Synthetic CT reconstruction using a deep spatial pyramid convolutional framework for MR-only breast radiotherapy.

The coronavirus disease 2019 (COVID-19) epidemic has spread worldwide and the healthcare system is in crisis. Accurate, automated and rapid segmentation of COVID-19 lesion in computed tomography (CT) images can help doctors diagnose and provide prognostic information. However, the variety of lesions and small regions of early lesion complicate their segmentation. To solve these problems, we propose a new SAUNet++ model with squeeze excitation residual (SER) module and atrous spatial pyramid pooling (ASPP) module. The SER module can assign more weights to more important channels and mitigate the problem of gradient disappearance; the ASPP module can obtain context information by atrous convolution using various sampling rates. In addition, the generalized dice loss (GDL) can reduce the correlation between lesion size and dice loss, and is introduced to solve the problem of small regions segmentation of COVID-19 lesion. We collected multinational CT scan data from China, Italy and Russia and conducted extensive comparative and ablation studies. The experimental results demonstrated that our method outperforms state-of-the-art models and can effectively improve the accuracy of COVID-19 lesion segmentation on the dice similarity coefficient (our: 87.38 $$\%$$ vs. U-Net++: 84.25 $$\%$$ ), sensitivity (our: 93.28 $$\%$$ vs. U-Net++: 89.85 $$\%$$ ) and Hausdorff distance (our: 19.99 mm vs. U-Net++: 26.79 mm), respectively.

IntroductionWeeds compete with crops for water, nutrients, and light, negatively impacting maize yield and quality. To enhance weed identification accuracy and meet the requirements of precision agriculture, we propose a lightweight semantic segmentation model named DSC-DeepLabv3+.MethodsMobileNetV2 is adopted as the backbone, and standard convolutions in atrous spatial pyramid pooling (ASPP) and decoder modules are replaced with depthwise separable dilated convolutions (DSDConv), significantly reducing model complexity and improving segmentation efficiency. To capture rich contextual information, strip pooling is incorporated into the ASPP module, forming the strip pooling–atrous spatial pyramid pooling (S-ASPP) structure. In addition, a convolutional block attention module (CBAM) is introduced to refine feature representations, and multi-scale features are further fused using the CBAM–Cascade Feature Fusion (C-CFF) module to improve semantic understanding.ResultsExperimental results show that the proposed model reduces the number of parameters from 54.714M to 2.89M and decreases the computational cost from 167.139 GFLOPs to 15.326 GFLOPs, while achieving an inference speed of 42.89 FPS and a mean Intersection over Union (mIoU) of 85.57%.DiscussionThese results demonstrate that DSC-DeepLabv3+ strikes an effective balance between accuracy and efficiency, outperforming several classical lightweight models, making it a promising solution for accurate and efficient weed segmentation in agricultural applications.

Coronavirus disease (COVID‐19) affects the lives of billions of people worldwide and has destructive impacts on daily life routines, the global economy, and public health. Early diagnosis and quantification of COVID‐19 infection have a vital role in improving treatment outcomes and interrupting transmission. For this purpose, advances in medical imaging techniques like computed tomography (CT) scans offer great potential as an alternative to RT‐PCR assay. CT scans enable a better understanding of infection morphology and tracking of lesion boundaries. Since manual analysis of CT can be extremely tedious and time‐consuming, robust automated image segmentation is necessary for clinical diagnosis and decision support. This paper proposes an efficient segmentation framework based on the modified DeepLabV3+ using lower atrous rates in the Atrous Spatial Pyramid Pooling (ASPP) module. The lower atrous rates make receptive small to capture intricate morphological details. The encoder part of the framework utilizes a pre‐trained residual network based on dilated convolutions for optimum resolution of feature maps. In order to evaluate the robustness of the modified model, a comprehensive comparison with other state‐of‐the‐art segmentation methods was also performed. The experiments were carried out using a fivefold cross‐validation technique on a publicly available database containing 100 single‐slice CT scans from >40 patients with COVID‐19. The modified DeepLabV3+ achieved good segmentation performance using around 43.9 M parameters. The lower atrous rates in the ASPP module improved segmentation performance. After fivefold cross‐validation, the framework achieved an overall Dice similarity coefficient score of 0.881. The results demonstrate that several minor modifications to the DeepLabV3+ pipeline can provide robust solutions for improving segmentation performance and hardware implementation.

In today’s modern communication society, the authenticity of digital media has never been of such importance as it is now. In this aspect, the reliability of digital images is of paramount importance because images can be easily manipulated by means of sophisticated software, such as Photoshop. Splicing tampering is a commonly used photographic manipulation for modifying images. Detecting splicing tampering remains a challenging task in the area of image forensics. A new multitask model based on attention mechanism, densely connected network, Atrous Spatial Pyramid Pooling (ASPP) and U-Net for locating splicing tampering in an image, AttDAU-Net, was proposed. The proposed AttDAU-Net is basically a U-Net that incorporates the spatial rich model filtering, an attention mechanism, an ASPP module and a multitask learning framework, in order to capture more multi-scale information while enlarging the receptive field and improving the detection precision of image splicing tampering. The experimental results on the datasets of CASIA1 and CASIA2 showed promising performance metrics for the proposed model (F1-scores of 0.7736 and 0.6937, respectively), which were better than other state-of-the-art methods for comparison, demonstrating the feasibility and effectiveness of the proposed AttDAU-Net in locating image splicing tampering.

The use of MRI-guided radiation therapy (MRIgRT) has shown considerable advantages. However, the acquisition of electron density information still relies on Computed tomography (CT) images. In the context of medical image synthesis, achieving high global and local accuracy, as well as efficient synthetic CT (sCT) generation, remains a key challenge. This study aims to improve the accuracy of sCT image generation from MRI by introducing a novel deep learning model that leverages global context and local detail, with a minimal increase in model complexity. In this study, we propose a novel generative adversarial network based on Mamba block and Residual Constraint (RC) strategy, namely RC-MambaGAN, which achieves a significant improvement in accuracy with only a minimal increase in computation time required for sCT generation. Specifically, we integrate Mamba block into the generator to enhance the model's ability to capture long-range contextual information, while preserving the precision of local features and maintaining the global structure of the image. The RC strategy improves the alignment between sCT and real CT by minimizing residuals. The model was validated on multi-center datasets that included both tumor and pelvic-region data. Furthermore, the dosimetric accuracy of the generated sCT images was evaluated to assess their clinical applicability. RC-MambaGAN achieved high performance with mean absolute error (MAE) of 37.094±8.761 HU, peak signal-to-noise ratio (PSNR) of 28.424±1.145dB, structural similarity index measure (SSIM) of 0.947±0.004, and Mutual Information (MI) of 1.426±0.012. External validation demonstrated that RC-MambaGAN outperformed existing state-of-the-art methods in both image quality and quantitative accuracy, even for structures visible in MRI but not in CT images. The proposed RC-MambaGAN markedly improves the image quality and anatomical accuracy of sCT images derived from MRI, thereby advancing the feasibility of MRI-only radiotherapy workflows.

This study aims to investigate the feasibility of a single general model to synthesize CT images across body sites, thorax, abdomen, and pelvis, to support treatment planning for MRI-only radiotherapy. A total of 157 patients who received MRI-guided radiation therapy in the thorax, abdomen, and pelvis on a 0.35T MRIdian Linac were included. A subset of 122 cases were used for model training and the remaining 35 cases were used for model validation. All patient datasets had semi-paired CT-simulation image and 0.35T MR image acquired using TrueFISP. A conditional generative adversarial network with a multi-planar method was used to generate synthetic CT images from 0.35T MR images. The effect of preprocessing methods (with and without bias field corrections) on the quality of synthetic CT was evaluated and found to be insignificant. The general models trained on all cases performed comparably to the site-specific models trained on individual body sites. For all models, the peak signal-to-noise ratios ranged from 31.7 to 34.9 and the structural index similarity measures ranged from 0.9547 to 0.9758. For the datasets with bias field corrections, the mean-absolute-errors in HU (general model vs. site-specific model) were 49.7±9.4 vs. 49.5±8.9, 48.7±7.6 vs. 43±7.8 and 32.8±5.5 vs 31.8±5.3 for the thorax, abdomen, and pelvis, respectively. When comparing plans between synthetic CTs and ground truth CTs, the dosimetric difference was on average less than 0.5% (0.2 Gy) for target coverage and less than 2.1% (0.4 Gy) for organ-at-risk metrics for all body sites with either the general or specific models. Synthetic CT plans showed good agreement with mean gamma pass rates of >94% and >99% for 1%/1 mm and 2%/2 mm, respectively. This study has demonstrated the feasibility of using a general model for multiple body sites and the potential of using synthetic CT to support an MRI-guided radiotherapy workflow.&#xD.

IntroductionEarly detection of leaf diseases is necessary to control the spread of plant diseases, and one of the important steps is the segmentation of leaf and disease images. The uneven light and leaf overlap in complex situations make segmentation of leaves and diseases quite difficult. Moreover, the significant differences in ratios of leaf and disease pixels results in a challenge in identifying diseases.MethodsTo solve the above issues, the residual attention mechanism combined with atrous spatial pyramid pooling and weight compression loss of UNet is proposed, which is named RAAWC-UNet. Firstly, weights compression loss is a method that introduces a modulation factor in front of the cross-entropy loss, aiming at solving the problem of the imbalance between foreground and background pixels. Secondly, the residual network and the convolutional block attention module are combined to form Res_CBAM. It can accurately localize pixels at the edge of the disease and alleviate the vanishing of gradient and semantic information from downsampling. Finally, in the last layer of downsampling, the atrous spatial pyramid pooling is used instead of two convolutions to solve the problem of insufficient spatial context information.ResultsThe experimental results show that the proposed RAAWC-UNet increases the intersection over union in leaf and disease segmentation by 1.91% and 5.61%, and the pixel accuracy of disease by 4.65% compared with UNet.DiscussionThe effectiveness of the proposed method was further verified by the better results in comparison with deep learning methods with similar network architectures.

Monte Carlo (MC) dose calculation is generally superior to analytical dose calculation (ADC) used in commercial TPS to model the dose distribution especially for heterogeneous sites, such as lung and head/neck patients. The purpose of this study was to provide a validated, fast, and open-source MC code, MCsquare, to assess the impact of approximations in ADC on clinical pencil beam scanning (PBS) plans covering various sites. First, MCsquare was validated using tissue-mimicking IROC lung phantom measurements as well as benchmarked with the general purpose Monte Carlo TOPAS for patient dose calculation. Then a comparative analysis between MCsquare and ADC was performed for a total of 50 patients with 10 patients per site (including liver, pelvis, brain, head-and-neck, and lung). Differences among TOPAS, MCsquare, and ADC were evaluated using four dosimetric indices based on the dose-volume histogram (target Dmean, D95, homogeneity index, V95), a 3D gamma index analysis (using 3%/3mm criteria), and estimations of tumor control probability (TCP). Comparison between MCsquare and TOPAS showed less than 1.8% difference for all of the dosimetric indices/TCP values and resulted in a 3D gamma index passing rate for voxels within the target in excess of 99%. When comparing ADC and MCsquare, the variances of all the indices were found to increase as the degree of tissue heterogeneity increased. In the case of lung, the D95s for ADC were found to differ by as much as 6.5% from the corresponding MCsquare statistic. The median gamma index passing rate for voxels within the target volume decreased from 99.3% for liver to 75.8% for lung. Resulting TCP differences can be large for lung (≤10.5%) and head-and-neck (≤6.2%), while smaller for brain, pelvis and liver (≤1.5%). Given the differences found in the analysis, accurate dose calculation algorithms such as Monte Carlo simulations are needed for proton therapy, especially for disease sites with high heterogeneity, such as head-and-neck and lung. The establishment of MCsquare can facilitate patient plan reviews at any institution and can potentially provide unbiased comparison in clinical trials given its accuracy, speed and open-source availability.

2D multi-person pose estimation is a challenging task in computer vision. Some regression-based single-stage methods lack pertinence for learning multi-person pose representation, which leads to insufficient feature extraction capability for the human joint structure and feature fusion capability for the keypoint location. This paper improves the problem of insufficient constraint for the keypoint features and proposes an algorithm with enhanced human keypoint features. Firstly, based on the idea of MixFormer, the strategy of the multi-head self-attention mechanism and depthwise convolution parallelism is proposed, which enhances the local and global features of the human pose simultaneously. High-quality visual representations can be obtained while learning more human joint structure information. Second, the strategy of serial fusion of the coordinate attention mechanism and atrous spatial pyramid pooling is proposed. The human pose features are split to capture cross-channel information, and then the atrous convolution is used to expand the receptive field, thus reducing the loss of small object information and enhancing the multi-scale feature fusion ability. Finally, the YOLO-Pose is combined for multi-person pose estimation. Experiments on the two data sets show that the algorithm in this paper improves the AP by 0.9 percentage points and the AR by 1.2 percentage points on the COCO2017 data sets. The AP on the OC_Human crowded data sets are improved by 2.3 percentage points. With the guarantee of the running speed unchanged, the human keypoint features are enhanced and the overall performance is improved.

Recently, semantic segmentation has been widely used in text detection tasks and many excellent text detection methods have been proposed. They usually adopt deep convolutional neural network with consecutive striding or pooling operations to obtain a larger receptive field. However, that would lead to the lack of context which is crucial for text detection. In this paper, we propose an end-to-end trainable neural network to directly detect text regions without redundant stage other than a locality-aware non-maximum suppression is involved. We introduce atrous convolution in the backbone network to enlarge the receptive field, retaining more context information while controlling the spatial resolution of feature maps. The Atrous Spatial Pyramid Pooling (ASPP) module is attached on top of the feature maps to effectively detect texts of multiple scales. We have benchmarked our algorithm on three public datasets. It achieves highly competitive results in terms of text localization precision. More specifically, on the MSRA-TD500 datasets, the proposed algorithm achieves an F-score of 0.813, outperforming the previous best by a large margin.

In Earth observation, cloud severely affects the interpretation of optical satellites generated high-resolution images. Cloud-free optical images are vital for downstream tasks such as semantic segmentation and object detection. Thus, the elimination of clouds from optical imagery has emerged as a significant topic in remote sensing. Currently, most existing methods are proposed to leverage the texture information from auxiliary synthetic aperture radar (SAR) images to restore cloud-free images via direct channel merging. However, such a unified feature extraction approach often neglects the inherent distribution disparity between SAR and optical images—the result of differing imaging principles-potentially leading to significant feature loss. To this end, we introduce a network by jointing SAR and optical images multimodal and cross-attention network (MMCANet) to effectively extract multiscale contextual features from SAR imagery and integrate them with optical features. Specifically, instead of simple concatenation of the channels of SAR and optical images, we obtain high-dimensional features from them through independent feature extractors. The integration of these features is facilitated by a cross-attention mechanism that provides a more fine-grained amalgamation of information. Meanwhile, an atrous spatial pyramid pooling (ASPP) module is introduced into the integration of high-level features, which captures multiscale contextual information around clouded areas. In addition, we propose four advanced remote sensing image restoration algorithms that approach image restoration as a series of subtasks, gradually eliminating clouds to enhance performance. Comprehensive assessments show that MMCANet performs well on the SEN 12 MS-CR dataset with peak signal-to-noise ratio (PSNR) of 39.8871, structural similarity index (SSIM) of 0.9672, mean absolute error (MAE) of 0.0081, and spectral angle mapper (SAM) of 2.9884.

Objective. Cone beam CT (CBCT) typically has severe image artifacts and inaccurate HU values, which limits its application in radiation medicines. Scholars have proposed the use of cycle consistent generative adversarial network (Cycle-GAN) to address these issues. However, the generation quality of Cycle-GAN needs to be improved. This issue is exacerbated by the inherent size discrepancies between pelvic CT scans from different patients, as well as varying slice positions within the same patient, which introduce a scaling problem during training. Approach. We introduced the Enhanced Edge and Mask (EEM) approach in our structural constraint Cycle-EEM-GAN. This approach is designed to not only solve the scaling problem but also significantly improve the generation quality of the synthetic CT images. Then data from sixty pelvic patients were used to investigate the generation of synthetic CT (sCT) from CBCT. Main results. The mean absolute error (MAE), the root mean square error (RMSE), the peak signal to noise ratio (PSNR), the structural similarity index (SSIM), and spatial nonuniformity (SNU) are used to assess the quality of the sCT generated from CBCT. Compared with CBCT images, the MAE improved from 53.09 to 37.74, RMSE from 185.22 to 146.63, SNU from 0.38 to 0.35, PSNR from 24.68 to 32.33, SSIM from 0.624 to 0.981. Also, the Cycle-EEM-GAN outperformed Cycle-GAN in terms of visual evaluation and loss. Significance. Cycle-EEM-GAN has improved the quality of CBCT images, making the structural details clear while prevents image scaling during the generation process, so that further promotes the application of CBCT in radiotherapy.

Background: Examining chest radiograph images (CXR) is an intricate and time-consuming process, sometimes requiring the identification of many anomalies at the same time. Lung segmentation is key to overcoming this challenge through different deep learning (DL) techniques. Many researchers are working to improve the performance and efficiency of lung segmentation models. This article presents a DL-based approach to accurately identify the lung mask region in CXR images to assist radiologists in recognizing early signs of high-risk lung diseases. Methods: This paper proposes a novel technique, Lightweight Residual U-Net, combining the strengths of the convolutional block attention module (CBAM), the Atrous Spatial Pyramid Pooling (ASPP) block, and the attention module, which consists of only 3.24 million trainable parameters. Furthermore, the proposed model has been trained using both the RELU and LeakyReLU activation functions, with LeakyReLU yielding superior performance. The study indicates that the Dice loss function is more effective in achieving better results. Results: The proposed model is evaluated on three benchmark datasets: JSRT, SZ, and MC, achieving a Dice score of 98.72%, 97.49%, and 99.08%, respectively, outperforming the state-of-the-art models. Conclusions: Using the capabilities of DL and cutting-edge attention processes, the proposed model improves current efforts to enhance lung segmentation for the early identification of many serious lung diseases.

In light of recent advances in deep learning and Synthetic Aperture Radar (SAR) technology, there has been a growing adoption of ship detection models that are based on deep learning methodologies. However, the efficiency of SAR ship detection models is significantly impacted by complex backgrounds, noise, and multi-scale ships (the number of pixels occupied by ships in SAR images varies significantly). To address the aforementioned issues, this research proposes a Pyramid Pooling Attention Network (PPA-Net) for SAR multi-scale ship detection. Firstly, a Pyramid Pooled Attention Module (PPAM) is designed to alleviate the influence of background noise on ship detection while its parallel component favors the processing of multiple ship sizes. Different from the previous attention module, the PPAM module can better suppress the background noise in SAR images because it considers the saliency of ships in SAR images. Secondly, an Adaptive Feature Balancing Module (AFBM) is developed, which can automatically balance the conflict between ship semantic information and location information. Finally, the detection capabilities of the ship detection model for multi-scale ships are further improved by introducing the Atrous Spatial Pyramid Pooling (ASPP) module. This innovative module enhances the detection model’s ability to detect ships of varying scales by extracting features from multiple scales using atrous convolutions and spatial pyramid pooling. PPA-Net achieved detection accuracies of 95.19% and 89.27% on the High-Resolution SAR Images Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD), respectively. The experimental results demonstrate that PPA-Net outperforms other ship detection models.

MRI has been increasingly implemented for the treatment planning process and the MRI-only workflow in both photon and proton therapy. This study aims to investigate and explore the accuracy of dose calculations in head and neck region based on synthetic CT (sCT) images, using the commercial software methods for both volumetric modulated arc therapy (VMAT) and intensity modulated proton therapy (IMPT) plans. The sCT images were generated from MRI images for five head and neck cancer cases that underwent VMAT and IMPT by MRI Planner commercial software. The mean absolute error (MAE) and mean error (ME) within the body, bone and brainstem contour and dice scores in body, and bone were used for evaluation. The treatment plans of VMAT (3 arcs) and IMPT (3-6 beam direction) were generated and optimized in the Eclipse treatment planning system (Version 16.1). The treatment plans were originally optimized and calculated on reference CT images and subsequently recalculated on synthetic CT images. The dose distributions were evaluated at D98%, D95% and D2% of PTV high risk and low risk for VMAT plans and CTV high risk and low risk for IMPT plans, Dmean and Dmax of organs at risk. Moreover, the dose comparisons between reference CT (rCT) and synthetic CT (sCT) images were analyzed at 3%/2mm gamma criteria. The MAE within the body, bone, and brainstem contour was 137.7±40.68, 387.27±114.84, and 33.07±2.78 Hounsfield Units (HU). Dice scores of body, and bone were 0.92±0.05 and 0.82±0.09. Comparing the average dose, the dose difference between using rCT and sCT images for VMAT was less than 2% in the PTV and less than 3% in the CTV. Additionally, in organs at risk, the highest dose difference between using rCT and sCT images was 30.09% for VMAT and 22.56% for IMPT. The average gamma passing rate at 3%/2mm was 98.8% for VMAT plan in PTV HR and 98.3% for PTV LR, respectively. The average gamma passing rate at 3%/2mm was 91.0% for IMPT plan in CTV HR and 93.8% for CTV LR, respectively. The dose difference between using rCT and sCT images has a greater impact for IMPT compared to VMAT. The commercial software used for generating sCTs has demonstrated significant dose differences for IMPT over VMAT plans for the head and neck region. The dose calculations based on these sCTs lead to more inaccurate dosimetric results; therefore, it should be considered when dealing with proton treatment plans.