Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation

Fang, Chaowei; Li, Guanbin; Pan, Chengwei; Li, Yiming; Yu, Yizhou

doi:10.1007/978-3-030-32245-8_24

Cited by 29 publications

(25 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of the classic methods of pancreas segmentation use fourfold cross-validation. [36][37][38][39][40] In order to conduct a more fair comparison test, this article uses the same four-fold cross-validation method for comparison. In this study, 3D model segmentation is better when the pancreatic head or tail has a complex shape, as shown in Fig.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

MAD‐UNet: A deep U‐shaped network combined with an attention mechanism for pancreas segmentation in CT images

Qin

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose Pancreas segmentation is a difficult task because of the high intrapatient variability in the shape, size, and location of the organ, as well as the low contrast and small footprint of the CT scan. At present, the U‐Net model is likely to lead to the problems of intraclass inconsistency and interclass indistinction in pancreas segmentation. To solve this problem, we improved the contextual and semantic feature information acquisition method of the biomedical image segmentation model (U‐Net) based on a convolutional network and proposed an improved segmentation model called the multiscale attention dense residual U‐shaped network (MAD‐UNet). Methods There are two aspects considered in this method. First, we adopted dense residual blocks and weighted binary cross‐entropy to enhance the semantic features to learn the details of the pancreas. Using such an approach can reduce the effects of intraclass inconsistency. Second, we used an attention mechanism and multiscale convolution to enrich the contextual information and suppress learning in unrelated areas. We let the model be more sensitive to pancreatic marginal information and reduced the impact of interclass indistinction. Results We evaluated our model using fourfold cross‐validation on 82 abdominal enhanced three‐dimensional (3D) CT scans from the National Institutes of Health (NIH‐82) and 281 3D CT scans from the 2018 MICCAI segmentation decathlon challenge (MSD). The experimental results showed that our method achieved state‐of‐the‐art performance on the two pancreatic datasets. The mean Dice coefficients were 86.10% ± 3.52% and 88.50% ± 3.70%. Conclusions Our model can effectively solve the problems of intraclass inconsistency and interclass indistinction in the segmentation of the pancreas, and it has value in clinical application. Code is available at https://github.com/Mrqins/pancreas-segmentation.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Although, fourfold cross‐validation is a relatively ideal result. However, most of the classic methods of pancreas segmentation use fourfold cross‐validation 36–40 . In order to conduct a more fair comparison test, this article uses the same four‐fold cross‐validation method for comparison.…”

Section: Discussionmentioning

confidence: 99%

MAD‐UNet: A deep U‐shaped network combined with an attention mechanism for pancreas segmentation in CT images

Qin

et al. 2020

Medical Physics

View full text Add to dashboard Cite

show abstract

“…9) is rather small, we can get enough receptive field in the inter-slice dimension without downsampling. Regarding 2D feature map conversions, Fang et al [13] proposed to extract C 2D feature maps (1 × 1 × H × W ) corresponding to the center slice and concatenate them to form the converted 2D feature map of size (C × H × W ). However, this method can not fully exploit the 3D context information resided in other adjacent slices.…”

Section: D Context Modeling With An Mp3d Resnet Backbonementioning

confidence: 99%

“…MP3D with 7 slices as input get the best trade-off between effectiveness and efficiency. Conversion Type: Table 3 demonstrates the comparisons of proposed GTM with the center-cropping transform module (CTM), which is proposed by Fang et al [13]. The proposed GTM brings better results as it can efficiently aggregate information from all adjacent slices for further detection.…”

Section: Ablation Studymentioning

confidence: 99%

Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices

Zhang

Chen³

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Universal lesion detection from computed tomography (CT) slices is important for comprehensive disease screening. Since each lesion can locate in multiple adjacent slices, 3D context modeling is of great significance for developing automated lesion detection algorithms. In this work, we propose a Modified Pseudo-3D Feature Pyramid Network (MP3D FPN) that leverages depthwise separable convolutional filters and a group transform module (GTM) to efficiently extract 3D context enhanced 2D features for universal lesion detection in CT slices. To facilitate faster convergence, a novel 3D network pre-training method is derived using solely large-scale 2D object detection dataset in the natural image domain. We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3.48% absolute improvement in the sensitivity of FPs@0.5), significantly surpassing the baseline method by up to 6.06% (in MAP@0.5) which adopts 2D convolution for 3D context modeling. Moreover, the proposed 3D pre-trained weights can potentially be used to boost the performance of other 3D medical image analysis tasks.

show abstract

“…But the 2.5D structure is destroyed by the network with 2D convolutional layers. Recently, Fang et al 14 and Chen et al 9 combine 2D and 3D sub‐networks in their model. This combination is designed to capture both global features and 3D geometric information.…”

Section: Related Workmentioning

confidence: 99%

Improving the slice interaction of 2.5D CNN for automatic pancreas segmentation

et al. 2020

View full text Add to dashboard Cite

Purpose Volumetric pancreas segmentation can be used in the diagnosis of pancreatic diseases, the research about diabetes and surgical planning. Since manual delineation is time‐consuming and laborious, we develop a deep learning‐based framework for automatic pancreas segmentation in three dimensional (3D) medical images. Methods A two‐stage framework is designed for automatic pancreas delineation. In the localization stage, a Square Root Dice loss is developed to handle the trade‐off between sensitivity and specificity. In refinement stage, a novel 2.5D slice interaction network with slice correlation module is proposed to capture the non‐local cross‐slice information at multiple feature levels. Also a self‐supervised learning‐based pre‐training method, slice shuffle, is designed to encourage the inter‐slice communication. To further improve the accuracy and robustness, ensemble learning and a recurrent refinement process are adopted in the segmentation flow. Results The segmentation technique is validated in a public dataset (NIH Pancreas‐CT) with 82 abdominal contrast‐enhanced 3D CT scans. Fourfold cross‐validation is performed to assess the capability and robustness of our method. The dice similarity coefficient, sensitivity, and specificity of our results are 86.21 ± 4.37%, 87.49 ± 6.38% and 85.11 ± 6.49% respectively, which is the state‐of‐the‐art performance in this dataset. Conclusions We proposed an automatic pancreas segmentation framework and validate in an open dataset. It is found that 2.5D network benefits from multi‐level slice interaction and suitable self‐supervised learning method for pre‐training can boost the performance of neural network. This technique could provide new image findings for the routine diagnosis of pancreatic disease.

show abstract

Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation

Cited by 29 publications

References 12 publications

MAD‐UNet: A deep U‐shaped network combined with an attention mechanism for pancreas segmentation in CT images

MAD‐UNet: A deep U‐shaped network combined with an attention mechanism for pancreas segmentation in CT images

Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices

Improving the slice interaction of 2.5D CNN for automatic pancreas segmentation

Contact Info

Product

Resources

About