Body Extraction Research Articles

Water Body Extraction of the Weihe River Basin Based on MF-SegFormer Applied to Landsat8 OLI Data

In the era of big data, making full use of remote sensing images to automatically extract surface water bodies (WBs) in complex environments is extremely challenging. Due to the weak capability of existing algorithms in extracting small WBs and WB edge information from remote sensing images, we proposed a new method—Multiscale Fusion SegFormer (MF-SegFormer)—for WB extraction in the Weihe River Basin of China using Landsat 8 OLI images. The MF-SegFormer method adopts a cascading approach to fuse features output by the SegFormer encoder at multiple scales. A feature fusion (FF) module is proposed to enhance the extraction of WB edge information, while an Atrous Spatial Pyramid Pooling (ASPP) module is employed to enhance the extraction of small WBs. Furthermore, we analyzed the impact of four kinds of band combinations on WB extraction by the MF-SegFormer model, including true color composite images, false color images, true color images, and false color images enhanced by Gaussian stretch. We also compared our proposed method with several different approaches. The results suggested that false color composite images enhanced by Gaussian stretching are beneficial for extracting WBs, and the MF-SegFormer model achieves the highest accuracy across the study area with a precision of 77.6%, recall of 84.4%, F1-score of 80.9%, and mean intersection over union (mIoU) of 83.9%. In addition, we used the determination coefficient (R2) and root-mean-square error (RMSE) to evaluate the performance of river width extraction. Our extraction results in an overall R2 of 0.946 and an RMSE of 28.21 m for the mainstream width in the “Xi’an-Xianyang” section of the Weihe River. The proposed MF-SegFormer method used in this study outperformed other methods and was found to be more robust for WB extraction.

Endoscopic removal of ingested foreign body in children: experience of a tertiary care hospital of Bangladesh

Purpose: Foreign body ingestion is a common incident in children & majority of ingested foreign body removed spontaneously, few percentages (10%) remain in GI tract. The timing of endoscopy depends on some clinical & radiological parameters. The aim of this study to is to observe clinical profile of foreign body ingestion in children in Bangladesh. Methods: This cross-sectional descriptive study was conducted from February 2016 to December 2019 in the department of Paediatric Gastroenterology and Nutrition, Bangabandhu Sheikh Mujib Medical University (BSMMU), Dhaka. A total of 29 cases of upper GI tract foreign bodies were studied. Patients with history of ingested foreign body, were clinically examined. Asymptomatic foreign body ingestion was frequently observed. Routine neck and chest X-ray in both AP and lateral views were obtained for these cases. Flexible endoscopy for foreign body extraction with suitable foreign body retriever was used to remove the foreign bodies. Data were expressed as percentage & number. Results: Foreign body was commonly seen 22 (75.9%) in 1-5 years of age. Sex distribution of foreign body ingestion cases, where 15 (51.7%) were male child. Among the ingested foreign bodies only 3 (10.3%) were removed within 24 hours of ingestion, 10 (34.5%) cases were removed between 24-48 hours and the remaining 16 (55.2%) were removed after 48 hours. Coin was the most common foreign body 19(65.5%). Other foreign bodies were metallic chain 3 (10.3%), button battery 2 (6.9%), others 5 (17.2%). Conclusion: The study showed that foreign body ingestion is more common in 1-5 years age group, coin was the most commonly ingested foreign body.

Boundary-Guided Semantic Context Network for Water Body Extraction from Remote Sensing Images

Automatically extracting water bodies is a significant task in interpreting remote sensing images (RSIs). Convolutional neural networks (CNNs) have exhibited excellent performance in processing RSIs, which have been widely used for fine-grained extraction of water bodies. However, it is difficult for the extraction accuracy of CNNs to satisfy the requirements in practice due to the limited receptive field and the gradually reduced spatial size during the encoder stage. In complicated scenarios, in particular, the existing methods perform even worse. To address this problem, a novel boundary-guided semantic context network (BGSNet) is proposed to accurately extract water bodies via leveraging boundary features to guide the integration of semantic context. Firstly, a boundary refinement (BR) module is proposed to preserve sufficient boundary distributions from shallow layer features. In addition, abstract semantic information of deep layers is also captured by a semantic context fusion (SCF) module. Based on the results obtained from the aforementioned modules, a boundary-guided semantic context (BGS) module is devised to aggregate semantic context information along the boundaries, thereby enhancing intra-class consistency of water bodies. Extensive experiments were conducted on the Qinghai–Tibet Plateau Lake (QTPL) and the Land-cOVEr Domain Adaptive semantic segmentation (LoveDA) datasets. The results demonstrate that the proposed BGSNet outperforms the mainstream approaches in terms of OA, MIoU, F1-score, and kappa. Specifically, BGSNet achieves an OA of 98.97% on the QTPL dataset and 95.70% on the LoveDA dataset. Additionally, an ablation study was conducted to validate the efficacy of the proposed modules.

Water index and Swin Transformer Ensemble (WISTE) for water body extraction from multispectral remote sensing images

ABSTRACT Automatic surface water body mapping using remote sensing technology is greatly meaningful for studying inland water dynamics at regional to global scales. Convolutional neural networks (CNN) have become an efficient semantic segmentation technique for the interpretation of remote sensing images. However, the receptive field value of a CNN is restricted by the convolutional kernel size because the network only focuses on local features. The Swin Transformer has recently demonstrated its outstanding performance in computer vision tasks, and it could be useful for processing multispectral remote sensing images. In this article, a Water Index and Swin Transformer Ensemble (WISTE) method for automatic water body extraction is proposed. First, a dual-branch encoder architecture is designed for the Swin Transformer, aggregating the global semantic information and pixel neighbor relationships captured by fully convolutional networks (FCN) and multihead self-attention. Second, to prevent the Swin Transformer from ignoring multispectral information, we construct a prediction map ensemble module. The predictions of the Swin Transformer and the Normalized Difference Water Index (NDWI) are combined by a Bayesian averaging strategy. Finally, the experimental results obtained on two distinct datasets demonstrate that the WISTE has advantages over other segmentation methods and achieves the best results. The method proposed in this study can be used for improving regional to continental surface water mapping and related hydrological studies.

A K-Net-based hybrid semantic segmentation method for extracting lake water bodies

Lakes have a crucial impact on natural disaster prevention, resource recycling, maintenance of agricultural production and daily life. The traditional way of acquiring lake water body information lacks efficiency, is dangerous, and is not suitable for lake water body information acquisition and real-time monitoring. For this reason, the automated lake water body extraction method based on deep learning semantic segmentation model is gradually becoming a mainstream method. However, most of the semantic segmentation models used for lake extraction today express features through static semantics, while ignoring the extraction relationships of different convolutional kernels for these features. In order to better extract lake water bodies from remote sensing images, this paper proposes a hybrid semantic segmentation method based on K-Net, which achieves high accuracy extraction of lake water bodies by introducing dynamic semantic kernels to iteratively refine the feature information. The superiority of the K-Net-based hybrid model on a Google remote sensing image dataset of lakes is validated. The experimental results show that (1) the hybrid model is able to achieve accurate extraction of lake water bodies, with the UperNet + K-Net model using Swin-l performing the best among all six evaluation metrics, with mean intersection over union (mIoU) reaching 97.77%; and that (2) after incorporating the K-Net module, all tested models obtain a larger mIoU than before.

Novel Threshold Self-Regulating Water Extraction Method

Water resources are crucial for human activities and sustainable socioeconomic development. Understanding surface water information can play a key role in water resource management, which affects the global water cycle and ecological environments. Considering the Hailar River water body as an example, this study proposes a new threshold self-learning water body extraction method (TSLWEM) based on modified normalized difference water index (MNDWI) data. The optimal water extraction thresholds determined by the TSLWEM algorithm for four test images were −0.0030, 0, 0.1990, and −0.0800. The TSLWEM algorithm effectively identified the target water body with recognition accuracies of 98.08%, 99.93%, 93.39%, and 93.20% for the four test images. Moreover, it can accurately identify small tributaries, such as lakes and rivers. The TSLWEM algorithm is suitable for Landsat 8 Operational Land Imager (OLI) data, which can effectively monitor and map complex surface water in temperate and semiarid regions while improving the accuracy of water body identification. The study’s findings provide technical support for the protection of water resources as well as their rational utilization and monitoring.

Unusual Intra-Orbital Foreign Body Removed by a Unique Surgical Approach

INTRODUCTION
 A retained intra-orbital foreign body can give rise to serious complications. This case report highlights an interesting case where a metallic foreign body remained lodged inside the orbit for over a year, unbeknownst to the patient, and was eventually detected and surgically extracted.
 CASE REPORT
 We report a case of a 57-year-old female who presented with mild pain of the left orbit following an injury with an umbrella after a fall one year ago. Following a near normal physical examination, on radiological evaluation we found a linear, presumably metallic foreign body lodged into the orbit, without piercing the globe. An inferolateral orbitotomy approach was used to gain adequate exposure and facilitate the removal of a 3.5 cm metallic remnant of an umbrella stick.
 DISCUSSION
 The management of intra-orbital foreign bodies poses several challenges. The choice between conservative and surgical management is one of them. CT scan is the diagnostic tool of choice. When surgical removal is indicated, a suitably planned approach facilitates extraction of the foreign body with minimal morbidity. This rare case is testament to the fact that although it may not be part of their conventional realm, carefully selected intra-orbital foreign bodies can be efficiently managed surgically by ENT professionals.

Age-related changes in the pharmacokinetics of meloxicam after intravenous administration in sheep.

The pharmacokinetics of meloxicam was studied in 1-, 6-, and 12-month-old sheep following a single intravenous (i.v.) dose of 1 mg/kg. The experiments were carried out when the Romanov sheep were 1 month old (7.93 ± 0.91 kg), 6 months old (27.47 ± 4.91 kg), and 12 months old (37.10 ± 3.64 kg). Meloxicam concentration in plasma was determined by high-performance liquid chromatography and the data collected were evaluated by non-compartmental kinetic analysis. Meloxicam was detected in the plasma up to 72 h following i.v. administration in all age groups. The volume of distribution at steady state (Vdss ) and total body clearance (ClT ) were significantly higher in 1-month-old (304.87 mL/kg and 16.57 mL/h/kg) than in 12-month-old (193.43 mL/kg and 10.50 mL/h/kg) sheep. The area under the concentration-time curve from 0 to 72 h value of meloxicam was lower in 1-month-old (58.51 h*μg/mL) compared to 12-month-old (92.59 h*μg/mL) sheep. There was no difference in t1/2ʎz value in different age groups. The body extraction ratio values for meloxicam ranged from 0.0186 to 0.0719 after i.v. administration in all age groups. Meloxicam showed an increase in plasma concentration and a decrease in Vdss and ClT in 12-month-old compared to 1-month-old sheep. Compared to 1-month-old and 12-month-old sheep, there was no difference in these parameters in 6-month-old sheep. Because the age of sheep has an influence on the pharmacokinetics of meloxicam, dosage apparently may need to be adjusted for age.

MU-Net: Embedding MixFormer into Unet to Extract Water Bodies from Remote Sensing Images

Water bodies extraction is important in water resource utilization and flood prevention and mitigation. Remote sensing images contain rich information, but due to the complex spatial background features and noise interference, problems such as inaccurate tributary extraction and inaccurate segmentation occur when extracting water bodies. Recently, using a convolutional neural network (CNN) to extract water bodies is gradually becoming popular. However, the local property of CNN limits the extraction of global information, while Transformer, using a self-attention mechanism, has great potential in modeling global information. This paper proposes the MU-Net, a hybrid MixFormer architecture, as a novel method for automatically extracting water bodies. First, the MixFormer block is embedded into Unet. The combination of CNN and MixFormer is used to model the local spatial detail information and global contextual information of the image to improve the ability of the network to capture semantic features of the water body. Then, the features generated by the encoder are refined by the attention mechanism module to suppress the interference of image background noise and non-water body features, which further improves the accuracy of water body extraction. The experiments show that our method has higher segmentation accuracy and robust performance compared with the mainstream CNN- and Transformer-based semantic segmentation networks. The proposed MU-Net achieves 90.25% and 76.52% IoU on the GID and LoveDA datasets, respectively. The experimental results also validate the potential of MixFormer in water extraction studies.

Worker Abnormal Behavior Recognition Based on Spatio-Temporal Graph Convolution and Attention Model

In response to the problem where many existing research models only consider acquiring the temporal information between sequences of continuous skeletons and in response to the lack of the ability to model spatial information, this study proposes a model for recognizing worker falls and lays out abnormal behaviors based on human skeletal key points and a spatio-temporal graph convolutional network (ST-GCN). Skeleton extraction of the human body in video sequences was performed using Alphapose. To resolve the problem of graph convolutional networks not being effective enough for skeletal key points feature aggregation, we propose an NAM-STGCN model that incorporates a normalized attention mechanism. By using the activation function PReLU to optimize the model structure, the improved ST-GCN model can more effectively extract skeletal key points action features in the spatio-temporal dimension for the purposes of abnormal behavior recognition. The experimental results show that our optimized model achieves a 96.72% accuracy for recognition on the self-built dataset, which is 4.92% better than the original model; the model loss value converges below 0.2. Tests were performed on the KTH and Le2i datasets, which are both better than typical classification recognition networks. The model can precisely identify abnormal human behaviors, facilitating the detection of abnormalities and rescue in a timely manner and offering novel ideas for smart site construction.

Extraction of a foreign body due to a penetrating wound in the buttock region by a firearm ultrasound-guided: a case report

The use of ultrasound as a diagnostic and therapeutic support method for patients with penetrating gunshot wounds must be individualized in patients who require the removal of the foreign body. We report the case of a male in the fourth decade of life with a penetrating wound in the gluteal region on the left side of approximately 0.5 cm by 0.5 cm. Initially, stabilization was performed according to ATLS and later the patient was left in charge of general surgery. Doppler ultrasound was performed as the first and only imaging study to assess a possible vascular condition, which was negative. Due to the location of the projectile added to the medical-legal need of the patient to obtain the projectile, it was extracted with the help of an ultrasound-guided radiologist without the need to make an incision, since the bullet was extracted through the entrance hole. The reported literature mentions that there are key points, mentioned later in this article, for the extraction of bullets by firearm. Evidence for the use of ultrasound is limited but it should be kept in mind that ultrasound can be a useful diagnostic and therapeutic tool in removal of foreign bodies.

Improvement and application of UNet network for avoiding the effect of urban dense high-rise buildings and other feature shadows on water body extraction

ABSTRACT Finding a means to extract water body information efficiently and accurately from high-resolution remote sensing images has been an important research direction in the field of water body extraction in recent years. However, shadows from buildings and other obstacles interfere with the accuracy of water body extraction. To address this problem, this paper proposes a neural network method incorporating an attention mechanism for water body extraction. This paper is based on the U-Net convolutional neural network and adds the squeeze-and-excitation module of SENet, an attention mechanism, to the downsampling process of the U-Net network. The module weights the feature maps so that the network focuses more on the features of the water body information and thus reduces attention to the shadow features from buildings and other features, thus improving the accuracy of image segmentation. The dropout and batch normalization layers are also added to improve the generalization ability and stability of the model. In this paper, a water extraction network SE-CU-Net model is presented to overcome the shadowing effect from buildings and other features. Using GF-2 images of Jiangsu province as the data source, the recognition results of this paper are compared with Dense-Net, Res-Net, Seg-Net, U-net, SVM, and RF. Through the comparison experiments, the model of this paper can not only better overcome the influence of shadows from buildings and other features, but it also has a stronger recognition ability and recognition effect. The average ASCR, Precision, mIoU, OA, F1-Score and kappa coefficients in the three tested areas reached 98.27%, 97.17%, 89.33%, 98.2%, 89.3% and 0.883, respectively, with significantly higher accuracy than the other six classical methods, verifying the effectiveness of the model in overcoming the influence of shadows from buildings and other features in water body extraction research.

MSAFNet: Multiscale Successive Attention Fusion Network for Water Body Extraction of Remote Sensing Images

Water body extraction is a typical task in the semantic segmentation of remote sensing images (RSIs). Deep convolutional neural networks (DCNNs) outperform traditional methods in mining visual features; however, due to the inherent convolutional mechanism of the network, spatial details and abstract semantic representations at different levels are difficult to capture accurately at the same time, and then the extraction results decline to become suboptimal, especially on narrow areas and boundaries. To address the above-mentioned problem, a multiscale successive attention fusion network, named MSAFNet, is proposed to efficiently aggregate the multiscale features from two aspects. A successive attention fusion module (SAFM) is first devised to extract multiscale and fine-grained features of water bodies, while a joint attention module (JAM) is proposed to further mine salient semantic information by jointly modeling contextual dependencies. Furthermore, the multi-level features extracted by the above-mentioned modules are aggregated by a feature fusion module (FFM) so that the edges of water bodies are well mapped, directly improving the segmentation of various water bodies. Extensive experiments were conducted on the Qinghai-Tibet Plateau Lake (QTPL) and the Land-cOVEr Domain Adaptive semantic segmentation (LoveDA) datasets. Numerically, MSAFNet reached the highest accuracy on both QTPL and LoveDA datasets, including Kappa, MIoU, FWIoU, F1, and OA, outperforming several mainstream methods. Regarding the QTPL dataset, MSAFNet peaked at 99.14% and 98.97% in terms of F1 and OA. Although the LoveDA dataset is more challenging, MSAFNet retained the best performance, with F1 and OA being 97.69% and 95.87%. Additionally, visual inspections exhibited consistency with numerical evaluations.

Deep Learning for Automatic Extraction of Water Bodies Using Satellite Imagery

The study introduces an automated approach for extracting water bodies from satellite images using the Faster R-CNN algorithm. The approach was tested on two datasets consisting of water body images collected from Sentinel-2 and Landsat-8 (OLI) satellite images, totaling over 3500 images. The results showed that the proposed approach achieved an accuracy of 98.7% and 96.1% for the two datasets, respectively. This is significantly higher than the accuracy achieved by the convolutional neural network (CNN) approach, which achieved 96% and 80% for the two datasets, respectively. These findings highlight the effectiveness of the proposed approach in accurately mapping water bodies from satellite imagery. Additionally, the Sentinel-2 dataset performed better than the Landsat dataset in both the Faster R-CNN and CNN approaches for water body extraction.

Pediatric anesthetic for tracheobronchial foreign body extraction: A survey of practice in France.

Tracheobronchial foreign body aspiration is a classic pediatric emergency, and its associated morbidity particularly depends on the anesthetic management, which differs according to the center and the practitioner. The aim of this study was to evaluate the different anesthetic practices for tracheobronchial foreign body extraction. A survey was sent via email to the member physicians of the Association des Anesthésistes Réanimateurs Pédiatriques d'Expression Française (ADARPEF). The survey included 28 questions about the organizational and anesthetic management of an evolving clinical case. A total of 151 physicians responded to the survey. Only 13.2% of the respondents reported that their institution had a management protocol, and 21.7% required a computerized tomography scan before the procedure was performed for children who were asymptomatic or mildly symptomatic during the night. There were 56.3% of the respondents who reported that extraction with a rigid bronchoscope is the only procedure usually performed in their institution. Regarding rigid bronchoscopy, 47.0% used combined intravenous-inhalation anesthesia. The objective was to maintain the child on spontaneous ventilation for 63.6% of the respondents, but anesthesia management differed according to the physician's experience. Our study confirms the diversity of practices concerning anesthetic for tracheobronchial foreign body extraction and found reveal differences in practice according to physician experience.

The Effect of Developmental Delay and Autism Spectrum Disorder on External Auditory Canal Foreign Body Extraction.

To determine the effect of developmental delay (DD) and autism spectrum disorder (ASD) on pediatric external auditory canal foreign body (EAC FB) retrieval outcomes. A retrospective chart review of children presenting with EAC FB at a tertiary children's hospital was performed between January 2018 and December 2019. Charts were reviewed for demographics, presence of otalgia, complications, number of EAC FB episodes, indications for operating room removal, DD, and ASD status. A total of 1467 patients underwent EAC FB removal. One hundred thirty-seven children (9.3%) had DD, and, of those with DD, 63 (46%) had ASD. Children with DD were 1.76 years older compared with children with non-DD (NDD) ( P < 0.0001) at the time of presentation, whereas children with ASD were 1.45 years older than children with NDD ( P = 0.0023). Children with DD and ASD were more likely to require removal of FB in the operating room (OR) compared with the NDD group (36.5% vs 16.7%, P = 0.0001). This was not true for children with DD without ASD. Patients with DD reported significantly less otalgia when compared with NDD patients (26.3% vs 37.4%, P = 0.0097). A similar trend, although not statistically significant, was observed when comparing children with ASD with NDD patients. The NDD patients (1.1) had fewer EAC FB episodes than patients with DD (1.6, P < 0.0001) and ASD (1.8, P < 0.0016). Hazard ratios for multiple episodes of FB were 4.5 (95% confidence interval, 2.9-6.8) for DD, and 5.6 for ASD (95% confidence interval, 3.2-9.9). The complication rate for all groups was low. Due to the different ways that children with DD and ASD present compared with NDD children, physicians should be vigilant when evaluating symptoms and conducting physical examinations for EAC FB in those patients. A lower threshold for referral to otolaryngologists may result in more favorable outcomes.

Ultrasound-assisted alkali removal of proteins from wastewater generated during oil bodies extraction

In this study, an ultrasonic-assisted alkaline method was used to remove proteins from wastewater generated during oil-body extraction, and the effects of different ultrasonic power settings (0, 150, 300, and 450 W) on protein recovery were investigated. The recoveries of the ultrasonically treated samples were higher than those of the samples without ultrasonic treatment, and the protein recoveries increased with increasing power, with a protein recovery of 50.10 % ± 0.19 % when the ultrasonic power was 450 W. Amino acid analysis showed that the amino acids comprising the recovered samples were consistent, regardless of the ultrasonic power used, but significant differences in the contents of amino acids were observed. No significant changes were observed in the protein electrophoretic profile using dodecyl polyacrylamide gel, indicating that sonication did not change the primary structures of the recovered samples. Fourier transform infrared and fluorescence spectroscopy revealed that the molecular structures of the samples changed after sonication, and the fluorescence intensity increased gradually with increasing sonication power. The contents of α-helices and random coils obtained at an ultrasonic power of 450 W decreased to 13.44 % and 14.31 %, respectively, whereas the β-sheet content generally increased. The denaturation temperatures of the proteins were determined using differential scanning calorimetry, and ultrasound treatment reduced the denaturation temperatures of the samples, which was associated with the structural and conformational changes caused by their chemical bonding. The solubility of the recovered protein increased with increasing ultrasound power, and a high solubility was essential in good emulsification. The emulsification of the samples was improved well. In conclusion, ultrasound treatment changed the structure and thus improved the functional properties of the protein.

Panchkarma in Surgical Diseases: A Review of Classical Text

Panchkarma is a part of Kayachikitsa with a fivefold cleansing or detoxification process, which includes Vamana, Virechana, Basti, Raktamokshana, and Nasya. These fivefold Shodhana karmas exert their efficacy by influencing different doshas or adhisthana and expelling them through the nearest exit source. Although the field of Panchkarma comes under Kayachikitsa, there are several mentions of the extensive use of Panchkarma in all branches of Ashtanga Ayurveda. For example, Shalya tantra is one of the crucial branches of Ashtanga Ayurveda which specifically focuses on the process of Shalya (foreign body) extraction. In contrast, Acharaya Sushruta mentions using Panchkarma as purva karma for different surgical processes. Like any other Nidana (etiological factor), Shalya also acts as a nidana by vitiating doshas according to its location, nature or kala (period). The study's primary aim is to do a comprehensive review of Panchkarma procedures mentioned in surgical diseases covering all references and studies. Research is conducted by searching various classical texts and databases to fulfil the objective. Along with its application in surgical diseases, this article also highlights the application of Panchkarma in emergency conditions. In this article, all Panchkarma processes mentioned in surgical diseases are explained, and a table is made for reviewing it easily. Thus, this review will focus on the Panchkarma process mentioned in Shalya Tantra and the need for extensive research in this field, as most procedures still need to be explored.

Investigating the seasonal dynamics of surface water over the Qinghai–Tibet Plateau using Sentinel-1 imagery and a novel gated multiscale ConvNet

ABSTRACT The surface water in the Qinghai–Tibet Plateau (QTP) region has undergone dramatic changes in recent decades. To capture dynamic surface water information, many satellite imagery-based methods have been proposed. However, these methods are still limited in terms of automation and accuracy and thus prevent surface water dynamic studies in large-scale QTP regions. In this study, we developed a new fully automatic method for accurate surface water mapping by using Sentinel-1 synthetic aperture radar (SAR) imagery and convolutional networks (ConvNets). Specifically, we built a new multiscale ConvNet structure to improve the model capability in surface water body extraction. Moreover, a gating mechanism is introduced to promote the efficient use of multiscale information. According to the accuracy assessment, the proposed gated multiscale ConvNet (GMNet) achieved the highest overall accuracy of 98.07%. We applied our GMNet for monthly surface water mapping on the QTP; accordingly, we found that the QTP region experienced significant surface water fluctuations over one year. The surface water also showed distinct spatial heterogeneity on the QTP; that is, the surface water fraction of the Inner Tibetan Basin was significantly higher than that of the Mekong Basin in both the wet and dry seasons.

Intraocular Foreign Body: Striving the Optimal Visual Outcome

Introduction: Intraocular foreign bodies (IOFBs) are defined as intraocularly retained, unintentional projectiles that require urgent diagnosis and treatment to prevent blindness or globe loss. Case Presentation: We report a case of IOFB due to occupational accidents. In this case, there were delays in extraction considering the health facilities and conditions related to COVID-19 infection. Initially, the patient underwent closure of the entrance wound, which was performed within the first 24 hours post-trauma. However, although there was no endophthalmitis, visual acuity at the end of the observation still showed an unexpected outcome. The patient was followed up for three months after IOFBs extraction. The timing of IOFBs removal depends on several factors, including the patient’s overall health status, the nature of the injury, and the composition of the IOFBs. The postoperative examinations focus on complications such as endophthalmitis, postoperative retinal detachment, proliferative vitreoretinopathy (PVR), and sympathetic ophthalmia. The numerical values can then be used to predict the expected visual acuity using the ocular trauma score system. Conclusions: Many factors could affect the outcome quality of visual acuity. Primary wound closure, foreign body extraction, and anatomic reconstruction of the holistic ocular should be performed as soon as possible. Delay in definitive treatment was thought to affect worsening prognosis due to tissue proliferation and the tendency for severe complications, including endophthalmitis.