RESUMEN

Oil spill SAR images are characterized by high noise, low contrast, and irregular boundaries, which lead to the problems of overfitting and insufficient capturing of detailed features of the oil spill region in the current method when processing oil spill SAR images. An improved DeepLabV3+ model is proposed to address the above problems. First, the original backbone network Xception is replaced by the lightweight MobileNetV2, which significantly improves the generalization ability of the model while drastically reducing the number of model parameters and effectively addresses the overfitting problem. Further, the spatial and channel Squeeze and Excitation module (scSE) is introduced and the joint loss function of Bce + Dice is adopted to enhance the sensitivity of the model to the detailed parts of the oil spill area, which effectively solves the problem of insufficient capture of the detailed features of the oil spill area. The experimental results show that the mIOU and F1-score of the improved model in an oil spill region in the Gulf of Mexico reach 80.26% and 88.66%, respectively. In an oil spill region in the Persian Gulf, the mIOU and F1-score reach 81.34% and 89.62%, respectively, which are better than the metrics of the control model.

RESUMEN

Brain-computer interface (BCI) is a technology that directly connects signals between the human brain and a computer or other external device. Motor imagery electroencephalographic (MI-EEG) signals are considered a promising paradigm for BCI systems, with a wide range of potential applications in medical rehabilitation, human-computer interaction, and virtual reality. Accurate decoding of MI-EEG signals poses a significant challenge due to issues related to the quality of the collected EEG data and subject variability. Therefore, developing an efficient MI-EEG decoding network is crucial and warrants research. This paper proposes a loss joint training model based on the vision transformer (VIT) and the temporal convolutional network (EEG-VTTCNet) to classify MI-EEG signals. To take advantage of multiple modules together, the EEG-VTTCNet adopts a shared convolution strategy and a dual-branching strategy. The dual-branching modules perform complementary learning and jointly train shared convolutional modules with better performance. We conducted experiments on the BCI Competition IV-2a and IV-2b datasets, and the proposed network outperformed the current state-of-the-art techniques with an accuracy of 84.58% and 90.94%, respectively, for the subject-dependent mode. In addition, we used t-SNE to visualize the features extracted by the proposed network, further demonstrating the effectiveness of the feature extraction framework. We also conducted extensive ablation and hyperparameter tuning experiments to construct a robust network architecture that can be well generalized.

Asunto(s)

RESUMEN

The intricate task of precisely segmenting retinal vessels from images, which is critical for diagnosing various eye diseases, presents significant challenges for models due to factors such as scale variation, complex anatomical patterns, low contrast, and limitations in training data. Building on these challenges, we offer novel contributions spanning model architecture, loss function design, robustness, and real-time efficacy. To comprehensively address these challenges, a new U-Net-like, lightweight Transformer network for retinal vessel segmentation is presented. By integrating MobileViT+ and a novel local representation in the encoder, our design emphasizes lightweight processing while capturing intricate image structures, enhancing vessel edge precision. A novel joint loss is designed, leveraging the characteristics of weighted cross-entropy and Dice loss to effectively guide the model through the task's challenges, such as foreground-background imbalance and intricate vascular structures. Exhaustive experiments were performed on three prominent retinal image databases. The results underscore the robustness and generalizability of the proposed LiViT-Net, which outperforms other methods in complex scenarios, especially in intricate environments with fine vessels or vessel edges. Importantly, optimized for efficiency, LiViT-Net excels on devices with constrained computational power, as evidenced by its fast performance. To demonstrate the model proposed in this study, a freely accessible and interactive website was established (https://hz-t3.matpool.com:28765?token=aQjYR4hqMI), revealing real-time performance with no login requirements.

RESUMEN

Segmentation of the temporomandibular joint (TMJ) disc and condyle from magnetic resonance imaging (MRI) is a crucial task in TMJ internal derangement research. The automatic segmentation of the disc structure presents challenges due to its intricate and variable shapes, low contrast, and unclear boundaries. Existing TMJ segmentation methods often overlook spatial and channel information in features and neglect overall topological considerations, with few studies exploring the interaction between segmentation and topology preservation. To address these challenges, we propose a Three-Branch Jointed Feature and Topology Decoder (TFTD) for the segmentation of TMJ disc and condyle in MRI. This structure effectively preserves the topological information of the disc structure and enhances features. We introduce a cross-dimensional spatial and channel attention mechanism (SCIA) to enhance features. This mechanism captures spatial, channel, and cross-dimensional information of the decoded features, leading to improved segmentation performance. Moreover, we explore the interaction between topology preservation and segmentation from the perspective of game theory. Based on this interaction, we design the Joint Loss Function (JLF) to fully leverage the features of segmentation, topology preservation, and joint interaction branches. Results on the TMJ MRI dataset demonstrate the superior performance of our TFTD compared to existing methods.

Asunto(s)

RESUMEN

Background: Ultrasound image segmentation is challenging due to the low signal-to-noise ratio and poor quality of ultrasound images. With deep learning advancements, convolutional neural networks (CNNs) have been widely used for ultrasound image segmentation. However, due to the intrinsic locality of convolutional operations and the varying shapes of segmentation objects, segmentation methods based on CNNs still face challenges with accuracy and generalization. In addition, Transformer is a network architecture with self-attention mechanisms that performs well in the field of computer vision. Based on the characteristics of Transformer and CNNs, we propose a hybrid architecture based on Transformer and U-Net with joint loss for ultrasound image segmentation, referred to as TU-Net. Methods: TU-Net is based on the encoder-decoder architecture and includes encoder, parallel attention mechanism and decoder modules. The encoder module is responsible for reducing dimensions and capturing different levels of feature information from ultrasound images; the parallel attention mechanism is responsible for capturing global and multiscale local feature information; and the decoder module is responsible for gradually recovering dimensions and delineating the boundaries of the segmentation target. Additionally, we adopt joint loss to optimize learning and improve segmentation accuracy. We use experiments on datasets of two types of ultrasound images to verify the proposed architecture. We use the Dice scores, precision, recall, Hausdorff distance (HD) and average symmetric surface distance (ASD) as evaluation metrics for segmentation performance. Results: For the brachia plexus and fetal head ultrasound image datasets, TU-Net achieves mean Dice scores of 79.59% and 97.94%; precisions of 81.25% and 98.18%; recalls of 80.19% and 97.72%; HDs (mm) of 12.44 and 6.93; and ASDs (mm) of 4.29 and 2.97, respectively. Compared with those of the other six segmentation algorithms, the mean values of TU-Net increased by approximately 3.41%, 2.62%, 3.74%, 36.40% and 31.96% for the Dice score, precision, recall, HD and ASD, respectively.

RESUMEN

In the field of single-image super-resolution reconstruction, GAN can obtain the image texture more in line with the human eye. However, during the reconstruction process, it is easy to generate artifacts, false textures, and large deviations in details between the reconstructed image and the Ground Truth. In order to further improve the visual quality, we study the feature correlation between adjacent layers and propose a differential value dense residual network to solve this problem. We first use the deconvolution layer to enlarge the features, then extract the features through the convolution layer, and finally make a difference between the features before being magnified and the features after being extracted so that the difference can better reflect the areas that need attention. In the process of extracting the differential value, using the dense residual connection method for each layer can make the magnified features more complete, so the differential value obtained is more accurate. Next, the joint loss function is introduced to fuse high-frequency information and low-frequency information, which improves the visual effect of the reconstructed image to a certain extent. The experimental results on Set5, Set14, BSD100, and Urban datasets show that our proposed DVDR-SRGAN model is improved in terms of PSNR, SSIM, and LPIPS compared with the Bicubic, SRGAN, ESRGAN, Beby-GAN, and SPSR models.

RESUMEN

In the complex environment of orchards, in view of low fruit recognition accuracy, poor real-time and robustness of traditional recognition algorithms, this paper propose an improved fruit recognition algorithm based on deep learning. Firstly, the residual module was assembled with the cross stage parity network (CSP Net) to optimize recognition performance and reduce the computing burden of the network. Secondly, the spatial pyramid pool (SPP) module is integrated into the recognition network of the YOLOv5 to blend the local and global features of the fruit, thus improving the recall rate of the minimum fruit target. Meanwhile, the NMS algorithm was replaced by the Soft NMS algorithm to enhance the ability of identifying overlapped fruits. Finally, a joint loss function was constructed based on focal and CIoU loss to optimize the algorithm, and the recognition accuracy was significantly improved. The test results show that the MAP value of the improved model after dataset training reaches 96.3% in the test set, which is 3.8% higher than the original model. F1 value reaches 91.8%, which is 3.8% higher than the original model. The average detection speed under GPU reaches 27.8 frames/s, which is 5.6 frames/s higher than the original model. Compared with current advanced detection methods such as Faster RCNN and RetinaNet, among others, the test results show that this method has excellent detection accuracy, good robustness and real-time performance, and has important reference value for solving the problem of accurate recognition of fruit in complex environment.

Asunto(s)

RESUMEN

With the development of deep learning, medical image segmentation has become a promising technique for computer-aided medical diagnosis. However, the supervised training of the algorithm relies on a large amount of labeled data, and the private dataset bias generally exists in previous research, which seriously affects the algorithm's performance. In order to alleviate this problem and improve the robustness and generalization of the model, this paper proposes an end-to-end weakly supervised semantic segmentation network to learn and infer mappings. Firstly, an attention compensation mechanism (ACM) aggregating the class activation map (CAM) is designed to learn complementarily. Then the conditional random field (CRF) is introduced to prune the foreground and background regions. Finally, the obtained high-confidence regions are used as pseudo labels for the segmentation branch to train and optimize using a joint loss function. Our model achieves a Mean Intersection over Union (MIoU) score of 62.84% in the segmentation task, which is an effective improvement of 11.18% compared to the previous network for segmenting dental diseases. Moreover, we further verify that our model has higher robustness to dataset bias by improved localization mechanism (CAM). The research shows that our proposed approach improves the accuracy and robustness of dental disease identification.

Asunto(s)

RESUMEN

Protein arginine methylation is an important posttranslational modification (PTM) associated with protein functional diversity and pathological conditions including cancer. Identification of methylation binding sites facilitates a better understanding of the molecular function of proteins. Recent developments in the field of deep neural networks have led to a proliferation of deep learning-based methylation identification studies because of their fast and accurate prediction. In this paper, we propose DeepGpgs, an advanced deep learning model incorporating Gaussian prior and gated attention mechanism. We introduce a residual network channel to extract the evolutionary information of proteins. Then we combine the adaptive embedding with bidirectional long short-term memory networks to form a context-shared encoder layer. A gated multi-head attention mechanism is followed to obtain the global information about the sequence. A Gaussian prior is injected into the sequence to assist in predicting PTMs. We also propose a weighted joint loss function to alleviate the false negative problem. We empirically show that DeepGpgs improves Matthews correlation coefficient by 6.3% on the arginine methylation independent test set compared with the existing state-of-the-art methylation site prediction methods. Furthermore, DeepGpgs has good robustness in phosphorylation site prediction of SARS-CoV-2, which indicates that DeepGpgs has good transferability and the potential to be extended to other modification sites prediction. The open-source code and data of the DeepGpgs can be obtained from https://github.com/saizhou1/DeepGpgs.

Asunto(s)

RESUMEN

Social media content moderation is the standard practice as on today to promote healthy discussion forums. Toxic span prediction is helpful for explaining the toxic comment classification labels, thus is an important step towards building automated moderation systems. The relation between toxic comment classification and toxic span prediction makes joint learning objective meaningful. We propose a multi-task learning model using ToxicXLMR for bidirectional contextual embeddings of input text for toxic comment classification, and a Bi-LSTM CRF layer for toxic span or rationale identification. To enable multi-task learning in this domain, we have curated a dataset from Jigsaw and Toxic span prediction datasets. The proposed model outperformed the single task models on the curated and toxic span prediction datasets with 4% and 2% improvement for classification and rationale identification, respectively. We investigated the domain adaptation ability of the proposed MTL model on HASOC and OLID datasets that contain the out of domain text from Twitter and found a 3% improvement in the F1 score over single task models.

RESUMEN

Detection and analysis of retinal blood vessels contribute to the clinical diagnosis of many ophthalmic diseases. In this paper, aiming on achieving more accurate segmentation of retinal vessels and enhance the ability of the algorithm to identify microvessels, we propose a U-shaped network based on adaptive aggregation of feature information. The introduced feature selection module, which could strengthen feature transmission and selectively emphasize feature information. To effectively capture the characteristics of vessels at different scales, generate richer and denser context information, and DenseASPP is embedded at the bottom of the network. Meanwhile, we propose an adaptive aggregation module to aggregate the semantic information in each layer of the encoder part and transmit it to subsequent layers, which is beneficial to the spatial reconstruction of retinal vessels. A joint loss function is also introduced to facilitate network training. The proposed network is evaluated on three public datasets. The sensitivity, accuracy, and area under curve(AUC) are 83.48%/83.16/85.86, 95.67%/96.67%/96.52%, and 98.11%/98.69%/98.60% on DRIVE, STARE and CHASE_DB1, respectively. In order to achieve more accurate retinal blood vessel segmentation and improve the ability of the algorithm to identify microvessels. We propose a U-shaped network based on adaptive aggregation of feature information. The introduction of the adaptive aggregation module aggregates the semantic information of each level of the encoder part, which improves the robustness of the model to segment blood vessels.

Asunto(s)

RESUMEN

OBJECTIVE: This study aims to investigate the feasibility and clinical application value of a new method for primary donor-site closure of radial forearm flaps with the use of rotation and advancement of radial-based fasciocutaneous flaps. METHODS: The forearm donor-site defects of 36 patients were primarily closed by rotation and advancement of radial-based fasciocutaneous flaps after radial flap harvest from November 2014 to May 2015. Patients included 28 males and 8 females aged 28 to 67 years (53.6 years old on average). Flap size ranged from 3.0 cm×5.0 cm to 4.0 cm×6.0 cm. Wound healing, scar hyperplasia, and forearm appearance were recorded and evaluated. Wrist flexion angle, dorsal extension angle, ulnar deviation angle, and radial deviation angle were measured three and six months after the operation. Wrist joint loss index was calculated and compared with the preoperative index to evaluate wrist function recovery. The results were subjected to comparative t-
test to perform statistical analysis with SPSS 19.0 statistical software package. RESULTS: Forearm donor sites were successfully closed without skin grafting in all patients. Skin ischemia caused by excessive tension was observed at the incision edge in five cases, thereby leading to skin exfoliation and pigment loss without affecting wound healing. All patients were followed up at six and twelve months, and presented a satisfactory appearance. No scar hyperplasia was observed. No significant difference was observed in radial deviation, ulnar deviation, palmar flexion, dorsiflexion, radial deflection angle, or wrist joint loss index (P>0.05) after the operation. CONCLUSIONS: Application of rotation and advancement of radial-based fasciocutaneous flaps can directly close small-to-medium radial forearm flap donor defects. Satisfactory postoperative appearance can be achieved with no loss in wrist joint function. The novel method prove worthy of promotion and application in clinical work.

Asunto(s)

RESUMEN

<p><b>OBJECTIVE</b>This study aims to investigate the feasibility and clinical application value of a new method for primary donor-site closure of radial forearm flaps with the use of rotation and advancement of radial-based fasciocutaneous flaps.</p><p><b>METHODS</b>The forearm donor-site defects of 36 patients were primarily closed by rotation and advancement of radial-based fasciocutaneous flaps after radial flap harvest from November 2014 to May 2015. Patients included 28 males and 8 females aged 28 to 67 years (53.6 years old on average). Flap size ranged from 3.0 cm×5.0 cm to 4.0 cm×6.0 cm. Wound healing, scar hyperplasia, and forearm appearance were recorded and evaluated. Wrist flexion angle, dorsal extension angle, ulnar deviation angle, and radial deviation angle were measured three and six months after the operation. Wrist joint loss index was calculated and compared with the preoperative index to evaluate wrist function recovery. The results were subjected to comparative t-
test to perform statistical analysis with SPSS 19.0 statistical software package.</p><p><b>RESULTS</b>Forearm donor sites were successfully closed without skin grafting in all patients. Skin ischemia caused by excessive tension was observed at the incision edge in five cases, thereby leading to skin exfoliation and pigment loss without affecting wound healing. All patients were followed up at six and twelve months, and presented a satisfactory appearance. No scar hyperplasia was observed. No significant difference was observed in radial deviation, ulnar deviation, palmar flexion, dorsiflexion, radial deflection angle, or wrist joint loss index (P>0.05) after the operation.</p><p><b>CONCLUSIONS</b>Application of rotation and advancement of radial-based fasciocutaneous flaps can directly close small-to-medium radial forearm flap donor defects. Satisfactory postoperative appearance can be achieved with no loss in wrist joint function. The novel method prove worthy of promotion and application in clinical work.</p>

Asunto(s)