Publications
Results
- Showing results for:
- Reset all filters
Search results
-
Conference paperDong S, Gao Z, Sun S, et al., 2019,
Holistic and deep feature pyramids for saliency detection
© 2018. The copyright of this document resides with its authors. Saliency detection has been increasingly gaining research interest in recent years since many computer vision applications need to derive object attentions from images in the first steps. Multi-scale awareness of the saliency detector becomes essential to find thin and small attention regions as well as keeping high-level semantics. In this paper, we propose a novel holistic and deep feature pyramid neural network architecture that can leverage multi-scale semantics in feature encoding stage and saliency region prediction (decoding) stage. In the encoding stage, we exploit multi-scale and pyramidal hierarchy of feature maps via the densely connected network with variable-size dilated convolutions as well as a pyramid pooling. In the decoding stage, we fuse multi-level feature maps via up-sampling and convolution. In addition, we utilize the multi-level deep supervision via plugging in loss functions at every feature fusion level. Multi-loss supervision regularizes weights searching space among different tasks minimizing over-fitting and enhances gradient signal during backpropagation, and thus enables us training the network from scratch. This architecture builds an inherent multi-level semantic pyramidal feature maps at different scales and enhances model's capability in the saliency detection task. We validated our approach on six benchmark datasets and compared with eleven state-of-the-art methods. The results demonstrated that the design effectiveness and our approach outperformed the compared methods.
-
Conference paperZhang D, Yang G, Zhao S, et al., 2019,
Direct Quantification for Coronary Artery Stenosis Using Multiview Learning
, 10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 449-457, ISSN: 0302-9743- Author Web Link
- Cite
- Citations: 8
-
Conference paperLi M, Zhang W, Yang G, et al., 2019,
Recurrent Aggregation Learning for Multi-view Echocardiographic Sequences Segmentation
, 10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 678-686, ISSN: 0302-9743- Author Web Link
- Cite
- Citations: 17
-
Journal articleLiu Y, Sung K, Yang G, et al., 2019,
Automatic Prostate Zonal Segmentation Using Fully Convolutional Network with Feature Pyramid Attention
, IEEE Access, Vol: 7, Pages: 163626-163632Our main objective in the paper is to develop a novel deep learning-based algorithm for automatic segmentation of prostate zones and to evaluate the performance of the algorithm on an additional independent testing dataset in comparison with inter-reader agreement between two experts. With IRB approval and HIPAA compliance, we designed a novel convolutional neural network (CNN) for automatic segmentation of the prostatic transition zone (TZ) and peripheral zone (PZ) on T2-weighted (T2w) 3 Tesla (3T) MRI. The total study cohort included 359 MRI scans of patients in subcohorts; 313 scans from a deidentified publicly available dataset (SPIE-AAPM-NCI PROSTATEX challenge) and 46 scans from a large U.S. tertiary referral center (external testing dataset (ETD)). The TZ and PZ contours were manually annotated by research fellows, supervised by expert genitourinary (GU) radiologists. The model was developed using 250 patients and tested internally using the remaining 63 patients from the PROSTATEX (internal testing dataset (ITD)) and tested again (n=46) externally using the ETD. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation performance. DSCs for PZ and TZ were 0.74±0.08 and 0.86±0.07 in the ITD respectively. In the ETD, DSCs for PZ and TZ were 0.74±0.07 and 0.79±0.12, respectively. The inter-reader consistency (Expert 2 vs. Expert 1) were 0.71±0.13 (PZ) and 0.75±0.14 (TZ). This novel DL algorithm enabled automatic segmentation of PZ and TZ with high accuracy on both ITD and ETD without a performance difference for PZ and less than 10% TZ difference. In the ETD, the proposed method can be comparable to experts in the segmentation of prostate zones. Part of our source code and datasets with annotations is available at https://github.com/ykl-ucla/prostate_zonal_seg
-
Conference paperLi M, Dong S, Zhang K, et al., 2019,
Deep Learning intra-image and inter-images features for Co-saliency detection
© 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. In this paper, we propose a novel deep end-to-end co-saliency detection approach to extract common salient objects from images group. The existing approaches rely heavily on manually designed metrics to characterize co-saliency. However, these methods are so subjective and not flexible enough that leads to poor generalization ability. Furthermore, most approaches separate the process of single image features and group images features extraction, which ignore the correlation between these two features that can promote the model performance. The proposed approach solves these two problems by multistage representation to extract features based on high-spatial resolution CNN. In addition, we utilize the modified CAE to explore the learnable consistency. Finally, the intra-image contrast and the inter-images consistency are fused to generate the final co-saliency maps automatically among group images by multistage learning. Experiment results demonstrate the effectiveness and superiority of our approach beyond the state-of-the-art methods.
-
Conference paperDong S, Gao Z, Sun S, et al., 2019,
Holistic and deep feature pyramids for saliency detection
© 2018. The copyright of this document resides with its authors. Saliency detection has been increasingly gaining research interest in recent years since many computer vision applications need to derive object attentions from images in the first steps. Multi-scale awareness of the saliency detector becomes essential to find thin and small attention regions as well as keeping high-level semantics. In this paper, we propose a novel holistic and deep feature pyramid neural network architecture that can leverage multi-scale semantics in feature encoding stage and saliency region prediction (decoding) stage. In the encoding stage, we exploit multi-scale and pyramidal hierarchy of feature maps via the densely connected network with variable-size dilated convolutions as well as a pyramid pooling. In the decoding stage, we fuse multi-level feature maps via up-sampling and convolution. In addition, we utilize the multi-level deep supervision via plugging in loss functions at every feature fusion level. Multi-loss supervision regularizes weights searching space among different tasks minimizing over-fitting and enhances gradient signal during backpropagation, and thus enables us training the network from scratch. This architecture builds an inherent multi-level semantic pyramidal feature maps at different scales and enhances model's capability in the saliency detection task. We validated our approach on six benchmark datasets and compared with eleven state-of-the-art methods. The results demonstrated that the design effectiveness and our approach outperformed the compared methods.
-
Conference paperZhu J, Yang G, Lio P, 2019,
HOW CAN WE MAKE GAN PERFORM BETTER IN SINGLE MEDICAL IMAGE SUPER-RESOLUTION? A LESION FOCUSED MULTI-SCALE APPROACH
, 16th IEEE International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 1669-1673, ISSN: 1945-7928- Author Web Link
- Cite
- Citations: 36
-
Conference paperLi L, Yang G, Wu F, et al., 2019,
Atrial Scar Segmentation via Potential Learning in the Graph-Cut Framework
, Pages: 152-160, ISSN: 0302-9743Late Gadolinium Enhancement Magnetic Resonance Imaging (LGE MRI) emerges as a routine scan for patients with atrial fibrillation (AF). However, due to the low image quality automating the quantification and analysis of the atrial scars is challenging. In this study, we proposed a fully automated method based on the graph-cut framework, where the potential of the graph is learned on a surface mesh of the left atrium (LA), using an equidistant projection and a deep neural network (DNN). For validation, we employed 100 datasets with manual delineation. The results showed that the performance of the proposed method was improved and converged with respect to the increased size of training patches, which provide important features of the structural and texture information learned by the DNN. The segmentation could be further improved when the contribution from the t-link and n-link is balanced, thanks to the inter-relationship learned by the DNN for the graph-cut algorithm. Compared with the existing methods which mostly acquired an initialization from manual delineation of the LA or LA wall, our method is fully automated and has demonstrated great potentials in tackling this task. The accuracy of quantifying the LA scars using the proposed method was 0.822, and the Dice score was 0.566. The results are promising and the method can be useful in diagnosis and prognosis of AF.
-
Journal articleRaschke F, Barrick TR, Jones TL, et al., 2019,
Tissue-type mapping of gliomas
, NEUROIMAGE-CLINICAL, Vol: 21, ISSN: 2213-1582- Author Web Link
- Cite
- Citations: 30
-
Journal articleDooley D, van Timmeren MM, O'Reilly VP, et al., 2018,
Alkylating histone deacetylase inhibitors may have therapeutic value in experimental myeloperoxidase-ANCA vasculitis
, Kidney International, Vol: 94, Pages: 926-936, ISSN: 0085-2538Current therapies for treating antineutrophil cytoplasm autoantibody (ANCA)–associated vasculitis include cyclophosphamide and corticosteroids. Unfortunately, these agents are associated with severe adverse effects, despite inducing remission in most patients. Histone deacetylase inhibitors are effective in rodent models of inflammation and act synergistically with many pharmacological agents, including alkylating agents like cyclophosphamide. EDO-S101 is an alkylating fusion histone deacetylase inhibitor molecule combining the DNA alkylating effect of Bendamustine with a pan-histone deacetylase inhibitor, Vorinostat. Here we studied the effects of EDO-S101 in two established rodent models of ANCA-associated vasculitis: a passive mouse model of anti-myeloperoxidase IgG-induced glomerulonephritis and an active rat model of myeloperoxidase-ANCA microscopic polyangiitis. Although pretreatment with EDO-S101 reduced circulating leukocytes, it did not prevent the development of passive IgG-induced glomerulonephritis in mice. On the other hand, treatment in rats significantly reduced glomerulonephritis and lung hemorrhage. EDO-S101 also significantly depleted rat B and T cells, and induced DNA damage and apoptosis in proliferating human B cells, suggesting a selective effect on the adaptive immune response. Thus, EDO-S101 may have a role in treatment of ANCA-associated vasculitis, operating primarily through its effects on the adaptive immune response to the autoantigen myeloperoxidase.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.