Publications

Search or filter publications

Search publications Search

Filter by type:

Filter by publication type

• Book
• Book chapter
• Conference paper
• Journal article
• Patent
• Report
• Software

Filter by year:

Filter from 202320222021202020192018 to Filter to 202320222021202020192018

---

Search results

• Conference paper
  Dong S, Gao Z, Sun S, Wang X, Li M, Zhang H, Yang G, Liu H, Li Set 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.

  • Abstract
  • Cite
  • Citations: 2
• Conference paper
  Dong S, Gao Z, Sun S, Wang X, Li M, Zhang H, Yang G, Liu H, Li Set 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.

  • Abstract
  • Cite
  • Citations: 3
• Conference paper
  Li M, Dong S, Zhang K, Gao Z, Wu X, Zhang H, Yang G, Li Set 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.

  • Abstract
  • Cite
  • Citations: 2
• Journal article
  Raschke F, Barrick TR, Jones TL, Yang G, Ye X, Howe FAet al., 2019,

  Tissue-type mapping of gliomas

  , NEUROIMAGE-CLINICAL, Vol: 21, ISSN: 2213-1582
  • Author Web Link
  • Cite
  • Citations: 50
• Conference paper
  Zhu 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: 41
• Conference paper
  Zhang D, Yang G, Zhao S, Zhang Y, Zhang H, Li Set 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: 16
• Conference paper
  Li M, Zhang W, Yang G, Wang C, Zhang H, Liu H, Zheng W, Li Set 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: 30
• Conference paper
  Ali A-R, Li J, O'Shea SJ, Yang G, Trappenberg T, Ye Xet al., 2019,

  A Deep Learning Based Approach to Skin Lesion Border Extraction With a Novel Edge Detector in Dermoscopy Images

  , International Joint Conference on Neural Networks (IJCNN), Publisher: IEEE, ISSN: 2161-4393
  • Author Web Link
  • Cite
  • Citations: 7
• Journal article
  Liu Y, Yang G, Afshari Mirak S, Hosseiny M, Azadikhah A, Zhong X, Reiter RE, Lee Y, Raman SS, Sung Ket al., 2019,

  Automatic Prostate Zonal Segmentation Using Fully Convolutional Network With Feature Pyramid Attention

  , IEEE ACCESS, Vol: 7, Pages: 163626-163632, ISSN: 2169-3536
  • Author Web Link
  • Cite
  • Citations: 55
• Journal article
  Dooley D, van Timmeren MM, O'Reilly VP, Brady G, O'Brien EC, Fazekas B, Hickey FB, Leacy E, Pusey CD, Tam FWK, Mehrling T, Heeringa P, Little MAet al., 2018,

  Alkylating histone deacetylase inhibitors may have therapeutic value in experimental myeloperoxidase-ANCA vasculitis

  , Kidney International, Vol: 94, Pages: 926-936, ISSN: 0085-2538

  Current 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.

  • Abstract
  • Author Web Link
  • Cite

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.