Semi-Supervised Modified-UNet for Lung Infection Image Segmentation

Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE

Towards Lifting the Trade-off between Accuracy and Adversarial Robustness of Deep Neural Networks with Application on COVID 19 CT Image Classification and Medical Image Segmentation

Deep neural networks (DNNs) are vulnerable to adversarial noises. Adversarial training is a general strategy to improve DNN robustness. But training a DNN model with adversarial noises may result in a much lower accuracy on clean data, which is termed the trade-off between accuracy and adversarial robustness. Towards lifting this trade-off, we propose an adversarial training method that generates optimal adversarial training samples. We evaluate our methods on PathMNIST and COVID-19 CT image classification tasks, where the DNN model is ResNet-18, and Heart MRI and Prostate MRI image segmentation tasks, where the DNN model is nnUnet. All these four datasets are publicly available. The experiment results show that our method has the best robustness against adversarial noises and has the least accuracy degradation compared to the other defense methods. © 2023 SPIE.

Medical image mis-segmentation region refinement framework based on dynamic graph convolution

In medical image segmentation tasks, it is hard for traditional Convolutional Neural Network (CNN) to capture essential information such as spatial structure and global contextual semantic features since it suffers from a limited receptive field. The deficiency weakens the CNN segmentation performance in the lesion boundary regions. To handle the aforementioned problems, a medical image mis-segmentation region refinement framework based on dynamic graph convolution is proposed to refine the boundary and under-segmentation regions. The proposed framework first employs a lightweight dual-path network to detect the boundaries and nearby regions, which can further obtain potentially misclassified pixels from the coarse segmentation results of the CNN. Then, we construct the pixels into the appropriate graphs by CNN-extracted features. Finally, we design a dynamic residual graph convolutional network to reclassify the graph nodes and generate the final refinement results. We chose UNet and its eight representative improved networks as the basic networks and tested them on the COVID, DSB, and BUSI datasets. Experiments demonstrated that the average Dice of our framework is improved by 1.79%, 2.29%, and 2.24%, the average IoU is improved by 2.30%, 3.53%, and 2.39%, and the Se is improved by 5.08%, 4.78%, and 5.31% respectively. The experimental results prove that the proposed framework has the refinement capability to remarkably strengthen the segmentation result of the basic network. Furthermore, the framework has the advantage of high portability and usability, which can be inserted into the end of mainstream medical image segmentation networks as a plug-and-play enhancement block.

Multi-Attentional U-Net for Medical Image Segmentation

Deep learning (DL) approaches for image segmentation have been gaining state-of-the-art performance in recent years. Particularly, in deep learning, U-Net model has been successfully used in the field of image segmentation. However, traditional U-Net methods extract features, aggregate remote information, and reconstruct images by stacking convolution, pooling, and up sampling blocks. The traditional approach is very inefficient due of the stacked local operators. In this paper, we propose the multi-attentional U-Net that is equipped with non-local blocks based self-attention, channel-attention, and spatial-attention for image segmentation. These blocks can be inserted into U-Net to flexibly aggregate information on the plane and spatial scales. We perform and evaluate the multi-attentional U-Net model on three benchmark data sets, which are COVID-19 segmentation, skin cancer segmentation, thyroid nodules segmentation. Results show that our proposed models achieve better performances with faster computation and fewer parameters. The multi-attention U-Net can improve the medical image segmentation results. © 2022 IEEE.

ATFormer: Advanced transformer for medical image segmentation

Combining transformers and convolutional neural networks is considered one of the most important directions for tackling medical image segmentation problems. To learn the long-range dependencies and local contexts, previous approaches embedded a convolutional layer into feedforward neural network inside the transformer block. However, a common issue is the instability during training since large differences in amplitude across layers by pre-layer normalization. Furthermore, multi-scale features were directly fused using the transformer from the encoder to decoder, which could disrupt valuable information for segmentation. To address these concerns, we propose Advanced TransFormer (ATFormer), a novel hybrid architecture that combines convolutional neural networks and transformers for medical image segmentation. First, the traditional transformer block has been refined into an Advanced Transformer Block, which adopts post-layer normalization to obtain mild activation values and employs the scaled cosine attention with shifted window for accurate spatial information. Second, the Progressive Guided Fusion module is introduced to make multi-scale features more discriminative while reducing the computational complexity. Experimental results on the ACDC, COVID-19 CT-Seg, and Tumor datasets demonstrate the significant advantage of ATFormer over existing methods that rely solely on convolutional neural networks, transformers, or their combination.

FSA-Net: Rethinking the attention mechanisms in medical image segmentation from releasing global suppressed information.

Attention mechanism-based medical image segmentation methods have developed rapidly recently. For the attention mechanisms, it is crucial to accurately capture the distribution weights of the effective features contained in the data. To accomplish this task, most attention mechanisms prefer using the global squeezing approach. However, it will lead to a problem of over-focusing on the global most salient effective features of the region of interest, while suppressing the secondary salient ones. Making partial fine-grained features are abandoned directly. To address this issue, we propose to use a multiple-local perception method to aggregate global effective features, and design a fine-grained medical image segmentation network, named FSA-Net. This network consists of two key components: 1) the novel Separable Attention Mechanisms which replace global squeezing with local squeezing to release the suppressed secondary salient effective features. 2) a Multi-Attention Aggregator (MAA) which can fuse multi-level attention to efficiently aggregate task-relevant semantic information. We conduct extensive experimental evaluations on five publicly available medical image segmentation datasets: MoNuSeg, COVID-19-CT100, GlaS, CVC-ClinicDB, ISIC2018, and DRIVE datasets. Experimental results show that FSA-Net outperforms state-of-the-art methods in medical image segmentation.

NAG-Net: Nested attention-guided learning for segmentation of carotid lumen-intima interface and media-adventitia interface.

Cardiovascular diseases (CVD), as the leading cause of death in the world, poses a serious threat to human health. The segmentation of carotid Lumen-intima interface (LII) and Media-adventitia interface (MAI) is a prerequisite for measuring intima-media thickness (IMT), which is of great significance for early screening and prevention of CVD. Despite recent advances, existing methods still fail to incorporate task-related clinical domain knowledge and require complex post-processing steps to obtain fine contours of LII and MAI. In this paper, a nested attention-guided deep learning model (named NAG-Net) is proposed for accurate segmentation of LII and MAI. The NAG-Net consists of two nested sub-networks, the Intima-Media Region Segmentation Network (IMRSN) and the LII and MAI Segmentation Network (LII-MAISN). It innovatively incorporates task-related clinical domain knowledge through the visual attention map generated by IMRSN, enabling LII-MAISN to focus more on the clinician's visual focus region under the same task during segmentation. Moreover, the segmentation results can directly obtain fine contours of LII and MAI through simple refinement without complicated post-processing steps. To further improve the feature extraction ability of the model and reduce the impact of data scarcity, the strategy of transfer learning is also adopted to apply the pretrained weights of VGG-16. In addition, a channel attention-based encoder feature fusion block (EFFB-ATT) is specially designed to achieve efficient representation of useful features extracted by two parallel encoders in LII-MAISN. Extensive experimental results have demonstrated that our proposed NAG-Net outperformed other state-of-the-art methods and achieved the highest performance on all evaluation metrics.

GSAL: Geometric structure adversarial learning for robust medical image segmentation

• A new learning mechanism for medical image segmentation. We introduce a novel Geometric Structure Learning Mechanism (GSLM) that enhances model learning "focus, path, and difficulty". It enables geometric structure attention learning to bridge image features with large differences, thus capturing the contextual dependencies of images. The image features maintain consistency and continuity along the internal and external geometry structure, which improves the integrity and boundary accuracy of the segmentation results. To the best of our knowledge, we are the first attempt to explicitly establish the target's geometric structure, which has been successfully applied to medical image segmentation. • A novel geometric structure adversarial learning for robust medical image segmentation. We present the geometric structure adversarial learning model (GSAL) that consists of a geometric structure generator, skeleton-like and boundary discriminators, and a geometric structure fusion sub-network. The generator yields the geometric structure that preserves interior characteristics consistency and external boundary structure continuity. The dual discriminators are trained simultaneously to enhance and correct the characterization of interior structure and boundary structure, respectively. The fusion sub-network aims to fuse the geometric structure that optimized by adversarial learning to refine the final segmentation results with higher credibility. • State-of-art results on widely-used benchmarks. Our GSAL achieves SOTA performance on a variety of benchmarks, including Kvasir&CVC-612 dataset, COVID-19 dataset, and LIDC-IDRI dataset. It confirms the robustness and generalizability of our framework. In addition, our method has great advantages in terms of the integrity and boundary accuracy of the segmentation target compared to other competitive methods. GSAL can also achieve a considerable trade-off in terms of accuracy, inference speed, and model complexity, which helps deploy in clinical practice systems. Automatic medical image segmentation plays a crucial role in clinical diagnosis and treatment. However, it is still a challenging task due to the complex interior characteristics (e.g. , inconsistent intensity, low contrast, texture heterogeneity) and ambiguous external boundary structures. In this paper, we introduce a novel geometric structure learning mechanism (GSLM) to overcome the limitations of existing segmentation models that lack learning "focus, path, and difficulty." The geometric structure in this mechanism is jointly characterized by the skeleton-like structure extracted by the mask distance transform (MDT) and the boundary structure extracted by the mask distance inverse transform (MDIT). Among them, the skeleton-like and boundary pay attention to the trend of interior characteristics consistency and external structure continuity, respectively. With this idea, we design GSAL, a novel end-to-end geometric structure adversarial learning for robust medical image segmentation. GSAL has four components: a geometric structure generator, which yields the geometric structure to learn the most discriminative features that preserve interior characteristics consistency and external boundary structure continuity, skeleton-like and boundary structure discriminators, which enhance and correct the characterization of internal and external geometry to mutually promote the capture of global contextual dependencies, and a geometric structure fusion sub-network, which fuses the two complementary and refined skeleton-like and boundary structures to generate the high-quality segmentation results. The proposed approach has been successfully applied to three different challenging medical image segmentation tasks, including polyp segmentation, COVID-19 lung infection segmentation, and lung nodule segmentation. Extensive experimental results demonstrate that the proposed GSAL achieves favorably against most state-of-the-art methods under different evaluation metrics. The code is available at: https://github.com/DLWK/GSAL. [ BSTRACT FROM AUTHOR] Copyright of Pattern Recognition is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Dual attention fusion UNet for COVID-19 lesion segmentation from CT images.

BACKGROUND: Chest CT scan is an effective way to detect and diagnose COVID-19 infection. However, features of COVID-19 infection in chest CT images are very complex and heterogeneous, which make segmentation of COVID-19 lesions from CT images quite challenging. OBJECTIVE: To overcome this challenge, this study proposes and tests an end-to-end deep learning method called dual attention fusion UNet (DAF-UNet). METHODS: The proposed DAF-UNet improves the typical UNet into an advanced architecture. The dense-connected convolution is adopted to replace the convolution operation. The mixture of average-pooling and max-pooling acts as the down-sampling in the encoder. Bridge-connected layers, including convolution, batch normalization, and leaky rectified linear unit (leaky ReLU) activation, serve as the skip connections between the encoder and decoder to bridge the semantic gap differences. A multiscale pyramid pooling module acts as the bottleneck to fit the features of COVID-19 lesion with complexity. Furthermore, dual attention feature (DAF) fusion containing channel and position attentions followed the improved UNet to learn the long-dependency contextual features of COVID-19 and further enhance the capacity of the proposed DAF-UNet. The proposed model is first pre-trained on the pseudo label dataset (generated by Inf-Net) containing many samples, then fine-tuned on the standard annotation dataset (provided by the Italian Society of Medical and Interventional Radiology) with high-quality but limited samples to improve performance of COVID-19 lesion segmentation on chest CT images. RESULTS: The Dice coefficient and Sensitivity are 0.778 and 0.798 respectively. The proposed DAF-UNet has higher scores than the popular models (Att-UNet, Dense-UNet, Inf-Net, COPLE-Net) tested using the same dataset as our model. CONCLUSION: The study demonstrates that the proposed DAF-UNet achieves superior performance for precisely segmenting COVID-19 lesions from chest CT scans compared with the state-of-the-art approaches. Thus, the DAF-UNet has promising potential for assisting COVID-19 disease screening and detection.

Segmentation Algorithm for COVID-19 Infections using Joint Mix and Context Encoder

Automatic image segmentation is critical for medical image segmentation. For example, automatic segmentation of infection area of COVID-19 before and after diagnosis and treatment can help us automatically analyze the diagnosis and treatment effect. The existing algorithms do not solve the problems of insufficient data and insufficient feature extraction at the same time. In this paper, we propose a new data augmentation algorithm to handle the insufficient data problem, named Joint Mix;we utilize an improved U-Net with context encoder to enhance the feature extraction ability. Experiments in the segmentation of COVID-19 infection region using CT images demonstrate its effectiveness. © 2022 IEEE.

A graph-based edge attention gate medical image segmentation method

For the purpose of solving the problems of missing edges and low segmentation accuracy in medical image segmentation, a medical image segmentation network (EAGC_UNet++) based on residual graph convolution UNet++ with edge attention gate (EAG) is proposed in the study. With UNet++ as the backbone network, the idea of graph theory is introduced into the model. First, the dropout residual graph convolution block (DropRes_GCN Block) and the traditional convolution structure in UNet++ are used as encoders. Second, EAGs are adopted so that the model pays more attention to image edge features during decoding. Finally, aiming at the imbalance problem of positive and negative samples in medical image segmentation, a new weighted loss function is introduced to enhance segmentation accuracy. In the experimental part, three datasets (LiTS2017, ISIC2018, COVID-19 CT scans) were used to evaluate the performances of various models;multiple groups of ablation experiments were designed to verify the effectiveness of each part of the model. The experimental results showed that EAGC_UNet++ had better segmentation performance than the other models under three quantitative evaluation indicators and better solved the problem of missing edges in medical image segmentation. © 2023 The Authors. IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

An Effective Segmentation Method for COVID-19 CT Image Based on Attention Mechanism and Inf-Net

The corona virus disease 2019 (COVID-19) pandemic has recently ravaged the world, seriously affecting the life and health of human society. Computerized tomography (CT) imaging technology is an important diagnostic method for detecting COVID-19. Automatic and accurate segmentation of the lesion is of great significance for diagnosis, treatment and prognosis. Aiming at the segmentation of new coronary pneumonia lesions, an improved automatic segmentation method based on the Inf-Net algorithm is proposed, which introduces the channel attention module to improve feature representation and attention gate model to better fuse edge information. The experimental results on COVID-19 CT Segmentation dataset show that the Dice similarity coefficient, Sensitivity and Specificity of the proposed method are 75.1%, 75.4% and 95.4%. The segmentation performance of it is superior to that of other state-of-the-art ones. (English) [ABSTRACT FROM AUTHOR] 新型冠状病毒肺炎肆虐全球, 严重影响了人类社会的生活和健康。CT影像技术是检测新冠肺炎的重要诊断方式, 从CT图像中自动准确分割出新冠肺炎病灶区域, 对于诊断、治疗和预后都有重要意义。针对新冠肺炎病灶的自动分割, 文中提出基于Inf-Net算法改进的自动分割方法, 通过引入通道注意力机制加强特征表示, 并运用注意力门模块来更好地融合边缘信息。在COVID-19 CT分割数据集上的实验结果表明, 文中所提出新冠肺炎图像分割方法的Dice系数、灵敏度、特异率分别为75.1%、75.4%和95.4%, 算法性能也优于部分主流方法 (Chinese) [ABSTRACT FROM AUTHOR] Copyright of Electronic Science & Technology is the property of Electronic Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A Novel Automated Classification and Segmentation for COVID-19 using 3D CT Scans

Medical image classification and segmentation based on deep learning (DL) are emergency research topics for diagnosing variant viruses of the current COVID-19 situation. In COVID-19 computed tomography (CT) images of the lungs, ground glass turbidity is the most common finding that requires specialist diagnosis. Based on this situation, some researchers propose the relevant DL models which can replace professional diagnostic specialists in clinics when lacking expertise. However, although DL methods have a stunning performance in medical image processing, the limited datasets can be a challenge in developing the accuracy of diagnosis at the human level. In addition, deep learning algorithms face the challenge of classifying and segmenting medical images in three or even multiple dimensions and maintaining high accuracy rates. Consequently, with a guaranteed high level of accuracy, our model can classify the patients' CT images into three types: Normal, Pneumonia and COVID. Subsequently, two datasets are used for segmentation, one of the datasets even has only a limited amount of data (20 cases). Our system combined the classification model and the segmentation model together, a fully integrated diagnostic model was built on the basis of ResNet50 and 3D U-Net algorithm. By feeding with different datasets, the COVID image segmentation of the infected area will be carried out according to classification results. Our model achieves 94.52% accuracy in the classification of lung lesions by 3 types: COVID, Pneumonia and Normal. For 2 labels (ground truth, lung lesions) segmentation, the model gets 99.57% of accuracy, 0.2191 of train loss and 0.78 ± 0.03 of MeanDice±Std, while the 4 labels (ground truth, left lung, right lung, lung lesions) segmentation achieves 98.89% of accuracy, 0.1132 of train loss and 0.83 ± 0.13 of MeanDice±Std. For future medical use, embedding the model into the medical facilities might be an efficient way of assisting or substituting doctors with diagnoses, therefore, a broader range of the problem of variant viruses in the COVID-19 situation may also be successfully solved. © 2022 IEEE.

COVID-19 Detection Using Deep Learning Based Medical Image Segmentation

COVID-19 is a rapidly spreading illness around the globe, yet healthcare resources are limited. Timely screening of people who may have had COVID-19 is critical in reducing the virus's spread considering the lack of an effective treatment or medication. COVID-19 patients should be diagnosed as well as isolated as early as possible to avoid the infection from spreading and levelling the pandemic arc. To detect COVID-19, chest ultrasound tomography seems to be an option to the RT-PCR assay. The Ultrasound of the lung is a very precise, quick, relatively reliable surgical assay that can be used in conjunction with the RT PCR (Reverse Transcription Polymerase Chain Reaction) assay. Differential diagnosis is difficult due to large differences in structure, shape, and position of illnesses. The efficiency of conventional neural learning-based Computed tomography scans feature extraction is limited by discontinuous ground-glass and acquisitions, as well as clinical alterations. Deep learning-based techniques, primarily Convolutional Neural Networks (CNN), had successfully proved remarkable therapeutic outcomes. Moreover, CNNs are unable to capture complex features amongst images examples, necessitating the use of huge databases. In this paper semantic segmentation method is used. The semantic segmentation architecture U-Net is applied on COVID-19 CT images as well as another method is suggested based on prior semantic segmentation. The accuracy of U-Net is 87% and by using pre-trained U-Net with convolution layers gives accuracy of 89.07%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Medical Image Segmentation Based on Transformer and HarDNet Structures

Medical image segmentation is a crucial way to assist doctors in the accurate diagnosis of diseases. However, the accuracy of medical image segmentation needs further improvement due to the problems of many noisy medical images and the high similarity between background and target regions. The current mainstream image segmentation networks, such as TransUnet, have achieved accurate image segmentation. Still, the encoders of such segmentation networks do not consider the local connection between adjacent chunks and lack the interaction of inter-channel information during the upsampling of the decoder. To address the above problems, this paper proposed a dual-encoder image segmentation network, including HarDNet68 and Transformer branch, which can extract the local features and global feature information of the input image, allowing the segmentation network to learn more image information, thus improving the effectiveness and accuracy of medical segmentation. In this paper, to realize the fusion of image feature information of different dimensions in two stages of encoding and decoding, we propose a feature adaptation fusion module to fuse the channel information of multi-level features and realize the information interaction between channels, and then improve the segmentation network accuracy. The experimental results on CVC-ClinicDB, ETIS-Larib, and COVID-19 CT datasets show that the proposed model performs better in four evaluation metrics, Dice, Iou, Prec, and Sens, and achieves better segmentation results in both internal filling and edge prediction of medical images. Accurate medical image segmentation can assist doctors in making a critical diagnosis of cancerous regions in advance, ensure cancer patients receive timely targeted treatment, and improve their survival quality. © 2013 IEEE.

MESTrans: Multi-scale embedding spatial transformer for medical image segmentation.

BACKGROUND AND OBJECTIVE: Transformers profiting from global information modeling derived from the self-attention mechanism have recently achieved remarkable performance in computer vision. In this study, a novel transformer-based medical image segmentation network called the multi-scale embedding spatial transformer (MESTrans) was proposed for medical image segmentation. METHODS: First, a dataset called COVID-DS36 was created from 4369 computed tomography (CT) images of 36 patients from a partner hospital, of which 18 had COVID-19 and 18 did not. Subsequently, a novel medical image segmentation network was proposed, which introduced a self-attention mechanism to improve the inherent limitation of convolutional neural networks (CNNs) and was capable of adaptively extracting discriminative information in both global and local content. Specifically, based on U-Net, a multi-scale embedding block (MEB) and multi-layer spatial attention transformer (SATrans) structure were designed, which can dynamically adjust the receptive field in accordance with the input content. The spatial relationship between multi-level and multi-scale image patches was modeled, and the global context information was captured effectively. To make the network concentrate on the salient feature region, a feature fusion module (FFM) was established, which performed global learning and soft selection between shallow and deep features, adaptively combining the encoder and decoder features. Four datasets comprising CT images, magnetic resonance (MR) images, and H&E-stained slide images were used to assess the performance of the proposed network. RESULTS: Experiments were performed using four different types of medical image datasets. For the COVID-DS36 dataset, our method achieved a Dice similarity coefficient (DSC) of 81.23%. For the GlaS dataset, 89.95% DSC and 82.39% intersection over union (IoU) were obtained. On the Synapse dataset, the average DSC was 77.48% and the average Hausdorff distance (HD) was 31.69 mm. For the I2CVB dataset, 92.3% DSC and 85.8% IoU were obtained. CONCLUSIONS: The experimental results demonstrate that the proposed model has an excellent generalization ability and outperforms other state-of-the-art methods. It is expected to be a potent tool to assist clinicians in auxiliary diagnosis and to promote the development of medical intelligence technology.

HD2A-Net: A novel dual gated attention network using comprehensive hybrid dilated convolutions for medical image segmentation.

The convolutional neural networks (CNNs) have been widely proposed in the medical image analysis tasks, especially in the image segmentations. In recent years, the encoder-decoder structures, such as the U-Net, were rendered. However, the multi-scale information transmission and effective modeling for long-range feature dependencies in these structures were not sufficiently considered. To improve the performance of the existing methods, we propose a novel hybrid dual dilated attention network (HD2A-Net) to conduct the lesion region segmentations. In the proposed network, we innovatively present the comprehensive hybrid dilated convolution (CHDC) module, which facilitates the transmission of the multi-scale information. Based on the CHDC module and the attention mechanisms, we design a novel dual dilated gated attention (DDGA) block to enhance the saliency of related regions from the multi-scale aspect. Besides, a dilated dense (DD) block is designed to expand the receptive fields. The ablation studies were performed to verify our proposed blocks. Besides, the interpretability of the HD2A-Net was analyzed through the visualization of the attention weight maps from the key blocks. Compared to the state-of-the-art methods including CA-Net, DeepLabV3+, and Attention U-Net, the HD2A-Net outperforms significantly, with the metrics of Dice, Average Symmetric Surface Distance (ASSD), and mean Intersection-over-Union (mIoU) reaching 93.16%, 93.63%, and 94.72%, 0.36 pix, 0.69 pix, and 0.52 pix, and 88.03%, 88.67%, and 90.33% on three publicly available medical image datasets: MAEDE-MAFTOUNI (COVID-19 CT), ISIC-2018 (Melanoma Dermoscopy), and Kvasir-SEG (Gastrointestinal Disease Polyp), respectively.

PGUNET: COVID-19 CT IMAGE SEGMENTATION USING GAN AND FEATURE PYRAMID

Since computed tomography (CT) provides the most sensitive radiological technique for diagnosing COVID-19, CT has been used as an efficient and necessary aided diagnosis. However, the size and number of publicly available COVID-19 imaging datasets are limited and have problems such as low data volume, easy overfitting for training, and significant differences in the characteristics of lesions at different scales. Our work presents an image segmentation network, Pyramid-and-GAN-UNet (PGUNet), to support the segmentation of COVID-19 lesions by combining feature pyramid and generative adversarial network (GAN). Using GAN, the segmentation network can learn more abundant high-level features and increase the generalization ability. The module of the feature pyramid is used to solve the differences between image features at different levels. Compared with the current mainstream method, our experimental results show that the proposed network achieved more competitive performances on the CT slice datasets of the COVID-19 CT Segmentation dataset and CC-CCII dataset. © 2022 IEEE.

PGUNET: COVID-19 CT IMAGE SEGMENTATION USING GAN AND FEATURE PYRAMID

Since computed tomography (CT) provides the most sensitive radiological technique for diagnosing COVID-19, CT has been used as an efficient and necessary aided diagnosis. However, the size and number of publicly available COVID-19 imaging datasets are limited and have problems such as low data volume, easy overfitting for training, and significant differences in the characteristics of lesions at different scales. Our work presents an image segmentation network, Pyramid-and-GAN-UNet (PGUNet), to support the segmentation of COVID-19 lesions by combining feature pyramid and generative adversarial network (GAN). Using GAN, the segmentation network can learn more abundant high-level features and increase the generalization ability. The module of the feature pyramid is used to solve the differences between image features at different levels. Compared with the current mainstream method, our experimental results show that the proposed network achieved more competitive performances on the CT slice datasets of the COVID-19 CT Segmentation dataset and CC-CCII dataset. © 2022 IEEE.

MCA-UNet: multi-scale cross co-attentional U-Net for automatic medical image segmentation.

Medical image segmentation is a challenging task due to the high variation in shape, size and position of infections or lesions in medical images. It is necessary to construct multi-scale representations to capture image contents from different scales. However, it is still challenging for U-Net with a simple skip connection to model the global multi-scale context. To overcome it, we proposed a dense skip-connection with cross co-attention in U-Net to solve the semantic gaps for an accurate automatic medical image segmentation. We name our method MCA-UNet, which enjoys two benefits: (1) it has a strong ability to model the multi-scale features, and (2) it jointly explores the spatial and channel attentions. The experimental results on the COVID-19 and IDRiD datasets suggest that our MCA-UNet produces more precise segmentation performance for the consolidation, ground-glass opacity (GGO), microaneurysms (MA) and hard exudates (EX). The source code of this work will be released via https://github.com/McGregorWwww/MCA-UNet/.