Calculator Research Articles

HVSMR-2.0: A 3D cardiovascular MR dataset for whole-heart segmentation in congenital heart disease

Patients with congenital heart disease often have cardiac anatomy that deviates significantly from normal, frequently requiring multiple heart surgeries. Image segmentation from a preoperative cardiovascular magnetic resonance (CMR) scan would enable creation of patient-specific 3D surface models of the heart, which have potential to improve surgical planning, enable surgical simulation, and allow automatic computation of quantitative metrics of heart function. However, there is no publicly available CMR dataset for whole-heart segmentation in patients with congenital heart disease. Here, we release the HVSMR-2.0 dataset, comprising 60 CMR scans alongside manual segmentation masks of the 4 cardiac chambers and 4 great vessels. The images showcase a wide range of heart defects and prior surgical interventions. The dataset also includes masks of required and optional extents of the great vessels, enabling fairer comparisons across algorithms. Detailed diagnoses for each subject are also provided. By releasing HVSMR-2.0, we aim to encourage development of robust segmentation algorithms and clinically relevant tools for congenital heart disease.

Pencegahan Stunting Berbasis TI di posyandu Buah Hati Ibu Rawang Kecamatan Padang Selatan

Posyandu is a forum that can help the government monitor the health of its people so that it helps the government in determining appropriate policies. One of the most important programs from Posyandu is preventing stunting in toddlers. Stunting is a disorder of growth and development in children due to chronic malnutrition which is characterized by their length or height below the standard set by the Minister of Health. The definition of stunting according to the Ministry of Health (Kemenkes) is a toddler with a Z-Score value of less than -2.00 SD/standard deviation (stunted) and less than -3.00 SD (severely stunted). However, the manual process used in many Posyandu, including Posyandu Buah Hati Ibu in Rawang, Padang Selatan District, Padang City, is often time-consuming and prone to errors. This is a challenge for cadres in analyzing and reporting toddler data, which in turn hinders efforts to prevent stunting. Therefore, community service is needed by building a web-based Information Technology system that can facilitate the data collection process, automatic Z-Score calculations, and reporting results effectively and efficiently.

Selected demographic determinants of CSR, financial & environmental management and business ethics in SMEs

Research background: Small and medium-sized enterprises are at the heart of the business environment in every country. At the same time, emphasis is placed on the environmental aspect and, in many cases, corporate social responsibility. In this context, business ethics is also a widely discussed topic. At the same time, financial management is one of the critical areas of business management. These aspects can be influenced by various demographic factors related to the company, as well as by the business owners or managers. Purpose of the article: The objective of this paper is to examine the influence of selected demographic factors on Corporate Social Responsibility (CSR), financial management, environmental practices, and business ethics in small and medium-sized enterprises (SMEs) in Slovakia and the Czech Republic. Methods: The empirical research was carried out as part of a broad-based research that aimed to ascertain the attitudes of small and medium-sized firms. It was conducted in June 2022 in Slovakia and the Czech Republic using the CAWI Research Method. The questionnaire could be completed by the owner or the top manager of the SME. The questionnaire was secured against automatic computer completion. Descriptive statistical analysis was used to analyse the characteristics of the variable, and regression (LRM) and correlation analysis methods were applied to find statistically significant differences in the influence of each independent factor. Findings & Value added: The analysis suggests interesting differences in how demographic factors influence ethics, CSR, environment and financial management in the Czech and Slovak Republics. In general, the impacts of these factors on these areas are very weak. The results showed that firm size influences SMEs' attitudes towards the environment, financial management and CSR in all countries combined. The other independent variables of the sector, such as length of business and age, do not affect attitudes towards ethics, environment, CSR, or financial management. We can generalise that in the conditions of Slovakia and the Czech Republic, among demographic criteria, only firm size plays a significant role in determining the attitudes of SME managers.

Chroma: A MATLAB package and open-source platform for biomarker data processing and automatic index calculations

The molecular ratio indices of biological markers (biomarkers), such as the Carbon Preference Index (CPI) or Paq, are frequently used as proxies for paleoclimatic and palaeoecological conditions. These indices are regularly extracted from the relative abundances of target molecules detected by a Gas Chromatography analyzer with a Flame Ionization Detector (GC-FID). Despite their use in biogeochemical studies for over a half-century, it remains common procedure to quantify the abundance of individual compounds by manual integration of chromatogram peaks (i.e., interpret baselines visually and characterize peaks by hand), which is time consuming and can lead to inconsistent results. Here, we introduce a new MATLAB package (Chroma) for the automatic detection and integration of standard-referenced biomarker abundances and the calculation of a variety of established hydrocarbon indices commonly reported in the published literature. The algorithm identifies the detector response timing of specific target peaks in a sample chromatogram by cross-referencing to a standard (e.g., Mix-A6, Schimmelmann, Indiana University Bloomington), then calculates the peak areas for an approximation of molecular abundance. This new toolkit for automatic and rapid integration of GC-acquired data provides a consistent and reproducible approach for the calculation of hydrocarbon indices and offers a standardized inter-laboratory platform for data comparisons and exchange. We validate the utility of the Chroma package with the chromatograms of plant wax n-alkanes, a widely used proxy for ecology and hydrology, from six stratigraphic sections in the Tibetan Plateau. Chroma is an effective tool for efficient data processing and will continuously evolve to accommodate extended uses in related areas of biomarker research beyond n-alkanes.

Dual-path lightweight convolutional neural network for automatic sorting of olive fruit based on cultivar and maturity

Identifying olive cultivars and maturity stages is crucial in the olive industry, as these traits significantly impact the nutritional and sensory properties of olive products and extracted oil. For this purpose, this study presents a novel automatic computer vision system that applies state-of-the-art deep learning technology to sort and classify two Iranian olive cultivars, Zard and Roghani, in five maturity stages, resulting in a total of ten distinct classes. The model was developed by evaluating multiple user-defined and standard structures. It was based on a dual-path lightweight convolutional neural network that uses both regular and dilated convolution operators. Dilated convolutions were used to extract more information and capture different properties by providing larger receptive fields. With a significantly lower number of trainable parameters than standard architectures, the lightweight nature of the model would enhance its potential for delivering fast responses in on-the-go applications. Four optimizers (RMSProp, SGD, Adam, and Nadam) were tested on the developed model to enhance its performance, and Nadam exhibited the greatest accuracy. The proposed model achieved a total classification accuracy of 95.79 % and a loss of 0.2214. The proposed model was completely accurate for some classes, and the classification metrics for all categories were high, ranging from 88 % to 100 % for precision, 83–100 % for recall, and 86–100 % for F1-score. The accuracy of classification within the Roghani cultivar classes stood at 98.28 %, while for the Zard cultivar classes, it achieved 97.76 %. The study found that the proposed model can be efficiently incorporated into an olive sorting system, facilitating the identification of olives with different cultivars and varying levels of maturity, thereby enhancing the production of post-harvest products and superior quality of oil.

Pixel-level automatic detection and quantification of running bands on rail surfaces

The running band on the rail surface serves as a crucial indicator of the wheel-rail contact relationship, making quantitative detection of the running band vital for railroad inspection and maintenance. However, current rail running band detection methods remain manual, and leveraging state-of-the-art deep learning technology can significantly enhance detection efficiency and minimize the reliance on human labor. This paper presents an improved version of ShuttleNet, called ShuttleNetM2T, for rail surface running band detection, emphasizing high stability. Efficient self-attention in ShuttleNetM2T captures global information, maintaining efficiency and rectifying issues like misrecognition and incomplete edges. Experimental results show ShuttleNetM2T achieves 0.9823 average F-measure and 0.9653 average Intersection-Over-Union on test images. For automatic running band width detection, we propose a pixel-to-physical distance conversion-based calculation, yielding just 0.625% relative error. Overall, the findings in this paper facilitate accurate detection and automatic calculation of the running band width, with promising applications in intelligent rail surface detection.

Updating predictions in a complex repertoire of actions and its neural representation

Even though actions we observe in everyday life seem to unfold in a continuous manner, they are automatically divided into meaningful chunks, that are single actions or segments, which provide information for the formation and updating of internal predictive models. Specifically, boundaries between actions constitute a hub for predictive processing since the prediction of the current action comes to an end and calls for updating of predictions for the next action. In the current study, we investigated neural processes which characterize such boundaries using a repertoire of complex action sequences with a predefined probabilistic structure. Action sequences consisted of actions that started with the hand touching an object (T) and ended with the hand releasing the object (U). These action boundaries were determined using an automatic computer vision algorithm. Participants trained all action sequences by imitating demo videos. Subsequently, they returned for an fMRI session during which the original action sequences were presented in addition to slightly modified versions thereof. Participants completed a post-fMRI memory test to assess the retention of original action sequences. The exchange of individual actions, and thus a violation of action prediction, resulted in increased activation of the action observation network and the anterior insula. At U events, marking the end of an action, increased brain activation in supplementary motor area, striatum, and lingual gyrus was indicative of the retrieval of the previously encoded action repertoire. As expected, brain activation at U events also reflected the predefined probabilistic branching structure of the action repertoire. At T events, marking the beginning of the next action, midline and hippocampal regions were recruited, reflecting the selected prediction of the unfolding action segment. In conclusion, our findings contribute to a better understanding of the various cerebral processes characterizing prediction during the observation of complex action repertoires.

Geoelectric analysis for groundwater potential assessment and aquifer protection in a part of Shango, North-Central Nigeria

Groundwater is vital for sustainable development, and this study addresses potable water challenges in Shango, North-Central Nigeria. The main goal is to identify optimal sites for new wells and boreholes, utilizing geological and geo-electrical attributes from existing boreholes and wells. Vertical Electrical Sounding (VES) assessed groundwater potential, aquifer protection, and overburden corrosivity. Sixteen VES stations were probed using Schlumberger array with a maximum current electrode spacing (AB/2) of 200 m using a resistivity meter. The data were interpreted using an automatic computer inversion program, IPI2WIN. The VES results revealed five subsurface geo-electric units, with depths to the aquifer ranging from 58 to 68 m, each exhibiting distinct characteristics contributing to the lithological variability of the research area. Hydraulic conductivity ranged from 0.465 to 0.534 m/day, while transmissivity varied from 9.589 m2/day to 26.029 m2/day across different VES points. Regions exhibiting thick layers and low resistivity values indicate high longitudinal conductivity. Furthermore, areas with low protective capacity are susceptible to the risks of pollution and contamination stemming from leaks and waste sites. The study revealed that all VES points are in practically non-corrosive zones, making them suitable for burying underground tanks with extremely low deterioration rates. Based on geoelectrical characteristics, the study area was divided into three groundwater potential zones: low, medium, and high. These findings provide valuable insights into the groundwater potential and protective capacity of the Shango area, while emphasizing on the vulnerability of these regions and highlighting the pressing need for appropriate preventive measures to safeguard against potential environmental hazards.

Towards the automatic calculation of the EQUAL Candida Score: Extraction of CVC-related information from EMRs of critically ill patients with candidemia in Intensive Care Units

ObjectivesCandidemia is the most frequent invasive fungal disease and the fourth most frequent bloodstream infection in hospitalized patients. Its optimal management is crucial for improving patients’ survival. The quality of candidemia management can be assessed with the EQUAL Candida Score. The objective of this work is to support its automatic calculation by extracting central venous catheter-related information from Italian text in clinical notes of electronic medical records. Materials and methodsThe sample includes 4,787 clinical notes of 108 patients hospitalized between January 2018 to December 2020 in the Intensive Care Units of the IRCCS San Martino Polyclinic Hospital in Genoa (Italy). The devised pipeline exploits natural language processing (NLP) to produce numerical representations of clinical notes used as input of machine learning (ML) algorithms to identify CVC presence and removal. It compares the performances of (i) rule-based method, (ii) count-based method together with a ML algorithm, and (iii) a transformers-based model. ResultsResults, obtained with three different approaches, were evaluated in terms of weighted F1 Score. The random forest classifier showed the higher performance in both tasks reaching 82.35%. ConclusionThe present work constitutes a first step towards the automatic calculation of the EQUAL Candida Score from unstructured daily collected data by combining ML and NLP methods. The automatic calculation of the EQUAL Candida Score could provide crucial real-time feedback on the quality of candidemia management, aimed at further improving patients’ health.

Use of an AI-powered visualization platform to support precision clinical decision-making in patients with breast cancer undergoing neoadjuvant chemotherapy.

e12618 Background: Chemotherapy to reduce cancer burden and tumor size ("downstaging") is widely used in neoadjuvant treatment of early-stage breast cancer (ESBC) and can have a dramatic impact on selection of further treatment courses, including surgery. The resulting decision-making process between physicians and cancer patients requires detailed and effective communication of the patient's disease status, and clear presentation of this information in Tumor Board settings. Artificial intelligence (AI) -powered visualization platforms offer the potential to aid in evaluating breast tumor location and morphology, and accordingly optimize treatment. Additionally, these tools offer enhanced communication with patients regarding future treatment options, particularly serving as clinical decision support (CDS) tools. Methods: We assessed the performance of an AI platform that employs dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to render three-dimensional (3D) visualizations of breast tumors and 5 additional chest tissues on an independent validation dataset comprise of 100 ESBC cases with ground-truth tumor labels vetted by 2 breast-specialized radiologists. The platform provides 3D depictions of the tumor and its multi-tissue context, as well as functionalities for quantifying tumor morphology, tumor-to-landmark structure distances, excision volumes, and approximate surgical margins. We subsequently evaluated the tool's utility in a real-world setting to understand how the tool impacts clinical decision-making and patient communication, specifically around surgical planning in the context of neoadjuvant chemotherapy (NACT). Results: The platform generated accurate 3D tumor maps, as evidenced by a median Dice score of 75.6% and a median Hausdorff distances of 15.1 mm relative to the radiologist validation set. The automatic longest tumor dimension calculations were linearly correlated with radiologist direct measurements (Pearson correlation coefficient = 0.78) and had a median absolute difference of 6.3 mm. We found strong overlap between the platform’s ground-truth convex hulls, as shown by a median Dice score of 81.5%. When used by a skilled breast-specialized surgeon, the tool enabled rapid and intuitive patient-physician communication of the location and extent of disease, and potential degrees of downstaging to breast-conserving surgery. Conclusions: Detailed 3D tumor and surrounding multi-tissue depictions offer both qualitative and quantitative comprehension of cancer topology and may aid in formulating an optimal treatment approach for breast cancer treatment. We show that detailed depictions enhance communication between physicians and patients and may aid in streamlining decision-making.

UTJECAJ ODABRANIH MAKROEKONOMSKIH VARIJABLI NA CIJENE STAMBENIH OBJEKATA U HRVATSKOJ

Recognizing the macroeconomic determinants that have a statistically significant influence on the formation of house prices is in the interest of the general public due to its informative effect on various interest groups involved in housing construction. Thus, real estate buyers, investors, as well as local government and self-government units should be interested in this information because monitoring of standard macroeconomic variables can provide conclusions about the possible development of residential property prices. Previously conducted research can be classified into four distinctive categories depending on what they take as determining variables: microelements specific to individual micro location, the impact of the COVID-19 pandemic, standard macroeconomic variables, or tourism development. The aim of this study is to analyze the influence of selected macroeconomic variables on residential property prices in Croatia. This study employs Autometrics, i.e. an automatic computer implementation of general-to-specific VAR (vector autoregressive) modelling framework and quarterly data on real GDP, domestic credit, consumer prices, interest rate, tourist arrivals and house prices in the period from March 2005 to September 2022. Performed Granger causality tests and impulse response functions analysis indicate that an increase in real GDP, domestic credit and tourist arrivals increases house prices in Croatia while an increase in consumer prices and interest rate reduces them.

WED-224 Screening for liver fibrosis in tertiary care using automatic calculation of FIB4 in patients at-risk of diabetes

WED-224 Screening for liver fibrosis in tertiary care using automatic calculation of FIB4 in patients at-risk of diabetes

A qualitative study of patients’ perceptions of DASH diet apps for dietary self- management of hypertension in Saudi Arabia

Nutrition smartphone apps have become a popular and readily accessible approach to improving dietary behaviour. Hypertension is often associated with a poor diet, and its prevalence is increasing in Saudi Arabia(1). The Dietary Approaches to Stop Hypertension (DASH) eating plan has been shown to reduce blood pressure in people with hypertension(2). A previous study identified two high-quality, safe, and potentially effective smartphone apps for managing hypertension: NOOM and DASH To TEN(3). This study aimed to explore the potential of these two DASH diet self- management apps for controlling blood pressure in the Saudi Arabian context.Fifteen patients were recruited at King Abdullah bin Abdulaziz University Hospital in Riyadh, Saudi Arabia. Ten patients had hypertension, and five had prehypertension (mean age = 45). Patients were given the two apps and asked to try each for one week. Focus groups (n=4) were held at the end of the trial to understand the patient perceptions of the apps. Discussions were recorded, and the transcriptions were analysed using a thematic framework analysis(4).The following four themes emerged:1.Managing hypertension through diet was perceived as important. Most patients reported thatadhering to the DASH diet was challenging due to a lack of motivation and willpower,inadequate support from household members, and high prices for healthy food.2.The potential and current reach of dietary apps emerged as a main theme, and manycomments related to patients’ belief that dietary apps could increase their motivation and awareness about the DASH diet. Barriers to the use of apps were also identified including their difficulty of use, a preference for dietetic monitoring, and cost.3.Interactive app functionality was identified as a key theme, as evidenced by comments about a straightforward sign-up process, an extensive food database for dietary self-monitoring, feedback, goal setting, and reminders, considered essential for diet adherence.4.A preference for the NOOM app emerged. Patients perceived the NOOM app more suitable in the Saudi context. Noom was deemed to support DASH self-management because it supports weight reduction, which helps lower blood pressure. NOOM was perceived as highly interactive, offering motivational reminders, feedback, realistic dietary plans, and a comprehensive food database. Patients made several recommendations for app improvement; these included Arabic language support, automatic calculation of sodium and potassium consumption, and lower cost. Patients also expressed a desire for training in the use of the app.This qualitative analysis suggests that the NOOM app could be suitable for use with hypertensive patients in Saudi Arabia. Further research is needed to determine the feasibility and efficacy of long- term use of the NOOM app with a Saudi Arabia population.

Fish Species Detection Using Deep Learning

Abstract: This research explores the application of deep learning techniques for fish species detection in underwater environments. convolutional neural networks (CNNs) trained on extensive datasets, the study aims to enhance the accuracy and efficiency of species identification. The proposed model demon- strates promising results in differentiating diverse fish species, contributing to advancements in aquatic ecology monitoring and biodiversity conservation. The integration of deep learning in fish species detection holds potential for improving our understanding of underwater ecosystems and supporting sustainable fisheries management. The relative abundance of fish pieces in their habitats on a regular basis and keeping an eye on population fluctuations, this are a crucial task for marine scientists andconservationists diverse automatic computer based fish sample methods have been demonstrated in underwater photos and videos as alternatives to time consuming hand sampling there isn’t however a perfect method for automatically detecting fish and classifying the species this is mostly due to the difficulties in producing clear underwater images and videos which include environmental fluctuations in lightning fish camouflage Dynamicbackdrops murky water low resolution shape deformations of moving fish.

A Clinical Picture of Unselected Patients with Systemic Lupus Erythematosus in a Tertiary Hungarian Center-A Spectrum Ranging from Pure Lupus to Overlap Syndromes.

Introduction: Systemic lupus erythematosus (SLE) is a multidimensional disease; however, the association of another systemic autoimmune disease further complicates its clinical presentation. Aim: We decided to investigate whether the association of overlap syndromes is linked with a different clinical picture compared to pure lupus and whether this association changes the sensitivity of the following commonly used criteria: the 2019 European League Against Rheumatism/American College of Rheumatology (EULAR/ACR), the ACR-1997 and the 2012 Systemic Lupus International Collaborating Clinics (SLICC) criteria. Method: We performed a retrospective observational study among 382 patients afflicted with lupus: we measured as much of the full clinical and laboratory picture as possible in an unselected cohort. The diagnosis of SLE and other systemic autoimmune diseases was established by the rheumatologist in routine care and then the authors compared the characteristics of patients with pure lupus and those with overlapping pathologies. The diagnosis rates were compared to those that were determined based on the three classification criteria in order to identify various sensitivities and whether the existence of an overlap affects their rates. The fulfillment of each set of criteria was calculated using an Excel-based automatic calculation. Results: Among the patients, the ACR 1997's sensitivity was 81.2% (310 patients), and the SLICC 2012 criteria achieved 94.5% sensitivity (361 patients). The 2019 EULAR/ACR classification criteria resulted in a slightly lower sensitivity (90.3%-345 patients) when compared to the original publication (96%) due to the lower sensitivity of our anti-nuclear antibody (ANA) test (measured via enzyme-linked immunosorbent assay (ELISA)). Nearly all ANA-negative (21/22-95%) patients showed a positive lupus-associated antibody test. The proportion of ANA-negative cases showed no significant difference among pure and overlap patients. No significant difference was found between patients with overlap (138 patients-36%) and pure SLE (244 patients-64%) through the use of these criteria, with the exception of the SLICC criteria (ACR: 80.4% vs. 81.6%; SLICC: 97.4% vs. 92.6%, p = 0.035; EULAR/ACR 2019: 91.4% vs. 89.6%). Patients with an overlap syndrome were significantly older (55 vs. 50 years, p = 0.001), more likely to suffer from interstitial lung disease (ILD: 20% vs. 11%, p = 0.0343) and less frequently showed class III/IV lupus nephritis (7% vs. 14%, p = 0.029) when compared with their pure lupus counterparts. Conclusion: All investigated criteria regarding sensitivity were similar to the original publication's findings. The sensitivity of the EULAR/ACR 2019 classification criterion in cases with overlap syndrome proved excellent, with results very similar to patients afflicted with pure SLE. In the presence of an overlap syndrome, we found significantly fewer patients with lupus nephritis III/IV but no differences in other typical lupus organ manifestation beyond the kidney, whereas we found a higher proportion of ILD in patients with an overlap, indicating that the presence of an overlap syndrome significantly influences the observed clinical picture in real-world conditions.

Computer-Assisted Histopathological Calculation Analysis of the Sciatic Nerve of Diabetic Neuropathy Rat Model

Histopathology is the science that studies the signs of disease by studying the structural and functional changes that occur in cells using certain types of dyes such as hematoxylin and eosin (H&E). Traditionally histopathological testing is carried out using semi-quantitative methods. A more advanced method is done by taking photos digitally, and then digital photos are quantified with the help of software such as ImageJ using plug-in tools. Recent advances in digital pathology require the development of more efficient computerized image analysis such as the Gaussian adaptive threshold method. This research aims to compare the calculation results of computer-assisted digitalization of histopathology using the ImageJ plugin manual method with automatic calculations using Gaussian adaptive threshold to quantify the amount of sciatic nerve cell damage in the Diabetic peripheral neuropathy (DPN) rat model. In this study, two image analysis methods were used to test their ability to measure the amount of cell damage in the sciatic nerve of normal rats using a model of diabetic neuropathy. The first method uses the ImageJ plugin manual. The second method is the Gaussian adaptive threshold method. The ImageJ plugin manual method obtained a cell abnormality value of 213 cells. Meanwhile, with the Gaussian adaptive threshold method, a value of 204 cells was obtained. The calculation results of the two methods show an insignificant difference between the methods p >0.05. This study presents a computerized morphometric image analysis method with the potential for pathology digitalization applications.

Automatic prediction of isocitrate dehydrogenase mutation status of low-grade gliomas using radiomics and domain knowledge inspired features in magnetic resonance imaging

Aim: Most common and most deadly primary central nervous tumors, glial tumors harbor many heterogeneous clones of cells. Noninvasive determination of the genomic profiles of these tumors would have important implications regarding the classification, management, and prognostication of these tumors. Isocitrate dehydrogenase mutation is a key genomic signature that can downgrade the expected dismal course of these tumors. In this study we aimed to build a performant prediction model which can determine the Isocitrate Dehydrogenase (IDH) mutation status of glial tumors, using radiomics and leveraging automatic computation of domain knowledge-inspired features. Methods: Radiomics methods based on high throughput feature extraction and application of data science principles to these extracted features are promising tools for the noninvasive classification of lesions. Domain knowledge-inspired features besides radiomics features can contribute positively to the performance of the models. Some efforts particularly a joint approach to standardize the magnetic resonance imaging (MRI), reporting of glial tumors are mainstay for domain knowledge-inspired features. However, this requires active involvement and reporting of the radiologist which hampers automatization efforts. Additionally, this feature set evaluates a small subset of all possible signal and spatial-based computations. In this study, we combined domain knowledge-inspired features with radiomics features along with a multiparametric multihabitat comprehensive lesion description strategy. Results: Our best model which consisted of a combination of radiomics, and radiologist knowledge-inspired features reached a 0.93 f1 score (standard deviation (SD): 0.03), 0.93 accuracy (SD:0.03), and 0.98 area under curve (AUC), (SD:0.02). Conclusion: The multiparametric and multiregional approach employed in this study coupled with the integration of both radiomics and domain knowledge-inspired features resulted in a high-performance model emphasizing the contribution of each strategy to the outcome.

Neural network for automatic ICD-EGMs matching in pace-mapping and ablation of ventricular arrhythmias

Abstract Background Mapping of the ventricular arrhythmias (VA) is often not possible due to the non-inducibility of the electrophysiological study (EPS). Since twelve-lead electrocardiograms (ECG) of the clinical ventricular tachycardia (VT) are also often not available, therefore stored implantable cardioverter-defibrillator (ICD) electrograms (EGMs) of the clinical VT are often the only documentation. The pace mapping matching to the stored ICD-EGM template of the clinical VT can help to identify the VT exit site. Automatic objective computing of similarity scores between EGMs is impossible because ICD programmer devices do not have any interface allowing the export of digital EGMs. Therefore, images can only be accessed for similarity by subjective eyeballing. The MatcherNet Siamese neural network takes a pair of EGM images and predicts their similarity. Purpose This study aimed to assess the feasibility of the automatic ICD-EGMs matching by MatcherNet neural network for pace mapping of VT/premature ventricular contraction (PVC) exit site. Methods Consecutive patients undergoing VT ablation or ablation of ventricular fibrillation, triggered by PVC were included in the study, if the clinical VT/PVC was not inducible during EPS but ICD-EGMs of clinical VT/PVC were stored in the device. Electro-anatomical mapping was performed to reveal substrates (low-voltage areas, abnormal potentials, DEEP-potentials, conduction crowding). Subsequently, the low-output pacing from various locations tagged on the 3D map of LV was performed, and the paced ICD-EGM images were stored from the ICD programmer device for offline analysis and calculation of the similarity. RF ablation was conducted based on the substrate map findings, including the area of the most remarkable similarity between paced ICD-EGMs and clinical ICD-EGM templates assessed by eyeballing. The ICD-EGMs similarity scores (Manhattan similarity and Pearson correlation) were predicted by MatcherNet for each pacing site offline and transferred to the 3D map for the assessment of similarity distribution (Figure 1). Results We included 7 patients with VA episodes registered and stored by their ICD. The clinical characteristics are presented in Table1. In all patients, we were able to find the sites of highest ICD-EGM similarity to the clinical template with gradual decrementing of the similarity score at the increasingly distant pacing areas. The site of the highest similarity was collocated with VT substrate and ablation areas in all patients. Abrupt change of the similarity score at the adjacent pacing sites was detected in the 2 cases, indicating the possible protected VT isthmus. After ablation procedure only one patient with DCM experienced VA recurrence. Conclusion This technology opens new possibilities for the utilization of ICD-EGMs during the pace mapping of ventricular tachycardia, especially in the cases of non-inducibility during electrophysiological study.Figure 1Table 1

Computer-Vision- and Deep-Learning-Based Determination of Flow Regimes, Void Fraction, and Resistance Sensor Data in Microchannel Flow Boiling.

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10-6.

#958 Development and Validation of a Score Estimating the Probability of obtaining a genetic diagnosis in adults with CKD of uncertain origin

Abstract Background and Aims We aim to derive and validate a score estimating the probability of identifying a variant explicative of the renal phenotype using Exome Sequencing (ES) in adults with CKD of uncertain origin. Method Participants: prospective cohort study including all consecutive index patients with a CKD from uncertain origin in three French nephrology units (metropolitan: Sorbonne University Hospitals, Paris, and Conception Hospital, Marseille; overseas: La Réunion University Hospital, Réunion island) who underwent ES between October 11th, 2017 and May 31st, 2023. Outcome measure: identification of a causal variant using ES data, according to the American College of Medical Genetics and Genomics diagnostic criteria. Candiate variables and feature engineering: raw data regarding patients’ phenotypes was prospectively entered in a collection form at the time of ES by the prescribing physician. Structured data (yes/no questions and lists) was mapped to Human Phenotype Ontology (HPO) terms. Unstructured data (free text) was manually translated into HPO terms by the same investigator (nephrologist), which was blinded to ES results. First, second and third-order ancestor HPO terms were included in the analysis. Score's derivation: an optimal weighted average of multiple models (“ensemble model”) was specified, following guidelines provided in a recently published article (PMID:36905602). Score's validation: internal validation using 10-fold cross validation, followed by internal-external validation (data from 2/3 centers was used to develop a model which was then tested using data from the remaining center; this process was repeated in each center). Results We included 2,490 patients, 560/2,490 (22.5%) of whom had a causal variant identified by ES. We collected 1,028 distinct HPO terms describing the patients’ phenotypes. The most common term was “Hypertension”, occurring in 2,079/2,490 (83.5%) patients. In internal validation, the score showed accurate calibration and discrimination (area under the receiver operating characteristics curve (AUC): 0.71, 95% CI 0.68 to 0.73; index of precision accuracy (IPA): 0.11, 95% CI 0.09 to 0.13). Performances were moderately diminished in internal-external validation but remained satisfactory (Tenon: AUC 0.64, IPA 0.04; Marseille: AUC 0.67, IPA 0.04; La Réunion: 0.68, IPA 0.09). Conclusion We derived, internally and internally-externally validated a clinical score which accurately predicts the probability of obtaining a genetic diagnosis using Exome Sequencing. Feature engineering could further increase the score's performances. Automatic computation by clinicians using an interactive tool is achievable and could be of clinical utility, especially to guide resource allocation in case of a low pretest probability.