Ability Of Segments Research Articles

Artificial neural network for cervical abnormalities detection on computed tomography images

<span lang="EN-US">Cervical cancer is the second deadliest after breast cancer in Indonesia. Sundry diagnostic imaging modalities had been used to decide the location and severity of cervical cancer, one among those is computed tomography (CT) Scan. This study handles a CT image dataset consisting of two categories, abnormal cervical images of cervical cancer patients and normal cervix images of patients with other diseases. It focuses on the ability of segmentation and classification programs to localize cervical cancer areas and classify images into normal and abnormal categories based on the features contained in them. We conferred a novel methodology for the contour detection round the cervical organ classified with artificial neural network (ANN) which was employed to categorize the image data. The segmentation algorithm used was a region-based snake model. The texture features of the cervical image area were arranged in the form of gray level co-occurrence matrix (GLCM). Support vector machine (SVM) had been added to determine which algorithm was better for comparison. Experimental results show that ANN model has better receiver operating characteristic (ROC) parameter values than SVM model’s and existing approach’s regarding 96.2% of sensitivity, 95.32% of specificity, and 95.75% of accuracy. </span>

Prognostic utility of linear segmentation in nonmetastatic renal cell carcinoma: Correlation of overall survival with muscle mass.

617 Background: In renal cell carcinoma (RCC) and other solid organ malignancies, sarcopenia has been associated with decreased survival and increased perioperative complications. Traditional body composition analysis is an expensive and time extensive process. As a modifiable risk factor, more clinic friendly methods to identify patients with low muscle composition is of interest. Linear segmentation on routine imaging has been proposed as a fast, reliable and reproducible alternative. This study assesses the prognostic ability of linear segmentation in patients with nonmetastatic RCC. Methods: Patients that underwent nephrectomy for nonmetastatic RCC from 2005-2021 at an academic referral center were identified. Linear segmentation of the bilateral psoas/paraspinal muscles was completed on preoperative imaging obtained within 60 days of surgery. Cox proportional-hazards analysis was used to determine association between total muscle index and overall survival. Results: 532 (388 clear cell) patients were analyzed and a median total muscle index was 28.6 (25.8-32.5) for women and 33.3 (29.1-36.9) for men. As a binary variable, lower total muscle index was significantly associated with decreased survival in both the full (HR=1.96, 95% CI 1.32-2.90, p<0.001) and clear cell only cohorts (HR=1.78, 95% CI 1.08-2.75, p=0.022). As a continuous variable, unit increases in total muscle index were significantly associated with improved survival in the full cohort (HR=0.95, 95% CI 0.92-0.99, p=0.006) and the clear cell only cohort (HR=0.95, 95% CI 0.92-0.99, p=0.016). Conclusions: Assessment of muscle composition via linear segmentation on routinely obtained preoperative imaging is a clinically feasible technique with prognostic utility in patients with localized RCC. In this cohort of patients with nonmetastatic RCC, linear segmentation demonstrated significant associations with overall survival as a binary and continuous variable. This simplified technique may allow for routine inclusion of body composition into clinical decision making. [Table: see text]

Segmentation ability map: Interpret deep features for medical image segmentation.

Deep convolutional neural networks (CNNs) have been widely used for medical image segmentation. In most studies, only the output layer is exploited to compute the final segmentation results and the hidden representations of the deep learned features have not been well understood. In this paper, we propose a prototype segmentation (ProtoSeg) method to compute a binary segmentation map based on deep features. We measure the segmentation abilities of the features by computing the Dice between the feature segmentation map and ground-truth, named as the segmentation ability score (SA score for short). The corresponding SA score can quantify the segmentation abilities of deep features in different layers and units to understand the deep neural networks for segmentation. In addition, our method can provide a mean SA score which can give a performance estimation of the output on the test images without ground-truth. Finally, we use the proposed ProtoSeg method to compute the segmentation map directly on input images to further understand the segmentation ability of each input image. Results are presented on segmenting tumors in brain MRI, lesions in skin images, COVID-related abnormality in CT images, prostate segmentation in abdominal MRI, and pancreatic mass segmentation in CT images. Our method can provide new insights for interpreting and explainable AI systems for medical image segmentation. Our code is available on: https://github.com/shengfly/ProtoSeg.

A Novel Model of Thyroid Nodule Segmentation for Ultrasound Images.

Ultrasonography is regarded as an effective technique for the detection, diagnosis and monitoring of thyroid nodules. Segmentation of thyroid nodules on ultrasound images is important in clinical practice. However, because in ultrasound images there is an unclear boundary between thyroid nodules and surrounding tissues, the accuracy of segmentation remains a challenge. Although the deep learning model provides an accurate and convenient method for thyroid nodule segmentation, it is unsatisfactory of the existing model in segmenting the margin of thyroid nodules. In this study, we developed boundary attention transformer net (BTNet), a novel segmentation network with a boundary attention mechanism combining the advantages of a convolutional neural network and transformer, which could fuse the features of both long and short ranges. Boundary attention is improved to focus on learning the boundary information, and this module enhances the segmentation ability of the network boundary. For features of different scales, we also incorporate a deep supervision mechanism to blend the outputs of different levels to enhance the segmentation effect. As the BTNet model incorporates the long range-short range connectivity effect and the boundary-regional cooperation capability, our model has excellent segmentation performance in thyroid nodule segmentation. The development of BTNet was based on the data set from Shanghai Jiao Tong University School of Medicine Affiliated Sixth People's Hospital and the public data set. BTNet achieved good performance in the segmentation of thyroid nodules with an intersection-over-union of 0.810 and Dice coefficient of 0.892 Moreover, our work revealed great improvement in the boundary metrics; for example, the boundary distance was 7.308, the boundary overlap 0.201 and the boundary Dice 0.194, all with p values <0.05.

MINet: Multi-scale input network for fundus microvascular segmentation

Vessel segmentation in fundus images is a key procedure in the diagnosis of ophthalmic diseases, which can play a role in assisting doctors in diagnosis. Although current deep learning-based methods can achieve high accuracy in segmenting fundus vessel images, the results are not satisfactory in segmenting microscopic vessels that are close to the background region. The reason for this problem is that thin blood vessels contain very little information, with the convolution operation of each layer in the deep network, this part of the information will be randomly lost. To improve the segmentation ability of the small blood vessel region, a multi-input network (MINet) was proposed to segment vascular regions more accurately. We designed a multi-input fusion module (MIF) in the encoder, which is proposed to acquire multi-scale features in the encoder stage while preserving the microvessel feature information. In addition, to further aggregate multi-scale information from adjacent regions, a multi-scale atrous spatial pyramid (MASP) module is proposed. This module can enhance the extraction of vascular information without reducing the resolution loss. In order to better recover segmentation results with details, we designed a refinement module, which acts on the last layer of the network output to refine the results of the last layer of the network to get more accurate segmentation results. We use the HRF, CHASE_DB1 public dataset to validate the fundus vessel segmentation performance of the MINet model. Also, we merged these two public datasets with our collected Ultra-widefield fundus image (UWF) data as one dataset to test the generalization ability of the model. Experimental results show that MINet achieves an F1 score of 0.8324 on the microvessel segmentation task, achieving a high accuracy compared to the current mainstream models.

A depth information aided real-time instance segmentation method for space task scenarios under CPU platform

Visual instance segmentation ability is one of the effective means to promote the autonomy and intelligence of space agents. However, due to the limited airborne computing capacity, current methods are difficult to deploy on space agents, because these methods are developed based on GPU. To this end, this paper proposes a novel framework of instance segmentation by introducing depth information and combining traditional computer vision techniques with an object detection method. This framework provides a new idea for the implementation of instance segmentation. The experiment results show that the proposed method achieves a real-time performance under a common laptop CPU platform. In addition, thanks to the introduction of depth information, the proposed method can obtain better segmentation results compared to Mask R–CNN and SOLOv2 in complex scenes (poor illumination and occlusion). Finally, because the semantic information is obtained by the object detection method in this paper, the model training adopts a weakly supervised manner from bounding-box annotations, which can reduce various costs of data labeling to a certain extent.

RCCT-ASPPNet: Dual-Encoder Remote Image Segmentation Based on Transformer and ASPP

Remote image semantic segmentation technology is one of the core research elements in the field of computer vision and has a wide range of applications in production life. Most remote image semantic segmentation methods are based on CNN. Recently, Transformer provided a view of long-distance dependencies in images. In this paper, we propose RCCT-ASPPNet, which includes the dual-encoder structure of Residual Multiscale Channel Cross-Fusion with Transformer (RCCT) and Atrous Spatial Pyramid Pooling (ASPP). RCCT uses Transformer to cross fuse global multiscale semantic information; the residual structure is then used to connect the inputs and outputs. ASPP based on CNN extracts contextual information of high-level semantics from different perspectives and uses Convolutional Block Attention Module (CBAM) to extract spatial and channel information, which will further improve the model segmentation ability. The experimental results show that the mIoU of our method is 94.14% and 61.30% on the datasets Farmland and AeroScapes, respectively, and that the mPA is 97.12% and 84.36%, respectively, both outperforming DeepLabV3+ and UCTransNet.

COVID-19 Lung CT image segmentation using localization and enhancement methods with U-Net

Segmentation of pneumonia lesions from Lung CT images has become vital for diagnosing the disease and evaluating the severity of the patients during the COVID-19 pandemic. Several AI-based systems have been proposed for this task. However, some low-contrast abnormal zones in CT images make the task challenging. The researchers investigated image preprocessing techniques to accomplish this problem and to enable more accurate segmentation by the AI-based systems. This study proposes a COVID-19 Lung-CT segmentation system based on histogram-based non-parametric region localization and enhancement (LE) methods prior to the U-Net architecture. The COVID-19-infected lung CT images were initially processed by the LE method, and the infected regions were detected and enhanced to provide more discriminative features to the deep learning segmentation methods. The U-Net is trained using the enhanced images to segment the regions affected by COVID-19. The proposed system achieved 97.75%, 0.85, and 0.74 accuracy, dice score, and Jaccard index, respectively. The comparison results suggested that the use of LE methods as a preprocessing step in CT Lung images significantly improved the feature extraction and segmentation abilities of the U-Net model by a 0.21 dice score. The results might lead to implementing the LE method in segmenting varied medical images.

Entropy Regularized Unsupervised Clustering Based on Maximum Correntropy Criterion and Adaptive Neighbors

Constructing accurate similarity graph is an important process in graph-based clustering. However, traditional methods have three drawbacks, such as the inaccuracy of the similarity graph, the vulnerability to noise and outliers, and the need for additional discretization process. In order to eliminate these limitations, an entropy regularized unsupervised clustering based on maximum correntropy criterion and adaptive neighbors (ERMCC) is proposed. 1) Combining information entropy and adaptive neighbors to solve the trivial similarity distributions. And we introduce ℓ0-norm and spectral embedding to construct similarity graph with sparsity and strong segmentation ability. 2) Reducing the negative impact of non-Gaussian noise by reconstructing the error using correntropy. 3) The prediction label vector is directly obtained by calculating the sparse strongly connected components of the similarity graph Z, which avoids additional discretization process. Experiments are conducted on six typical datasets and the results showed the effectiveness of the method.

ViT-SAPS: Detail-Aware Transformer for Mechanical Assembly Semantic Segmentation

Semantic segmentation of mechanical assembly images provides an effective way to monitor the assembly process and improve the product quality. Compared with other deep learning models, Transformer has advantages in modeling global context, and it has been widely applied in various computer vision tasks including semantic segmentation. However, Transformer pays the same granularity of attention on all the regions of an image, so it has some difficulty to be applied to the semantic segmentation of mechanical assembly images, in which mechanical parts have large size differences and the information quantity distribution is uneven. This paper proposes a novel Transformer-based model called Vision Transformer with Self-Adaptive Patch Size (ViT-SAPS). ViT-SAPS can perceive the detail information in an image and pays finer-grained attention on the regions where the detail information locates, thus meeting the requirements of mechanical assembly semantic segmentation. Specifically, a self-adaptive patch splitting algorithm is proposed to split an image into patches of various sizes. The more detail information an image region has, the smaller patches it is split into. Further, to handle these unfixed-size patches, a position encoding scheme and a non-uniform bilinear interpolation algorithm used after sequence decoding are proposed. Experimental results show that ViT-SAPS has stronger detail segmentation ability than the model with fixed patch size, and achieves an impressive locality-globality trade-off. This study not only provides a practical method for mechanical assembly semantic segmentation, but also has much value for the application of vision Transformers in other fields. The code is available at: https://github.com/QDLGARIM/ViT-SAPS.

DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images

Unsupervised domain adaptation (UDA) has become an important technique for cross-domain semantic segmentation (SS) in the remote sensing community and obtained remarkable results. However, when transferring from high-resolution (HR) remote sensing images to low-resolution (LR) images, the existing UDA frameworks always fail to segment the LR target images, especially for small objects (e.g., cars), due to the severe spatial resolution shift problem. In this article, to improve the segmentation ability of UDA models for LR target images and small objects, we propose a novel multitask domain adaptation network (DASRSNet) for SS of remote sensing images with the aid of super-resolution (SR). The proposed DASRSNet contains domain adaptation for SS (DASS) branch, domain adaptation for SR (DASR) branch, and feature affinity (FA) module. Specifically, the DASS and DASR branches share the same encoder to extract the domain-invariant features for the target and source domains, and these two branches utilize different decoders and discriminators to conduct cross-domain SS task and SR task, which align the domain shift in output space and image space, respectively. Finally, the FA module, which involves the proposed FA loss, is applied to enhance the affinity of SS features and SR features for both source and target domains. The experimental results on the cross-city aerial datasets demonstrate the effectiveness and superiority of our DASRSNet against the recent UDA models.

Crack Unet: Crack Recognition Algorithm Based on Three-Dimensional Ground Penetrating Radar Images

Three-dimensional (3D) ground-penetrating radar is an effective method for detecting internal crack damage in pavement structures. Inefficient manual interpretation of radar images and high personnel requirements have substantially restrained the generalization of 3D ground-penetrating radar. An improved Crack Unet model based on the Unet semantic segmentation model is proposed herein for 3D ground-penetrating radar crack image processing. The experiment showed that the MPA, MioU, and accuracy of the model were improved, and it displayed better capacity in the radar image crack segmentation task than current mainstream algorithms do, such as deepLabv3, PSPNet, and Unet. In the test dataset without cracks, Crack Unet is on the same level as deepLabv3 and PSPNet, which can meet engineering requirements and display a significant improvement compared with Unet. According to the ablation experiment, the MPA and MioU of Unet configured with PMDA, MC-FS, and RS modules were larger than those of Unet configured with one or two modules. The PMDA module adopted by the Crack Unet model showed a higher MPA and MioU than the SE module and the CBAM module did, respectively. The results show that the Crack Unet model has a better segmentation ability than the current mainstream algorithms do in the task of the crack segmentation of radar images, and the performance of crack segmentation is significantly improved compared with the Unet model. The Crack Unet model has excellent engineering application value in the task of the crack segmentation of radar images.

Wave-Net: A lightweight deep network for retinal vessel segmentation from fundus images

Accurate segmentation of retinal vessels from fundus images is fundamental for the diagnosis of numerous diseases of eye, and an automated vessel segmentation method can effectively help clinicians to make accurate diagnosis for the patients and provide the appropriate treatment schemes. It is important to note that both thick and thin vessels play the key role for disease judgements. Because of complex factors, the precise segmentation of thin vessels is still a great challenge, such as the presence of various lesions, image noise, complex backgrounds and poor contrast in the fundus images. Recently, because of the advantage of context feature representation learning capabilities, deep learning has shown a remarkable segmentation performance on retinal vessels. However, it still has some shortcomings on high-precision retinal vessel extraction due to some factors, such as semantic information loss caused by pooling operations, limited receptive field, etc. To address these problems, this paper proposes a new lightweight segmentation network for precise retinal vessel segmentation, which is called as Wave-Net model on account of the whole shape. To alleviate the influence of semantic information loss problem to thin vessels, to acquire more contexts about micro structures and details, a detail enhancement and denoising block (DED) is proposed to improve the segmentation precision on thin vessels, which replaces the simple skip connections of original U-Net. On the other hand, it could well alleviate the influence of the semantic gap problem. Further, faced with limited receptive field, for multi-scale vessel detection, a multi-scale feature fusion block (MFF) is proposed to fuse cross-scale contexts to achieve higher segmentation accuracy and realize effective processing of local feature maps. Experiments indicate that proposed Wave-Net achieves an excellent performance on retinal vessel segmentation while maintaining a lightweight network design compared to other advanced segmentation methods, and it also has shown a better segmentation ability to thin vessels.

Hierarchical Object-Focused and Grid-Based Deep Unsupervised Segmentation Method for High-Resolution Remote Sensing Images

Since the unsupervised segmentation of high-resolution remote sensing is a highly challenging task, the introduction of deep learning and processing may be a sensible choice to improve the quality of unsupervised segmentation. Unfortunately, any attempt to direct using unsupervised deep neural networks (UDNNs) to perform this task will be hindered by many obstacles: uncontrollable refinement processes, excessive fragmentation at the borders and excessive computing resource requirements. These obstacles can prevent us from obtaining acceptable results. To address this problem, this article proposes a hierarchical object-focused and grid-based deep unsupervised segmentation method for high-resolution remote sensing images (HOFG). Based on a grid approach, HOFG first adopt a lazy deep segmentation method (LDSM) to handle fragmentation and large image sizes. Then, a hierarchical and iterative segmentation strategy is introduced to reduce the accuracy expectation for the LDSM by means of a cascaded focus mechanism, making the entire segmentation process more controllable. HOFG can overcome all of the above obstacles while utilizing the high recognition ability of UDNNs. In experiments, HOFG are compared with shallow and deep unsupervised segmentation methods. The results show that HOFG can obtain fewer segments while maintaining a high accuracy. HOFG transform the unsupervised classification ability of UDNNs into a controllable and stable segmentation ability, making HOFG valuable for practical applications. The results show that on average, HOFG need only 81.73% as many segments as traditional shallow methods to achieve a high overall accuracy, and HOFG can obtain a 7.2% higher accuracy than a UDNN even when using only approximately 18% as many segments. HOFG can effectively and controllably utilize the recognition ability of UDNNs to achieve better unsupervised segmentation results.

Mask Region-Based Convolutional Neural Network (R-CNN) Based Image Segmentation of Rays in Softwoods

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10–15 μm were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

KADIN DOSTU KENT YAKLAŞIMI İLE KENTSEL AÇIK VE YEŞİL ALANLARIN DEĞERLENDİRİLMESİ: EFELER / AYDIN ÖRNEĞİ

Toplum içinde her bir bireyin kentsel açık ve yeşil alanları kullanma ve bu alanlardan faydalanma hakları vardır. Tüm dünyada ve ülkemizde kentsel açık ve yeşil alanların toplumun çeşitli katmanları tarafından kullanılma biçimleri ile bu mekânların kullanılma motivasyonlarını etkileyen faktörler yaşanabilirlik ve sürdürülebilirlik konularının temel odağında yer almaktadır. Bir kentsel açık ve yeşil alanın kent içinde bulunduğu konum, alanın çevresinin mimari özellikleri, insanlara sunduğu farklı kullanım olanakları, erişilebilirliği ve güvenliği gibi birçok faktör toplumun farklı kesimlerinin bu alanları kullanma veya kullan(a)mamaları üzerinde etkili olmaktadır. Tüm toplumlarda olduğu gibi Türk toplumunda da çeşitli olanak ve hizmetlere erişimde cinsiyet eşitliği kavramı tartışmaya daima açık bir konu olarak değerlendirilmektedir. Bu kapsamda, bu çalışma ile Aydın ili Efeler ilçesinde seçilen örnek parklar kadın dostu kent yaklaşımı ile değerlendirilerek, geleceğe yönelik planlama ve tasarım önerileri geliştirilmiştir.

Multilevel feature context semantic fusion network for cloud and cloud shadow segmentation

Cloud detection is an important prerequisite for remote sensing image application. Any remote sensing image from which the information of ground object could be obtained will inevitably be preprocessed on cloud occlusion. In the traditional method, the segmentation of cloud and its shadow will be affected by the complex background. In the detection process, due to insufficient information extraction, misjudgment often occurs, and the cloud boundary processing is also very rough. In order to improve the accuracy of cloud and cloud shadow segmentation, we propose a multilevel feature context semantic fusion network. The network takes the residual network as the backbone networkand adopts the structure of encoding and decoding as a whole. In the model, we introduce the multibranch residual context semantic module, the multiscale convolution subchannel attention module, and the feature fusion upsampling module to strengthen the feature extraction, refine the cloud and cloud shadow edge information, and enhance the actual segmentation ability of the model. The experimental results show that the proposed method is more accurate than the previous network in the segmentation of cloud and cloud shadow and has good generalization ability on other datasets, which is of great significance for the study of cloud.

CPAD-Net: Contextual parallel attention and dilated network for liver tumor segmentation

Liver cancer is one of the leading causes of cancer death. Accurate and automatic liver tumor segmentation methods are urgent needs in clinical practice. Currently, Fully Convolutional Network and U-Net framework have achieved good results in medical image segmentation tasks, but there is still room for improvement. The traditional U-Net extracted a large number of low-level features, and the detailed features cannot be transmitted to deeper layers, resulting in poor segmentation ability. Therefore, this paper proposed a novel liver tumor segmentation network with contextual parallel attention and dilated convolution, called CPAD-Net. The proposed network applies a subsampled module, which has the same dimensionality reduction function as max-pooling without losing detailed features. CPAD-Net employs a contextual parallel attention module at skip connection. The module fuses contextual multi-scale features and extracts channel-spatial features in parallel. These features are concatenated with deep features to narrow the semantic gap and increase detailed information. Hybrid dilated convolution and double-dilated convolution are used in the encoding and decoding stages to expand the network receptive field. Dropout is added after each hybrid dilated convolution block to prevent overfitting. The efficacy of the proposed network is proved by widespread experimentation on two public datasets (LiTS2017 and 3Dircadb-01) and a clinical dataset from the Affiliated Hospital of Hebei University. The proposed network achieved Dice scores of 74.2%, 73.7% and 73.26%. The experimental results show that the proposed network outperforms most segmentation networks.

EA-Net: Edge-aware network for brain structure segmentation via decoupled high and low frequency features

Automatic brain structure segmentation in Magnetic Resonance Image (MRI) plays an important role in the diagnosis of various neuropsychiatric diseases. However, most existing methods yield unsatisfactory results due to blurred boundaries and complex structures. Improving the segmentation ability requires the model to be explicit about the spatial localization and shape appearance of targets, which correspond to the low-frequency content features and the high-frequency edge features, respectively. Therefore, in this paper, to extract rich edge and content feature representations, we focus on the composition of the feature and utilize a frequency decoupling (FD) block to separate the low-frequency and high-frequency parts of the feature. Further, a novel edge-aware network (EA-Net) is proposed for jointly learning to segment brain structures and detect object edges. First, an encoder–decoder sub-network is utilized to obtain multi-level information from the input MRI, which is then sent to the FD block to complete the frequency separation. Further, we use different mechanisms to optimize both the low-frequency and high-frequency features. Finally, these two parts are fused to generate the final prediction. In particular, we extract the content mask and the edge mask from the optimization feature with different supervisions, which forces the network to learn the boundary features of the object. Extensive experiments are performed on two public brain MRI T1 scan datasets (the IBSR dataset and the MALC dataset) to evaluate the effectiveness of the proposed algorithm. The experiments show that the EA-Net achieves the best performance compared with the state-of-the-art methods, and improves the segmentation DSC score by 1.31% at most compared with the U-Net model and its variants. Moreover, we evaluate the EA-Net under different noise disturbances, and the results demonstrate the robustness and superiority of our method under low-quality noisy MRI. Code is available at https://github.com/huqian999/EA-Net.

DBF-Net: a semi-supervised dual-task balanced fusion network for segmenting infected regions from lung CT images.

Accurate segmentation of infected regions in lung computed tomography (CT) images is essential to improve the timeliness and effectiveness of treatment for coronavirus disease 2019 (COVID-19). However, the main difficulties in developing of lung lesion segmentation in COVID-19 are still the fuzzy boundary of the lung-infected region, the low contrast between the infected region and the normal trend region, and the difficulty in obtaining labeled data. To this end, we propose a novel dual-task consistent network framework that uses multiple inputs to continuously learn and extract lung infection region features, which is used to generate reliable label images (pseudo-labels) and expand the dataset. Specifically, we periodically feed multiple sets of raw and data-enhanced images into two trunk branches of the network; the characteristics of the lung infection region are extracted by a lightweight double convolution (LDC) module and fusiform equilibrium fusion pyramid (FEFP) convolution in the backbone. According to the learned features, the infected regions are segmented, and pseudo-labels are made based on the semi-supervised learning strategy, which effectively alleviates the semi-supervised problem of unlabeled data. Our proposed semi-supervised dual-task balanced fusion network (DBF-Net) creates pseudo-labels on the COVID-SemiSeg dataset and the COVID-19 CT segmentation dataset. Furthermore, we perform lung infection segmentation on the DBF-Net model, with a segmentation sensitivity of 70.6% and specificity of 92.8%. The results of the investigation indicate that the proposed network greatly enhances the segmentation ability of COVID-19 infection.