Notice of Retraction: DIEN Network: Detailed Information Extracting Network for Detecting Continuous Circular Capsulorhexis Boundaries of Cataracts

Abstract

Robotic surgery is an arising area to satisfy the tremendous demand of modern clinical application, and it is becoming more and more acceptable by the normal. In this paper, we are dedicated to finding a more modern solution for continuous circular capsulorhexis of cataract surgery via deep learning method. We take inspiration from former works and propose a detailed information extracting network structure that is suitable applied in the area of clinical, where more side-output layers are used in the convolutional modules, rather than single side-output of specific layer. Moreover, to balance the positive samples and the negative samples and make the network model more stable convergence, we introduce focal loss as the loss function of the model. Instead of exploiting network structure deeper and deeper, the boundary of continuous circular capsulorhexis extracted by above approaches can satisfy the demand of the surgery robots need during a cataract surgery. We evaluate the results on the dataset provided by clinical ophthalmologists, and achieves F=.808. INDEX TERMS deep learning, edge detection, image processing, robotic surgery.

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

“…Fig. 9 compares the class activation maps corresponding to these four locations in DeepPyram and alternative approaches for cornea segmentation in a representative image 9 . A comparison between the activation maps of DeepPyram and DeepP yram −P L indicates how negatively removing the P L module affects the discrimination ability in different semantic levels.…”

“…We can infer that the P L module can effectively reinforce the semantic representations in different semantic levels of the network. The effect of pixel- 9 These activation maps are obtained using Score-CAM [51] visualization approach.…”