Network For Image Segmentation Research Articles

Redefining Contextual and Boundary Synergy: A Boundary-Guided Fusion Network for Medical Image Segmentation

Medical image segmentation plays a crucial role in medical image processing, focusing on the automated extraction of regions of interest (such as organs, lesions, etc.) from medical images. This process supports various clinical applications, including diagnosis, surgical planning, and treatment. In this paper, we introduce a Boundary-guided Context Fusion U-Net (BCF-UNet), a novel approach designed to tackle a critical shortcoming in current methods: the inability to effectively integrate boundary information with semantic context. The BCF-UNet introduces a Adaptive Multi-Frequency Encoder (AMFE), which uses multi-frequency analysis inspired by the Wavelet Transform (WT) to capture both local and global features efficiently. The Adaptive Multi-Frequency Encoder (AMFE) decomposes images into different frequency components and adapts more effectively to boundary texture information through a learnable activation function. Additionally, we introduce a new multi-scale feature fusion module, the Atten-kernel Adaptive Fusion Module (AKAFM), designed to integrate deep semantic information with shallow texture details, significantly bridging the gap between features at different scales. Furthermore, each layer of the encoder sub-network integrates a Boundary-aware Pyramid Module (BAPM), which utilizes a simple and effective method and combines it with a priori knowledge to extract multi-scale edge features to improve the accuracy of boundary segmentation. In BCF-UNet, semantic context is used to guide edge information extraction, enabling the model to more effectively comprehend and identify relationships among various organizational structures. Comprehensive experimental evaluations on two datasets demonstrate that the proposed BCF-UNet achieves superior performance compared to existing state-of-the-art methods.

Semi-supervised medical image segmentation network based on mutual learning.

Semi-supervised learning provides an effective means to address the challenge of insufficient labeled data in medical image segmentation tasks. However, when a semi-supervised segmentation model is overfitted and exhibits cognitive bias, its performance will deteriorate. Errors stemming from cognitive bias can quickly amplify and become difficult to correct during the training process of neural networks, resulting in the continuous accumulation of erroneous knowledge. To address the issue of error accumulation, a novel learning strategy is required to enhance the accuracy of medical image segmentation. This paper proposes a semi-supervised medical image segmentation network based on mutual learning (MLNet) to alleviate the issue of continuous accumulation of erroneous knowledge. The MLNet adopts a teacher-student network as the backbone framework, training student and teacher networks on labeled data and mutually updating network parameter weights, enabling the two models to learn from each other. Additionally, an image partial exchange algorithm (IPE) as an appropriate perturbation addition method is proposed to reduce the introduction of erroneous information and the disruption to the contextual information of the image. In the 10% labeled experiment on the ACDC dataset, our Dice coefficient reached 89.48%, a 9.28% improvement over the baseline model. In the 10% labeled experiment on the BraTS2019 dataset, the proposed method still performs exceptionally well, achieving 84.56%, surpassing other comparative methods. Compared with other methods, experimental results demonstrate that our approach achieves optimal performance across all metrics, proving its effectiveness and reliability.

Semi-supervised learning network for deep-sea nodule mineral image segmentation

The accurate segmentation of deep-sea nodule mineral images is crucial for scientific mining. However, due to the low contrast of deep-sea images and the varying sizes of nodule minerals, existing methods are not effective in segmenting these images. Furthermore, fully supervised deep learning methods require numerous labelled images for training, and labelling deep-sea nodule mineral images is highly difficult, resulting in a scarcity of available labeled images, which limits the model generalization ability. To address these challenges, a semi-supervised learning network for deep-sea nodule image segmentation (NmiNet) was proposed. In this method, a semi-supervised training paradigm based on underwater image enhancement perturbation and uncertainty weighted optimization (UEUO) was designed. This paradigm enabled the model to fully mine the features in many unlabeled nodule mineral images under the condition of few labelled nodule mineral images, improving the model generalization ability. Moreover, a lightweight global and local feature extraction (GLFE) module was designed to enhance the attention of the module to small nodules, and its ability to locate nodules of different scales by fusing local and global features without considerably increasing model complexity. Experimental results on deep-sea nodule mineral images reveal that this method outperforms existing approaches.

MT-SCnet: multi-scale token divided and spatial-channel fusion transformer network for microscopic hyperspectral image segmentation.

Hybrid architectures based on convolutional neural networks and Transformers, effectively captures both the local details and the overall structural context of lesion tissues and cells, achieving highly competitive segmentation results in microscopic hyperspectral image (MHSI) segmentation tasks. However, the fixed tokenization schemes and single-dimensional feature extraction and fusion in existing methods lead to insufficient global feature extraction in hyperspectral pathology images. Base on this, we propose a multi-scale token divided and spatial-channel fusion transformer network (MT-SCnet) for MHSIs segmentation. Specifically, we first designed a Multi-Scale Token Divided module. It divides token at different scale based on mirror padding and promotes information interaction and fusion between different tokens to obtain more representative features for subsequent global feature extraction. Secondly, a novel spatial channel fusion transformer was designed to capture richer features from spatial and channel dimensions, and eliminates the semantic gap between features from different dimensions based on cross-attention fusion block. Additionally, to better restore spatial information, deformable convolutions were introduced in decoder. The Experiments on two MHSI datasets demonstrate that MT-SCnet outperforms the comparison methods. This advance has significant implications for the field of MHSIs segmentation. Our code is freely available at https://github.com/sharycao/MT-SCnet.

LGCE-Net: a local and global contextual encoding network for effective and efficient medical image segmentation

LGCE-Net: a local and global contextual encoding network for effective and efficient medical image segmentation

Uncertainty bidirectional guidance of multi-task mamba network for medical image classification and segmentation

Uncertainty bidirectional guidance of multi-task mamba network for medical image classification and segmentation

An improved multi-scale feature extraction network for medical image segmentation.

The use of U-Net and its variations has led to significant advancements in medical image segmentation. However, the encoder-decoder structures of these models often lose spatial information during downsampling. Skip connections can help address this issue; however, they may also introduce excessive irrelevant background information. Additionally, medical images display significant scale variations and complex tissue structures, making it challenging for existing models to accurately separate tissues from the background. To address these issues, we developed the Res2Net-ConvFormer-Dilation-UNet (Res2-CD-UNet), a multi-scale feature extraction network for medical image segmentation. This study presents a novel U-shaped segmentation network that employs Res2Net as the backbone and incorporates a convolution-style transformer in the encoding stage to enhance global attention. Additionally, a novel channel feature fusion block (CFFB) has been introduced in the skip connection stage to minimize the effects of background noise. The proposed model was evaluated using publicly available datasets, Synapse and Seg.A.2023. Using the Synapse dataset, the average dice similarity coefficient (DSC) reached 83.92%, which was 1.96% higher than the suboptimal model, and the average Hausdorff distance (HD) was 14.51 mm. Among the eight organs evaluated, optimal results were achieved for four organs. Similarly, using the Seg.A.2023 dataset, the proposed model also achieved the best results with an average DSC of 93.27%. The results of this study indicate that the proposed model can more accurately segment regions of interest and better extract multi-scale features in medical images than existing deep-learning algorithms.

TAC-UNet: transformer-assisted convolutional neural network for medical image segmentation.

Medical image segmentation is crucial for improving healthcare outcomes. Convolutional neural networks (CNNs) have been widely applied in medical image analysis; however, their inherent inductive biases limit their ability to capture global contextual information. Vision transformer (ViT) architectures address this limitation by leveraging attention mechanisms to model global relationships; however, they typically require large-scale datasets for effective training, which is challenging in the field of medical imaging due to limited data availability. This study aimed to integrate the advantages of CNN and ViT architectures to improve segmentation performance on small-scale medical image datasets. In this study, we established a U-shaped network architecture based on a Transformer-assisted convolutional neural network (TAC-UNet). The TAC-UNet is primarily composed of a hybrid structure integrating CNN and Transformer components. Specifically, the hybrid architecture follows a dual-path design in which the Transformer branch continuously conveys global contextual information to the CNN backbone. This allows the CNN backbone to enhance its global perception while building on the local features it extracts, thereby improving its ability to comprehend complex image structures. A channel cross-attention (CCA) module is also incorporated as a bridge between the encoder and decoder to better reconcile the semantic discrepancies between them. Detailed experiments on three public datasets were conducted. Specifically, our model was trained on 30 images from the Multi-organ Nucleus Segmentation (MoNuSeg) training dataset, 85 images from the Gland Segmentation (GlaS) training dataset, and 551 images from the Computer Vision Center Colorectal Cancer-Clinic Database (CVC-ClinicDB) dataset. We evaluated the performance of our model on the corresponding test sets. Our TAC-UNet achieved the best Dice scores (80.36%, 90.70%, and 91.81% on the MoNuSeg, GlaS, and CVC-ClinicDB datasets, respectively) of all the models. Compared to other CNN-based, Transformer-based, and hybrid methods, the TAC-UNet demonstrated significantly superior segmentation performance. Our TAC-UNet model showed advanced segmentation performance on small-scale medical image datasets. The detailed experimental results showed the effectiveness of the method. Our model's code is available at: https://github.com/hejlhello/TAC-UNet.

Dual multi scale networks for medical image segmentation using contrastive learning

Dual multi scale networks for medical image segmentation using contrastive learning

Development of the architecture of a computer aided diagnosis system in medicine

With the development of information technology, automation of various production processes is an urgent task, and medical diagnostics is no exception. In recent decades, artificial intelligence and information technology have been widely used in computer diagnostic systems. However, as technology advances, so do the challenges. Not every system is optimized and fast, and traditional methods are fading into the background. Often, systems do not use cloud technologies and have unoptimized architectures. This all affects their performance and, accordingly, is an urgent problem. The study analyzes the methods used in computer diagnostic systems and compares them in terms of advantages and disadvantages. The scientific works related to computer diagnostic systems in medicine for specific tasks are analyzed. The existing architectures of computer diagnostic systems are analyzed, which made it possible to identify the use of consistent approaches to diagnosis. Based on the analyzed data, the purpose, objectives, object and subject of the study are determined. A new architecture has been developed that uses the capabilities of U-Net for image segmentation and convolutional neural networks for medical image classification. The developed architecture is designed to increase the speed and automation of diagnostic processes through the use of neural networks and, accordingly, reduce human intervention. The scientific novelty of the developed architecture lies in the parallel execution of medical image segmentation and classification tasks, which gives a potential increase in data processing speed, and in the availability of an image generator, which solves the problem of lack of test data for model training.

Edge-guided and hierarchical aggregation network for robust medical image segmentation

Medical image segmentation with the convolutional neural networks (CNNs), significantly enhances clinical analysis and disease diagnosis. However, medical images inherently exhibit large intra-class variability, minimal inter-class differences, and substantial noise levels. Extracting robust contextual information and aggregating discriminative features for fine-grained segmentation remains a formidable task. Additionally, existing methods often struggle with producing accurate mask edges, leading to blurred boundaries and reduced segmentation precision. This paper introduces a novel Edge-guided and Hierarchical Aggregation Network (EHANet) which excels at capturing rich contextual information and preserving fine spatial details, addressing the critical issues of inaccurate mask edges and detail loss prevalent in current segmentation models. The Inter-layer Edge-aware Module (IEM) enhances edge prediction accuracy by fusing early encoder layers, ensuring precise edge delineation. The Efficient Fusion Attention Module (EFA) adaptively emphasizes critical spatial and channel features while filtering out redundancies, enhancing the model’s perception and representation capabilities. The Adaptive Hierarchical Feature Aggregation Module (AHFA) module optimizes feature fusion within the decoder, maintaining essential information and improving reconstruction fidelity through hierarchical processing. Quantitative and qualitative experiments on four public datasets demonstrate the effectiveness of EHANet in achieving superior mIoU, mDice, and edge accuracy against eight other state-of-the-art segmentation methods, highlighting its robustness and precision in diverse clinical scenarios.

AFCF-Net: A novel U-Net based asymmetric feature calibration and fusion network for skin lesion image segmentation.

Skin lesion segmentation plays a pivotal role in the diagnosis and treatment of skin diseases. By using deep neural networks to segment lesion areas, doctors can more accurately assess the severity of health-related conditions of patients and promptly implement appropriate treatment measures, thereby enhancing treatment outcomes and improving the quality of life (QoL) of patients. However, existing segmentation networks still face challenges in balancing segmentation performance and efficiency. To address this issue, a novel network, named AFCF-Net, is proposed in this paper for skin lesion segmentation tasks. Firstly, the proposed network employs a newly designed spatial channel feature calibration convolution (SCFCConv) to enhance its ability to perceive spatial and channel features. Secondly, AFCF-Net utilizes newly designed feature symmetric fusion convolution (FSFConv) in skip connections to selectively fuse features from different levels, thereby enhancing its sensitivity to texture, edges, and other detailed features. In addition, a feature attention recombination module (FARM) is added to the bottleneck of the proposed network to comprehensively acquire and utilize contextual information at different scales, thus improving the network's generalization ability. Finally, a newly designed multi-level feature aggregation branch is introduced as an additional decoder for AFCF-Net to supplement key features lost during the original decoding process. Experiments, conducted on four skin image datasets, demonstrate that the proposed AFCF-Net network achieves better segmentation performance with fewer parameters and computational resources, compared to state-of-the-art segmentation networks. Additionally, AFCF-Net exhibits stronger generalization ability.

LDN-SNP: SNP-based lightweight deep network for CT image segmentation of COVID-19

The rapid prevalence and spread of 2019 coronavirus (COVID-19) has brought tremendous impact and damage to the world’s health and economy. Chest CT images have been used as an important screening and diagnostic tool in identifying and managing COVID-19 infection, and the deep learning models have been successfully used in COVID-19 CT image segmentation. However, they encounter some challenges, especially the limited labeled samples and large models with huge numbers of training parameters. To address these challenges, this paper proposes a lightweight segmentation network for COVID-19 CT images, termed as LDN-SNP network. The LDN-SNP network is based on a new type of neuron model, SNP-type neurons. Based on SNP-type neurons, we design four convolution modules. The LDN-SNP network is composed of encoder and decoder, where the encoder is stacked by the first three modules, while the decoder is stacked by the fourth module. The proposed LDN-SNP network contains only 81316 training parameters. Three benchmark CT image data sets of COVID-19 are used to evaluate the proposed LDN-SNP network and compare the eleven state-of-the-art deep learning networks. LDN-SNP has several significant advantages: (1) It introduces a new neuron model and gives its mathematical model, which is different from the traditional neuron model; (2) It has only 81 K parameters and is therefore not prone to overfitting; (3) It is computationally efficient and therefore convenient for subsequent practical deployment. Experimental results demonstrate the advantages of the proposed LDN-SNP network for CT image segmentation of COVID-19.

A Near-Infrared Imaging System for Robotic Venous Blood Collection.

Venous blood collection is a widely used medical diagnostic technique, and with rapid advancements in robotics, robotic venous blood collection has the potential to replace traditional manual methods. The success of this robotic approach is heavily dependent on the quality of vein imaging. In this paper, we develop a vein imaging device based on the simulation analysis of vein imaging parameters and propose a U-Net+ResNet18 neural network for vein image segmentation. The U-Net+ResNet18 neural network integrates the residual blocks from ResNet18 into the encoder of the U-Net to form a new neural network. ResNet18 is pre-trained using the Bootstrap Your Own Latent (BYOL) framework, and its encoder parameters are transferred to the U-Net+ResNet18 neural network, enhancing the segmentation performance of vein images with limited labelled data. Furthermore, we optimize the AD-Census stereo matching algorithm by developing a variable-weight version, which improves its adaptability to image variations across different regions. Results show that, compared to U-Net, the BYOL+U-Net+ResNet18 method achieves an 8.31% reduction in Binary Cross-Entropy (BCE), a 5.50% reduction in Hausdorff Distance (HD), a 15.95% increase in Intersection over Union (IoU), and a 9.20% increase in the Dice coefficient (Dice), indicating improved image segmentation quality. The average error of the optimized AD-Census stereo matching algorithm is reduced by 25.69%, and the improvement of the image stereo matching performance is more obvious. Future research will explore the application of the vein imaging system in robotic venous blood collection to facilitate real-time puncture guidance.

EDB-Diff: a EdgeDevice based diffusion network for brain tumor image segmentation

EDB-Diff: a EdgeDevice based diffusion network for brain tumor image segmentation

Cross-Granularity Infrared Image Segmentation Network for Nighttime Marine Observations

Infrared image segmentation in marine environments is crucial for enhancing nighttime observations and ensuring maritime safety. While recent advancements in deep learning have significantly improved segmentation accuracy, challenges remain due to nighttime marine scenes including low contrast and noise backgrounds. This paper introduces a cross-granularity infrared image segmentation network CGSegNet designed to address these challenges specifically for infrared images. The proposed method designs a hybrid feature framework with cross-granularity to enhance segmentation performance in complex water surface scenarios. To suppress feature semantic disparity against different feature granularity, we propose an adaptive multi-scale fusion module (AMF) that combines local granularity extraction with global context granularity. Additionally, incorporating a handcrafted histogram of oriented gradients (HOG) features, we designed a novel HOG feature fusion module to improve edge detection accuracy under low-contrast conditions. Comprehensive experiments conducted on the public infrared segmentation dataset demonstrate that our method outperforms state-of-the-art techniques, achieving superior segmentation results compared to professional infrared image segmentation methods. The results highlight the potential of our approach in facilitating accurate infrared image segmentation for nighttime marine observation, with implications for maritime safety and environmental monitoring.

A highly efficient tunnel lining crack detection model based on Mini-Unet

The accurate detection of tunnel lining cracks and prompt identification of their primary causes are critical for maintaining tunnel availability. The advancement of deep learning, particularly in the domain of convolutional neural network (CNN) for image segmentation, has made tunnel lining crack detection more feasible. However, the CNN-based technique for tunnel lining crack detection commonly prioritizes increasing algorithmic complexity to enhance detection accuracy, posing a challenge in balancing the accuracy of detection and the efficiency of the algorithm. Motivated by the superior performance of Unet in image segmentation, this paper proposes a lightweight tunnel lining crack detection model named Mini-Unet, which refined the Unet architecture and utilized depthwise separable convolutions (DSConv) to replace some standard convolution layers. In the optimization of the proposed model parameters, applying a hybrid loss function that integrated dice loss and cross-entropy loss effectively tackled the imbalance between crack and background categories. Several models were set up to contrast with Mini-Unet and the experimental results were analyzed. Mini-Unet achieves a mean intersection over union (MIoU) of 60.76%, a mean precision of 84.18%, and a frame per second (FPS) of 5.635, respectively. Mini-Unet outperforms several mainstream models, enabling rapid detection while maintaining identified accuracy and facilitating the practical application of AI power for real-time tunnel lining crack detection.

The impact of multi-class information decoupling in latent space on skin lesion segmentation

Noise, out-of-distribution (OOD) challenges, and boundary ambiguity are not only challenges in skin disease segmentation, but also difficulties in the field of medical image segmentation. Although various medical image segmentation networks have emerged, there are certain limitations in addressing these issues because previous research has neglected the expression of medical image features in latent space. In this article, we study the relationship between latent space information and medical image segmentation. We demonstrate that the decoupling of multi-class information in latent space is closely related to the accuracy of medical image segmentation. Therefore, this study proposes a new segmentation scheme - Contextual directional decoupling network (CodeNet), which aims to enhance feature representation by decoupling multi-class information in latent space, enabling the model to successfully address noise, artifacts, OOD challenges, and boundary ambiguity. Comprehensive experiments on four public datasets and one private dataset show that our proposed CodeNet is superior to other state-of-the-art models and achieves good performance on multiple commonly used metrics. This demonstrates the effectiveness of our method in skin lesion segmentation.

DSIFNet: Implicit feature network for nasal cavity and vestibule segmentation from 3D head CT

This study is dedicated to accurately segment the nasal cavity and its intricate internal anatomy from head CT images, which is critical for understanding nasal physiology, diagnosing diseases, and planning surgeries. Nasal cavity and it’s anatomical structures such as the sinuses, and vestibule exhibit significant scale differences, with complex shapes and variable microstructures. These features require the segmentation method to have strong cross-scale feature extraction capabilities. To effectively address this challenge, we propose an image segmentation network named the Deeply Supervised Implicit Feature Network (DSIFNet). This network uniquely incorporates an Implicit Feature Function Module Guided by Local and Global Positional Information (LGPI-IFF), enabling effective fusion of features across scales and enhancing the network's ability to recognize details and overall structures. Additionally, we introduce a deep supervision mechanism based on implicit feature functions in the network's decoding phase, optimizing the utilization of multi-scale feature information, thus improving segmentation precision and detail representation. Furthermore, we constructed a dataset comprising 7116 CT volumes (including 1,292,508 slices) and implemented PixPro-based self-supervised pretraining to utilize unlabeled data for enhanced feature extraction. Our tests on nasal cavity and vestibule segmentation, conducted on a dataset comprising 128 head CT volumes (including 34,006 slices), demonstrate the robustness and superior performance of proposed method, achieving leading results across multiple segmentation metrics.

MFHARFNet: multi-branch feature hybrid and adaptive receptive field network for image segmentation

Abstract Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model’s adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.