Set Of Images Research Articles

Development and Clinical Application of Artificial Intelligence Assistant System for Rotator Cuff Ultrasound Scanning

We developed an intelligent assistance system for shoulder ultrasound imaging, incorporating deep-learning algorithms to facilitate standard plane recognition and automatic tissue segmentation of the rotator cuff and its surrounding structures. We evaluated the system's performance using a dedicated data set of rotator cuff ultrasound images to assess its feasibility in clinical practice. To fulfill the system's primary functions, we designed a standard plane recognition module based on the ResNet50 network and an automatic tissue segmentation module using the Mask R-CNN model. The modules were trained on carefully curated data sets. The standard plane recognition module automatically identifies a specific standard plane based on the ultrasound image characteristics. The automatic tissue segmentation module effectively delineates and segments anatomical structures within the identified standard plane. With the use of 59,265 shoulder joint ultrasound images, the standard plane recognition model achieved an impressive recognition accuracy of 94.9% in the test set, with an average precision rate of 96.4%, recall rate of 95.4% and F1 score of 95.9%. The automatic tissue segmentation model, tested on 1886 images, exhibited a commendable average intersection over union value of 96.2%, indicating robustness and accuracy. The model achieved mean intersection over union values exceeding 90.0% for all standard planes, indicating its effectiveness in precisely delineating the anatomical structures. Our shoulder joint musculoskeletal intelligence system swiftly and accurately identifies standard planes and performs automatic tissue segmentation.

Emoji

Abstract Online users devise different strategies and techniques to make up for the absence of physical bodies in online communications, one of which is using emojis. Emojis are a diverse set of small images, symbols, or icons, standardized by the Unicode Consortium for utilization in electronic communication platforms. Their primary role is to effectively convey the emotional attitude of the writer, succinctly provide information, and playfully communicate messages. This article posits that bodily emojis (emojis portraying a body gesture or facial expression) are a form of digital embodiment. Their usage, thus, creates a form of digital performance. Emojis appear as a screen body in a space that lacks the physical one. Furthermore, I suggest that this body could be described as aesthetically Baroque. My proposition is that emojis exhibit Baroque characteristics such as dynamic and exaggerated forms and decorate texts. Emojis share similarities with the appearance and function of the Baroque body both in Baroque visual art and Baroque dance.

Tight Remainder-Form Decomposition Functions With Applications to Constrained Reachability and Guaranteed State Estimation

This paper proposes a tractable family of remainder-form mixed-monotone decomposition functions that are useful for over-approximating the image set of nonlinear mappings in reachability and estimation problems. Our approach applies to a new class of nonsmooth, discontinuous nonlinear systems that we call either-sided locally Lipschitz semicontinuous (ELLS) systems, which we show to be a strict superset of locally Lipschitz continuous (LLC) systems, thus expanding the set of systems that are formally known to be mixed-monotone. In addition, we derive lower and upper bounds for the over-approximation error and show that the lower bound is achieved with our proposed approach, i.e., our approach constructs the tightest, tractable remainder-form mixed-monotone decomposition function. Moreover, we introduce a set inversion algorithm that along with the proposed decomposition functions, can be used for constrained reachability analysis and guaranteed state estimation for continuous- and discrete-time systems with bounded noise.

Multichannel Image Completion With Mixture Noise: Adaptive Sparse Low-Rank Tensor Subspace Meets Nonlocal Self-Similarity.

Multichannel image completion with mixture noise is a common but complex problem in the fields of machine learning, image processing, and computer vision. Most existing algorithms devote to explore global low-rank information and fail to optimize local and joint-mode structures, which may lead to oversmooth restoration results or lower quality restoration details. In this study, we propose a novel model to deal with multichannel image completion with mixture noise based on adaptive sparse low-rank tensor subspace and nonlocal self-similarity (ASLTS-NS). In the proposed model, a nonlocal similar patch matching framework cooperating with Tucker decomposition is used to explore information of global and joint modes and optimize the local structure for improving restoration quality. In order to enhance the robustness of low-rank decomposition to data missing and mixture noise, we present an adaptive sparse low-rank regularization to construct robust tensor subspace for self-weighing importance of different modes and capturing a stable inherent structure. In addition, joint tensor Frobenius and l1 regularizations are exploited to control two different types of noise. Based on alternating directions method of multipliers (ADMM), a convergent learning algorithm is designed to solve this model. Experimental results on three different types of multichannel image sets demonstrate the advantages of ASLTS-NS under five complex scenarios.

Preliminary study of cine-MRI compression in MR-guided radiotherapy.

Cine-magnetic resonance imaging (MRI) is currently used in real-time tumor tracking during magnetic resonance (MR)-guided radiotherapy. As a type of MRI specified for motion tracking, a few minutes' acquisition results in thousands of 2-dimensional (2D) images. For MR-guided radiotherapy consisting of multiple treatment fractions, the large number of cine-MRI images would be disproportionate to the tight clinical data storage available. To alleviate this issue, the feasibility of compression of cine-MRI via video encoders was investigated in this study. The cine-MRI images were first sorted into 3 sequences according to their plane orientations. Then, each sequence was reordered according to their acquisition times [time-based (TB)] or content similarities [similarity-based (SB)]. As a result, 3 sequences were obtained for 3 plan orientations. Next, the obtained sequences were processed by a video encoder and the corresponding 3 video files were achieved. We employed 3 popular video encoders: Motion JPEG (M-JPEG), Advanced Video Coding (AVC), and High Efficiency Video Coding (HEVC). The performances of the sequence reordering methods and video encoders were evaluated based on a total of 150 image sets. The mean correlation quantities for SB sequences were higher than those for TB sequences by 3% (sagittal), 2% (coronal), and 1% (transverse), respectively. The average compression ratio (CR) yielded by the SB sequences was higher than that achieved by the TB sequences. Comparing with M-JPEG, the CRs obtained by AVC and HEVC were increased by 58% and 62% (sagittal), 16% and 23% (coronal), and 48% and 56% (transverse), respectively. Among the 3 video encoders, the highest CRs and restoration accuracy were achieved by HEVC. HEVC with inter-frame coding is more effective in reducing the redundant information in consecutive images. It is feasible to implement the video encoder for high-performance cine-MRI compression.

The Application of Dual-layer Spectral Detector CT in Abdominal Vascular Imaging.

As a convenient and non-invasive diagnostic method, computed tomography (CT) has been developing continuously, and dual-energy CT imaging is one of its current research hotspots. Dualenergy CT, using two different X-ray energies for imaging, can generate spectral image sets such as virtual monoenergetic images, virtual non-contrast images, iodine density images, uric acid images, calcium inhibition images, and effective atomic number images. These images could help to increase the contrast of vascular, improve the detection rate of lesions, reduce artifacts, reduce the dose of radiation, and characterize materials. Dual-layer spectral detector CT, a detector-based dual-energy scanning device, has an X-ray tube and a dual-layer X-ray detector that can simultaneously separate lowenergy and high-energy photons from a multi-energy X-ray beam, which means excellent time registration. This paper aims to introduce the applications of dual-layer spectral detector CT in abdominal angiography, including optimizing image quality, reducing the dose of contrast agent and radiation, providing richer diagnostic information, organ perfusion, and thrombus identification.

Autoimmune Pancreatitis Surveillance: A Simplified MRI Protocol Versus a Comprehensive Pancreatic MRI Protocol

Magnetic resonance imaging (MRI) has good diagnostic performance and causes no radiation damage, making it an ideal tool for the autoimmune pancreatitis (AIP) surveillance. However, its time cost is high. This study aimed to evaluate (1) whether a simplified protocol (SP) of MRI for AIP surveillance provides information equivalent to the comprehensive protocol (CP) and (2) the time cost reductions associated with using an SP. This retrospective single-institutional study included 40 patients with AIP with at least two contrast-enhanced MRI/magnetic resonance cholangiopancreatography studies. Two radiologists evaluated two imaging sets (CP/SP) per patient, independently. Intra- and inter-observer agreement in the evaluation of the pancreas and extrapancreatic organs involvement using the SP/CP in addition to the time cost differences between the SP and CP were assessed. Intra- and inter-rater reliability were assessed using Cohen's kappa test, intraclass correlations, or the weighted kappa test. The differences in time costs between the CP and SP were compared using the Mann-Whitney U test or Wilcoxon signed-rank test. The SP had strong intra- and inter-observer agreement with the CP in evaluating MRI parameters (κ＞0.60, moderate to excellent) and disease activity status (κ＞0.80, all excellent). The overall image acquisition time cost for the SP was 49.2% of the CP. For the two radiologists, the image interpretation time cost of the SP was reduced by approximately 35% and 27% compared to the CP. For AIP surveillance, SP MRI provides information consistent with the CP and is less time-consuming.

Augmented Grad-CAM++: Super-Resolution Saliency Maps for Visual Interpretation of Deep Neural Network

In recent years, deep neural networks have shown superior performance in various fields, but interpretability has always been the Achilles’ heel of deep neural networks. The existing visual interpretation methods for deep neural networks still suffer from inaccurate and insufficient target localization and low-resolution saliency maps. To address the above issues, this paper presents a saliency map generation method based on image geometry augmentation and super-resolution called augmented high-order gradient weighting class activation mapping (augmented grad-CAM++). Unlike previous approaches that rely on a single input image to generate saliency maps, this method first introduces the image geometry augmentation technique to create a set of augmented images for the input image and generate activation mappings separately. Secondly, the augmented activation mappings are combined to form the final saliency map. Finally, a super-resolution technique is introduced to add pixel points to reconstruct the saliency map pixels to improve the resolution of the saliency map. The proposed method is applied to analyze standard image data and industrial surface defect images. The results indicate that, in experiments conducted on standard image data, the proposed method achieved a 3.1% improvement in the accuracy of capturing target objects compared to traditional methods. Furthermore, the resolution of saliency maps was three times higher than that of traditional methods. In the application of industrial surface defect detection, the proposed method demonstrated an 11.6% enhancement in the accuracy of capturing target objects, concurrently reducing the false positive rate. The presented approach enables more accurate and comprehensive capture of target objects with higher resolution, thereby enhancing the visual interpretability of deep neural networks. This improvement contributes to the greater interpretability of deep learning models in industrial applications, offering substantial performance gains for the practical deployment of deep learning networks in the industrial domain.

Correlation between maximum heart distance and thoracic diameter changes and diaphragmatic descent in left-sided breast cancer patients during deep inspiration breath-hold (DIBH).

Cardioprotection is valued in radiotherapy for patients with left-sided breast cancer. Deep inspiration breath-hold (DIBH) technique can achieve cardioprotection well. However, during DIBH, the extent to which the heart enters the radiation field is affected by the movement of the thorax and diaphragm. The aim of this study was to analyze the correlation between the maximum distance of the heart entering the field (maximum heart distance, MHD) and thoracic diameter changes and diaphragmatic descent in left-sided breast cancer patients during DIBH. Ninety-eight patients with left-sided breast cancer were included in this retrospective study. They performed simulation in Sentinel-guided DIBH, and two sets of CT images were collected under both free breathing (FB) and DIBH, and diaphragm positions, anteroposterior thoracic diameter (ATD), transverse thoracic diameter (TTD), gating window level (GWL), and MHD were measured, and the change (Δ) of each parameter in DIBH relative to that in FB were calculated. Pearson or Spearman test were used to analyze the correlation between ΔMHD and the changes in other parameters. For all patients with DIBH, the average of ΔMHD was -8.3 mm, and the average of ΔATD and ΔTTD were 11.0 and 8.6 mm, and the median of both left diaphragmatic descent (LDD) and right diaphragmatic descent (RDD) were 35.0 mm, and the median of GWL was 11.1 mm. The correlation coefficients between MHD decrease (ΔMHD) and LDD, RDD, and ΔTTD were -0.430 (p = 0.000), -0.592 (p = 0.000) and 0.208 (p = 0.040), respectively, but not significantly correlated with ΔATD or GWL. The MHD decrease showed a moderate correlation with diaphragmatic descent In Sentinel-guided DIBH for patients with left-sided breast cancer, while there was a weak or no correlation with thoracic diameter changes or GWL. Abdominal breathing can lower diaphragm more and may be more beneficial to the heart stay away from tangential field.

Photon-Counting Detector CT Versus Energy-Integrating Detector CT of the Lumbar Spine: Comparison of Radiation Dose and Image Quality.

BACKGROUND. Photon-counting detector (PCD) CT could be useful to help address the typically high radiation doses of conventional energy-integrating detector (EID) CT of the lumbar spine. OBJECTIVE. The purpose of our study was to compare PCD CT and EID CT of the lumbar spine, both performed using tin filtration, in terms of radiation dose and image quality. METHODS. This study included a prospective sample of 39 patients (22 men, 17 women; mean age, 27.2 years) who underwent investigational PCD CT of the lumbar spine as part of a separate study and a retrospective sample of 39 patients (22 men, 17 women; mean age, 34.9 years) who underwent clinically indicated EID CT of the lumbar spine. In both groups, all examinations were performed using unenhanced technique with tin prefiltration between June 2022 and January 2023. Patients were matched between groups using age, sex, and BMI. A custom gaussian curve-fitting algorithm was used to automatically calculate image noise, SNR, and CNR for each examination, on the basis of all voxels within the image set. Three radiologists independently reviewed examinations to perform a subjective visual assessment of visualization of trabecular architecture, cortical bone, neuroforaminal content, paraspinal muscles, and intervertebral disk, as well as overall image quality, using a 4-point Likert scale (1 = poor, 4 = excellent). PCD CT and EID CT examinations were compared. RESULTS. Mean CTDIvol was 4.4 ± 1.0 (SD) mGy for PCD CT versus 11.1 ± 1.9 mGy for EID CT (p < .001). Mean size-specific dose estimate (SSDE) was 6.2 ± 1.0 (SD) mGy for PCD CT versus 14.2 ± 1.8 mGy for EID CT (p < .001). PCD CT and EID CT examinations were not significantly different in terms of image noise or SNR (both p > .05). PCD CT, in comparison with EID CT, showed significantly higher CNR (mean ± SD, 33.6 ± 3.3 vs 29.3 ± 4.1; p < .001). For all three readers, the median score for overall image quality was 4 (range, 3-4) for both PCD CT and EID CT. PCD CT and EID CT examinations showed no significant difference in terms of any qualitative measure for any reader (all p > .05). CONCLUSION. PCD CT, in comparison with EID CT, yielded significantly lower radiation dose with preserved image quality. CLINICAL IMPACT. The findings support expanded use of PCD CT for lumbar spine evaluation.

Retracted: A Method for Expanding the Training Set of White Blood Cell Images

Retracted: A Method for Expanding the Training Set of White Blood Cell Images

A New Benchmark for Consumer Visual Tracking and Apparent Demographic Estimation from RGB and Thermal Images

Visual tracking and attribute estimation related to age or gender information of multiple person entities in a scene are mature research topics with the advent of deep learning techniques. However, when it comes to indoor images such as video sequences of retail consumers, data are not always adequate or accurate enough to essentially train effective models for consumer detection and tracking under various adverse factors. This in turn affects the quality of recognizing age or gender for those detected instances. In this work, we introduce two novel datasets: Consumers comprises 145 video sequences compliant to personal information regulations as far as facial images are concerned and BID is a set of cropped body images from each sequence that can be used for numerous computer vision tasks. We also propose an end-to-end framework which comprises CNNs as object detectors, LSTMs for motion forecasting of the tracklet association component in a sequence, along with a multi-attribute classification model for apparent demographic estimation of the detected outputs, aiming to capture useful metadata of consumer product preferences. Obtained results on tracking and age/gender prediction are promising with respect to reference systems while they indicate the proposed model’s potential for practical consumer metadata extraction.

Generating novel scene compositions from single images and videos

Given a large dataset for training, generative adversarial networks (GANs) can achieve remarkable performance for the image synthesis task. However, training GANs in extremely low data regimes remains a challenge as overfitting often occurs, leading to memorization or training divergence. In this work, we introduce SIV-GAN, an unconditional generative model that can generate new scene compositions from a single training image or a single video clip. We propose a two-branch discriminator architecture with content and layout branches that are designed to judge internal content and scene layout realism separately from each other. This discriminator design enables the synthesis of visually plausible, novel compositions of a scene with varying content and layout while preserving the context of the original sample. Compared to previous single-image GANs, our model generates more diverse images of higher quality while not being restricted to a single image setting. We further introduce a new challenging task of learning from a few frames of a single video. In this training setup the training images are highly similar to each other, which makes it difficult for prior GAN models to achieve a synthesis of both high quality and diversity.

Camouflage Backdoor Attack against Pedestrian Detection

Pedestrian detection models in autonomous driving systems heavily rely on deep neural networks (DNNs) to perceive their surroundings. Recent research has unveiled the vulnerability of DNNs to backdoor attacks, in which malicious actors manipulate the system by embedding specific triggers within the training data. In this paper, we propose a tailored camouflaged backdoor attack method designed for pedestrian detection in autonomous driving systems. Our approach begins with the construction of a set of trigger-embedded images. Subsequently, we employ an image scaling function to seamlessly integrate these trigger-embedded images into the original benign images, thereby creating potentially poisoned training images. Importantly, these potentially poisoned images exhibit minimal discernible differences from the original benign images and are virtually imperceptible to the human eye. We then strategically activate these concealed backdoors in specific scenarios, causing the pedestrian detection models to make incorrect judgments. Our study demonstrates that once our attack successfully embeds the backdoor into the target model, it can deceive the model into failing to detect any pedestrians marked with our trigger patterns. Extensive evaluations conducted on a publicly available pedestrian detection dataset confirm the effectiveness and stealthiness of our camouflaged backdoor attacks.

Multi-Institutional Development and Validation of a Radiomic Model to Predict Prostate Cancer Recurrence Following Radical Prostatectomy

The use of multiparametric magnetic resonance imaging (mpMRI)-derived radiomics has the potential to offer noninvasive, imaging-based biomarkers for the identification of subvisual characteristics indicative of a poor oncologic outcome. The present study, therefore, seeks to develop, validate, and assess the performance of an MRI-derived radiomic model for the prediction of prostate cancer (PC) recurrence following radical prostatectomy (RP) with curative intent. mpMRI imaging was obtained from 251 patients who had undergone an RP for the treatment of localized prostate cancer across two institutions and three surgeons. All patients had a minimum of 2 years follow-up via prostate-specific antigen serum testing. Each prostate mpMRI was individually reviewed, and the prostate was delineated as a single slice (ROI) on axial T2 high-resolution image sets. A total of 924 radiomic features were extracted and tested for stability via intraclass correlation coefficient (ICC) following image normalization via histogram matching. Fourteen important and nonredundant features were found to be predictors of PC recurrence at a mean ± SD of 3.2 ± 2.2 years post-RP. Five-fold, ten-run cross-validation of the model containing these fourteen features yielded an area under the curve (AUC) of 0.89 ± 0.04 in the training set (n = 225). In comparison, the University of California San Fransisco Cancer of the Prostate Risk Assessment score (UCSF-CAPRA) and Memorial Sloan Kettering Cancer Center (MSKCC) Pre-Radical prostatectomy nomograms yielded AUC of 0.66 ± 0.05 and 0.67 ± 0.05, respectively (p &lt; 0.01). When the radiomic model was applied to the test set (n = 26), AUC was 0.78; sensitivity, specificity, positive predictive value, and negative predictive value were 60%, 86%, 52%, and 89%, respectively. Accuracy in predicting PC recurrence was 81%.

Endoscopy-based IBD identification by a quantized deep learning pipeline

BackgroundDiscrimination between patients affected by inflammatory bowel diseases and healthy controls on the basis of endoscopic imaging is an challenging problem for machine learning models. Such task is used here as the testbed for a novel deep learning classification pipeline, powered by a set of solutions enhancing characterising elements such as reproducibility, interpretability, reduced computational workload, bias-free modeling and careful image preprocessing.ResultsFirst, an automatic preprocessing procedure is devised, aimed to remove artifacts from clinical data, feeding then the resulting images to an aggregated per-patient model to mimic the clinicians decision process. The predictions are based on multiple snapshots obtained through resampling, reducing the risk of misleading outcomes by removing the low confidence predictions. Each patient’s outcome is explained by returning the images the prediction is based upon, supporting clinicians in verifying diagnoses without the need for evaluating the full set of endoscopic images. As a major theoretical contribution, quantization is employed to reduce the complexity and the computational cost of the model, allowing its deployment on small power devices with an almost negligible 3% performance degradation. Such quantization procedure holds relevance not only in the context of per-patient models but also for assessing its feasibility in providing real-time support to clinicians even in low-resources environments. The pipeline is demonstrated on a private dataset of endoscopic images of 758 IBD patients and 601 healthy controls, achieving Matthews Correlation Coefficient 0.9 as top performance on test set.ConclusionWe highlighted how a comprehensive pre-processing pipeline plays a crucial role in identifying and removing artifacts from data, solving one of the principal challenges encountered when working with clinical data. Furthermore, we constructively showed how it is possible to emulate clinicians decision process and how it offers significant advantages, particularly in terms of explainability and trust within the healthcare context. Last but not least, we proved that quantization can be a useful tool to reduce the time and resources consumption with an acceptable degradation of the model performs. The quantization study proposed in this work points up the potential development of real-time quantized algorithms as valuable tools to support clinicians during endoscopy procedures.

Deep learning-based extraction and quantification of features in XCT images of steel corrosion in concrete

The corrosion of rebars in concrete has been regarded as one of the most predominant factors for the degradation of reinforced concrete (RC) structures. The accurate predictions of corrosion damages are the basis for the safety assessment of in-service RC structures and the enhancement of new structure designs. X-ray computed tomography (XCT), known for its non-destructive capabilities, has been widely utilized to understand the corrosion process inside the concrete, offering three-dimensional (3D) visualization and aiding in the identification of the parameters in the predictive model of steel corrosion. This study uses U-Net, a deep learning network, to detect various phases of steel corrosion evolution in concrete, including the identification of rebar, corrosion products, pores, cement mortar, and corrosion-induced cracking. A galvanostatic accelerated corrosion test was conducted to simulate rebar corrosion within the mortar. The XCT test was performed, producing a series of XCT images that revealed the corrosion-induced cracks in the concrete. This set of images formed a comprehensive training database for the U-Net model. The performance of the model was significantly improved by data augmentation within the training dataset, thereby enabling it to recognize corrosion-induced cracking and pores. The U-Net model proved effective in accurately segmenting the XCT images into different phases, demonstrating a high accuracy rate of 99.18% on the validation dataset. A mean Intersection over Union (IoU) of 82.1% and a mean F1 score of 89.1% are observed on the test dataset, showing superior segmentation performance on XCT images. This significant advancement has automated the process of visualizing and 3D reconstructing the steel corrosion process inside the concrete. Concurrently, it has enabled the quantification of the volumetric expansion coefficient of corrosion products. The findings reveal spatial and temporal variations in this coefficient due to the migration of the corrosion product through the cracks.

Large‐Scale Daylight Photoluminescence: Automated Photovoltaic Module Operating Point Detection and Performance Loss Assessment by Quantitative Signal Analysis

Daylight photoluminescence (DPL) is a relatively novel imaging technique utilized in photovoltaic (PV) system inspection, using the sun as excitation source. Filtering the luminescence signal from the strong sun irradiation is its main challenge. Images acquired at two different operating points (OPs) of the module, allow subtraction of the background radiation while maintaining the luminescence signal. A DPL‐ready inverter, which is able to toggle between manually selectable OPs of connected PV modules, is presented in this work. Synchronization of image acquisition and OP switching becomes particularly challenging if the camera is applied to unmanned aerial vehicles. To overcome this challenge, an algorithm is developed to identify OP switches in a set of images taken in the field by investigating image intensities. Further, by working out the detailed dependencies of the signal recorded during DPL, the temperature coefficient of photoluminescence intensity is derived theoretically, and its impact on quantitative inspections. The potential field application of DPL images to identify performance loss in PV modules is investigated by two approaches: recording the signal intensity of images over time and comparing the signal intensity of different PV modules in one image. For both approaches, their hypothetical applicability is shown experimentally.

Instrumentation time and effectiveness of hand and rotary files in a prototyped second mandibular primary molar: A micro-CT study.

Eccentric instruments have been proposed as more effective and less time-consuming for endodontic instrumentation. To compare biomechanical outcomes of different instrumentation systems and time undertaken for instrumentation in resin prototypes. Sixty standardized prototypes of mandibular second primary molars were instrumented according to the following systems: K-files, ProTaper Next (PTN), XP-endo Shaper (XPS), XP-endo Finisher (XPF), XP-Clean (XPC), and Sequence Baby File (SBF; n = 10/each). Irrigation was performed with saline with simultaneous aspiration, and time spent was recorded. The prototypes were micro-CT-scanned before and after the instrumentation, and image sets were reconstructed and registered. Non-instrumented areas, accumulated debris, removed root material volume, and canal transportation were quantified. Data were analyzed through ANOVA, the Kruskal-Wallis test, and the Wilcoxon signed-rank test (α = 5%). K-files and SBF resulted in more instrumentation time (p < .05). SBF, XPC and PTN removed less root dentine (p < .05), but PTN left more untouched areas (p < .05). Accumulated debris were lower for XPC and SBF (p < .05). Canal transportation was similar among the groups. Rotary systems reduced instrumentation time, whereas SBF and XPC resulted in more conservative instrumentation, with less debris accumulation and non-instrumented areas. A dedicated paediatric endodontic system (SBF) outperformed eccentric instruments in terms of effectiveness.

Evaluating the Performance of a Visual Support System for Driving Assistance using a Deep Learning Algorithm

The issue of road accidents endangering human life has become a global concern due to the rise in traffic volumes. This article presents the evaluation of an object detection model for University of Malaysia Pahang (UMP) roadside conditions, focusing on the detection of vehicles, motorcycles, and traffic lamps. The dataset consists of the driving distance from Hospital Pekan to the University of Malaysia Pahang. Around one thousand images were selected in Roboflow for the train dataset. The model utilises the YOLO V8 deep learning algorithm in the Google Colab environment and is trained using a custom dataset managed by the Roboflow dataset manager. The dataset comprises a diverse set of training and validation images, capturing the unique characteristics of Malaysian roads. The train model's performance was assessed using the F1 score, precision, and recall, with results of 71%, 88.2%, and 84%, respectively. A comprehensive comparison with validation results has shown the efficacy of the proposed model in accurately detecting vehicles, motorcycles, and traffic lamps in real-world Malaysian road scenarios. This study contributes to the improvement of intelligent transportation systems and road safety in Malaysia.