate application of laboratory data to all relevant medications becomes necessary to maximize PGx value. However, many clinicians lack PGx knowledge and confidence, so prescribers may appreciate clinical support when applying PGx data to a patient's entire medication list. Pharmacists routinely provide PGx consult support, and asynchronous written consults may improve logistical simplicity, but specific process steps and time expectations are less settled. Four pharmacists produced written consult reports for 18 patient cases across three rounds of review. Discussion took place before each of the three rounds to drive consensus in steps, process, and resources used. Time per process step was tracked in the third round. Asynchronous written PGx consult reports generally required less than 30 min to generate if no more than 2 medications had PGx-based guidance, but that time more than doubled when more medications require PGx-based guidance. After three rounds of review, pharmacists found consensus regarding an optimal workflow for generating a PGx consult. Findings from this study may support pharmacist training, practice management, and expectation management for asynchronous written PGx consult development.

Optimizing Workflow Efficiency in Digital Printing Imposition: A Visual Tutorial on Design Impact Printing Methods

The rapid evolution of digital printing technologies has necessitated a parallel advancement in imposition workflows to ensure maximum efficiency, cost-effectiveness, and high-quality results. The purpose of this study sought to outline a visual tutorial focused on the intersection of design impact and workflow optimization in the realm of digital printing imposition. In an attempt, the study demonstrated the benefits of template-based imposition for standardized layouts and design consistency using imposer pro software. As a qualitative research method, the study adopted case study design on a visual tutorial approach, utilizing a combination of images, diagrams, and video explanatory text to present step-by-step guides and examples. The content was structured to cover fundamental concepts, software selection, template-based imposition, automation and variable data printing (VDP) integration. The outcome of the study revealed that the tutorial's visual format effectively communicated the intricacies of optimizing workflow efficiency in digital printing imposition. The study encourages design practitioners to leverage the tutorial as a practical resource for achieving efficiency gains, reducing turnaround times, and elevating design impact in the rapidly evolving digital printing landscape.

Automated workflow for characterization of bacteriocin production in natural producers Lactococcus lactis and Latilactobacillus sakei

BackgroundLactic acid bacteria are commonly used as protective starter cultures in food products. Among their beneficial effects is the production of ribosomally synthesized peptides termed bacteriocins that kill or inhibit food-spoiling bacteria and pathogens, e.g., members of the Listeria species. As new bacteriocins and producer strains are being discovered rapidly, modern automated methods for strain evaluation and bioprocess development are required to accelerate screening and development processes.ResultsIn this study, we developed an automated workflow for screening and bioprocess optimization for bacteriocin producing lactic acid bacteria, consisting of microcultivation, sample processing and automated antimicrobial activity assay. We implemented sample processing workflows to minimize bacteriocin adsorption to producer cells via addition of Tween 80 and divalent cations to the cultivation media as well as acidification of culture broth prior to cell separation. Moreover, we demonstrated the applicability of the automated workflow to analyze influence of media components such as MES buffer or yeast extract for bacteriocin producers Lactococcus lactis B1629 and Latilactobacillus sakei A1608.ConclusionsOur automated workflow provides advanced possibilities to accelerate screening and bioprocess optimization for natural bacteriocin producers. Based on its modular concept, adaptations for other strains, bacteriocin products and applications are easily carried out and a unique tool to support bacteriocin research and bioprocess development is provided.

Designing workflows for materials characterization

Experimental science is enabled by the combination of synthesis, imaging, and functional characterization organized into evolving discovery loop. Synthesis of new material is typically followed by a set of characterization steps aiming to provide feedback for optimization or discover fundamental mechanisms. However, the sequence of synthesis and characterization methods and their interpretation, or research workflow, has traditionally been driven by human intuition and is highly domain specific. Here, we explore concepts of scientific workflows that emerge at the interface between theory, characterization, and imaging. We discuss the criteria by which these workflows can be constructed for special cases of multiresolution structural imaging and functional characterization, as a part of more general material synthesis workflows. Some considerations for theory–experiment workflows are provided. We further pose that the emergence of user facilities and cloud labs disrupts the classical progression from ideation, orchestration, and execution stages of workflow development. To accelerate this transition, we propose the framework for workflow design, including universal hyperlanguages describing laboratory operation, ontological domain matching, reward functions and their integration between domains, and policy development for workflow optimization. These tools will enable knowledge-based workflow optimization; enable lateral instrumental networks, sequential and parallel orchestration of characterization between dissimilar facilities; and empower distributed research.

Atrial fibrillation ablation workflow optimization facilitated by high-power short-duration ablation and high-resolution mapping.

Pulmonary vein isolation (PVI) for catheter ablation of atrial fibrillation (AF) is a time-demanding procedure. High-power short-duration (HPSD) ablation protocols and high-density mapping catheters have recently been introduced to clinical practice. We investigated the impact of high-density mapping and HPSD ablation protocols on procedural timing, efficacy, and safety by comparing different standardized set-ups. Three electrophysiology (EP) laboratory set-ups were analysed: (i) circular catheter for mapping and HPSD ablation with 30/35 W guided by an ablation index (AI); (ii) pentaspline catheter for mapping an HPSD ablation with 50 W guided by an AI; and (iii) pentaspline catheter for mapping and HPSD ablation with 90 W over 4 s using a novel ablation catheter. All patients underwent PVI without additional left atrial ablation strategies. Procedural data and operating intervals in the EP laboratory were systematically analysed. Three hundred seven patients were analysed (30/35 W AI: n = 102, 50 W AI: n = 102, 90 W/4 s: n = 103). Skin-to-skin times [105.3 ± 22.7 (30/35 W AI) vs. 81.4 ± 21.3 (50 W AI) vs. 69.5 ± 12.2 (90 W/4 s) min, P ≤ 0.001] and total laboratory times (132.8 ± 42.1 vs. 107.4 ± 25.7 vs. 95.2 ± 14.0 min, P < 0.001) significantly differed among the study groups. Laboratory interval analysis revealed significant shortening of mapping and ablation times. Arrhythmia-free survival after 12 months was not different among the study groups (log-rank P = 0.96). The integration of high-density mapping and HPSD protocols into an institutional AF ablation process resulted in reduced procedure times without compromising safety or efficacy.

Workflow scheduling and optimization using evaluationary method and deep learning algorithm in cloud

Workflow scheduling and optimization using evaluationary method and deep learning algorithm in cloud

Workflow Optimization of Material Management Process by Digital Adoption in Indian Residential Projects

To analyze the present day’s material management process and the extent of digital adoption in the workflow; to identify the shortcomings in the present day’s practice; and to formulate digital inclusive framework to manage materials. Objectives 1 &amp; 2 is achieved through 3 step process – Literature review to identify the related shortcomings (factors) and online/ web search to explore available technology; Survey(s) to assess the real time status on the factors, to identify more practical difficulties and the extent of digital adoption in the workflow; Interviewing seasoned professions to gather data in detail with respect to material. Objective 3 is achieved by comparison and analysis of the findings. Validation of the framework to assess the potential effects – Partial validation is performed as part of this study. Workflow involved in construction material management is optimized via framework. Autodesk Revit, MS Project, and MS Access are the 3 platforms proposed to be part of the framework that suits every phase of the process like Quantity survey and Estimation, Procurement Planning, Inventory, Purchasing and Store Management. Partial framework - MS Project has been validated and the results are – Ability to map the data efficiently; Précised Budget &amp; material requirement identification resulted in an increase of 1% cost in the overall project budget; Easy Cross verification; Easy documentation; Data driven decision making; Multi - dimensional data visibility. The studies in the past have stressed on the benefits of digitalization and the willingness of construction sector in adopting the same. 2019, 2020 and 2021 studies have explored individual digital platform such as MSP, Primavera, and Revit in terms of part functions involved in material management. Whereas there is no study stating the order of workflow between these platforms for complete material management. Also, the studies in the past failed to identify and address the shortcomings related to the digital adoption. Hence, this study proposed a framework that determines the order of the workflow involved in material management between these digital platforms with an aim to optimizing the workflow.

Environmental performance driven optimization of urban modular housing layout in Singapore

ABSTRACT With the growing size of cities and the need to renew residential areas, architects are calling for more efficient use of already settled areas. This paper presents a performance-driven architectural design (PDAD) workflow for shape generation and genetic optimization based on environmental data, using public housing in the Singapore region as a case study. It integrates three-dimensional cellular automata, parametric performance simulation, genetic optimization algorithms, and hierarchical clustering algorithms. The results show that the average value of Useful Daylight Illuminance (UDI) is 85.19%, the average value of Energy Use Intensity (EUI) is 159.41 kWh/m2, and the average value of Predicted Mean Vote (PMV) is 0.64 for the optimal set of solutions produced after genetic optimization. The optimal solution set was further classified into 4 categories by a hierarchical clustering algorithm and was visualized for further evaluation and selection by the architect. The study helps architects to integrate data analysis results with human decision-making as a design research method in the early stages of design and leads to further discussion on bottom-up design approaches in the urban renewal process.

Automated Transition Metal Catalysts Discovery and Optimisation with AI and Machine Learning

AbstractSignificant progress has been made in recent years in the use of AI and Machine Learning (ML) for catalyst discovery and optimisation. The effectiveness of ML and data science techniques was demonstrated in predicting and optimising enantioselectivity and regioselectivity in catalytic reactions through optimisation of the ligands, counterions and reaction conditions. Direct discovery of new catalysts/reactions is more difficult and requires efficient exploration of transition metal chemical space. A range of computational techniques for descriptor generation, ranging from molecular mechanics to DFT methods, have been successfully demonstrated, often in conjunction with ML to reduce computational cost associated with TS calculations. Complex aspects of catalytic reactions, such as solvent, temperature, etc., have also been successfully incorporated into the ML optimisation and discovery workflow.

Gastric Emptying Studies in Pediatrics: A Cincinnati Children's Hospital Experience.

Gastric emptying studies are routinely performed in many nuclear medicine departments; however, there are many different techniques used to perform the procedure across the country. Creating consistency in clinical practice will aid gastroenterologists in diagnosing and treating illnesses associated with abnormalities related to gastric emptying. In 2017, Cincinnati Children's Hospital adopted adult standards for pediatric gastric emptying studies that included a standard meal along with imaging over the course of 4 h. Gastric emptying studies are the second-highest-volume examination performed in the nuclear medicine section at Cincinnati Children's Hospital. Accommodating this volume required changes in the scheduling template, scheduling questionnaire, and epic order sets, as well as identification of specific days and locations for gastric emptying studies. Both protocol standardization and workflow optimization are critically important in creating consistency in patient care. Gastric emptying can be evaluated with solid food, liquid food, or solid and liquid food simultaneously. The methodology of the study is initially determined by the ordering provider but may require special accommodations based on what the patient will tolerate. In coordination with the ordering and interpreting physicians, the nuclear medicine technologists at Cincinnati Children's Hospital have the decision-making ability to deviate from the provider's request as necessary, which helps expedite workflow and eliminates wasted time. Any deviation from the standardized protocol is documented by the nuclear medicine technologist and incorporated into the final report by the interpreting physician, as dietary information is meaningful to the ordering provider. Reference values associated with the standardized or modified protocol are also included in the final report.

Artificial intelligence (AI) in diagnostic imaging.

In the last few years artificial intelligence (AI) has increasingly become a topic of interest, especially in diagnostic imaging. There are two main expected potential benefits: workflow effectiveness and diagnostic support systems, particularly as far as quality assurance is concerned. To meet these objectives, it is necessary to define what artificial intelligence in medicine means and to discuss which detailed steps should be fulfilled, e. g., for MSK imaging in the daily routine. In addition, this article provides an overview of what is necessary for an efficient IT-based workflow including the clinical question, the choice of modalities and investigation protocols, structured reports, and clinical classification. This is particularly interesting for potential providers, who are keen to apply new soft skills to support imaging diagnostic processes. The use of AI-supported diagnostic imaging could result in a paradigm shift from a modality-oriented to a clinical problem-oriented workflow. In order to streamline trauma, degeneration, inflammation, and oncology-MSK diagnostic imaging, the potential benefits of AI-based workflow optimization should be taken advantage of. The following article describes a five-point plan combining patient expectations and specialized radiological standards with respect to investigation protocols and reports. Moreover, this AI-based strategy could help to improve interdisciplinary networking, e. g., boards etc., and facilitate the required leap in quality towards "personalized precision medicine" for the patient. According to the global discussion, there is a need to point out that it is not currently realistic to replace doctors with AI. · AI as support-system has a paramount clinical impact. · AI in the daily routine could be for work-flow-support (processing) - a physician-replacement is un-realistic yet. · Standardization of work-flow by AI could be an important contribution of quality assurance. · Braunschweig R, Kildal D, Janka R. Artificial intelligence (AI) in diagnostic imaging . Fortschr Röntgenstr 2024; DOI: 10.1055/a-2208-6487.

Rapid, high-throughput, cost-effective whole-genome sequencing of SARS-CoV-2 using a condensed library preparation of the Illumina DNA Prep kit.

Sequencing has played an invaluable role in the response to the COVID-19 pandemic. Ongoing work in this area, however, demands optimization of laboratory workflow to increase sequencing capacity, improve turnaround time, and reduce cost without compromising sequence quality. This report describes an optimized DNA library preparation method for improved whole-genome sequencing of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pathogen. The workflow advantages summarized here include significant time, cost, and consumable savings, which suggest that this new method is an efficient, scalable, and pragmatic alternative for SARS-CoV-2 whole-genome sequencing.

Implementing AI-Driven Efficiency: Best Practices for Intelligent Order Processing in SAP

Abstract: In today's hyper-competitive business environment, streamlining order processing is crucial for maximizing efficiency, minimizing errors, and fostering customer satisfaction. Traditional methods, often manual and error-prone, struggle to keep pace with the demands of modern commerce. This paper delves into the transformative power of Artificial Intelligence (AI) in revolutionizing order processing within SAP. the leading Enterprise Resource Planning (ERP) system. The article explores the integration of Artificial Intelligence (AI) and Optical Character Recognition (OCR) technologies, shedding light on how this union reshapes traditional workflows. From streamlining data entry processes to empowering intelligent decision-making, the article delineates the best practices for organizations seeking to harness the power of AI in SAP order processing. The discussion encompasses key considerations before implementation, seamless integration strategies, and best practices in training AI models. Real-world case studies illustrate successful implementations, highlighting the tangible benefits achieved in terms of efficiency, accuracy, and overall workflow optimization.

A novel approach toward optimal workflow selection for DNA methylation biomarker discovery

DNA methylation is a major epigenetic modification involved in many physiological processes. Normal methylation patterns are disrupted in many diseases and methylation-based biomarkers have shown promise in several contexts. Marker discovery typically involves the analysis of publicly available DNA methylation data from high-throughput assays. Numerous methods for identification of differentially methylated biomarkers have been developed, making the need for best practices guidelines and context-specific analyses workflows exceedingly high. To this end, here we propose TASA, a novel method for simulating methylation array data in various scenarios. We then comprehensively assess different data analysis workflows using real and simulated data and suggest optimal start-to-finish analysis workflows. Our study demonstrates that the choice of analysis pipeline for DNA methylation-based marker discovery is crucial and different across different contexts.

Positron emission tomography/magnetic resonance in musculoskeletal disorders: proper sequences and workflow optimization

Positron emission tomography/magnetic resonance in musculoskeletal disorders: proper sequences and workflow optimization