Down-sampling Layers Research Articles

HAD-Net: An attention U-based network with hyper-scale shifted aggregating and max-diagonal sampling for medical image segmentation

Objectives:Accurate extraction of regions of interest (ROI) with variable shapes and scales is one of the primary challenges in medical image segmentation. Current U-based networks mostly aggregate multi-stage encoding outputs as an improved multi-scale skip connection. Although this design has been proven to provide scale diversity and contextual integrity, there remain several intuitive limits: (i) the encoding outputs are resampled to the same size simply, which destruct the fine-grained information. The advantages of utilization of multiple scales are insufficient. (ii) Certain redundant information proportional to the feature dimension size is introduced and causes multi-stage interference. And (iii) the precision of information delivery relies on the up-sampling and down-sampling layers, but guidance on maintaining consistency in feature locations and trends between them is lacking. Methods:To improve these situations, this paper proposed a U-based CNN network named HAD-Net, by assembling a new hyper-scale shifted aggregating module (HSAM) paradigm and progressive reusing attention (PRA) for skip connections, as well as employing a novel pair of dual-branch parameter-free sampling layers, i.e. max-diagonal pooling (MDP) and max-diagonal un-pooling (MDUP). That is, the aggregating scheme additionally combines five subregions with certain offsets in the shallower stage. Since the lower scale-down ratios of subregions enrich scales and fine-grain context. Then, the attention scheme contains a partial-to-global channel attention (PGCA) and a multi-scale reusing spatial attention (MRSA), it builds reusing connections internally and adjusts the focus on more useful dimensions. Finally, MDP and MDUP are explored in pairs to improve texture delivery and feature consistency, enhancing information retention and avoiding positional confusion. Results:Compared to state-of-the-art networks, HAD-Net has achieved comparable and even better performances with Dice of 90.13%, 81.51%, and 75.43% for each class on BraTS20, 89.59% Dice and 98.56% AUC on Kvasir-SEG, as well as 82.17% Dice and 98.05% AUC on DRIVE. Conclusions:The scheme of HSAM+PRA+MDP+MDUP has been proven to be a remarkable improvement and leaves room for further research.

Vision foundation model for agricultural applications with efficient layer aggregation network

Agricultural production is transitioning from traditional tools to IoT-connected automation devices. The integration of computer vision and agricultural automation is becoming closer with the rapid development of deep learning technology. Agricultural vision tasks, nevertheless, are relatively simple and less diverse compared to large-scale vision tasks, and there is a scarcity of plant data. This is also the reason why researchers need to make significant adjustments when directly applying advanced algorithms to the agricultural domain. In practice, downstream vision models should be designed to be concise and efficient. In this paper, we meticulously designed a deep convolutional network called TasselELANet for agricultural vision applications. It features a concise and efficient global architecture, including a 16-fold downsampling layer encoder and a decoder utilizing only 2 feature layers, which is greatly different from the general approaches. At its core is the efficient layer aggregation network, which utilizes the cross-stage fusion strategy to effectively optimize the gradient propagation path, thereby enhancing the learning ability and inference speed of the network. We validated the performance of TasselELANet on three challenging publicly available plant detection and counting datasets: maize tassels, wheat ears, and rice panels. The experimental tests achieved an average Accuracy of 0.899 and an average determination coefficient R2 of 0.867, remarkably outperforming other advanced computer vision methods in terms of accuracy and efficiency, and demonstrating sufficient generalizability. We firmly believe that TasselELANet can serve as a powerful and reliable vision tool for agricultural practitioners while also providing a solid foundation for future research. The code, datasets can be accessed at https://github.com/Ye-Sk/TasselELANet.git.

The weighted multi-scale connections networks for macrodispersivity estimation

Macrodispersivity is critical for predicting solute behaviors with dispersive transport models. Conventional methods of estimating macrodispersivity usually need to solve flow equations and are time-consuming. Convolutional neural networks (CNN) have recently been proven capable of efficiently mapping the hydraulic conductivity field and macrodispersivity. However, the mapping accuracy still needs further improvement. In this paper, we present a new network shortcut connection style called weighted multi-scale connections (WMC) for convolutional neural networks to improve mapping accuracy. We provide empirical evidence showing that the WMC can improve the performance of CNN in macrodispersivity estimation by implementing the WMC in CNNs (CNN without short-cut connections, ResNet, and DenseNet), and evaluating them on datasets of macrodispersivity estimation. For the CNN without short-cut connections, the WMC can improve the estimating R2 by at least 3% on three datasets of conductivity fields. For ResNet18, the WMC improved the estimated R2 by an average of 2.5% on all three datasets. For ResNet34, the WMC improved the estimated R2 by an average of 5.6%. For ResNet50, the WMC improved the estimated R2 by an average of 16%. For ResNet101, the WMC improved the estimating R2 by an average of 30%. For DenseNets, the improved estimated R2 ranges from 0.5% to 5%. The WMC can strengthen feature propagation of different sizes and alleviate the vanishing-gradient issue. Moreover, it can be implemented to any CNN with down-sampling layers or blocks.

Efficient Mixed-Type Wafer Defect Pattern Recognition Based on Light-Weight Neural Network.

Wafer defect pattern recognition can help engineers improve the production process of semiconductor chips. In real industrial scenarios, the recognition of mixed-type wafer defects is difficult and the production scale of semiconductor wafers is large, which requires high accuracy and speed in wafer defect pattern recognition. This study proposes a light-weight neural network model to efficiently recognize mixed-type wafer defects. The proposed model is constructed via inverted residual convolution blocks with attention mechanisms and large kernel convolution downsampling layers. The inference speed of the inverted residual convolution block is fast, and the attention mechanism can enhance feature extraction capabilities. Large kernel convolutions help the network retain more important feature information during downsampling operations. The experimental results on the real Mixed-type WM38 dataset show that the proposed model achieves a recognition accuracy of 98.69% with only 1.01 M parameters. Compared with some popular high-performance models and light-weight models, our model has advantages in both recognition accuracy and inference speed. Finally, we deploy the model as a TensorRT engine, which significantly improves the inference speed of the model, enabling it to process more than 1300 wafer maps per second.

SPMUNet: Semantic segmentation of citrus surface defects driven by superpixel feature

The segmentation of surface defects in citrus fruit makes a significant contribution to quality assessment and post-harvest processing. However, semantic segmentation of citrus surface defects remains challenging owing to the complexity of defect features, unclear defect boundaries and semantic gaps in models. Therefore, a superpixel driven and multiscale channel cross-fusion transformer (MCCT)-based UNet (named SPMUNet) was proposed to segment citrus surface defects. The model first created a multiscale superpixel region feature (MSRF) branch using the simple linear iterative cluster (SLIC) algorithm to form the key features embedded in the downsampling layer. Then, the proposed Superpixel Loss optimized the loss function based on superpixel grid to provide error information for boundary segmentation. In addition, the MCCT module was used to improve the skip connection layers, and feature fusion was achieved by collaborative learning. Finally, the performance of the model was validated through ablation studies, feature map visualization, and comparison experiments. The results showed that the mPA, mIoU, and dice coefficients of SPMUNet for citrus surface segmentation were 89.1%, 83.8%, and 88.6%, respectively. Compared with the baseline, the proposed MSRF branch, MCCT, and Superpixel Loss improved mIoU by 2.6%, 1.3%, and 4.2%, respectively. And the effectiveness of the proposed methods was also validated by the feature map visualization. Furthermore, the proposed SPMUNet achieved optimal segmentation performance compared to other semantic segmentation models (UNet, ResUNet++, DeepLabv3+, SwinUNet, TransUNet). SPMUNet also excelled in the segmentation of small targets and boundaries, improving by 10.2% and 7.0%, respectively, over the baseline. The improvement in segmentation performance demonstrated the effectiveness of the selected superpixel features. The proposed citrus surface defect segmentation model achieved high-precision segmentation and serves as a technical reference for citrus sorting and quality assessment.

MultiTumor Analyzer (MTA-20–55): A network for efficient classification of detected brain tumors from MRI images

Brain cancer, one of the leading causes of mortality worldwide, is caused by brain tumors. Early diagnosis of tumors and predicting their progression can help doctors to save lives. In this article, we have designed an automated approach for locating and classifying tumors from MRI images. The novelties of the research work include the following two stages: Developing an encoder-decoder type 20-Layered deep neural network (DNN) named MultiTumor Analyzer (MTA-20) with 15 down-sampling layers and 4 up-sampling layers, the segmentation is performed in the initial stage. Here, we have adhered a Leaky ReLU activation function instead of ReLU which learn a parameter with negative values that may have valuable information which is essential specifically for image segmentation. Further, a 55-layered DNN using multistage feature fusion is developed in the second stage of the work for the classification of localized tumors. The classification is performed using developed MultiTumor Analyzer (MTA-55) DNN with Softmax classifier. The efficacy of the designed network is validated using highly cited quantitative measures such as accuracy, sensitivity, specificity, dice similarity coefficient (DSC), precision, and F1-measure. It is observed that the proposed MTA-20 DNN attains the average accuracy, sensitivity, specificity, DSC, and precision of 99.2 %, 94.6 %, 99.3 %, 88 %, and 82.5 % respectively against seven state-of-the-art techniques. Also, it is found that, the proposed MTA-55 DNN provides the overall accuracy, recall, specificity, F1-measure, precision, and DSC of 99.8 %, 99.633 %, 99.844 %, 99.659 %, 99.689 %, and 99.656 % respectively as compared to thirteen state-of-the-art techniques. These results corroborate the superiority of the proposed technique.

Synthetic Aperture Radar Radio Frequency Interference Suppression Method Based on Fusing Segmentation and Inpainting Networks

Synthetic Aperture Radar (SAR) is a high-resolution imaging sensor commonly mounted on platforms such as airplanes and satellites for widespread use. In complex electromagnetic environments, radio frequency interference (RFI) severely degrades the quality of SAR images due to its widely varying bandwidth and numerous unknown emission sources. Although traditional deep learning-based methods have achieved remarkable results by directly processing SAR images as visual ones, there is still considerable room for improvement in their performance due to the wide coverage and high intensity of RFI. To address these issues, this paper proposes the fusion of segmentation and inpainting networks (FuSINet) to suppress SAR RFI in the time-frequency domain. Firstly, to weaken the dominance of RFI in SAR images caused by high-intensity interference, a simple CCN-based network is employed to learn and segment the RFI. This results in the removal of most of the original interference, leaving blanks that allow the targets to regain dominance in the overall image. Secondly, considering the wide coverage characteristic of RFI, a U-former network with global information capture capabilities is utilized to learn the content covered by the interference and fill in the blanks created by the segmentation network. Compared to the traditional Transformer, this paper enhances its global information capture capabilities through shift-windows and down-sampling layers. Finally, the segmentation and inpainting networks are fused together through a weighted parameter for joint training. This not only accelerates the learning speed but also enables better coordination between the two networks, leading to improved RFI suppression performance. Extensive experimental results demonstrate the substantial performance enhancement of the proposed FuSINet. Compared to the PISNet+, the proposed attention mechanism achieves a 2.49 dB improvement in peak signal-to-noise ratio (PSNR). Furthermore, compared to Uformer, the FuSINet achieves an additional 4.16 dB improvement in PSNR.

Real-time and lightweight detection of grape diseases based on Fusion Transformer YOLO.

Grapes are prone to various diseases throughout their growth cycle, and the failure to promptly control these diseases can result in reduced production and even complete crop failure. Therefore, effective disease control is essential for maximizing grape yield. Accurate disease identification plays a crucial role in this process. In this paper, we proposed a real-time and lightweight detection model called Fusion Transformer YOLO for 4 grape diseases detection. The primary source of the dataset comprises RGB images acquired from plantations situated in North China. Firstly, we introduce a lightweight high-performance VoVNet, which utilizes ghost convolutions and learnable downsampling layer. This backbone is further improved by integrating effective squeeze and excitation blocks and residual connections to the OSA module. These enhancements contribute to improved detection accuracy while maintaining a lightweight network. Secondly, an improved dual-flow PAN+FPN structure with Real-time Transformer is adopted in the neck component, by incorporating 2D position embedding and a single-scale Transformer Encoder into the last feature map. This modification enables real-time performance and improved accuracy in detecting small targets. Finally, we adopt the Decoupled Head based on the improved Task Aligned Predictor in the head component, which balances accuracy and speed. Experimental results demonstrate that FTR-YOLO achieves the high performance across various evaluation metrics, with a mean Average Precision (mAP) of 90.67%, a Frames Per Second (FPS) of 44, and a parameter size of 24.5M. The FTR-YOLO presented in this paper provides a real-time and lightweight solution for the detection of grape diseases. This model effectively assists farmers in detecting grape diseases.

ACANet: A Fine-grained Image Classification Optimization Method Based on Convolution and Attention Fusion

<p>The key to solve the problem of fine-grained image classification is to find the differentiation regions related to fine-grained features. In this paper, we try to add new network components to the original network and adjust various parameters to try to propose a new fine-grained image classification network. We propose a fine-grained image classification network based on the fusion of asymmetric convolution, convolution and self-attention mechanisms. Firstly, an enhanced module using asymmetric convolution to assist classical convolution proposed to help convolution learn deep features. Secondly, according to the common points of convolution and self-attention mechanism, we invented a fusion module of convolution and self-attention mechanism to improve the learning ability of the network.We integrate these two modules into the residual network and invent a new residual network .Finally, according to the experience, we design a new downsampling layer to adapt to the new component of the attention mechanism and improve the performance of the model. The experiment test on three publicly available datasets, and three methods for comparison. The results show that the new structure can effectively complete the task of fine-grained image classification, and the classification accuracy of different methods and different datasets are significantly improved.</p> <p> </p>

AnomalySeg: Deep Learning-Based Fast Anomaly Segmentation Approach for Surface Defect Detection

Product quality inspection is a crucial element of industrial manufacturing, yet flaws such as blemishes and stains frequently emerge after the product is completed. Most research has utilized detection models and avoided segmenting networks due to the unequal distribution of faulty information. To overcome this challenge, this work presents a rapid segmentation-based technique for surface defect detection. The proposed model is based on a modified U-Net, which introduces a hybrid residual module (SAFM), combining an improved spatial attention mechanism and a feedforward neural network in place of the remaining downsampling layers, except for the first layer of downsampling in the encoder, and applies this residual module to the decoder structure. Dilated convolutions are also incorporated in the decoder to obtain more spatial information about the feature defects and to reduce the gradient vanishing problem of the model. An improved hybrid loss function with Dice and focal loss is introduced to alleviate the small defect segmentation problem. Comparative experiments were conducted on different segmentation-based inspection methods, revealing that the Dice coefficient (DSC) evaluated by the proposed approach is better than previous generic segmentation benchmarks on KolektorSDD, KolektorSDD2, and RSDD datasets, with fewer parameters and FLOPs. Additionally, the detection network displays higher precision in recognizing the characteristics of minor flaws. This paper proposes a practical and effective technique for anomaly segmentation in surface defect identification, delivering considerable improvements over previous methods.

EDTNet: A spatial aware attention-based transformer for the pulmonary nodule segmentation.

Accurate segmentation of lung lesions in CT-scan images is essential to diagnose lung cancer. The challenges in lung nodule diagnosis arise due to their small size and diverse nature. We designed a transformer-based model EDTNet (Encoder Decoder Transformer Network) for PNS (Pulmonary Nodule Segmentation). Traditional CNN-based encoders and decoders are hindered by their inability to capture long-range spatial dependencies, leading to suboptimal performance in complex object segmentation tasks. To address the limitation, we leverage an enhanced spatial attention-based Vision Transformer (ViT) as an encoder and decoder in the EDTNet. The EDTNet integrates two successive transformer blocks, a patch-expanding layer, down-sampling layers, and up-sampling layers to improve segmentation capabilities. In addition, ESLA (Enhanced spatial aware local attention) and EGLA (Enhanced global aware local attention) blocks are added to provide attention to the spatial features. Furthermore, skip connections are introduced to facilitate symmetrical interaction between the corresponding encoder and decoder layer, enabling the retrieval of intricate details in the output. The EDTNet performance is compared with several models on DS1 and DS2, including Unet, ResUNet++, U-NET 3+, DeepLabV3+, SegNet, Trans-Unet, and Swin-UNet, demonstrates superior quantitative and visual results. On DS1, the EDTNet achieved 96.27%, 95.81%, 96.15% precision, IoU (Intersection over Union), and DSC (Sorensen-Dice coefficient). Moreover, the model has demonstrated sensitivity, IoU and SDC of 98.84%, 96.06% and 97.85% on DS2.

Graphformer: Adaptive graph correlation transformer for multivariate long sequence time series forecasting

Accurate long sequence time series forecasting (LSTF) remains a key challenge due to its complex time-dependent nature. Multivariate time series forecasting methods inherently assume that variables are interrelated and that the future state of each variable depends not only on its history but also on other variables. However, most existing methods, such as Transformer, cannot effectively exploit the potential spatial correlation between variables. To cope with the above problems, we propose a Transformer-based LSTF model, called Graphformer, which can efficiently learn complex temporal patterns and dependencies between multiple variables. First, in the encoder’s self-attentive downsampling layer, Graphformer replaces the standard convolutional layer with an dilated convolutional layer to efficiently capture long-term dependencies between time series at different granularity levels. Meanwhile, Graphformer replaces the self-attention mechanism with a graph self-attention mechanism that can automatically infer the implicit sparse graph structure from the data, showing better generality for time series without explicit graph structure and learning implicit spatial dependencies between sequences. In addition, Graphformer uses a temporal inertia module to enhance the sensitivity of future time steps to recent inputs, and a multi-scale feature fusion operation to extract temporal correlations at different granularity levels by slicing and fusing feature maps to improve model accuracy and efficiency. Our proposed Graphformer can improve the long sequence time series forecasting accuracy significantly when compared with that of SOTA Transformer-based models.

Segmentation of lung nodules based on a refined segmentation network.

Accurate segmentation of lung nodules is of great significance for early screening and diagnosis of lung cancer. However, the heterogeneity of lung nodules and the similarities between them and other lung tissues make it difficult to accurately segment these nodules. As regards the use of deep learning to segment lung nodules, convolutional neural networks would gradually lead to errors accumulating at the network layer due to the presence of multiple upsampling and downsampling layers, resulting in poor segmentation results. In this study, we developed a refined segmentation network (RS-Net) for lung nodule segmentation to solve this problem. Accordingly, the proposed RS-Net was first used to locate the core region of the lung nodules and to gradually refine the segmentation results of the core region. In addition, to solve the problem of misdetection of small-sized nodules owing to the imbalance of positive and negative samples, we devised an average dice-loss function computed on nodule level. By calculating the loss of each nodule sample to measure the overall loss, the network can address the misdetection problem of lung nodules with smaller diameters more efficiently. Our method was evaluated based on 1055 lung nodules from Lung Image Database Consortium data and a set of 120 lung nodules collected from Shanghai Chest Hospital for additional validation. The segmentation dice coefficients of RS-Net on these two datasets were 85.90% and 81.13%, respectively. The analysis of the segmentation effect of different properties and sizes of nodules indicates that RS-Net yields a stable segmentation effect. The results show that the segmentation strategy based on gradual refinement can considerably improve the segmentation of lung nodules.

YOLO-SDLUWD: YOLOv7-based small target detection network for infrared images in complex backgrounds

Infrared small-target detection has important applications in many fields due to its high penetration capability and detection distance. This study introduces a detector called “YOLO-SDLUWD” which is based on the YOLOv7 network, for small target detection in complex infrared backgrounds. The “SDLUWD” refers to the combination of the spatial depth layer followed convolutional layer structure (SD-Conv) and a linear up-sampling fusion path aggregation feature pyramid network (LU-PAFPN) and a training strategy based on the normalized Gaussian Wasserstein Distance loss (WD-loss) function. “YOLO-SDLUWD” aims to solve the problem of reduced detection accuracy when the maximum pooled downsampling layer in the backbone network loses important feature information and support the interaction and fusion of high-dimensional and low-dimensional feature information and overcome the false alarm predictions caused by noise in small target images. The detector achieved a mAP@0.5 of 90.4% and mAP@0.5:0.95 of 48.5% on IRIS-AG, an increase of 9%-11% over YOLOv7-tiny, outperforming other state-of-the-art target detectors in terms of accuracy and speed.

SliceSamp: A Promising Downsampling Alternative for Retaining Information in a Neural Network

Downsampling, which aims to improve computational efficiency by reducing the spatial resolution of feature maps, is a critical operation in neural networks. Many downsampling methods have been proposed to address the challenge of retaining feature map information. However, some detailed information is still lost, even though these methods can extract features with stronger semantics. In this paper, we propose a novel downsampling method which combines feature slicing and depthwise separable convolution for information-retaining downsampling. It slices the input feature map into multiple non-overlapping sub-feature maps by using indexes with a stride of two in the spatial dimension and applies depthwise separable convolution on each slice to extract feature information. To demonstrate the effectiveness of SliceSamp, we compare it with classical downsampling methods on image classification, object detection, and semantic segmentation tasks using several benchmark datasets, including ImageNet-1K, COCO, VOC, and ADE20K. Extensive experiments demonstrate that SliceSamp outperforms classical downsampling methods with consistent improvements in various computer vision tasks. The proposed SliceSamp shows advanced model performance with lower computational costs and memory requirements. By replacing the downsampling layers in different network architectures (including ResNet (Residual Network), YOLOv5, and Swin Transformer), SliceSamp brings different degrees of performance gains (+0.54~3.64%) compared to these baseline models. Additionally, SliceUpsamp enables high-resolution feature reconstruction and alignment during upsampling. SliceSamp and SliceUpsamp can be plug-and-play-integrated into existing neural network architectures. As a promising downsampling alternative to traditional methods, SliceSamp can also provide a reference for designing lightweight and high-performance model architectures in the future.

Blueprint Separable Subsampling and Aggregate Feature Conformer-Based End-to-End Neural Diarization

At present, a prevalent approach to speaker diarization is clustering based on speaker embeddings. However, this method encounters two primary issues. Firstly, it cannot directly minimize the diarization error during the training process; secondly, the majority of clustering-based methods struggle to handle speaker overlap in audio. A viable approach for addressing these issues involves adopting end-to-end speaker diarization (EEND). Nevertheless, training this EEND system generally requires lengthy audio inputs, which must be downsampled to allow efficient model processing. In this study, we develop a novel downsampling layer using blueprint separable convolution (BSConv) instead of depthwise separable convolution (DSC) as the foundational convolutional unit, which effectively preserves information from the original audio. Furthermore, we incorporate multi-scale feature aggregation (MFA) into the encoder structure to combine the features extracted by each conformer block to the output layer, consequently enhancing the expressiveness of the model’s feature extraction. Lastly, we employ the conformer as the backbone network to incorporate the proposed enhancements, resulting in an EEND system named BSAC-EEND. We assess our suggested methodology on both simulated and real datasets. The experiment indicates that our proposed EEND system reduces diarization error rate (DER) by an average of 17.3% for two-speaker datasets and 12.8% for three-speaker datasets compared to the baseline.

Efficient Distributed Mapping-Based Computation for Convolutional Neural Networks in Multi-Core Embedded Parallel Environment

Embedded systems are the best solution to achieve high-performance edge terminal computing tasks. With the rapid increase in the amount of data generated by edge devices, it is imperative to implement intelligent algorithms with large amounts of data and computation on embedded terminal systems. In this paper, a novel multi-core ARM-based embedded hardware platform with a three-dimensional mesh structure was first established to support the decentralized algorithms. To deploy deep convolutional neural networks (CNNs) in this embedded parallel environment, a distributed mapping mechanism was proposed to efficiently decentralize computation tasks in the form of a multi-branch assembly line. In addition, a dimensionality reduction initialization method was also utilized to successfully resolve the conflict between the storage requirement of computation tasks and the limited physical memories. LeNet-5 networks with different sizes were optimized and implemented in the embedded platform to verify the performance of our proposed strategies. The results showed that memory usage can be controlled within the usable range through dimensionality reduction. The down-sampling layer as the base point of the mapping for the inter-layer segmentation achieved the optimal operation in lateral dispersion with a reduction of around 10% in the running time compared with the other layers. Further, the computing speed for a network with an input size of 105 × 105 in the multi-core parallel environment is nearly 20 times faster than that in a single-core system. This paper provided a feasible strategy for edge deployments of artificial intelligent algorithms on multi-core embedded devices.

From coarse to fine: a deep 3D probability volume contours framework for tumour segmentation and dose painting in PET images.

With the increasing integration of functional imaging techniques like Positron Emission Tomography (PET) into radiotherapy (RT) practices, a paradigm shift in cancer treatment methodologies is underway. A fundamental step in RT planning is the accurate segmentation of tumours based on clinical diagnosis. Furthermore, novel tumour control methods, such as intensity modulated radiation therapy (IMRT) dose painting, demand the precise delineation of multiple intensity value contours to ensure optimal tumour dose distribution. Recently, convolutional neural networks (CNNs) have made significant strides in 3D image segmentation tasks, most of which present the output map at a voxel-wise level. However, because of information loss in subsequent downsampling layers, they frequently fail to precisely identify precise object boundaries. Moreover, in the context of dose painting strategies, there is an imperative need for reliable and precise image segmentation techniques to delineate high recurrence-risk contours. To address these challenges, we introduce a 3D coarse-to-fine framework, integrating a CNN with a kernel smoothing-based probability volume contour approach (KsPC). This integrated approach generates contour-based segmentation volumes, mimicking expert-level precision and providing accurate probability contours crucial for optimizing dose painting/IMRT strategies. Our final model, named KsPC-Net, leverages a CNN backbone to automatically learn parameters in the kernel smoothing process, thereby obviating the need for user-supplied tuning parameters. The 3D KsPC-Net exploits the strength of KsPC to simultaneously identify object boundaries and generate corresponding probability volume contours, which can be trained within an end-to-end framework. The proposed model has demonstrated promising performance, surpassing state-of-the-art models when tested against the MICCAI 2021 challenge dataset (HECKTOR).

A Novel Deep Learning Model for Medical Image Segmentation with Convolutional Neural Network and Transformer.

Accurate segmentation of medical images is essential for clinical decision-making, and deep learning techniques have shown remarkable results in this area. However, existing segmentation models that combine transformer and convolutional neural networks often use skip connections in U-shaped networks, which may limit their ability to capture contextual information in medical images. To address this limitation, we propose a coordinated mobile and residual transformer UNet (MRC-TransUNet) that combines the strengths of transformer and UNet architectures. Our approach uses a lightweight MR-ViT to address the semantic gap and a reciprocal attention module to compensate for the potential loss of details. To better explore long-range contextual information, we use skip connections only in the first layer and add MR-ViT and RPA modules in the subsequent downsampling layers. In our study, we evaluated the effectiveness of our proposed method on three different medical image segmentation datasets, namely, breast, brain, and lung. Our proposed method outperformed state-of-the-art methods in terms of various evaluation metrics, including the Dice coefficient and Hausdorff distance. These results demonstrate that our proposed method can significantly improve the accuracy of medical image segmentation and has the potential for clinical applications. Illustration of the proposed MRC-TransUNet. For the input medical images, we first subject them to an intrinsic downsampling operation and then replace the original jump connection structure using MR-ViT. The output feature representations at different scales are fused by the RPA module. Finally, an upsampling operation is performed to fuse the features to restore them to the same resolution as the input image.

Enhanced YOLOv5 Object Detection Algorithm for Accurate Detection of Adult Rhynchophorus ferrugineus.

The red palm weevil (RPW, Rhynchophorus ferrugineus) is an invasive and highly destructive pest that poses a serious threat to palm plants. To improve the efficiency of adult RPWs' management, an enhanced YOLOv5 object detection algorithm based on an attention mechanism is proposed in this paper. Firstly, the detection capabilities for small targets are enhanced by adding a convolutional layer to the backbone network of YOLOv5 and forming a quadruple down-sampling layer by splicing and down-sampling the convolutional layers. Secondly, the Squeeze-and-Excitation (SE) attention mechanism and Convolutional Block Attention Module (CBAM) attention mechanism are inserted directly before the SPPF structure to improve the feature extraction capability of the model for targets. Then, 2600 images of RPWs in different scenes and forms are collected and organized for data support. These images are divided into a training set, validation set and test set following a ratio of 7:2:1. Finally, an experiment is conducted, demonstrating that the enhanced YOLOv5 algorithm achieves an average precision of 90.1% (mAP@0.5) and a precision of 93.8% (P), which is a significant improvement compared with related models. In conclusion, the enhanced model brings a higher detection accuracy and real-time performance to the RPW-controlled pest pre-detection system, which helps us to take timely preventive and control measures to avoid serious pest infestation. It also provides scalability for other pest pre-detection systems; with the corresponding dataset and training, the algorithm can be adapted to the detection tasks of other pests, which in turn brings a wider range of applications in the field of monitoring and control of agricultural pests.