Filters








275 Hits in 3.9 sec

Pyramid Attention Aggregation Network for Semantic Segmentation of Surgical Instruments

Zhen-Liang Ni, Gui-Bin Bian, Guan-An Wang, Xiao-Hu Zhou, Zeng-Guang Hou, Hua-Bin Chen, Xiao-Liang Xie
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, a novel network, Pyramid Attention Aggregation Network, is proposed to aggregate multi-scale attentive features for surgical instruments.  ...  These issues make semantic segmentation of surgical instruments more challenging.  ...  To this end, the Pyramid Attention Aggregation Network (PAANet) is proposed to learn discriminative features for surgical instruments.  ... 
doi:10.1609/aaai.v34i07.6850 fatcat:shaiuxhoubftdnwrpi3dx7f35q

BARNet: Bilinear Attention Network with Adaptive Receptive Fields for Surgical Instrument Segmentation

Zhen-Liang Ni, Gui-Bin Bian, Guan-An Wang, Xiao-Hu Zhou, Zeng-Guang Hou, Xiao-Liang Xie, Zhen Li, Yu-Han Wang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Surgical instrument segmentation is crucial for computer-assisted surgery.  ...  In this paper, we propose a bilinear attention network with adaptive receptive fields to address these two issues.  ...  Acknowledgments Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/116 dblp:conf/ijcai/NiBWZHXLW20 fatcat:xct4te4e7ngsbgu2pcazlcnx4q

BARNet: Bilinear Attention Network with Adaptive Receptive Fields for Surgical Instrument Segmentation [article]

Zhen-Liang Ni, Gui-Bin Bian, Guan-An Wang, Xiao-Hu Zhou, Zeng-Guang Hou, Xiao-Liang Xie, Zhen Li, Yu-Han Wang
2020 arXiv   pre-print
Surgical instrument segmentation is extremely important for computer-assisted surgery.  ...  For the illumination variation, the bilinear attention module can capture second-order statistics to encode global contexts and semantic dependencies between local pixels.  ...  This issue makes the instrument segmentation more challenging. Recently, a series of methods have been proposed for the semantic segmentation of surgical instruments.  ... 
arXiv:2001.07093v4 fatcat:zm7jf633l5brbhubr5j62oexsq

DeepPyram: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos [article]

Negin Ghamsarian, Mario Taschwer, klaus Schoeffmann
2021 arXiv   pre-print
Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction.  ...  The proposed approach is evaluated using four datasets of cataract surgery for objects with different contextual features and compared with thirteen state-of-the-art segmentation networks.  ...  This module is specially designed to enhance the segmentation accuracy in the case of illumination and scale variation for surgical instruments.  ... 
arXiv:2109.05352v1 fatcat:n5u6crsgszblfgxnuxobzzgy6i

Multiscale matters for part segmentation of instruments in robotic surgery

Wenhao He, Haitao Song, Yue Guo, Guibin Bian, Yuejie Sun, Xiaowei Zhou, Xiaonan Wang
2020 IET Image Processing  
Most of the baselines can be used to accurately segment instruments, but sometimes our method outperforms baselines by a large margin on surgical contexts  ...  A challenging aspect of instrument segmentation in robotic surgery is to distinguish different parts of the same instrument.  ...  To obtain more informative representations for semantic segmentation on several occasions, features in some layers are aggregated in specified feature dimensions.  ... 
doi:10.1049/iet-ipr.2020.0320 fatcat:oir6g37vvvawnbeelto2tamcla

Real-time Instance Segmentation of Surgical Instruments using Attention and Multi-scale Feature Fusion [article]

Juan Carlos Angeles-Ceron, Gilberto Ochoa-Ruiz, Leonardo Chang, Sharib Ali
2021 arXiv   pre-print
In this paper, we use a light-weight single stage instance segmentation model complemented with a convolutional block attention module for achieving both faster and accurate inference.  ...  While accurate tracking of surgical instruments in real-time plays a crucial role in minimally invasive computer-assisted surgeries, it is a challenging task to achieve, mainly due to 1) complex surgical  ...  Acknowledgements The authors would like to thank the AI Hub and the CI-IOT at Tecnologico de Monterrey for their support for carrying the experiments on their NVIDIA's DGX computer.  ... 
arXiv:2111.04911v2 fatcat:wnph3f3oorbnnjluhfbw3qf2gy

Towards Better Surgical Instrument Segmentation in Endoscopic Vision: Multi-Angle Feature Aggregation and Contour Supervision [article]

Fangbo Qin, Shan Lin, Yangming Li, Randall A. Bly, Kris S. Moe, Blake Hannaford
2020 arXiv   pre-print
Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and  ...  For these challenging tasks more and more deep neural networks (DNN) models are designed in recent years.  ...  Moe, Blake Hannaford * , Fellow, IEEE lightweight encoder and channel-attention guided decoder, which achieves real-time speed for large surgical images TABLE I SEGMENTATION I PERFORMANCES IN ABLATION  ... 
arXiv:2002.10675v1 fatcat:vzczyrtscvdh5h6l7ssxnuwixm

Towards Robotic Knee Arthroscopy: Multi-Scale Network for Tissue-Tool Segmentation [article]

Shahnewaz Ali, Prof. Ross Crawford, Dr. Frederic Maire, Assoc. Prof. Ajay K. Pandey
2021 arXiv   pre-print
In arthroscopy, it is one of the challenging tasks due to surgical sites exhibit limited features and textures. Moreover, arthroscopic surgical video shows high intra-class variations.  ...  As consequences, fully conventional network-based segmentation model suffers from long- and short- term dependency problems.  ...  The network provides shape features for the key structures. Fig. 8 . 8 Segmented maps of arthroscopic surgical scenes obtained from our proposed method.  ... 
arXiv:2110.02657v1 fatcat:apd25s6r2zddnbop3esyq2vf3y

Effective semantic segmentation in Cataract Surgery: What matters most? [article]

Theodoros Pissas, Claudio Ravasio, Lyndon Da Cruz, Christos Bergeles
2021 arXiv   pre-print
Our methodology achieves strong performance across three semantic segmentation tasks with increasingly granular surgical tool class sets by effectively handling class imbalance, an inherent challenge in  ...  Our work proposes neural network design choices that set the state-of-the-art on a challenging public benchmark on cataract surgery, CaDIS.  ...  The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health and Social Care.  ... 
arXiv:2108.06119v1 fatcat:a5k5wtvirjaydkkkyezpvslndm

LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images [article]

Shan Lin, Fangbo Qin, Yangming Li, Randall A. Bly, Kris S. Moe, Blake Hannaford
2020 arXiv   pre-print
The proposed method fully makes use of the labeled cadaveric dataset for live image segmentation without the need to label the live dataset.  ...  Moreover, we propose the structural similarity loss and segmentation consistency loss to improve the semantic consistency during translation.  ...  METHODS In this work, we explore image-to-image translation to reduce the need for manual data labeling for surgical instrument segmentation.  ... 
arXiv:2003.04949v2 fatcat:pnlaqmtmivbi7jkmkf4ml2oxe4

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

Haimei Li, Bing Liu, Yongtao Zhang, Chao Fu, Xiaowei Han, Lei Du, Wenwen Gao, Yue Chen, Xiuxiu Liu, Yige Wang, Tianfu Wang, Guolin Ma (+1 others)
2021 Frontiers in Oncology  
Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge.  ...  This study designs a novel 3D improved feature pyramidal network (3D IFPN) to automatically segment gastric tumors in computed tomography (CT) images.  ...  Another typical deep learning network called the feature pyramid network (FPN) has achieved state-of-theart performance for medical imaging object detection and semantic segmentation, as its top-down architecture  ... 
doi:10.3389/fonc.2021.618496 pmid:34094903 pmcid:PMC8173118 fatcat:63zl5gbkrrej5lubx7z2syqznm

Real-Time Polyp Detection, Localisation and Segmentation in Colonoscopy Using Deep Learning [article]

Debesh Jha, Sharib Ali, Håvard D. Johansen, Dag D. Johansen, Jens Rittscher, Michael A. Riegler, Pål Halvorsen
2020 arXiv   pre-print
Likewise, UNet with a ResNet34 backbone achieved the highest dice coefficient of 0.8757 and the best average speed of 35 frames per second for the segmentation task.  ...  In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images, for polyp detection, localisation, and segmentation evaluating both method  ...  Pyramid scene parsing network (PSPNet, [54] ) introduced a pyramid pooling module aimed at aggregating global context information from different regions which are upsampled and concatenated to form the  ... 
arXiv:2011.07631v1 fatcat:7uxiptjrh5cudiddmimxntngsm

An Attention-Preserving Network-Based Method for Assisted Segmentation of Osteosarcoma MRI Images

Feng Liu, Fangfang Gou, Jia Wu
2022 Mathematics  
Therefore, this paper proposes a Contextual Axial-Preserving Attention Network (CaPaN)-based MRI image-assisted segmentation method for osteosarcoma detection.  ...  For the segmentation of small objects, the DSC value of CaPaN is 0.021 higher than that of the commonly used U-Net method.  ...  The fully connected network is replaced by a convolutional network, which solves the problem of image segmentation at the semantic level.  ... 
doi:10.3390/math10101665 fatcat:vomt5pm3kjdgtpscy6j5vwky4i

Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation [article]

Theodoros Pissas, Claudio S. Ravasio, Lyndon Da Cruz, Christos Bergeles
2022 arXiv   pre-print
We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks.  ...  This work considers supervised contrastive learning for semantic segmentation. Our approach is model agnostic.  ...  Context aggregation for semantic segmentation.  ... 
arXiv:2203.13409v1 fatcat:gfdphronffgknicll7lqjvm3fm

A Review on Deep Learning in Minimally Invasive Surgery

Irene Rivas-Blanco, Carlos J. Perez-Del-Pulgar, Isabel Garcia-Morales, Victor F. Munoz
2021 IEEE Access  
They combined an attention map created from high-level features with low-level features to enrich the low semantic information. 2) Segmentation of surgical instruments Binary segmentation of surgical  ...  of surgical instruments has grabbed the attention of many researchers in the field of machine learning applied to surgical procedures.  ...  She is currently an Associate Professor and is responsible for a variety of subjects related to robotics.  ... 
doi:10.1109/access.2021.3068852 fatcat:gfpghqfptzdktlody5z263cdju
« Previous Showing results 1 — 15 out of 275 results