Boundary-aware context neural network for medical image segmentation

Wang, Ruxin; Chen, Shuyuan; Ji, Chaojie; Fan, Jianping; Li, Ye

doi:10.1016/j.media.2022.102395

Cited by 112 publications

(24 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UNet [ 7 ] is a landmark work that first uses skip connections to apply the feature information in the encoder to the decoder. Although such a connection method can effectively alleviate the inevitable information loss in the downsampling process, However, different medical image segmentation tasks require different segmentation networks to enhance feature learning for specialized data, so after UNet, many more important medical image segmentation models have emerged, such as UNet++ [ 20 ], UNet3+ [ 21 ], R2U-Net [ 8 ], SA-UNet [ 22 ], CE-Net [ 23 ], FAC-Net [ 9 ], SMU-Net [ 24 ], and BA-Net [ 25 ]. Although these network architectures can achieve good performance in different tasks, their generalization ability is limited.…”

Section: Related Workmentioning

confidence: 99%

HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation

Yang

Wang

2023

Sensors

View full text Add to dashboard Cite

At present, convolutional neural networks (CNNs) have been widely applied to the task of skin disease image segmentation due to the fact of their powerful information discrimination abilities and have achieved good results. However, it is difficult for CNNs to capture the connection between long-range contexts when extracting deep semantic features of lesion images, and the resulting semantic gap leads to the problem of segmentation blur in skin lesion image segmentation. In order to solve the above problems, we designed a hybrid encoder network based on transformer and fully connected neural network (MLP) architecture, and we call this approach HMT-Net. In the HMT-Net network, we use the attention mechanism of the CTrans module to learn the global relevance of the feature map to improve the network’s ability to understand the overall foreground information of the lesion. On the other hand, we use the TokMLP module to effectively enhance the network’s ability to learn the boundary features of lesion images. In the TokMLP module, the tokenized MLP axial displacement operation strengthens the connection between pixels to facilitate the extraction of local feature information by our network. In order to verify the superiority of our network in segmentation tasks, we conducted extensive experiments on the proposed HMT-Net network and several newly proposed Transformer and MLP networks on three public datasets (ISIC2018, ISBI2017, and ISBI2016) and obtained the following results. Our method achieves 82.39%, 75.53%, and 83.98% on the Dice index and 89.35%, 84.93%, and 91.33% on the IOU. Compared with the latest skin disease segmentation network, FAC-Net, our method improves the Dice index by 1.99%, 1.68%, and 1.6%, respectively. In addition, the IOU indicators have increased by 0.45%, 2.36%, and 1.13%, respectively. The experimental results show that our designed HMT-Net achieves state-of-the-art performance superior to other segmentation methods.

show abstract

Section: Related Workmentioning

confidence: 99%

HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation

Yang

Wang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…As the newly-proposed methods, SANet [41] and MSNet [42] design the shallow attention module and subtraction unit, respectively, to achieve precise and efficient segmentation. Additionally, several works opt for introducing additional constraints via three main-stream manners: exerting explicit boundary supervision [43][44][45][46][47] , introducing implicit boundary-aware representation [48][49][50] , and exploring uncertainty for ambiguous regions [51] . 2) Transformer-based approaches.…”

Section: Image Polyp Segmentation (Ips)mentioning

confidence: 99%

Video Polyp Segmentation: A Deep Learning Perspective

Xiao

Chou

et al. 2022

Mach. Intell. Res.

View full text Add to dashboard Cite

We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era. Over the years, developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation annotations. To address this issue, we first introduce a high-quality frame-by-frame annotated VPS dataset, named SUN-SEG, which contains 158 690 colonoscopy video frames from the well-known SUN-database. We provide additional annotation covering diverse types, i.e., attribute, object mask, boundary, scribble, and polygon. Second, we design a simple but efficient baseline, named PNS+, which consists of a global encoder, a local encoder, and normalized self-attention (NS) blocks. The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations, which are then progressively refined by two NS blocks. Extensive experiments show that PNS+ achieves the best performance and real-time inference speed (170 fps), making it a promising solution for the VPS task. Third, we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons. Finally, we discuss several open issues and suggest possible research directions for the VPS community. Our project and dataset are publicly available at https://github.com/GewelsJI/VPS.

show abstract

“…Boundary detection has recently been an active research problem for which many techniques have been proposed to extract boundary information, thus mitigating the problem of ambiguous boundaries [14][15][16]. However, the problem of unclear boundaries between (WM) and (GM) remains challenging due to the low contrast of MRI images.…”

Section: Boundary Detectionmentioning

confidence: 99%

Learning to detect boundary information for brain image segmentation

2022

View full text Add to dashboard Cite

MRI brain images are always of low contrast, which makes it difficult to identify to which area the information at the boundary of brain images belongs. This can make the extraction of features at the boundary more challenging, since those features can be misleading as they might mix properties of different brain regions. Hence, to alleviate such a problem, image boundary detection plays a vital role in medical image segmentation, and brain segmentation in particular, as unclear boundaries can worsen brain segmentation results. Yet, given the low quality of brain images, boundary detection in the context of brain image segmentation remains challenging. Despite the research invested to improve boundary detection and brain segmentation, these two problems were addressed independently, i.e., little attention was paid to applying boundary detection to brain segmentation tasks. Therefore, in this paper, we propose a boundary detection-based model for brain image segmentation. To this end, we first design a boundary segmentation network for detecting and segmenting images brain tissues. Then, we design a boundary information module (BIM) to distinguish boundaries from the three different brain tissues. After that, we add a boundary attention gate (BAG) to the encoder output layers of our transformer to capture more informative local details. We evaluate our proposed model on two datasets of brain tissue images, including infant and adult brains. The extensive evaluation experiments of our model show better performance (a Dice Coefficient (DC) accuracy of up to $$5.3\%$$ 5.3 % compared to the state-of-the-art models) in detecting and segmenting brain tissue images.

show abstract

Boundary-aware context neural network for medical image segmentation

Cited by 112 publications

References 38 publications

HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation

HMT-Net: Transformer and MLP Hybrid Encoder for Skin Disease Segmentation

Video Polyp Segmentation: A Deep Learning Perspective

Learning to detect boundary information for brain image segmentation

Contact Info

Product

Resources

About