CCTrans: Improving Medical Image Segmentation with Contoured Convolutional Transformer Network

Wang, Jingling; Zhang, Haixian; Zhang, Yi

doi:10.3390/math11092082

Cited by 5 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [ 19 ] implemented IB-TransUNet, merging the Information Bottleneck and Transformer into the U-Net model, and in [ 20 ], they proposed the MultiIB-TransUNet architecture. Some more recent architectures include High Correlative Non-Local Network (HCNNet), Bilateral Segmentation Network (BiSeNet V3), Contoured Convolutional Transformer (CCTrans), Cross-Convolutional Transformer Network (C 2 Former), Double-stage Codec Attention Network (DSCA-Net), and Medical Vision Transformer (MedViT) [ 21 , 22 , 23 , 24 , 25 , 26 ]. Additionally, specific architectures have been designed for the processing of 3D medical images [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Urrea,

Garcia-Garcia,

Kern

2024

Biomedicines

View full text Add to dashboard Cite

This article addresses the semantic segmentation of laparoscopic surgery images, placing special emphasis on the segmentation of structures with a smaller number of observations. As a result of this study, adjustment parameters are proposed for deep neural network architectures, enabling a robust segmentation of all structures in the surgical scene. The U-Net architecture with five encoder–decoders (U-Net5ed), SegNet-VGG19, and DeepLabv3+ employing different backbones are implemented. Three main experiments are conducted, working with Rectified Linear Unit (ReLU), Gaussian Error Linear Unit (GELU), and Swish activation functions. The applied loss functions include Cross Entropy (CE), Focal Loss (FL), Tversky Loss (TL), Dice Loss (DiL), Cross Entropy Dice Loss (CEDL), and Cross Entropy Tversky Loss (CETL). The performance of Stochastic Gradient Descent with momentum (SGDM) and Adaptive Moment Estimation (Adam) optimizers is compared. It is qualitatively and quantitatively confirmed that DeepLabv3+ and U-Net5ed architectures yield the best results. The DeepLabv3+ architecture with the ResNet-50 backbone, Swish activation function, and CETL loss function reports a Mean Accuracy (MAcc) of 0.976 and Mean Intersection over Union (MIoU) of 0.977. The semantic segmentation of structures with a smaller number of observations, such as the hepatic vein, cystic duct, Liver Ligament, and blood, verifies that the obtained results are very competitive and promising compared to the consulted literature. The proposed selected parameters were validated in the YOLOv9 architecture, which showed an improvement in semantic segmentation compared to the results obtained with the original architecture.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Urrea,

Garcia-Garcia,

Kern

2024

Biomedicines

View full text Add to dashboard Cite

show abstract

“…Distinct from CNNs, which employ local convolutions to capture spatial information, ViTs utilize self-attention mechanisms [21] to simultaneously process both local and global contextual information. This attribute enables ViT networks to effectively capture intricate patterns and details, rendering them particularly suitable for medical image segmentation tasks that require a sufficient accurate delineation of complex structures [9,[22][23][24][25]. Current ViT-improved segmentation networks in the literature are largely designed around a U-Net style architecture with self-attention layers.…”

Section: Introductionmentioning

confidence: 99%

Dealing with Unreliable Annotations: A Noise-Robust Network for Semantic Segmentation through A Transformer-Improved Encoder and Convolution Decoder

Wang

Voiculescu

2023

Applied Sciences

View full text Add to dashboard Cite

Conventional deep learning methods have shown promising results in the medical domain when trained on accurate ground truth data. Pragmatically, due to constraints like lack of time or annotator inexperience, the ground truth data obtained from clinical environments may not always be impeccably accurate. In this paper, we investigate whether the presence of noise in ground truth data can be mitigated. We propose an innovative and efficient approach that addresses the challenge posed by noise in segmentation labels. Our method consists of four key components within a deep learning framework. First, we introduce a Vision Transformer-based modified encoder combined with a convolution-based decoder for the segmentation network, capitalizing on the recent success of self-attention mechanisms. Second, we consider a public CT spine segmentation dataset and devise a preprocessing step to generate (and even exaggerate) noisy labels, simulating real-world clinical situations. Third, to counteract the influence of noisy labels, we incorporate an adaptive denoising learning strategy (ADL) into the network training. Finally, we demonstrate through experimental results that the proposed method achieves noise-robust performance, outperforming existing baseline segmentation methods across multiple evaluation metrics.

show abstract

Segmentation of Lung Lesions through Bilateral Learning Branches to Aggregating Contextual and Local Characteristics

Niu,

Li,

Yuan

et al. 2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

Detecting and analyzing lung lesion regions using artificial intelligence is of great significance in the medical diagnosis of lung CT images, which can substantially improve the efficiency of doctors. However, segmentation of the inflammatory region in the CT image of the lung remains challenging due to the varied sizes, blurry local details, irregular shapes, and limited sizes of datasets. Faced with these challenges, this paper proposes a novel lung lesion segmentation network that incorporates two feature extraction branches to achieve a balance of speed and accuracy. We first design a context branch (CB) to preserve the scale-invariant global context information by the transformer-like module. Besides, a shallow detail branch (DB) based on a deep aggregation pyramid (DAP) module is designed to provide detailed information. Extensive experiments are conducted on two datasets, including the public COVID-19 dataset and a private dataset. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods. Moreover, the trade-off between accuracy and inference speed is achieved.

show abstract

CCTrans: Improving Medical Image Segmentation with Contoured Convolutional Transformer Network

Cited by 5 publications

References 30 publications

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Improving Surgical Scene Semantic Segmentation through a Deep Learning Architecture with Attention to Class Imbalance

Dealing with Unreliable Annotations: A Noise-Robust Network for Semantic Segmentation through A Transformer-Improved Encoder and Convolution Decoder

Segmentation of Lung Lesions through Bilateral Learning Branches to Aggregating Contextual and Local Characteristics

Contact Info

Product

Resources

About