Lightweight Attention Convolutional Neural Network for Retinal Vessel Image Segmentation

A Detailed Systematic Review on Retinal Image Segmentation Methods

The separation of blood vessels in the retina is a major aspect in detecting ailment and is carried out by segregating the retinal blood vessels from the fundus images. Moreover, it helps to provide earlier therapy for deadly diseases and prevent further impacts due to diabetes and hypertension. Many reviews already exist for this problem, but those reviews have presented the analysis of a single framework. Hence, this article on retinal segmentation review has revealed distinct methodologies with diverse frameworks that are utilized for blood vessel separation. The novelty of this review research lies in finding the best neural network model by comparing its efficiency. For that, machine learning (ML) and deep learning (DL) were compared and have been reported as the best model. Moreover, different datasets were used to segment the retinal blood vessels. The execution of each approach is compared based on the performance metrics such as sensitivity, specificity, and accuracy using publically accessible datasets like STARE, DRIVE, ROSE, REFUGE, and CHASE. This article discloses the implementation capacity of distinct techniques implemented for each segmentation method. Finally, the finest accuracy of 98% and sensitivity of 96% were achieved for the technique of Convolution Neural Network with Ranking Support Vector Machine (CNN-rSVM). Moreover, this technique has utilized public datasets to verify efficiency. Hence, the overall review of this article has revealed a method for earlier diagnosis of diseases to deliver earlier therapy.

Explainable multi-instance and multi-task learning for COVID-19 diagnosis and lesion segmentation in CT images

Coronavirus Disease 2019 (COVID-19) still presents a pandemic trend globally. Detecting infected individuals and analyzing their status can provide patients with proper healthcare while protecting the normal population. Chest CT (computed tomography) is an effective tool for screening of COVID-19. It displays detailed pathology-related information. To achieve automated COVID-19 diagnosis and lung CT image segmentation, convolutional neural networks (CNNs) have become mainstream methods. However, most of the previous works consider automated diagnosis and image segmentation as two independent tasks, in which some focus on lung fields segmentation and the others focus on single-lesion segmentation. Moreover, lack of clinical explainability is a common problem for CNN-based methods. In such context, we develop a multi-task learning framework in which the diagnosis of COVID-19 and multi-lesion recognition (segmentation of CT images) are achieved simultaneously. The core of the proposed framework is an explainable multi-instance multi-task network. The network learns task-related features adaptively with learnable weights, and gives explicable diagnosis results by suggesting local CT images with lesions as additional evidence. Then, severity assessment of COVID-19 and lesion quantification are performed to analyze patient status. Extensive experimental results on real-world datasets show that the proposed framework outperforms all the compared approaches for COVID-19 diagnosis and multi-lesion segmentation.

Segmentation and volume quantification of epicardial adipose tissue in computed tomography images

BACKGROUND

Many cardiovascular diseases are closely related to the composition of epicardial adipose tissue (EAT). Accurate segmentation of EAT can provide a reliable reference for doctors to diagnose the disease. The distribution and composition of EAT often have significant individual differences, and the traditional segmentation methods are not effective. In recent years, deep learning method has been gradually introduced into EAT segmentation task.

PURPOSE

The existing EAT segmentation methods based on deep learning have a large amount of computation and the segmentation accuracy needs to be improved. Therefore, the purpose of this paper is to develop a lightweight EAT segmentation network, which can obtain higher segmentation accuracy with less computation and further alleviate the problem of false positive segmentation.

METHODS

Firstly, the obtained Computed Tomography (CT) was preprocessed. That is, the threshold range of EAT was determined to be (-190, -30) HU according to prior knowledge, and the non-adipose pixels were excluded by threshold segmentation to reduce the difficulty of training. Secondly, the image obtained after thresholding was input into the lightweight RDU-Net network to perform the training, validating, and testing process. RDU-Net uses a residual multi-scale dilated convolution block in order to extract a wider range of information without changing the current resolution. At the same time, the form of residual connection is adopted to avoid the problem of gradient expansion or gradient explosion caused by too deep network, which also makes the learning easier. In order to optimize the training process, this paper proposes PNDiceLoss, which takes both positive and negative pixels as learning targets, fully considers the class imbalance problem and appropriately highlights the status of positive pixels.

RESULTS

In this paper, 50 CCTA images were randomly selected from the hospital, and the commonly used Dice similarity coefficient (DSC), Jaccard similarity (JS), Accuracy (ACC), Specificity (SP), Precision (PC), and Pearson correlation coefficient are used as evaluation metrics. Bland-Altman analysis results show that the extracted EAT volume is consistent with the actual volume. Compared with the existing methods, the segmentation results show that the proposed method achieves better performance on these metrics, achieving the DSC of 0.9262. The number of false positive pixels has been reduced by more than half. Pearson correlation coefficient reached 0.992, and linear regression coefficient reached 0.977 when measuring the volume of EAT obtained. In order to verify the effectiveness of the proposed method, experiments are carried out in the cardiac fat database of VisualLab. On this database, the proposed method also achieved good results, and the DSC value reached 0.927 in the case of only 878 slices.

CONCLUSIONS

A new method to segment and quantify EAT is proposed. Comprehensive experiments show that compared with some classical segmentation algorithms, the proposed method has the advantages of shorter time-consuming, less memory required for operations, and higher segmentation accuracy. The code is available at https://github.com/lvanlee/EAT_Seg/tree/main/EAT_seg. This article is protected by copyright. All rights reserved.

Hybrid algorithm for retinal blood vessel segmentation using different pattern recognition techniques

Blood vessel segmentation of the retina has become a necessary step in automatic disease identification and planning treatment in the field of Ophthalmology. To identify the disease properly, both thick and thin blood vessels should be distinguished clearly. Diagnosis of disease would be simple and easier only when the blood vessels are segmented accurately. Existing blood vessel segmentation methods are not supporting well to overcome the poor accuracy and low generalization problems because of the complex blood vessel structure of the retina. In this study, a hybrid algorithm is proposed using binarization, exclusively for segmenting the vessels from a retina image to enhance the exactness and specificity of segmentation of an image. The proposed algorithm extracts the advantages of pattern recognition techniques, such as Matched Filter (MF), Matched Filter with First-order Derivation of Gaussian (MF-FDOG), Multi-Scale Line Detector (MSLD) algorithms and developed as a hybrid algorithm. This algorithm is authenticated with the openly accessible dataset DRIVE. Using Python with OpenCV, the algorithm simulation results had attained an accurateness of 0.9602, a sensitivity of 0.6246, and a specificity of 0.9815 for the dataset. Simulation outcomes proved that the proposed hybrid algorithm accurately segments the blood vessels of the retina compared to the existing methodologies.

Dual Encoder-Based Dynamic-Channel Graph Convolutional Network With Edge Enhancement for Retinal Vessel Segmentation

Retinal vessel segmentation with deep learning technology is a crucial auxiliary method for clinicians to diagnose fundus diseases. However, the deep learning approaches inevitably lose the edge information, which contains spatial features of vessels while performing down-sampling, leading to the limited segmentation performance of fine blood vessels. Furthermore, the existing methods ignore the dynamic topological correlations among feature maps in the deep learning framework, resulting in the inefficient capture of the channel characterization. To address these limitations, we propose a novel dual encoder-based dynamic-channel graph convolutional network with edge enhancement (DE-DCGCN-EE) for retinal vessel segmentation. Specifically, we first design an edge detection-based dual encoder to preserve the edge of vessels in down-sampling. Secondly, we investigate a dynamic-channel graph convolutional network to map the image channels to the topological space and synthesize the features of each channel on the topological map, which solves the limitation of insufficient channel information utilization. Finally, we study an edge enhancement block, aiming to fuse the edge and spatial features in the dual encoder, which is beneficial to improve the accuracy of fine blood vessel segmentation. Competitive experimental results on five retinal image datasets validate the efficacy of the proposed DE-DCGCN-EE, which achieves more remarkable segmentation results against the other state-of-the-art methods, indicating its potential clinical application.

Image Segmentation of Retinal Blood Vessels Based on Dual-Attention Multiscale Feature Fusion

Aiming at the problem of insufficient details of retinal blood vessel segmentation in current research methods, this paper proposes a multiscale feature fusion residual network based on dual attention. Specifically, a feature fusion residual module with adaptive calibration weight features is designed, which avoids gradient dispersion and network degradation while effectively extracting image details. The SA module and ECA module are used many times in the backbone feature extraction network to adaptively select the focus position to generate more discriminative feature representations; at the same time, the information of different levels of the network is fused, and long-range and short-range features are used. This method aggregates low-level and high-level feature information, which effectively improves the segmentation performance. The experimental results show that the method in this paper achieves the classification accuracy of 0.9795 and 0.9785 on the STARE and DRIVE datasets, respectively, and the classification performance is better than the current mainstream methods.

SAR ship target detection method based on CNN structure with wavelet and attention mechanism

Ship target detection in synthetic aperture radar (SAR) images is an important application field. Due to the existence of sea clutter, especially the SAR imaging in huge wave area, SAR images contain a lot of complex noise, which brings great challenges to the effective detection of ship targets in SAR images. Although the deep semantic segmentation network has been widely used in the detection of ship targets in recent years, the global information of the image cannot be fully utilized. To solve this problem, a new convolutional neural network (CNN) method based on wavelet and attention mechanism was proposed in this paper, called the WA-CNN algorithm. The new method uses the U-Net structure to construct the network, which not only effectively reduces the depth of the network structure, but also significantly improves the complexity of the network. The basic network of WA-CNN algorithm consists of encoder and decoder. Dual tree complex wavelet transform (DTCWT) is introduced into the pooling layer of the encoder to smooth the speckle noise in SAR images, which is beneficial to preserve the contour structure and detail information of the target in the feature image. The attention mechanism theory is added into the decoder to obtain the global information of the ship target. Two public SAR image datasets were used to verify the proposed method, and good experimental results were obtained. This shows that the method proposed in this article is effective and feasible.

MEA-Net: multilayer edge attention network for medical image segmentation

Medical image segmentation is a fundamental step in medical analysis and diagnosis. In recent years, deep learning networks have been used for precise segmentation. Numerous improved encoder-decoder structures have been proposed for various segmentation tasks. However, high-level features have gained more research attention than the abundant low-level features in the early stages of segmentation. Consequently, the learning of edge feature maps has been limited, which can lead to ambiguous boundaries of the predicted results. Inspired by the encoder-decoder network and attention mechanism, this study investigates a novel multilayer edge attention network (MEA-Net) to fully utilize the edge information in the encoding stages. MEA-Net comprises three major components: a feature encoder module, a feature decoder module, and an edge module. An edge feature extraction module in the edge module is designed to produce edge feature maps by a sequence of convolution operations so as to integrate the inconsistent edge information from different encoding stages. A multilayer attention guidance module is designed to use each attention feature map to filter edge information and select important and useful features. Through experiments, MEA-Net is evaluated on four medical image datasets, including tongue images, retinal vessel images, lung images, and clinical images. The evaluation values of the Accuracy of four medical image datasets are 0.9957, 0.9736, 0.9942, and 0.9993, respectively. The values of the Dice coefficient are 0.9902, 0.8377, 0.9885, and 0.9704, respectively. Experimental results demonstrate that the network being studied outperforms current state-of-the-art methods in terms of the five commonly used evaluation metrics. The proposed MEA-Net can be used for the early diagnosis of relevant diseases. In addition, clinicians can obtain more accurate clinical information from segmented medical images.

Segmenting Retinal Vessels Using a Shallow Segmentation Network to Aid Ophthalmic Analysis

Retinal blood vessels possess a complex structure in the retina and are considered an important biomarker for several retinal diseases. Ophthalmic diseases result in specific changes in the retinal vasculature; for example, diabetic retinopathy causes the retinal vessels to swell, and depending upon disease severity, fluid or blood can leak. Similarly, hypertensive retinopathy causes a change in the retinal vasculature due to the thinning of these vessels. Central retinal vein occlusion (CRVO) is a phenomenon in which the main vein causes drainage of the blood from the retina and this main vein can close completely or partially with symptoms of blurred vision and similar eye problems. Considering the importance of the retinal vasculature as an ophthalmic disease biomarker, ophthalmologists manually analyze retinal vascular changes. Manual analysis is a tedious task that requires constant observation to detect changes. The deep learning-based methods can ease the problem by learning from the annotations provided by an expert ophthalmologist. However, current deep learning-based methods are relatively inaccurate, computationally expensive, complex, and require image preprocessing for final detection. Moreover, existing methods are unable to provide a better true positive rate (sensitivity), which shows that the model can predict most of the vessel pixels. Therefore, this study presents the so-called vessel segmentation ultra-lite network (VSUL-Net) to accurately extract the retinal vasculature from the background. The proposed VSUL-Net comprises only 0.37 million trainable parameters and uses an original image as input without preprocessing. The VSUL-Net uses a retention block that specifically maintains the larger feature map size and low-level spatial information transfer. This retention block results in better sensitivity of the proposed VSUL-Net without using expensive preprocessing schemes. The proposed method was tested on three publicly available datasets: digital retinal images for vessel extraction (DRIVE), structured analysis of retina (STARE), and children’s heart health study in England database (CHASE-DB1) for retinal vasculature segmentation. The experimental results demonstrated that VSUL-Net provides robust segmentation of retinal vasculature with sensitivity (Sen), specificity (Spe), accuracy (Acc), and area under the curve (AUC) values of 83.80%, 98.21%, 96.95%, and 98.54%, respectively, for DRIVE, 81.73%, 98.35%, 97.17%, and 98.69%, respectively, for CHASE-DB1, and 86.64%, 98.13%, 97.27%, and 99.01%, respectively, for STARE datasets. The proposed method provides an accurate segmentation mask for deep ophthalmic analysis.

Fault Recognition Method Based on Attention Mechanism and the 3D-UNet

Oil and gas reservoirs are of great significance for economic benefits. Faults act as important conduits for transporting hydrocarbons and as essential sealing conditions. The location and morphology of faults reflect changes in the shape of the strata, so fault interpretation of seismic data has been an essential task in oil and gas exploration and development. The traditional fault identification method is time-consuming and inaccurate with large uncertainties. This paper proposed a fault recognition method based on 3D-UNet that added attention mechanisms to a convolutional neural network (CNN). This approach takes advantage of the UNet end-to-end architecture and the attention mechanism to focus on essential areas and suppress irrelevant information, allowing the model to focus on more valuable features. A fault identification network for seismic data was proposed by combining the 3D-UNet architecture with the Squeeze-and-Excitation (SE) attention mechanism. The 3D-UNet architecture comprises two parts: encoding and decoding, and the network architecture realizes end-to-end training. At the same time, SE was used to focus on the advantages of feature channels, further improving the accuracy of the network. The model performance was evaluated using the synthetic dataset provided by Wu. Experimental results show that the proposed model has better prediction performance in terms of accuracy, better recognition continuity, and richer fault detail.

Lesion-attention pyramid network for diabetic retinopathy grading

As one of the most common diabetic complications, diabetic retinopathy (DR) can cause retinal damage, vision loss and even blindness. Automated DR grading technology has important clinical significance, which can help ophthalmologists achieve rapid and early diagnosis. With the popularity of deep learning, DR grading based on the convolutional neural networks (CNNs) has become the mainstream method. Unfortunately, although the CNN-based method can achieve satisfactory diagnostic accuracy, it lacks significant clinical information. In this paper, a lesion-attention pyramid network (LAPN) is presented. The pyramid network integrates the subnetworks with different resolutions to get multi-scale features. In order to take the lesion regions in the high-resolution image as the diagnostic evidence, the low-resolution network calculates the lesion activation map (using the weakly-supervised localization method) and guides the high-resolution network to concentrate on the lesion regions. Furthermore, a lesion attention module (LAM) is designed to capture the complementary relationship between the high-resolution features and the low-resolution features, and to fuse the lesion activation map. Experiment results show that the proposed scheme outperforms other existing approaches, and the proposed method can provide lesion activation map with lesion consistency as an additional evidence for clinical diagnosis.

Quo vadis artificial intelligence?

The study of artificial intelligence (AI) has been a continuous endeavor of scientists and engineers for over 65 years. The simple contention is that human-created machines can do more than just labor-intensive work; they can develop human-like intelligence. Being aware or not, AI has penetrated into our daily lives, playing novel roles in industry, healthcare, transportation, education, and many more areas that are close to the general public. AI is believed to be one of the major drives to change socio-economical lives. In another aspect, AI contributes to the advancement of state-of-the-art technologies in many fields of study, as helpful tools for groundbreaking research. However, the prosperity of AI as we witness today was not established smoothly. During the past decades, AI has struggled through historical stages with several winters. Therefore, at this juncture, to enlighten future development, it is time to discuss the past, present, and have an outlook on AI. In this article, we will discuss from a historical perspective how challenges were faced on the path of revolution of both the AI tools and the AI systems. Especially, in addition to the technical development of AI in the short to mid-term, thoughts and insights are also presented regarding the symbiotic relationship of AI and humans in the long run.

3D multi-scale residual fully convolutional neural network for segmentation of extremely large-sized kidney tumor

BACKGROUND AND OBJECTIVE

We propose a novel deep neural network, the 3D Multi-Scale Residual Fully Convolutional Neural Network (3D-MS-RFCNN) to improve segmentation in extremely large-sized kidney tumors.

METHOD

The multi-scale approach with a deep neural network is applied to capture global contextual features. Our method, 3D-MS-RFCNN, consists of two encoders and one decoder as a single complete network. One of the encoders is designed for capturing global contextual information by using the low-resolution, down-sampled data from input images. In the decoder, features from the encoder for global contextual features are concatenated with up-sampled features from the previous layer and features from the other encoder. Ensemble learning strategy is also applied.

RESULTS

We evaluated the performance of our proposed method using the KiTS public dataset and the in-house hospital dataset. When compared with the state-of-the-art method, Res3D U-Net, our model, 3D-MS-RFCNN, demonstrated greater accuracy (0.9390 dice score for KiTS dataset and 0.8575 dice score for external dataset) for segmenting extremely large-sized kidney tumors.

CONCLUSIONS

Our proposed network shows significantly improved segmentation performance of extremely large-sized targets. This study can be usefully employed in the field of medical image analysis.

A Novel ABRM Model for Predicting Coal Moisture Content

Coal moisture content monitoring plays an important role in carbon reduction and clean energy decisions of coal transportation-storage aspects. Traditional coal moisture content detection mechanisms rely heavily on detection equipment, which can be expensive or difficult to deploy under field conditions. To achieve fast prediction of coal moisture content, a novel neural network model based on attention mechanism and bidirectional ResNet-LSTM structure (ABRM) is proposed in this paper. The prediction of coal moisture content is achieved by training the model to learn the relationship between changes of coal moisture content and meteorological conditions. The experimental results show that the proposed method has superior performance in terms of moisture content prediction accuracy compared with other state-of-the-art methods, and that ABRM model approaches appear to have the greatest potential for predicting coal moisture content shifts in the face of meteorological elements.

Diabetic and Hypertensive Retinopathy Screening in Fundus Images Using Artificially Intelligent Shallow Architectures

Retinal blood vessels are considered valuable biomarkers for the detection of diabetic retinopathy, hypertensive retinopathy, and other retinal disorders. Ophthalmologists analyze retinal vasculature by manual segmentation, which is a tedious task. Numerous studies have focused on automatic retinal vasculature segmentation using different methods for ophthalmic disease analysis. However, most of these methods are computationally expensive and lack robustness. This paper proposes two new shallow deep learning architectures: dual-stream fusion network (DSF-Net) and dual-stream aggregation network (DSA-Net) to accurately detect retinal vasculature. The proposed method uses semantic segmentation in raw color fundus images for the screening of diabetic and hypertensive retinopathies. The proposed method's performance is assessed using three publicly available fundus image datasets: Digital Retinal Images for Vessel Extraction (DRIVE), Structured Analysis of Retina (STARE), and Children Heart Health Study in England Database (CHASE-DB1). The experimental results revealed that the proposed method provided superior segmentation performance with accuracy (Acc), sensitivity (SE), specificity (SP), and area under the curve (AUC) of 96.93%, 82.68%, 98.30%, and 98.42% for DRIVE, 97.25%, 82.22%, 98.38%, and 98.15% for CHASE-DB1, and 97.00%, 86.07%, 98.00%, and 98.65% for STARE datasets, respectively. The experimental results also show that the proposed DSA-Net provides higher SE compared to the existing approaches. It means that the proposed method detected the minor vessels and provided the least false negatives, which is extremely important for diagnosis. The proposed method provides an automatic and accurate segmentation mask that can be used to highlight the vessel pixels. This detected vasculature can be utilized to compute the ratio between the vessel and the non-vessel pixels and distinguish between diabetic and hypertensive retinopathies, and morphology can be analyzed for related retinal disorders.

Pseudo-siamese networks with lexicon for Chinese short text matching

Short text matching is one of the fundamental technologies in natural language processing. In previous studies, most of the text matching networks are initially designed for English text. The common approach to applying them to Chinese is segmenting each sentence into words, and then taking these words as input. However, this method often results in word segmentation errors. Chinese short text matching faces the challenges of constructing effective features and understanding the semantic relationship between two sentences. In this work, we propose a novel lexicon-based pseudo-siamese model (CL2 N), which can fully mine the information expressed in Chinese text. Instead of utilizing a character-sequence or a single word-sequence, CL2 N augments the text representation with multi-granularity information in characters and lexicons. Additionally, it integrates sentence-level features through single-sentence features as well as interactive features. Experimental studies on two Chinese text matching datasets show that our model has better performance than the state-of-the-art short text matching models, and the proposed method can solve the error propagation problem of Chinese word segmentation. Particularly, the incorporation of single-sentence features and interactive features allows the network to capture the contextual semantics and co-attentive lexical information, which contributes to our best result.

When medical images meet generative adversarial network: recent development and research opportunities

Deep learning techniques have promoted the rise of artificial intelligence (AI) and performed well in computer vision. Medical image analysis is an important application of deep learning, which is expected to greatly reduce the workload of doctors, contributing to more sustainable health systems. However, most current AI methods for medical image analysis are based on supervised learning, which requires a lot of annotated data. The number of medical images available is usually small and the acquisition of medical image annotations is an expensive process. Generative adversarial network (GAN), an unsupervised method that has become very popular in recent years, can simulate the distribution of real data and reconstruct approximate real data. GAN opens some exciting new ways for medical image generation, expanding the number of medical images available for deep learning methods. Generated data can solve the problem of insufficient data or imbalanced data categories. Adversarial training is another contribution of GAN to medical imaging that has been applied to many tasks, such as classification, segmentation, or detection. This paper investigates the research status of GAN in medical images and analyzes several GAN methods commonly applied in this area. The study addresses GAN application for both medical image synthesis and adversarial learning for other medical image tasks. The open challenges and future research directions are also discussed.

Efficient Medical Image Segmentation Based on Knowledge Distillation

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage.

Fundus image segmentation via hierarchical feature learning

Fundus Image Segmentation (FIS) is an essential procedure for the automated diagnosis of ophthalmic diseases. Recently, deep fully convolutional networks have been widely used for FIS with state-of-the-art performance. The representative deep model is the U-Net, which follows an encoder-decoder architecture. I believe it is suboptimal for FIS because consecutive pooling operations in the encoder lead to low-resolution representation and loss of detailed spatial information, which is particularly important for the segmentation of tiny vessels and lesions. Motivated by this, a high-resolution hierarchical network (HHNet) is proposed to learn semantic-rich high-resolution representations and preserve spatial details simultaneously. Specifically, a High-resolution Feature Learning (HFL) module with increasing dilation rates was first designed to learn the high-level high-resolution representations. Then, the HHNet was constructed by incorporating three HFL modules and two feature aggregation modules. The HHNet runs in a coarse-to-fine manner, and fine segmentation maps are output at the last level. Extensive experiments were conducted on fundus lesion segmentation, vessel segmentation, and optic cup segmentation. The experimental results reveal that the proposed method shows highly competitive or even superior performance in terms of segmentation performance and computation cost, indicating its potential advantages in clinical application.

GCA-Net: global context attention network for intestinal wall vascular segmentation

PURPOSE

Precise segmentation of intestinal wall vessels is vital to colonic perforation prevention. However, there are interferences such as gastric juice in the vessel image of the intestinal wall, especially vessels and the mucosal folds are difficult to distinguish, which easily lead to mis-segmentation. In addition, the insufficient feature extraction of intricate vessel structures may leave out information of tiny vessels that result in rupture. To overcome these challenges, an effective network is proposed for segmentation of intestinal wall vessels.

METHODS

A global context attention network (GCA-Net) that employs a multi-scale fusion attention (MFA) module is proposed to adaptively integrate local and global context information to improve the distinguishability of mucosal folds and vessels, more importantly, the ability to capture tiny vessels. Also, a parallel decoder is used to introduce a contour loss function to solve the blurry and noisy blood vessel boundaries.

RESULTS

Extensive experimental results demonstrate the superiority of the GCA-Net, with accuracy of 94.84%, specificity of 97.89%, F1-score of 73.80%, AUC of 96.30%, and MeanIOU of 76.46% in fivefold cross-validation, exceeding the comparison methods. In addition, the public dataset DRIVE is used to verify the potential of GCA-Net in retinal vessel image segmentation.

CONCLUSION

A novel network for segmentation of intestinal wall vessels is developed, which can suppress interferences in intestinal wall vessel images, improve the discernibility of blood vessels and mucosal folds, enhance vessel boundaries, and capture tiny vessels. Comprehensive experiments prove that the proposed GCA-Net can accurately segment the intestinal wall vessels.

A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.

A new deep learning method for blood vessel segmentation in retinal images based on convolutional kernels and modified U-Net model

BACKGROUND AND OBJECTIVE

Automatic monitoring of retinal blood vessels proves very useful for the clinical assessment of ocular vascular anomalies or retinopathies. This paper presents an efficient and accurate deep learning-based method for vessel segmentation in eye fundus images.

METHODS

The approach consists of a convolutional neural network based on a simplified version of the U-Net architecture that combines residual blocks and batch normalization in the up- and downscaling phases. The network receives patches extracted from the original image as input and is trained with a novel loss function that considers the distance of each pixel to the vascular tree. At its output, it generates the probability of each pixel of the input patch belonging to the vascular structure. The application of the network to the patches in which a retinal image can be divided allows obtaining the pixel-wise probability map of the complete image. This probability map is then binarized with a certain threshold to generate the blood vessel segmentation provided by the method.

RESULTS

The method has been developed and evaluated in the DRIVE, STARE and CHASE_Db1 databases, which offer a manual segmentation of the vascular tree by each of its images. Using this set of images as ground truth, the accuracy of the vessel segmentations obtained for an operating point proposal (established by a single threshold value for each database) was quantified. The overall performance was measured using the area of its receiver operating characteristic curve. The method demonstrated robustness in the face of the variability of the fundus images of diverse origin, being capable of working with the highest level of accuracy in the entire set of possible points of operation, compared to those provided by the most accurate methods found in literature.

CONCLUSIONS

The analysis of results concludes that the proposed method reaches better performance than the rest of state-of-art methods and can be considered the most promising for integration into a real tool for vascular structure segmentation.