Hyper-Pairing Network for Multi-phase Pancreatic Ductal Adenocarcinoma Segmentation

Zhou, Yuyin; Li, Yingwei; Zhang, Zhishuai; Wang, Yan; Wang, Angtian; Fishman, Elliot K.; Yuille, Alan; Park, Seyoun

doi:10.1007/978-3-030-32245-8_18

Cited by 57 publications

(70 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Main difficulties in automated pancreas and tumor segmentation arise from three aspects: 1) Variability in terms of size, shape and location of pancreas and especially PDAC mass, as illustrated in Fig. 1; 2) the small size of the pancreas and tumor in the whole CT scan; 3) poor contrast around the boundaries (7,(10)(11).…”

Section: Introductionmentioning

confidence: 99%

“…Frag et. al (10) applied cascade super pixels for pancreas segmentation on NIH dataset using deep and texture features. Gibson et.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, Zhang et.al (9) used multi-phase CT images for PDAC segmentation using a large dataset and nnUNet network, which achieved dice scores of 0.709 ± 0.159 and 0.522 ± 0.250 for multi and venous phase respectively. Zhou el.al (10) proposed PDAC segmentation using hyperpairing network which integrated the information from different phases. They reported dice scores of 63.94 ± 22.74 and 53.08 ± 27.06 using multi and venous phase respectively.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and Surrounding Vessels in CT Images Using Deep Convolutional Neural Networks and Texture Descriptors

Mahmoudi

Kouzehkanan

Radmard

et al. 2021

Preprint

View full text Add to dashboard Cite

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of Pancreatic Ductal Adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a new loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fin-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Frag et. al (10) applied cascade super pixels for pancreas segmentation on NIH dataset using deep and texture features. Gibson et.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and Surrounding Vessels in CT Images Using Deep Convolutional Neural Networks and Texture Descriptors

Mahmoudi

Kouzehkanan

Radmard

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, Zhang et.al (9) used multi-phase CT images for PDAC segmentation using a large dataset and nnUNet network, which achieved dice scores of 0.709 ± 0.159 and 0.522 ± 0.250 for multi and venous phase respectively. Zhou el.al (10) proposed PDAC segmentation using hyper-pairing network which integrated the information from different phases. They reported dice scores of 63.94 ± 22.74 and 53.08 ± 27.06 using multi and venous phase respectively.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and texture descriptors

Mahmoudi

Kouzehkanan

Radmard

et al. 2021

Preprint

View full text Add to dashboard Cite

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of Pancreatic Ductal Adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a new loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fin-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods (from 53.08% to 60.6%) in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response.

show abstract

“…at the time of diagnosis. Currently, detecting or segmenting PDACs through medical imaging at the localized disease stage followed by complete resection can offer the best chance of survival [1]. Computed tomography (CT) screening is the most commonly used imaging modality for the initial evaluation of PDACs.…”

mentioning

confidence: 99%

Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction

Wang

Tang

Zhou

et al. 2021

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause of cancer death in the United States. Predicting tumors like PDACs (including both classification and segmentation) from medical images by deep learning is becoming a growing trend, but usually a large number of annotated data are required for training, which is very labor-intensive and time-consuming. In this paper, we consider a partially supervised setting, where cheap imagelevel annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxellevel classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semisupervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier. Experimental results show that our IAG-Net boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts.

show abstract

Hyper-Pairing Network for Multi-phase Pancreatic Ductal Adenocarcinoma Segmentation

Cited by 57 publications

References 20 publications

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and Surrounding Vessels in CT Images Using Deep Convolutional Neural Networks and Texture Descriptors

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and Surrounding Vessels in CT Images Using Deep Convolutional Neural Networks and Texture Descriptors

Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and texture descriptors

Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction

Contact Info

Product

Resources

About