Map Scores Research Articles

Performance evaluation of a deep learning model for automatic detection and localization of idiopathic osteosclerosis on dental panoramic radiographs

Idiopathic osteosclerosis (IO) are focal radiopacities of unknown etiology observed in the jaws. These radiopacities are incidentally detected on dental panoramic radiographs taken for other reasons. In this study, we investigated the performance of a deep learning model in detecting IO using a small dataset of dental panoramic radiographs with varying contrasts and features. Two radiologists collected 175 IO-diagnosed dental panoramic radiographs from the dental school database. The dataset size is limited due to the rarity of IO, with its incidence in the Turkish population reported as 2.7% in studies. To overcome this limitation, data augmentation was performed by horizontally flipping the images, resulting in an augmented dataset of 350 panoramic radiographs. The images were annotated by two radiologists and divided into approximately 70% for training (245 radiographs), 15% for validation (53 radiographs), and 15% for testing (52 radiographs). The study employing the YOLOv5 deep learning model evaluated the results using precision, recall, F1-score, mAP (mean Average Precision), and average inference time score metrics. The training and testing processes were conducted on the Google Colab Pro virtual machine. The test process's performance criteria were obtained with a precision value of 0.981, a recall value of 0.929, an F1-score value of 0.954, and an average inference time of 25.4 ms. Although radiographs diagnosed with IO have a small dataset and exhibit different contrasts and features, it has been observed that the deep learning model provides high detection speed, accuracy, and localization results. The automatic identification of IO lesions using artificial intelligence algorithms, with high success rates, can contribute to the clinical workflow of dentists by preventing unnecessary biopsy procedure.

Enhancing identification for person search with multi-scale multi-grained representation learning

Person Search aims to simultaneously address Person Detection and Person Re-ID. There are various challenges in person search such as significant scale variations, occlusions, and partial instances. In this paper, we propose a Multi-Scale Multi-Grained (MSMG) sequential network for end-to-end person search, intended to alleviate these issues. To generate re-id representations robust to scale changes, MSMG leverages multi-scale RoI features and aggregates them with a proposed Multi-Scale feature Aggregation Encoder (MSAE). In this way, the aggregated multi-scale re-id features are enriched with more semantic information and detailed information, thereby being more discriminative for identification. Moreover, to produce re-id representations more robust to occlusions and partial instances, MSMG introduces a Multi-Grained feature Learning Decoder (MGLD) focused on multi-grained feature learning. MGLD adaptively decodes multi-grained re-id representations with more accurate semantic information through a regional deformable cross-attention module. Finally, the multi-scale multi-grained re-id representation substantially improves the identification accuracy under challenging cases. Through comprehensive experiments, we demonstrate that our method achieves state-of-the-art performance on two benchmark datasets. On the challenging PRW benchmark, MSMG obtains the best-reported results with a mean average precision (mAP) score of 61.3%.

A new approach to classifying polymer type of microplastics based on Faster-RCNN-FPN and spectroscopic imagery under ultraviolet light

Hazardous compounds from microplastics in coastal and marine environments are adsorbed by live organisms, affecting human and marine life. It takes time, money and effort to study the distribution and type of microplastics in the environment, using appropriate expensive equipment in a laboratory. However, deep learning can assist in identifying and quantifying microplastics from an image. This paper presents a novel microplastic classification method that combines the benefits of UV light with deep learning. The Faster-RCNN model with a ResNet-50-FPN backbone was implemented to detect and identify microplastics. Microplastic images from the field taken under UV light were used to train and validate the model. This classification model achieved a high precision of 85.5–87.8%, and the mAP scores were 33.9% on an internal test set and 35.7% on an external test set. This classification approach provides a high-accuracy, low-cost, and time-effective automated identification and counting of microplastics.

Visitor Experience Map and NFC-Based Scoring for Data-Driven Exhibition Enhancement

Visitor Experience Map and NFC-Based Scoring for Data-Driven Exhibition Enhancement

A Detection of Malacca Woven Fabric Motifs Using the YOLOv4 Method

Malacca is one of the districts that has a weaving culture and also produces woven cloth in East NusaTenggara. The large number of types of woven cloth from each Malacca tribe means that outsiders andeven native Malacca people are not yet familiar with typical Malacca motifs, therefore a system isneeded that can help make it easier for people to recognize the types of woven fabric motifs. Malaccawoven fabric in this study was used to detect the types of woven fabric motifs in Malacca district usingthe YOLOv4 method. The results of detecting Malacca woven fabric motifs correspond to each type ofwoven fabric. Apart from that, the Malacca woven fabric motif detection system with YOLOv4technology is an effective and efficient solution in recognizing Malacca woven fabric motifs. Malaccawoven fabric is classified into four classes with an impressive mAP score of 100%.

Validation of a simple body map to measure widespread pain in urologic chronic pelvic pain syndrome: A MAPP Research Network study.

In patients with urologic chronic pelvic pain syndrome (UCPPS), the presence of widespread pain appears to identify a distinct phenotype, with a different symptom trajectory and potentially different response to treatment than patients with pelvic pain only. A 76-site body map was administered four times, at weekly intervals, to 568 male and female UCPPS participants in the MAPP Network protocol. The 76 sites were classified into 13 regions (1 pelvic region and 12 nonpelvic regions). The degree of widespread pain was scored from 0 to 12 based on the number of reported nonpelvic pain regions. This continuous body map score was regressed over other measures of widespread pain, with UCPPS symptom severity, and with psychosocial variables to measure level of association. These models were repeated using an updated body map score (0-12) that incorporated a threshold of pain ≥ 4 at each site. Body map scores showed limited variability over the 4 weekly assessments, indicating that a single baseline assessment was sufficient. The widespread pain score correlated highly with other measures of widespread pain and correlated with worsened UCPPS symptom severity and psychosocial functioning. Incorporating a pain severity threshold ≥4 resulted in only marginal increases in these correlations. These results support the use of this 13-region body map in the baseline clinical assessment of UCPPS patients. It provides reliable data about the presence of widespread pain and does not require measurement of pain severity, making it relatively simple to use for clinical purposes.

YOLO-based CAD framework with ViT transformer for breast mass detection and classification in CESM and FFDM images

Breast cancer detection is considered a challenging task for the average experienced radiologist due to the variation of the lesions’ size and shape, especially with the existence of high fibro-glandular tissues. The revolution of deep learning and computer vision contributes recently in introducing systems that can provide an automated diagnosis for breast cancer that can act as a second opinion for doctors/radiologists. The most of previously proposed deep learning-based Computer-Aided Diagnosis (CAD) systems mainly utilized Convolutional Neural Networks (CNN) that focuses on local features. Recently, vision transformers (ViT) have shown great potential in image classification tasks due to its ability in learning the local and global spatial features. This paper proposes a fully automated CAD framework based on YOLOv4 network and ViT transformers for mass detection and classification of Contrast Enhanced Spectral Mammography (CESM) images. CESM is an evolution type of Full Field Digital Mammography (FFDM) images that provides enhanced visualization for breast tissues. Different experiments were conducted to evaluate the proposed framework on two different datasets that are INbreast and CDD-CESM that provides both FFDM and CESM images. The model achieved at mass detection a mean Average Precision (mAP) score of 98.69%, 81.52%, and 71.65% and mass classification accuracy of 95.65%, 97.61%, and 80% for INbreast, CE-CESM, and DM-CESM, respectively. The proposed framework showed competitive results regarding the state-of-the-art models in INbreast. It outperformed the previous work in the literature in terms of the F1-score by almost 5% for mass detection in CESM. Moreover, the experiments showed that the CESM could provide more morphological features that can be more informative, especially with the highly dense breast tissues.

Exploring deep learning-based content-based video retrieval with Hierarchical Navigable Small World index and ResNet-50 features for anomaly detection

Surveillance video can capture a variety of realistic scenarios for providing security in both private and public spaces. The prediction of anomalies promptly is essential. However, existing methods are time-consuming due to marking conflicting clips in training videos. Therefore, this paper proposes a CBVR (Content-Based Video Retrieval) framework for detecting anomalies in surveillance videos. The proposed method leverages deep learning techniques and the HNSW (Hierarchical Navigable Small World) index to achieve efficient and accurate video retrieval. To preprocess the video data, frames are resized and normalized, and the dataset is augmented with data transformations such as rotations, translations, and flips to improve model generalization. The best results are offered while evaluating with the UCSD Ped2 dataset which produces the MAP score of 94.25%, and recall, precision, and F1-scores of 96.15%, 98.03%, and 92.63% respectively. The results proved that maximizing the number of layers in the HNSW index enhances the MAP score, suggesting that deeper layers are more effective at retrieving relevant results. Overall, the proposed CBVR framework provides an efficient and accurate method for anomaly detection in surveillance videos. It has potential applications in various domains, including video summarization, recommendation, and surveillance, among others.

Multiple Pseudo-Siamese Network with Supervised Contrast Learning for Medical Multi-modal Retrieval

Medical multi-modal retrieval aims to provide doctors with similar medical images from different modalities, which can greatly promote the efficiency and accuracy of clinical diagnosis. However, most existing medical retrieval methods hardly support the retrieval of multi-modal medical images, i.e., the number of modalities is greater than 2, and just convert retrieval to classification or clustering. It futilely breaks the gap between the visual information and the semantic information in different medical image modalities. To solve the problem, a S upervised C ontrast L earning method based on a M ultiple P seudo- S iamese network (SCL-MPS) is proposed for multi-modal medical image retrieval. In order to make the samples with semantic similarity close neighbors on Riemann manifold, the multiple constraints based on semantic consistency and modal invariance are designed in different forward stages of SCL-MPS. We theoretically demonstrate the feasibility of the designed constraints. Finally, experiments on four benchmark datasets (ADNI1, ADNI2, ADNI3, and OASIS3) show that SCL-MPS achieves state-of-the-art performance compared to 15 retrieval methods. Especially, SCL-MPS achieves a 100% mAP score in medical cross-modal retrieval on ADNI1.

Multiscale Feature Fusion Convolutional Neural Network for Surface Damage Detection in Retired Steel Shafts

Abstract The detection of surface damage is an important part of the process before remanufacturing a retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster R-CNN–based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multiscale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multiscale object detection network is conducted. Experimental results show that our method improves the mean average precision (mAP) score by 8.9% compared with the original Faster R-CNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multiscale objects.

A Method for Calculating the Leaf Area of Pak Choi Based on an Improved Mask R-CNN

The leaf area of pak choi is a critical indicator of growth rate, nutrient absorption, and photosynthetic efficiency, and it is required to be precisely measured for an optimal agricultural output. Traditional methods often fail to deliver the necessary accuracy and efficiency. We propose a method for calculating the leaf area of pak choi based on an improved Mask R-CNN. We have enhanced Mask R-CNN by integrating an advanced attention mechanism and a two-layer fully convolutional network (FCN) into its segmentation branch. This integration significantly improves the model’s ability to detect and segment leaf edges with increased precision. By extracting the contours of reference objects, the conversion coefficient between the pixel area and the actual area is calculated. Using the mask segmentation output from the model, the area of each leaf is calculated. Experimental results demonstrate that the improved model achieves mean average precision (mAP) scores of 0.9136 and 0.9132 in detection and segmentation tasks, respectively, representing improvements of 1.01% and 1.02% over the original Mask R-CNN. The model demonstrates excellent recognition and segmentation capabilities for pak choi leaves. The error between the calculation result of the segmented leaf area and the actual measured area is less than 4.47%. These results indicate that the proposed method provides a reliable segmentation and prediction performance. It eliminates the need for detached leaf measurements, making it suitable for real-life leaf area measurement scenarios and providing valuable support for automated production technologies in plant factories.

An improved pistachio detection approach using YOLO-v8 Deep Learning Models

Pistachios are an agricultural product widely used in the food industry. It is very important that pistachios are presented to the consumer in good quality on time. At the same time, whether the shells of pistachios are open or closed is an important criterion from a commercial industrial point of view. Pistachios with their shells open have a high unsaturated fat content, a high maturity level and an expensive market value. In this study, the open or closed status of pistachios was determined by using Artificial Intelligence-based deep learning models. For pistachio detection, 423 image data belonging to the Pesteh dataset were classified using models of the Yolov8 algorithm, which detects objects using convolutional neural networks. The data set is divided into 80% training, 10% validation and 10% testing. The performances of the models were evaluated with precision, recall, F1 and mAP score metrics. The highest test mAP value of the Yolov8 algorithm, which was run with image data consisting of pistachios, was obtained with the Yolov8-m model with 94.8%. The Yolov8-m model achieved a very successful result with 49.6 MB weight size, 11.0 ms inference time value and 0.33 hours training time value. In addition, the model's fast classification performance and small file size facilitate its applicability in the industrial field. The results show that the classification and detection of open and closed shell pistachios has been successfully carried out with Yolo models.

Applying Digital Images to Identify Pavement Damage in Support of The Road Infrastructure Development Program

Road damage can cause discomfort while driving and even lead to accidents. According to the National Road Network Condition Map Data in 2017, the level of severe and minor road damage in the East Java region had reached 288 kilometers. Based on this data, periodic road condition assessments and maintenance are essential to minimize damage. Road maintenance efforts are crucial to support road infrastructure development programs. The initial step in road maintenance is to identify road damage, determining the necessary actions to be taken. In this research, road pavement damage identification is carried out using the Yolov5, Yolov6, and Yolov7 methods. Test results indicate that the Yolov5 method performed the best with a validation mAP (mean Average Precision) score of 42%, a Precision value of 0.544, and a Recall value of 0.453. These scores indicate that the accuracy of road pavement damage detection using the YOLO algorithm for depression, corrugation, potholes, and alligator cracking is at its maximum level.

Anchor Association Learning for Unsupervised Video Person Re-Identification.

Video-based person re-identification (re-id) has attracted a significant attention in recent years due to the increasing demand of video surveillance. However, existing methods are usually based on the supervised learning, which requires vast labeled identities across cameras and is not suitable for real scenes. Although some unsupervised approaches have been proposed for video re-id, their performance is far from satisfactory. In this article, we propose an unsupervised anchor association learning (UAAL) framework to address the video-based person re-id task, in which the feature representation of each sampled tracklet is regarded as an anchor. Specifically, we first propose an intracamera anchor association learning (IAAL) term that learns the discriminative anchor by utilizing the affiliation relations between an image and the anchors in each camera. Then, the exponential moving average (EMA) strategy is employed to update the anchor and the updated anchors are stored into an anchor memory module. On top of that, a cross-camera anchor association learning (CAAL) term is introduced to mine potential positive anchor pairs across cameras by presenting a cyclic ranking anchor alignment and threshold filtering method. Extensive experiments conducted on two public datasets show the superiority of the proposed method; for example, our method achieves 73.2% for rank-1 accuracy and 60.1% for mean average precision (mAP) score, respectively, on MARS, similarly 89.7% and 87.0% on DukeMTMC-VideoReID.

UIT-MLReceipts: A Multilingual Benchmark for Detecting and Recognizing Key Information in Receipts

The 4.0 industrial evolution has paved the way for development potential and revolution in Vietnam. In this movement, digitization appears to be necessary to transform numerous traditional economic sectors. It will provide valuable digital data for many automation applications and decision-making processes. Particularly in the retail industry, data has long played a vital factor. Hence, digitizing documents such as receipts can help businesses in management and enterprise development. Nevertheless, the digital transformation process is still slow because of the shortage of cleaned datasets for this type of document. This paper introduces a new dataset named UIT-MLReceipts for extracting key information in receipts. The task includes two sub-tasks: Receipt Text Detection (RTD) and Receipt Text Recognition (RTR). We thoroughly evaluate current state-of-the-art Receipt Text Detection using Faster R-CNN, YOLOv3, YOLOF, and Faster R-CNN with Precise RoI-Pooling on our dataset. To evaluate the performance of Receipt Text Recognition, we experiment with two text recognition baselines: RobustScanner and SATRN. Experimental results indicate that the Faster R-CNN with Precise RoI-Pooling outperforms the competitors and achieves the best mean Average Precision (mAP) score at 51.6% in the Receipt Text Detection task. With the Receipt Text Recognition task, results show that SATRN performs better.

DraiNet: AI-driven decision support in pneumothorax and pleural effusion management.

This study presents DraiNet, a deep learning model developed to detect pneumothorax and pleural effusion in pediatric patients and aid in assessing the necessity for tube thoracostomy. The primary goal is to utilize DraiNet as a decision support tool to enhance clinical decision-making in the management of these conditions. DraiNet was trained on a diverse dataset of pediatric CT scans, carefully annotated by experienced surgeons. The model incorporated advanced object detection techniques and underwent evaluation using standard metrics, such as mean Average Precision (mAP), to assess its performance. DraiNet achieved an impressive mAP score of 0.964, demonstrating high accuracy in detecting and precisely localizing abnormalities associated with pneumothorax and pleural effusion. The model's precision and recall further confirmed its ability to effectively predict positive cases. The integration of DraiNet as an AI-driven decision support system marks a significant advancement in pediatric healthcare. By combining deep learning algorithms with clinical expertise, DraiNet provides a valuable tool for non-surgical teams and emergency room doctors, aiding them in making informed decisions about surgical interventions. With its remarkable mAP score of 0.964, DraiNet has the potential to enhance patient outcomes and optimize the management of critical conditions, including pneumothorax and pleural effusion.

An Improved YOLOv5 Algorithm for Drowning Detection in the Indoor Swimming Pool

In order to mitigate the risk of irreversible drowning injuries, this study introduces an enhanced YOLOv5 algorithm aimed at improving the efficacy of indoor swimming pool drowning detection and facilitating the timely rescue of endangered individuals. To simulate drowning and swimming positions accurately, four swimmers were deliberately chosen and observed, with monitoring conducted by drones flying above the swimming pool. The study was approved by the ethics committee of our institution, with the registration number 2022024. The images captured by the drones underwent a meticulous evaluation, and only those deemed suitable were selected to construct the self-made dataset, comprising a total of 8572 images. Furthermore, two enhancements were implemented in the YOLOv5 algorithm. Firstly, the inclusion of the ICA module strengthened category classification and the localization of water behavioral postures, which is improved from the coordinated attention module (CA). Secondly, the PAN module was replaced with the bi-directional feature pyramid network (BiFPN). Subsequently, the improved YOLOv5 algorithm underwent training using the self-made dataset. Evaluation of the algorithm’s performance revealed a notably improved detection accuracy rate, recall rate, and an impressive mean Average Precision (mAP) score of 98.1%, 98.0%, and 98.5%, respectively. Our paper introduces the improved YOLOv5 algorithm, surpassing the original YOLOv5 algorithm in terms of recognition accuracy for instances of drowning.

AI-based dental caries and tooth number detection in intraoral photos: Model development and performance evaluation

ObjectivesIn this study, we aimed to integrate tooth number recognition and caries detection in full intraoral photographic images using a cascade region-based deep convolutional neural network (R-CNN) model to facilitate the practical application of artificial intelligence (AI)-driven automatic caries detection in clinical practice. MethodsOur dataset comprised 24,578 images, encompassing 4787 upper occlusal, 4347 lower occlusal, 5230 right lateral, 5010 left lateral, and 5204 frontal views. In each intraoral image, tooth numbers and, when present, dental caries, including their location and stage, were annotated using bounding boxes. A cascade R-CNN model was used for dental caries detection and tooth number recognition within intraoral images. ResultsFor tooth number recognition, the model achieved an average mean average precision (mAP) score of 0.880. In the task of dental caries detection, the model's average mAP score was 0.769, with individual scores spanning from 0.695 to 0.893. ConclusionsThe primary objective of integrating tooth number recognition and caries detection within full intraoral photographic images has been achieved by our deep learning model. The model's training on comprehensive intraoral datasets has demonstrated its potential for seamless clinical application. Clinical SignificanceThis research holds clinical significance by achieving AI-driven automatic integration of tooth number recognition and caries detection in full intraoral images where multiple teeth are visible. It has the potential to promote the practical application of AI in real-life and clinical settings.

Detection of Missing Component in PCB Using YOLO

The detection of missing components in printed circuit boards (PCBs) is a critical task in the electronics manufacturing industry. The current practice of manual inspection is time-consuming and prone to human error, which can result in faulty products and increased costs. In this paper, we propose a solution that uses the YOLO (You Only Look Once) object detection algorithm to automatically detect missing electronic components in PCBs. Electronic components detection model is trained using YOLOv3 architecture. Dataset is prepared using high quality printed circuit board images and manual labeling in Label Studio. The model is trained on a dataset of 16 different electronic components commonly found in PCBs including Electrolytic Capacitor, QFP, Toroidal core Inductor, Crystal Oscillator etc. Prepared model recognizes these electronic components with an average map score of 65.8%with IoU 50% and 42.6% with IoU 95%. The results show that the proposed solution can detect the missing components.

CNN-based Occluded Person Re-identification in a Multi Camera Environment

In the context of rising global urban security concerns and the growing use of surveillance cameras, this study aims to enhance individual identification accuracy in occlusion scenarios using deep learning. Four CNN-based models for person re-identification are analyzed and put into practice. Additionally, comparative studies are conducted, and the model’s performance is assessed using the Market-1501 and Occluded-Reid datasets. We propose the use of ensemble learning and convolutional neural networks (CNNs) to address occlusion issues. Our results show that the ensemble approach performs better in re-identification tasks than traditional deep learning algorithms with an improvement of 1%–2% in mAP and Rank-1 scores, respectively.