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

@article{Ni2020BARNetBA,
  title={BARNet: Bilinear Attention Network with Adaptive Receptive Field for Surgical Instrument Segmentation},
  author={Zhen-Liang Ni and Guibin Bian and Guan'an Wang and Xiao-Hu Zhou and Zeng-Guang Hou and Xiaoliang Xie and Zhuguo Li and Yuhan Wang},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.07093}
}
Surgical instrument segmentation is extremely important for computer-assisted surgery. Different from common object segmentation, it is more challenging due to the large illumination and scale variation caused by the special surgical scenes. In this paper, we propose a novel bilinear attention network with adaptive receptive field to solve these two challenges. For the illumination variation, the bilinear attention module can capture second-order statistics to encode global contexts and… Expand
Unsupervised Surgical Instrument Segmentation via Anchor Generation and Semantic Diffusion
TLDR
The proposed method achieves 0.71 IoU and 0.81 Dice score without using a single manual annotation, which is promising to show the potential of unsupervised learning for surgical tool segmentation. Expand
Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge
TLDR
The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap, and suggest that future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts). Expand
NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
TLDR
This work proposes NanoNet, a novel architecture for the segmentation of video capsule endoscopy and colonoscopy images that allows real-time performance and has higher segmentation accuracy compared to other more complex ones. Expand
Robust Medical Instrument Segmentation Challenge 2019
TLDR
The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap, and suggest that future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts). Expand
"Train one, Classify one, Teach one" - Cross-surgery transfer learning for surgical step recognition
TLDR
This work analyzes, for the first time, surgical step recognition on four different laparoscopic surgeries: Cholecystectomy, Right Hemicolectomy, Sleeve Gastrectomy, and Appendectomy, and proposes a Time-Series Adaptation Network (TSAN), an architecture optimized for transfer learning of surgical step Recognition. Expand
DeepPyram: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos
TLDR
A semantic segmentation network termed as DeepPyram is proposed that can achieve superior performance in segmenting relevant objects in cataract surgery videos with varying issues and outperforms the rival approaches without imposing additional trainable parameters. Expand
LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos
TLDR
A novel framework is proposed as the major step towards lens irregularity detection by proposing an end-to-end recurrent neural network to recognize the lens-implantation phase and a novel semantic segmentation network to segment the lens and pupil after the implantation phase. Expand
ReCal-Net: Joint Region-Channel-Wise Calibrated Network for Semantic Segmentation in Cataract Surgery Videos
TLDR
A novel convolutional module termed as ReCal module, which can calibrate the feature maps by employing region intra-and-inter-dependency and channel-region cross-dependencies and which can effectively enhance semantic representation by correlating different representations of the same semantic label, considering a multi-angle local view centering around each pixel is proposed. Expand

References

SHOWING 1-10 OF 37 REFERENCES
RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments
TLDR
A new attention module is designed to learn discriminative features and address the specular reflection issue, which captures global context and encodes semantic dependencies to emphasize key semantic features, boosting the feature representation. Expand
Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video
TLDR
This paper proposes a novel framework to leverage instrument motion information, by incorporating a derived temporal prior to an attention pyramid network for accurate segmentation, and demonstrates a promising potential for reducing annotation cost in the clinical practice. Expand
Surgical tool segmentation using a hybrid deep CNN-RNN auto encoder-decoder
TLDR
This work applied a hybrid method utilising both recurrent and convolutional networks to achieve higher accuracy of surgical tools segmentation, and achieved better performance compared to state-of-the-art methods on the same dataset for benchmarking. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TLDR
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand
2017 Robotic Instrument Segmentation Challenge
TLDR
The results of the 2017 challenge on robotic instrument segmentation which involved 10 teams participating in binary, parts and type based segmentation of articulated da Vinci robotic instruments are presented. Expand
ToolNet: Holistically-nested real-time segmentation of robotic surgical tools
TLDR
This work proposes two novel deep learning architectures for automatic segmentation of non-rigid surgical instruments and proposes the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization of the network while maintaining the segmentation accuracy. Expand
A2-Nets: Double Attention Networks
TLDR
This work proposes the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access featuresFrom the entire space efficiently. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Surgical Instrument Segmentation for Endoscopic Vision with Data Fusion of rediction and Kinematic Pose
TLDR
An instrument segmentation method fusing the convolutional neural networks prediction and the kinematic pose information is proposed, which determines an accurate silhouette mask, which is the final segmentation output. Expand
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TLDR
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner. Expand
...
1
2
3
4
...