Visual Mapping Research Articles

UVIO: Adaptive Kalman Filtering UWB-Aided Visual-Inertial SLAM System for Complex Indoor Environments

Precise positioning in an indoor environment is a challenging task because it is difficult to receive a strong and reliable global positioning system (GPS) signal. For existing wireless indoor positioning methods, ultra-wideband (UWB) has become more popular because of its low energy consumption and high interference immunity. Nevertheless, factors such as indoor non-line-of-sight (NLOS) obstructions can still lead to large errors or fluctuations in the measurement data. In this paper, we propose a fusion method based on ultra-wideband (UWB), inertial measurement unit (IMU), and visual simultaneous localization and mapping (V-SLAM) to achieve high accuracy and robustness in tracking a mobile robot in a complex indoor environment. Specifically, we first focus on the identification and correction between line-of-sight (LOS) and non-line-of-sight (NLOS) UWB signals. The distance evaluated from UWB is first processed by an adaptive Kalman filter with IMU signals for pose estimation, where a new noise covariance matrix using the received signal strength indicator (RSSI) and estimation of precision (EOP) is proposed to reduce the effect due to NLOS. After that, the corrected UWB estimation is tightly integrated with IMU and visual SLAM through factor graph optimization (FGO) to further refine the pose estimation. The experimental results show that, compared with single or dual positioning systems, the proposed fusion method provides significant improvements in positioning accuracy in a complex indoor environment.

Trends in Emotional Labor Research: Bibliometric and Science Mapping Analysis

Emotional labor is about employees in the service sector involving their emotions while performing the service job as required. Emotions are also used for commercial purposes. The study analyzes data on emotional labor through bibliometric and science mapping methods. For the analyses, data between 1982 and 2024 are scanned in the Web of Science (WoS) database, and data for 2,925 documents are accessed. After loading the data, the VOSviewer program is utilized to analyze it for bibliometric and science mapping purposes. Subsequently, the investigation unveiles the foremost authors, countries, journals, institutions, and keywords in emotional labor research. This is followed by analyzing their co-authorship, co-citation, bibliographic coupling, and keyword co-occurrence models. As a result, in emotional labor research, it is found that Alicia A. Grandey is the most productive and most cited author, the USA is the most productive country, Frontiers in Psychology is the most productive journal, and the most frequently encountered keywords are burnout, surface acting, job satisfaction, deep acting, and emotional exhaustion, respectively. The analysis findings reveal a collaborative nexus among authors, countries, and institutions, offering visual network maps and comprehensive insights into emotional labor's present status and trends within the scientific literature.

Research on the application of radiomics in breast cancer: A bibliometrics and visualization analysis.

Breast cancer is the most prevalent form of cancer worldwide. Therefore, improved disease detection has emerged as a focal point in clinical studies. At the forefront of innovation, radiomics has the capability to extract comprehensive insights from medical images, ultimately enhancing the accuracy of diagnostic procedures. There has been rapid growth in the field of radiomics research on breast cancer in the past few years. We explored pertinent research articles in the Web of Science Core Collection database to gain a thorough understanding of breast cancer radiomics. We used CiteSpace to conduct a bibliometric analysis of the annual distribution of different nations, institutions, journals, authors, keywords, and references in the field of breast cancer radiomics. GraphPad Prism software was used to examine and graph yearly and country-specific trends and the proportions of publications. The tools utilized for the visualization of science mapping included CiteSpace and VOSviewer. Of the 891 publications, most were original articles (731, 91.09%) and a few were reviews (160, 8.91%). Most academic research has been published in China and the United States. The study centers predominantly consisted of major academic institutions, such as Fudan University and the Chinese Academy of Sciences, with some of their members being prominent figures in the field. Pinker, Katja has published the largest number of research papers. The majority of these studies have been published in medical journals focusing on radiology and oncology in recent years. In the realm of cutting-edge medical research, the top two keywords, magnetic resonance imaging and machine learning stand at the forefront as current areas of intense focus. Breast cancer radiomics is advancing rapidly, presenting numerous opportunities and obstacles. Our study of the literature in this academic area aimed to pinpoint the primary themes addressed in the studies and anticipate prospective avenues for research.

Parallel implementation for real-time visual SLAM systems based on heterogeneous computing

Simultaneous localization and mapping has become rapidly developed and plays an indispensable role in intelligent vehicles. However, many state-of-the-art visual simultaneous localization and mapping (VSLAM) frameworks are very time-consuming both in front-end and back-end, especially for large-scale scenes. Nowadays, the increasingly popular use of graphics processors for general-purpose computing, and the progressively mature high-performance programming theory based on compute unified device architecture (CUDA) have given the possibility for large-scale VSLAM to solve the conflict between limited computing power and excessive computing tasks. The paper proposes a full-flow optimal parallelization scheme based on heterogeneous computing to speed up the time-consuming modules in VSLAM. Firstly, a parallel strategy for feature extraction and matching is designed to reduce the time consumption arising from multiple data transfers between devices. Secondly, a bundle adjustment method based solely on CUDA is developed. By fully optimizing memory scheduling and task allocation, a large increase in speed is achieved while maintaining accuracy. Besides, CUDA heterogeneous acceleration is fully utilized for tasks such as error computation and linear system construction in the VSLAM back-end to enhance the operation speed. Our proposed method is tested on numerous public datasets on both computer and embedded sides, respectively. A number of qualitative and quantitative experiments are performed to verify its superiority in terms of speed compared to other states-of-the-art.

Enhancing the Diagnostic Accuracy of Sacroiliitis: A Machine Learning Approach Applied to Computed Tomography Imaging.

Aims/Background Sacroiliitis is a challenging condition to diagnose accurately due to the subtle nature of its presentation in imaging studies. This study aims to improve the diagnostic accuracy of sacroiliitis by applying advanced machine learning techniques to computed tomography (CT) images. Methods We employed five convolutional neural network (CNN) models-Visual Geometry Group 16-layer Network (VGG16), ResNet101, DenseNet, Inception-v4, and ResNeXt-50-to analyze a dataset of 830 CT images, including both sacroiliitis and non-sacroiliitis cases. Each model's performance was evaluated using metrics such as accuracy, precision, recall, F1 score, Receiver Operating Characteristic (ROC), and Area Under the Curve (AUC). The interpretability of the models' decisions was enhanced using Gradient-weighted Class Activation Mapping (Grad-CAM) visualization. Results The ResNeXt-50 and Inception-v4 models demonstrated superior performance, achieving the highest accuracy and F1 scores among the tested models. Grad-CAM visualizations offered insights into the decision-making processes, highlighting the models' focus on relevant anatomical features critical for accurate diagnosis. Conclusion The use of CNN models, particularly ResNeXt-50 and Inception-v4, significantly improves the diagnosis of sacroiliitis from CT images. These models not only provide high diagnostic accuracy but also offer transparency in their decision-making processes, aiding clinicians in understanding and trusting Artificial Intelligence (AI)-driven diagnostics.

W-VSLAM: A Visual Mapping Algorithm for Indoor Inspection Robots.

In recent years, with the widespread application of indoor inspection robots, high-precision, robust environmental perception has become essential for robotic mapping. Addressing the issues of visual-inertial estimation inaccuracies due to redundant pose degrees of freedom and accelerometer drift during the planar motion of mobile robots in indoor environments, we propose a visual SLAM perception method that integrates wheel odometry information. First, the robot's body pose is parameterized in SE(2) and the corresponding camera pose is parameterized in SE(3). On this basis, we derive the visual constraint residuals and their Jacobian matrices for reprojection observations using the camera projection model. We employ the concept of pre-integration to derive pose-constraint residuals and their Jacobian matrices and utilize marginalization theory to derive the relative pose residuals and their Jacobians for loop closure constraints. This approach solves the nonlinear optimization problem to obtain the optimal pose and landmark points of the ground-moving robot. A comparison with the ORBSLAM3 algorithm reveals that, in the recorded indoor environment datasets, the proposed algorithm demonstrates significantly higher perception accuracy, with root mean square error (RMSE) improvements of 89.2% in translation and 98.5% in rotation for absolute trajectory error (ATE). The overall trajectory localization accuracy ranges between 5 and 17 cm, validating the effectiveness of the proposed algorithm. These findings can be applied to preliminary mapping for the autonomous navigation of indoor mobile robots and serve as a basis for path planning based on the mapping results.

Evaluation of The Studies on Unmanned Aircraft System Safety Management Systems with Bibliometric Analysis

UAV operations and their literature are developing rapidly. Along with the increasing number of risky situations, new technologies and measures are being developed to eliminate the unsafe situations created by them. Increasing UAVs have potential to lead to unsafe situations in airspace with incident and accident background. In addition to all other studies related to UAVs, studies on safety management systems, as well as other topics related to the safety management system, need to increase. In this study, a bibliometric analysis of the studies on UAVs between the years 2003-2022 was conducted from the perspective of safety management. For this purpose, the publications found in the Dimensions database were examined. Those publications related to UAVs were filtered according to certain criteria such as year, author, country, institution, and a sample was formed with 741 publications by using bibliometric analysis method. VOSViewer application was used for bibliometric analysis and the achieved data were visualized in the form of tables, graphics and visual maps. The findings show that the vast majority of publications on keywords were published in 2021. The most cited publication was written by Colomina and Molina in 2014. Most of the publications came up from the United States of America in total where 86 studies were conducted. The most cited organization is the University of Florida. In the cluster work, the words of remote sensing, sensor, and drones appear frequently.

When we talk about time, we mean many different things: employing visual mapping to think through more-than-human temporalities in participatory design

When we talk about time, we mean many different things: employing visual mapping to think through more-than-human temporalities in participatory design

Walnuts as functional food and nutraceutical: A bibliometric study of research trends on nutritional potential, phytochemistry and its health benefits

AimThis study aims to conduct a bibliometric analysis of English walnut (Juglans regia L.) using the Scopus database. This study has also attempted to explore walnut’s nutritional potential, phytochemistry, and functional properties for overall human health benefits. MethodologyThis study uses the R-Bibliometrics package software to explore the Scopus database from 2002 to 2021. The keywords used are “Walnut” OR “Juglans regia” OR “Nutritional Potential” OR “Functional Food” OR “Phytochemistry” OR “Human health”. ResultsThe global trends and bibliometric analysis of walnut from 2002–2021 found that there was a total of 9868 documents indexed in 3151 Scopus-indexed sources. The agricultural and biological sciences recorded the maximum net publication, while the dentistry field recorded the minimum. Countries like China and the United States were the major funding sources, having the maximum net publications all over the globe. Upon analysing international collaboration, countries such as China, the USA, Italy, Iran, Spain, and the United Kingdom emerged as the world’s top collaborators. Maximum co-occurrences of the following keywords found are walnut, omega-3 fatty acid, Juglans regia, and walnut food. The most productive journals in walnut research recorded according to Bradford Law, the most productive walnut research journals were Acta Horticulture, Food Chemistry, Plant Diseases, Journal of Agricultural Hortiscience, Scientia Horticultureae, Nutrients, Molecules, PloS One, and Journal of Ethnopharmacology. People around the world use walnuts in a variety of foods and consider them an integral part of their diets. Walnut contains a variety of bioactive compounds, such as polyphenols, alkaloids, and juglone, as well as nutrients like omega-3 fatty acids, which make it a functional food for humans. Walnuts are much more than just a culinary item in traditional foods; they can provide a variety of human health benefits. ConclusionsThis study attempted to conduct a bibliometric analysis to analyze global trends and research productivity of walnut as a functional food in terms of phytochemistry, nutritional potential, and human health benefits. This study will help to identify the research gap, offer opportunities for multidisciplinary research, and present a novel visualisation map for walnut research. This study declared walnut a functional food for the future.

Paddy seed viability prediction based on feature fusion of color and hyperspectral image with multivariate analysis

Seed viability is essential to have a homogeneous plant population. The seed industry cannot adopt traditional procedures for seed viability evaluation since they are destructive, time-consuming, and need chemicals. This study aimed to investigate the potential of combining hyperspectral and color image features to differentiate viable and non-viable paddy seeds. The hyperspectral and color image of the 355 paddy seeds was captured and later used to examine their viability. An image processing algorithm was developed to extract features from color images of paddy seeds and investigated significant differences in the retrieved feature data using variance analysis. The spectra were extracted from the selected region of interest (ROI) of the hyperspectral paddy seed image and averaged. In the next step, the partial least square discrimination analysis (PLS-DA) model was developed to distinguish viable and non-viable paddy seeds. Initially, the PLS-DA model was developed using spectral data with different preprocessing techniques, and the result obtained an accuracy of 88.9 % in the calibration set and 86.1 % in the prediction set using Savitzky-Golay 2nd derivative preprocessed spectra. With the fusion of spectral and significant color image features, the model's accuracy improved to 93.3 % and 90.9 % in the calibration and prediction sets, respectively. Results also showed that the fusion of selected color image features with Savitzky-Golay 2nd derivative preprocessed spectra could achieve higher F1-score, recall, and precision values. The visualization map for the viable and non-viable paddy seeds was also developed utilizing the most effective predictive model. The results demonstrate the possibility of using the fusion of the hyperspectral and color image features to sort seeds according to viability, which may be applied in developing an online seed sorting method.

Pengembangan Keuangan Mikro Islam untuk Mengatasi Kemiskinan dan Mencapai Tujuan SDGs: Pendekatan Bibliometrik

This study tries to review research on sustainable microfinance development in Scopus indexed journals. This analysis uses descriptive statistical analysis based on 319 selected papers related to microfinance sustainable development from both national and international journals. All samples of published journals have been published for 27 years from 1996 to 2022. The data is then processed and analyzed using the VOSviewer application program to find out the bibliometric visualization map for sustainable development of microfinance research. The results of this bibliometric mapping study show a map of the development of research in the field of microfinance sustainable development. This study also found a close relationship between microfinance sustainable development and the main goal of the SDGs, namely eradicating poverty to promote prosperity for all people of all ages around the world. This research finds new and interesting keywords for further research.

Knowledge structure and research hotspots on digital scanning for implant-supported complete-arch prosthesis: A bibliometric analysis

BackgroundDigital scanning is increasingly widely used for implant-supported complete-arch prosthese. However, a quantitative literature analysis is lacking for this field. This study aims to conduct a bibliometric analysis to summarize the knowledge structure and research hotspots of digital scanning for implant-supported complete-arch prosthesis. Materials and methodsRelevant articles and reviews, published between 1994 and 2023, were obtained from the Web of Science Core Collection (WoSCC). Indicators such as publication count, annual growth, citation count, co-citation count, impact factor, Journal citation reports (JCR) division, H-index are used to assess the contribution of countries, journals, authors or the quality of articles. Visual maps, cluster analysis and keyword cloud are used to evaluate the cooperation pattern and topic trends. Results580 eligible publications, including 555 articles and 25 reviews, were analyzed. The United States is the leading country in this area, received the most citations. The Journal of Prosthetic Dentistry is the scientific journal with the highest impact. The analysis of keywords and ongoing trials shows that the accuracy of relevant techniques is a current hot topic in this field. ConclusionIn recent years, digital scanning technique for implant-supported complete-arch prosthesis has made rapid progress. By reviewing the published literature, we found the United States is the global leader in the field of digital scanning for complete-arch implant prosthesis. Accuracy is the core word in this field, more scientific evidence is needed to support the clinical application of digital scanning in this field.

Global research trends in the treatment of squamous cell carcinoma over the past decade: A bibliometric analysis

ObjectiveThis study aims to identify research trends and hot spots in the treatment of Squamous Cell Carcinoma (SCC) over the past decade using bibliometric analysis. MethodsData were extracted from the Web of Science Core Collection, including Science Citation Index Expanded (SCI-Expanded), Social Sciences Citation Index (SSCI), and Emerging Sources Citation Index (ESCI). The data underwent manual cleaning to remove inaccuracies and irrelevancies, followed by transformation into an analyzable format via the VOSviewer software. This tool facilitated the visualization of co-occurrence networks and keyword maps, highlighting the relationships and the prominence of research themes. ResultsA total of 46448 authors from 7374 institutions across 108 countries contributed to the literature, reflecting a broad international effort. The study documented a consistent increase in SCC-related publications up to 2020, with some variability in subsequent years. Notably, the United States, Germany, China, the United Kingdom, and France were predominant in this research area. The University of Texas MD Anderson Cancer Center and the University of Pittsburgh were leading contributors in terms of publication volume and citation impact. Key journals included ‘Oral Oncology’ and ‘Clinical Cancer Research’, which were central to the dissemination of high-impact research. Our keyword analysis identified three major research clusters focused on molecular mechanisms, clinical treatment strategies, and emerging interests in immunotherapeutic approaches. ConclusionsThe extensive collaboration and the increasing publication trend underscore the growing global commitment to advancing SCC treatment. The high level of engagement from top institutions and the concentration of research in influential journals reflect the field's dynamic evolution towards innovative and effective treatment modalities. This study provides a valuable overview for researchers, guiding future studies towards areas of high impact and emerging trends in SCC treatment. The findings advocate for enhanced focus on personalized medicine and combination therapies, which are poised to improve outcomes for SCC patients.

SLG-SLAM: An integrated SLAM framework to improve accuracy using semantic information, laser and GNSS data

Visual Simultaneous Localization and Mapping (V-SLAM) is pivotal for precise positioning and mapping. However, visual data from crowd-sourced datasets often contains deficiencies that may lead to positioning errors. Despite existing optimization techniques, current algorithms do not adequately adapt to varied data in vehicle driving scenarios. To address this gap, this study introduces a novel SLAM framework (SLG-SLAM). This framework refines trajectories by integrating semantic information, laser point cloud, and global navigation satellite system (GNSS) data into V-SLAM. Initial trajectory estimates are made after filtering out dynamic targets and are subsequently refined with matched laser point clouds, then corrected for scale and direction using GNSS. The efficacy of this approach is assessed using four public datasets and one self-collected dataset, showing significant enhancements across all datasets. The proposed method reduces the mean absolute trajectory error by 43.50% on the KITTI dataset and 14.91% on the MVE dataset compared to the baseline. Unlike the baseline, which fails on three other datasets, the proposed method successfully performs localization and mapping. Additionally, compared to three other single-source methods (DynaSLAM, MCL, MVSLAM), the proposed method consistently outperforms, demonstrating its superior adaptability and effectiveness.

Retinotopy drives the variation in scene responses across visual field map divisions of the occipital place area.

The occipital place area (OPA) is a scene-selective region on the lateral surface of human occipitotemporal cortex that spatially overlaps multiple visual field maps, as well as portions of cortex that are not currently defined as retinotopic. Here we combined population receptive field modeling and responses to scenes in a representational similarity analysis (RSA) framework to test the prediction that the OPA's visual field map divisions contribute uniquely to the overall pattern of scene selectivity within the OPA. Consistent with this prediction, the patterns of response to a set of complex scenes were heterogeneous between maps. To explain this heterogeneity, we tested the explanatory power of seven candidate models using RSA. These models spanned different scene dimensions (Content, Expanse, Distance), low- and high-level visual features, and navigational affordances. None of the tested models could account for the variation in scene response observed between the OPA's visual field maps. However, the heterogeneity in scene response was correlated with the differences in retinotopic profiles across maps. These data highlight the need to carefully examine the relationship between regions defined as category-selective and the underlying retinotopy, and they suggest that, in the case of the OPA, it may not be appropriate to conceptualize it as a single scene-selective region.

Photobiomodulation therapy for oral lesions: a bibliometric analysis

Photobiomodulation therapy is a nonthermal light therapy with therapeutic properties for pain and inflammation relief, immune modulation, and tissue regeneration. Our goal was to provide a comprehensive overview of photobiomodulation therapy for oral lesions using visual mapping techniques. We used VOSViewer to analyze publications in the “photobiomodulation” and “oral lesion” categories from PubMed, Scopus, and Dimension AI databases, allowing us to track author contributions, journal, institutional affiliations, and contributions by country. A total of 373 publications from 1991 to 2022 were gathered. Notably, Brazil, the United States, and France emerged as major contributors in this field. The College of Dentistry at the University of Florida (US) ranked first with 515 citations. Jan Magnus Bjordal was the most prolific author, receiving 207 total citations. Supportive Care in Cancer and Photomedicine and Laser Surgery were identified as the two most promising journals. The intellectual structure was divided into four clusters: cluster one for ‘lllt’, cluster two for ‘head and neck cancer’, cluster three for ‘olp’, and cluster four for ‘inflammatory mediators’. Overall, there has been a significant increase in research on photobiomodulation, particularly over the last decade. The study identified four distinct research clusters: low-level light therapy, head and neck cancer, oral lichen planus, and inflammatory mediators. These findings highlight the need for further research into photobiomodulation in the treatment of various oral diseases. This trend may indicate an increase in the use of low-level light therapy to treat oral lesions in the population, as well as the potential for alternative treatments.

Public Health Risk from Influenza Viruses: A Scientometric Analysis of Influenza Research.

Seasonal influenza and novel H1N1 influenza from 2009 present worldwide difficulties for public health sectors. It is difficult to distinguish between significant research output due to the rising quantity of papers mentioning this infectious disease. We aimed to identify a scientometric analysis of influenza diseases. We aimed to highlight the progress made in the discipline by the researchers affiliated with most documents. The h-index was used to evaluate the publication performance of highly cited papers. We retrieved the scientometric data using the keywords "Influenza" OR "Flu" OR "Orthomyxoviridae" AND "Antiviral agents" OR "Antiviral drugs." In all, 59013 documents were retrieved from the Web of Science between 2011 and 2020. The exported data to Biblioshiny and Microsoft Excel tools included sources by year, active authors, active journals, and countries. Also, we made use of quantitative analysis with scientometric indicators and knowledge mapping through the VOSviewer visualization software for creating the network visualization maps. We found most papers written in English and other languages were from 402027 authors and listed in 4443 core journals. The researchers found that Palese P produced 155 and received an h-index of 55. The author Li Y has the highest contributions, with 313 publications. In global influenza research, Europe and North America are the most productive and impactful continents. The influenza research has been published in very few journals. This study will help hospital librarians and other library professionals to understand the status of research on influenza at any given point in time.

An Approach to Analyzing Migration Flow and House Price Data: Exploring Spatial Linkages between Flow, Price, Distance, Age at the Local Level

This paper is intended to elucidate the efficacy of employing a Geographic Information Systems (GIS) methodology to investigate the spatial interrelations among migration flows, housing prices, age demographics, and geographical distances. Utilizing data on migration flows and housing prices from Greater Manchester, UK, in 2011, in this study, we performed statistical analyses and generated a suite of visual mappings to illustrate the spatial dynamics between migration patterns, distances, age brackets, and the segmentation of migration destinations by housing price tiers. The findings reveal pronounced spatial associations among migration destinations, underscored by the interplay of housing price levels with age categories, distance intervals, or the origination points tied to specific housing price ranges. This GIS-based analytical framework offers policy-makers and urban planners a powerful tool for discerning distinct migration trends and locales, thereby facilitating more informed decision-making processes.

Review of Research on New Media Art in China from 2003 to 2022 - A Bibliometric Analysis Based on CiteSpace

With the enrichment of digital technology, new media art has become a hot topic in the current art field. However, the academic field lacks a comprehensive discussion on the development trend of new media art in China. To gain a clearer understanding of the development process of Chinese New Media Art, this research adopts the method of bibliometrics combined with CiteSpace Knowledge Map visualization software. Using 550 articles from the CSSCI Database for visualization knowledge map presentation, data analysis is conducted on the number of annual publications, academic institutions and authors, and bursting keywords. This presents the development history, evolution of hotspots, and future trends of Chinese New Media Art. The research found that the number of annual publications of Chinese new media art can be divided into four stages: slow growth from 2003 to 2006, rapid growth from 2007 to 2010, slow increase from 2011 to 2017, and fluctuating development from 2017 to 2022. Secondly, there is a low density of cooperation between authors and academic institutions, and no clear academic groups have been formed, with academic institutions mainly located in economically developed first-tier cities. It is predicted that "Virtual Reality, Artificial Intelligence, and Human-Computer Interaction" will become the future development directions of Chinese new media art research. It is hoped that this research can provide theoretical reference and data support for the future development of New Media Art in China.

Automatic detection and visualization of temporomandibular joint effusion with deep neural network

This study investigated the usefulness of deep learning-based automatic detection of temporomandibular joint (TMJ) effusion using magnetic resonance imaging (MRI) in patients with temporomandibular disorder and whether the diagnostic accuracy of the model improved when patients’ clinical information was provided in addition to MRI images. The sagittal MR images of 2948 TMJs were collected from 1017 women and 457 men (mean age 37.19 ± 18.64 years). The TMJ effusion diagnostic performances of three convolutional neural networks (scratch, fine-tuning, and freeze schemes) were compared with those of human experts based on areas under the curve (AUCs) and diagnosis accuracies. The fine-tuning model with proton density (PD) images showed acceptable prediction performance (AUC = 0.7895), and the from-scratch (0.6193) and freeze (0.6149) models showed lower performances (p < 0.05). The fine-tuning model had excellent specificity compared to the human experts (87.25% vs. 58.17%). However, the human experts were superior in sensitivity (80.00% vs. 57.43%) (all p < 0.001). In gradient-weighted class activation mapping (Grad-CAM) visualizations, the fine-tuning scheme focused more on effusion than on other structures of the TMJ, and the sparsity was higher than that of the from-scratch scheme (82.40% vs. 49.83%, p < 0.05). The Grad-CAM visualizations agreed with the model learned through important features in the TMJ area, particularly around the articular disc. Two fine-tuning models on PD and T2-weighted images showed that the diagnostic performance did not improve compared with using PD alone (p < 0.05). Diverse AUCs were observed across each group when the patients were divided according to age (0.7083–0.8375) and sex (male:0.7576, female:0.7083). The prediction accuracy of the ensemble model was higher than that of the human experts when all the data were used (74.21% vs. 67.71%, p < 0.05). A deep neural network (DNN) was developed to process multimodal data, including MRI and patient clinical data. Analysis of four age groups with the DNN model showed that the 41–60 age group had the best performance (AUC = 0.8258). The fine-tuning model and DNN were optimal for judging TMJ effusion and may be used to prevent true negative cases and aid in human diagnostic performance. Assistive automated diagnostic methods have the potential to increase clinicians’ diagnostic accuracy.