Evaluation Of Algorithms Research Articles

Mass Spectrometry-Based Assessment of M-Protein in Peripheral Blood during Maintenance Therapy in Multiple Myeloma (MM) in the Phase III ATLAS Trial

Introduction Minimal residual disease (MRD) assessment in bone marrow (BM) has emerged as one of the strongest prognostic factors in MM. Mass spectrometry (MS), capable of detecting MM-derived monoclonal proteins in peripheral blood with high sensitivity, has the potential to complement standard methods. While its role in evaluating residual disease and its prognostic performance compared to routine MRD assessments is not yet established, other unanswered questions remain: (1) What is the role of MS in response assessment for patients without a high disease burden baseline sample? (2) What is the optimal timing of MS assessment, considering the long half-life of immunoglobulins? Methods Stored serum samples collected at different timepoints [screening, cycle 6 (C6), C12, C18, C24, C36] from patients treated in the ATLAS trial, were analyzed using the EXENT® Immunoglobulin isotypes (GAM) assay (EXENT® Solution, in development by The Binding Site, part of Thermo Fisher Scientific), which utilizes MALDI-TOF MS. ATLAS is an ongoing phase 3 trial that randomized 180 patients with newly diagnosed MM after autologous stem cell transplantation (ASCT) to maintenance therapy with carfilzomib, lenalidomide, and dexamethasone (KRd) or lenalidomide alone (R). In the KRd arm, patients with standard-risk cytogenetics who achieved MRD-negativity after cycle 6 de-escalated therapy to receive R, from C9. No baseline diagnostic samples were available, and samples were not available for every patient at every timepoint. A sample was called positive by MS when the EXENT® solution confirmed the presence of an M protein, matching the known (diagnostic) isotype. BM MRD was assessed at the same timepoints using multicolor flow cytometry (MFC) with a limit of detection (LoD) of 10 -5 and next-generation sequencing (NGS, clonoSEQ, Adaptive, LoD 10 -6). Progression-free survival (PFS) was analyzed using the Kaplan-Meier method, with log-rank test for comparisons between groups. The data cutoff (31-Dec-2021) was the same as was used in the ATLAS publication by Dytfeld et al. Lancet Oncology 2023. Results 585 samples from 138 patients were analyzed by MS. There were 349 paired BM MRD results by NGS; patients with MRD 10 -5 were considered MRD(+). The overall agreement between the two methods equaled 70%, with a comparable number of patients being MS+/NGS- (56/349, 16%) and MS-/NGS+ (50/349, 14%). The agreement at screening was 61%, but it improved at further timepoints and reached the highest level at C18 (74%). For BM MFC, there were 499 paired samples. There was 67% agreement, and the discrepancy was driven mostly by MS+/MFC- patients (125/499, 25%), whereas MS-/MFC+ was less frequent (40/499, 8%). The agreement was lowest at screening (60%), similarly to the NGS-based assessment, and reached the highest level at C18 (73%). Based on these findings, we concluded that C18 may be the optimal timepoint to assess prognostic role of MS results. Using the landmark method, MS(-) following C18 was associated with superior PFS compared to MS(+) [HR=0.39 (95% CI: 0.17-0.91), p=0.025; Figure 1]. MFC [HR=0.13 (0.04-0.35), p=0.0002], and NGS [HR=0.15 (0.03-0.63), p=0.003] statuses were also associated with PFS using this landmark method. Although small numbers of patients preclude definitive conclusions, we observed a similar effect size in outcomes among NGS(-)/MS(-) vs NGS(-)/MS(+) patients [HR=0.14 (0.01-1.58), p=0.06] and MFC(-)/MS(-) vs MFC(-)/MS(+) [HR=0.40 (0.13-1.27), p=0.11], both favoring BM MRD(-) with concurrent MS(-). Out of the 45 patients who were initially MS(+) and subsequently converted to MS(-), 23 (51%) occurred following C12 or later. Patients who converted from MS(+) to MS(-) had similar PFS to those with sustained MS(-) throughout the analyzed period [HR=0.74 (0.32-1.68), p=0.47; Figure 2], with the majority of PFS events in the converted group occurring during first 18 months of observation. Conclusions MS-based disease assessment in the post-ASCT setting is feasible in many cases, if information on the original MM clone is available by traditional methods. Our results suggest that the optimal timepoint for such evaluation can be as long as 18 months after ASCT. The EXENT® assay may be complementary to BM-based techniques for MRD assessment, allowing for more accurate prognostication when used in combination. Further studies are needed to confirm its exact timing and role in the disease evaluation algorithms.

Calibration and fast evaluation algorithms for homogeneous orthotropic polynomial yield functions

Calibration and fast evaluation algorithms for homogeneous orthotropic polynomial yield functions

Research on the operation mechanism and path of regional public brand of agricultural products based on the perspective of industrial clusters

Abstract In this paper, the construction basis of an agricultural regional public brand, the construction main body and the structural model of resource advantageous agricultural regional public brand is discussed in the part of the agricultural regional public brand construction. In the part of the construction of the evaluation model of the competitive strength of agricultural regional public brands, the fuzzy power reconstraint BoD model based on Pareto optimum, Pareto importance criterion, Pareto rule and BoD discriminative criteria, fuzzy group opinion set and the proposed POGF-BoD evaluation algorithm are studied. Finally, an empirical analysis of the competitiveness of agricultural regional public brands was conducted. The results show that the evaluation system for regional public brand competitiveness of agricultural products has an evaluation result of 84.354, with a good evaluation grade. The first-level index brand element’s evaluation result is 88.964, which is the highest score among the four first-level indexes.

Portable automatic detection system with infrared imaging for measuring steel wires corrosion damage

Accurate, cost-efficient and lightweight quantitative detection of steel wire corrosion in cable is an unsolvable issue that puzzles researchers and bridge owners. This paper proposed a portable automatic detection system for quantitative corrosion detection of replaced steel wires. The developed system consists of three parts (an automatic detection device, high-precision infrared imager, and corrosion evaluation algorithm). The proposed method is derived on the basis of Joule's law and the formula for calculating heat release. Then, the corroded specimens with different corrosion degrees and corresponding mass loss ratio were obtained by pre-corroded test to simulate industrial air corrosion and pickling test. The prior knowledge acquisition test utilizing presented automatic detection equipment was conducted to acquire the surface temperature of steel wires with various corrosion ratios by infrared camera after electric heating. Subsequently, the optimal quantitative corrosion prediction model after electric excitation is selected after infrared image processing, outlier filtering, theoretical method comparison, and model modification. Finally, the damaged steel wires from an in-service cable-stayed bridge are chosen to validate the proposed model's generalization ability and predictive accuracy. Furthermore, based on the discovery of characteristics on surface temperature of corroded steel wires after heating, the automatic detection device can be upgraded to realize the quantitative detection of in-situ corrosion of bridge cable.

Reliability Evaluation and Optimization Configuration Method of Network Distribution Side Energy Storage System Based on Machine Vision

To reduce the motor power allocation error and improve voltage weak node conditions, this paper designed a reliability evaluation and optimization configuration method for network distribution side energy storage system based on machine vision. Firstly, the abnormal operation parameters of the energy storage system are collected and transmitted on-site. The operational reliability monitoring data of the distribution network side serves as the foundation for designing the operational reliability evaluation algorithm for the energy storage system on the same distribution network side. This algorithm further enables the optimal configuration of the energy storage system. The experimental comparison results demonstrate that upon implementation of the methods of this paper, the motor power allocation error is less, and the lowest is only 0.17 kW. Meanwhile, the fluctuation is relatively flat, and the range is between 0 kW and 0.46 kW. The improvement of weak voltage nodes is good, the voltage load is significantly decreased, and the minimum voltage load is only 5 kW, which proves that the design method of this paper has a certain application value.

The Evolution of Sinus Tarsi Syndrome—What Is the Underlying Pathology?—A Critical Review

Background and Objectives: Sinus tarsi syndrome (STS) is defined as pain located at the lateral opening of the tarsal sinus. The exact etiology of sinus tarsi syndrome is not completely understood. Some do not believe it to be a true pathology. This review aims to clarify the definition of sinus tarsi syndrome to better understand the underlying pathologies. We further propose an algorithm to evaluate sinus tarsi pain and provide advice for consecutive treatment options. Design: This is a narrative review. By searching PubMed, the available current literature was reviewed. Articles were critically analyzed to determine the pathoanatomy, biomechanics, and etiology of sinus tarsi pain. Algorithms for clinical evaluation, diagnosis, and treatment were also recorded. Finally, the authors approach to evaluating and treating sinus tarsi pain was included in this review. Results: Reviewing the available literature, STS seems to be a catch-all phrase used to describe any pain in this anatomic region. Many causes of sinus tarsi pain were listed, including impingement, subtalar instability, and many other pathologies around the ankle. Conclusions: A thorough evaluation of patients presenting with pain in the sinus tarsi or instability of the hindfoot is essential to determining the underlying cause. When the cause of pain is still not clear after clinical exam and radiologic assessment, subtalar arthroscopy can be helpful as both a diagnostic and treatment tool. We propose that the term of STS should be avoided and that a more accurate diagnosis be used when possible. Once a diagnosis is made, appropriate treatment can be initiated.

利用人工智能技术改进高校课程评估与个性化学习

With continuous advancements in education and the rapid proliferation of artificial intelligence technology, leveraging AI to improve university course evaluation and personalize learning experiences has garnered significant interest. This article aims to investigate the effective utilization of artificial intelligence technology in enhancing university course evaluation and achieving personalized learning outcomes. Firstly, it provides an overview of the current landscape of university course evaluation and personalized learning while highlighting the limitations of existing methodologies. It then delves into the application of artificial intelligence technology to address these challenges, discussing the utilization of machine learning algorithms for course evaluation, personalized recommendations, and student data analysis. In conclusion, the article summarizes the potential impact of artificial intelligence technology on university course evaluation and personalized learning.

Fully automated operational modal identification of regular and irregular buildings with ensemble learning

Modal identification, a type of system identification that employs modal analysis, can be automated to reduce user interference in extracting modal parameters. Modal analysis is a valuable tool for obtaining a structure's modal parameters, which define its dynamic characteristics. Operational modal identification is a specific type of modal analysis that uses only system outputs to extract modal parameters. The present study aims to introduce a fully automated modal identification algorithm to identify modal parameters for an unknown system based on its output information. The algorithm uses a stochastic subspace algorithm to extract modal parameters, requiring only the appropriate degree of the state-space model estimated using the Singular Value Criterion. Several features are used to create a feature space that separates physical and spurious modes. The Improved Distance Evaluation algorithm selects appropriate features, making the identification process more accurate and flexible. The identification algorithm employs clustering algorithms with different approaches and the Dempster-Shafer data fusion algorithm to integrate clustering algorithm results and avoid divergence among them. Due to limited data diversity for identification in cases where only one dataset is available, statistical resampling methods are used as an alternative. The proposed algorithm can identify modal parameters using only one dataset of the building structure. Signal processing, data collection, clustering, feature extraction, model reduction, and data fusion are all aspects of this algorithm. To assess its performance, four regular and irregular buildings are considered as case studies. The presented modal identification algorithm is highly accurate and robust with the repeatable result as compared to similar algorithms, with extracted modal parameters demonstrating high stability.

The organic integration of college Civic Education and practice based on multi-data chain network

Abstract This paper first investigates the hierarchical structure of multiple data chains and classifies the data chain structure into the application layer, transport layer, physical layer, etc., according to the role classification. Then, the communication of multi-data chain network points is explored, and the forwarding paths between different data chain nodes are planned according to the types of data chains. The data chain messages are planned using the time slot evaluation algorithm, and the practical teaching platform for multi-data chain network thinking is constructed. Finally, the effectiveness of the practical teaching of Civics was evaluated in terms of practical ability, practical literacy, and student performance. The study showed that the significance test of the difference between the post-test of the Civics performance of the two classes was 0.001, which was less than 0.05. Under the dimension of science literacy, the mean value of the Civics practice pre-test was 6.75, and the mean value of the post-test was 7.55, with a difference of 0.4. The quality and efficiency of civics education were significantly improved by teaching civics practice.

Analytical advances alleviate model misspecification in non-Brownian multivariate comparative methods.

Adams and Collyer argue that contemporary multivariate (Gaussian) phylogenetic comparative methods are prone to favouring more complex models of evolution and sometimes rotation invariance can be an issue. Here we dissect the concept of rotation invariance and point out that, depending on the understanding, this can be an issue with any method that relies on numerical instead of analytical estimation approaches. We relate this to the ongoing discussion concerning phylogenetic principal component analysis. Contrary to what Adams and Collyer found, we do not observe a bias against the simpler Brownian motion process in simulations when we use the new, improved, likelihood evaluation algorithm employed by mvSLOUCH, which allows for studying much larger phylogenies and more complex model setups.

PENDEKATAN ALGORITMA UNTUK EVALUASI DOSIS RADIASI DENGAN TLD-900 BARC PADA PENGUKURAN RADIASI ENERGI RENDAH

Accurate radiation dose evaluation for radiation workers is crucial to determine the radiation dose received from exposure. Using passive dosimeters such as TLD-900 can assist in monitoring and controlling radiation exposure by evaluating accumulated dose readings over a specific period. Due to its utilization in diverse radiation fields, the dose evaluation method should be able to differentiate the energy range employed. Energy dependence can pose a challenge in reading the received dose, particularly in the case of low-energy X-ray usage. Therefore, this study aims to develop an algorithm for individual equivalent dose evaluation Hp(10) in low-energy (<20 KeV) usage. The data will be obtained from the Nuclear Agency of Malaysia's Secondary Standard Dosimetry Laboratory (SSDL), including various ISO narrow series X-ray sources and several radioactive sources such as Cs-137, Co-60, Sr-90, Kr-85, and Pm-147. The evaluation method will involve a trumpet curve and ANSI bias plot, enabling an assessment of the performance of the developed algorithm. Ultimately, the algorithm will be used for long-term dose evaluation intercomparisons in low-dose reviews. The low-energy energy evaluation algorithm for equivalent doses has successfully been conducted. The algorithm performs very well in distinguishing energy types using the parameter r12. In contrast, the low-energy dose evaluation algorithm encounters difficulties due to the low-energy characteristics in energy deposition, which are similar for each element D. Keywords: Algorithm,radiation dose evaluation, TLD, Low Energy.

Resilient evaluation algorithm of caesium fountain clock based on robust adaptive observation model

The caesium fountain clock (CSF) is a primary frequency standard used to define the second, which can greatly improve the autonomous timekeeping ability of laboratories. However, CSF are susceptible to issues such as data interruptions, outliers, and significant fluctuations during operation, ultimately hindering their application in timekeeping. To address these issues, a resilient evaluation algorithm based on a robust adaptive observation model has been proposed. Robust and adaptive factors were introduced into the observation model of the Kalman filter to mitigate abnormal CSF operations. The proposed algorithm was tested through simulations and experiments, which demonstrated significant improvements in the accuracy and stability of the evaluation. As a result, this algorithm effectively reduces the impact of abnormal CSF operations and expands the application scope of CSF in the field of timekeeping.

Research on the Standardized Management System and Operational Indicators of Water Control Dikes Based on GA-BP Artificial Neural Network Model

Water control dikes, as an important infrastructure for national economic and social development, play an important supporting and guaranteeing role in flood control, irrigation, power generation, water supply, tourism, and other aspects. Jiangxi is a major province in water conservancy, with dense rivers and lakes, and it owns tens of thousands of water control dikes of various types. Most of the water control dikes exhibit structural aging, continuous medical risks, and reduced benefits, which urgently require efficient maintenance and standardized management. Management is a complex task, and the level of management directly affects the functional efficiency and service life of dikes. In view of these issues, this study takes dikes as essential and typical water conservancy engineering objects and analyzes the evaluation criteria of safe production and the demands of engineering management. It establishes an evaluation index system suitable for normalized management. The Analytic Hierarchy Process (AHP) model is utilized to determine indicator weights, and a neural network water conservancy engineering evaluation algorithm is constructed to match the evaluation model. Finally, an improved algorithm for the GA (genetic algorithm)-BP (backpropagation) neural network is proposed, incorporating additional momentum factors and considering adaptive learning rates. The developed model is validated through a case study in Jiangxi, China, and the results demonstrate its accuracy and comprehensiveness in reflecting the actual situation. This research is relevant to designers, contractors, and governments seeking solutions to achieve standardized management in water control dikes.

A Rust Extraction and Evaluation Method for Navigation Buoys Based on Improved U-Net and Hue, Saturation, and Value.

Abnormalities of navigation buoys include tilting, rusting, breaking, etc. Realizing automatic extraction and evaluation of rust on buoys is of great significance for maritime supervision. Severe rust may cause damage to the buoy itself. Therefore, a lightweight method based on machine vision is proposed for extracting and evaluating the rust of the buoy. The method integrates image segmentation and processing. Firstly, image segmentation technology is used to extract the metal part of the buoy based on an improved U-Net. Secondly, the RGB image is converted into an HSV image by preprocessing, and the transformation law of HSV channel color value is analyzed to obtain the best segmentation threshold and then the pixels of the rusted and the metal parts can be extracted. Finally, the rust ratio of the buoy is calculated to evaluate the rust level of the buoy. Results show that both the segmentation precision and recall are above 0.95, and the accuracy is nearly 1.00. Compared with the rust evaluation algorithm directly using the image processing method, the accuracy and processing speed of rust grade evaluation are greatly improved.

Evaluation model and algorithm optimization of intelligent manufacturing system on the basis of BP neural network

Intelligent manufacturing is a key direction for the development of the manufacturing industry. Since the level of intelligent manufacturing varies among enterprises, building a scientific and reliable evaluation model is the key to evaluate enterprises. The study optimizes the Back Propagation (BP) neural network based on the Firefly Algorithm (FA) and innovatively introduces the Sparrow Search Algorithm (SSA), which changes the search mechanism of the BP and improves the traditional BP affected by the local optimum. of the traditional BP. In the experimental results, the average error of the improved model is 1.34 % and 0.41 % under the optimal preset parameters, which is significantly better than other advanced algorithms. It is verified that the improved evaluation model in this study has lower error and better effect, which has better application value in the evaluation of intelligent manufacturing system.

A multi-dimensional fusion strategy similarity measure method for patent application technology disclosure document.

Patent application technology disclosure document is one of the important bases for judging patent novelty and uniqueness. Automated evaluation can effectively solve the problems of long time and strong subjectivity of human evaluation. The text similarity evaluation algorithm based on corpus and deep learning technology has problems such as insufficient amount of cross-library learning data and insufficient core content tendency in the similarity judgment of patent application technology disclosure document, which limits their performance and practical application. In this paper, we propose a similarity evaluation method of patent application technology disclosure document based on multi-dimensional fusion strategy to realize the similarity measurement of patents. Firstly, in the text preprocessing section, word segmentation reconstruction and similarity evaluation optimization strategies based on word frequency and part-of-speech score weighted fusion are proposed. Then, a similarity calculation method of patent application technology disclosure document based on two new mapping spaces of dot matrix and image is proposed to achieve a more diversified comprehensive evaluation. The algorithm was evaluated by using four published text similarity matching datasets (containing 0-5 or 0/1 labels) and a set of patent application technology disclosure documents. Experimental results show that on the published text similarity matching datasets, the similarity evaluation method under the multi-dimensional fusion strategy proposed in this paper has a discrimination accuracy improvement of about 10% compared to traditional vector semantic model, and can match the discriminative ability of lightweight deep learning models without the need for training. At the same time, the discrimination accuracy of the proposed method on the sample dataset of patent application technology disclosure document is superior to traditional vector semantic model (20%) and various deep learning models (1%-8%), and the precision and recall rate are relatively balanced. The visual analysis results on the dataset of the patent application technology disclosure documents also prove the effectiveness and reliability of the similarity calculation method proposed in the dot matrix and image space, which provide a new idea and method for the similarity evaluation between patent application technology disclosure document.

Mitigation of Grid Current Harmonics by ABC- ANN based Shunt Active Power Filter

Harmonics are being introduced into power system networks as a result of the increasing use of nonlinear devices. These harmonics cause distortion of current and voltage signals, which in turn causes damage to power distribution systems. As a result, the suppression of harmonics is of extreme significance in power systems. This paper proposes Shunt Active Power Filters (SAPF) based on neural network algorithms like Artificial Neural Network (ANN) as a feasible approach to mitigating harmonic distortion and raising power quality in electrical distribution systems. This research shows that using shunt active power filters (SAPF), which use the Artificial Bee Colony Optimized Artificial Neural Network Controller (ABC-ANN), is an efficient method for enhancing power quality and minimizing harmonic distortion in distribution systems. The ABC-ANN algorithms have been produced for SAPF with the goal of improving system performance by reducing Grid current Harmonics .In the first stage of this work, PSO Technique is used to tune a standard PI controller to its optimum gain values (Ki ,Kp). Then, these target and input data of PSO tuned PI controller will be supplying inputs to the ANN controller. To find the optimal weight and bias values, this ANN controller has been tuned with the help of the ABC algorithm. Using MATLAB/SIMULINK software, we compare the performance of the proposed algorithm to that of other optimization algorithm like Differential Evaluation (DE) algorithm, as well as the PSO tuned PI controller and traditional PI controller. The findings from the simulation suggest that a SAPF utilizing an ABC trained ANN controller could improve THD in the supplying current while maintaining harmonics within IEEE-519 accepting levels.

Integration of single-nucleus RNA sequencing and network disturbance to elucidate crosstalk between multicomponent drugs and trigeminal ganglia cells in migraine

Ethnopharmacological relevanceMigraine is caused by hyperactivity of the trigeminovascular system, where trigeminal ganglia (TG) plays an important role. TG is composed of multiple neuronal and non-neuronal cell types, which is related to “neuro-inflammation-vascular” disorder in migraine. Tou Tong Ning capsule (TTNC), a CFDA-approved traditional Chinese medicine for treating migraine, has the characteristics of “multicomponents, multitargets, multipathways". Aim of the studyTo clarify the mechanism of TTNC and elucidate crosstalk between multicomponent drugs and neuronal and non-neuronal functions and cells in migraine. Materials and methodsWe integrated single-nucleus RNA sequencing and a quantitative evaluation algorithm of the disturbance of multitarget drugs on the disease network and explored the specific pathology of migraine and corresponding compounds. A cerebrovascular smooth muscle spasmolytic activity experiment was carried out to verify the results of the bioinformatics analysis. ResultsTTNC exhibited its regulation activities in neuronal and non-neuronal aspects based on drugs attack to four subnetworks and cell specific networks, which explored the MoA of TTNC in comprehensive and refined perspectives. Compared to neuronal regulation, TTNC showed more significant attack score on non-neuronal biological function (smooth muscle and vessel). And TTNC compound clusters C1, C6 and C7, targeting non-neuronal function and cells, had larger group area than C10, C4 and C6 for neuronal function and cell, which implied that TTNC may mainly regulate the non-neuronal function, e.g., vessel smooth muscle contraction. Contraction of cerebrovascular smooth muscle of mice ex vivo confirmed the vasodilation activity of TTNC and active compounds from C1, C6, C9 (Emodin, Luteolin and Levistilide A). Literature mining confirmed the vasospasmodolytic activity and neuroprotective effect of TTNC. ConclusionsThe study found that TTNC may primarily alleviate non-neuronal functional disorders in migraine by relaxing cerebral vascular smooth muscle cell spasm to alleviate migraine. Integrating single-nucleus RNA sequencing data and network disturbance tools provides a new strategy for the pharmacological mechanism of multicomponent drugs through cell subtyping.

Оценка кормового поведения радужной форели (Oncorhynchus mykiss) при внесении в корма комплексной кормовой добавки с включением компонентов, повышающих его поедаемость

The potential to enhance the nutritional appeal of standard formulated feeds for rainbow trout by incorporating an additive with attractant and/or stimulant properties is demonstrated in the study. To assess the feeding behavior of the fish the evaluation algorithm was developed using a specialized setup with two feeding points, along with automatic video recording of the outcomes. The components within the feed additive (89% rapeseed oil, 4% hemp oil, 5% lycopene, and 2% cinnamyl aldehyde) not only aid in improving its palatability but can also have a positive influence on the fatty acid composition of the feeds. It was revealed that the feed additive (at quantities of 0.3% and 0.5%) significantly augmented the attractiveness of the feeds resulting in an increased number of fish congregating in the feeding area and an elevated consumption rate. The computation of the index of relative attractiveness allowed to identify a noteworthy disparity between the experimental and control feeds. The data obtained from the study can recommend the investigated comprehensive feed additive for enhancing the digestibility of standard fish feeds.

An AI-based algorithm for the automatic evaluation of image quality in canine thoracic radiographs

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.