Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images

Li, Tianyu; Liu, Junchi; Ma, Yan; He, J.; Han, Jiuqiang; Ding, Xiaoyang; Chen, Chin-Tu

doi:10.1002/mp.14585

Cited by 42 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We mainly selected the results based on 2D model (14,(25)(26)(27)29), except for some 3D model results by Li and Liu (11,28). The proposed S-Net with the fusion of spatial features and attention mechanisms, outperformed than other 2D models.…”

Section: Discussionmentioning

confidence: 99%

Adaptive Attention Convolutional Neural Network for Liver Tumor Segmentation

et al. 2021

View full text Add to dashboard Cite

PurposeAccurate segmentation of liver and liver tumors is critical for radiotherapy. Liver tumor segmentation, however, remains a difficult and relevant problem in the field of medical image processing because of the various factors like complex and variable location, size, and shape of liver tumors, low contrast between tumors and normal tissues, and blurred or difficult-to-define lesion boundaries. In this paper, we proposed a neural network (S-Net) that can incorporate attention mechanisms to end-to-end segmentation of liver tumors from CT images.MethodsFirst, this study adopted a classical coding-decoding structure to realize end-to-end segmentation. Next, we introduced an attention mechanism between the contraction path and the expansion path so that the network could encode a longer range of semantic information in the local features and find the corresponding relationship between different channels. Then, we introduced long-hop connections between the layers of the contraction path and the expansion path, so that the semantic information extracted in both paths could be fused. Finally, the application of closed operation was used to dissipate the narrow interruptions and long, thin divide. This eliminated small cavities and produced a noise reduction effect.ResultsIn this paper, we used the MICCAI 2017 liver tumor segmentation (LiTS) challenge dataset, 3DIRCADb dataset and doctors’ manual contours of Hubei Cancer Hospital dataset to test the network architecture. We calculated the Dice Global (DG) score, Dice per Case (DC) score, volumetric overlap error (VOE), average symmetric surface distance (ASSD), and root mean square error (RMSE) to evaluate the accuracy of the architecture for liver tumor segmentation. The segmentation DG for tumor was found to be 0.7555, DC was 0.613, VOE was 0.413, ASSD was 1.186 and RMSE was 1.804. For a small tumor, DG was 0.3246 and DC was 0.3082. For a large tumor, DG was 0.7819 and DC was 0.7632.ConclusionS-Net obtained more semantic information with the introduction of an attention mechanism and long jump connection. Experimental results showed that this method effectively improved the effect of tumor recognition in CT images and could be applied to assist doctors in clinical treatment.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive Attention Convolutional Neural Network for Liver Tumor Segmentation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Devi and Seenivasagam suggested an SVM based classifier for segmentation and classification of liver tumor from CT image using feature difference 12 . The spatial feature fusion based CNN for liver and liver tumor segmentation from CT images were demonstrated 13 . The novel method was presented to detect and classify the liver tumor weak boundaries, touching organs, and heterogeneity.…”

Section: Related Workmentioning

confidence: 99%

Automatic liver tumor segmentation and identification using fully connected convolutional neural network from CT images

Vadlamudi

Reddy

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary In recent years, one of the largest causes of death in human beings is liver tumor and cancer. In the current scenario, identifying the cancer tumor manually is very difficult and takes a lot of time as the world is battling with COVID‐19. The doctors and physicians are busy in serving and curing them. To predict the stage of liver tumor and plan the treatment, the segmentation is done from CT scanned images. In this research, two‐stage automatic liver segmentation and tumor identification framework using a fully connected convolutional neural network (FC‐CNN) model is proposed. During the first stage, the liver region is segmented using level set method from the preprocessed (OTSU thresholding) CT images. The features are extracted and utilized to detect the liver tumor in the second stage. The developed FC‐CNN is trained and tested using the extracted second order statistical textural features to classify the tumor affected and normal image. The proposed FC‐CNN model is trained and tested with 3D‐IRCADb‐01 and Kaggle datasets. The tested results prove that the proposed FC‐CNN model outperforms other reported methods. From the performance analysis, it is observed that it achieves a good accuracy and sensitivity rate of 99.11% and 98.10%, respectively.

show abstract

“…For instance, Chen et al prostate segmentation from transrectal ultrasound, especially for ambiguous boundaries in the images. Liu et al 37 present a SSF-Net that extracts side-outputs at each convolutional block and make full use of them by feature fusion blocks for liver and tumor segmentation.…”

Section: Iib Attention Mechanismmentioning

confidence: 99%

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

Zhang¹,

Jiang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated liver tumor segmentation from Computed Tomography (CT) images is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on Fully Convolutional Network (FCN) for medical image segmentation drew on the success of learning discriminative pyramid features. In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low-and high-level features embedded in FCN to segment liver tumor. Methods: We first design a powerful Pyramid Feature Encoder (PFE) to extract multi-level features from input images. Then we decouple the characteristics of features concerning spatial dimension (i.e., height, width, depth) and semantic dimension (i.e., channel). On top of that, we present two types of attention modules, Spatial Correlation (SpaCor) and Semantic Correlation (SemCor) modules, to recursively measure the correlation of multi-level features. The former selectively emphasizes global semantic information in low-level features with the guidance of high-level ones. The latter adaptively enhance spatial details in high-level features with the guidance of low-level ones. Results: We evaluate the DPC-Net on MICCAI 2017 LiTS Liver Tumor Segmentation (LiTS) challenge dataset. Dice Similarity Coefficient (DSC) and Average Symmetric

show abstract

Spatial feature fusion convolutional network for liver and liver tumor segmentation from CT images

Cited by 42 publications

References 22 publications

Adaptive Attention Convolutional Neural Network for Liver Tumor Segmentation

Adaptive Attention Convolutional Neural Network for Liver Tumor Segmentation

Automatic liver tumor segmentation and identification using fully connected convolutional neural network from CT images

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

Contact Info

Product

Resources

About