Search

In this paper, a multi-view stereo vision patchmatch algorithm based on data augmentation is proposed. Compared to other works, this algorithm can reduce runtime and save computational memory through efficient cascading of modules; therefore, it can process higher-resolution images. Compared with algorithms utilizing 3D cost volume regularization, this algorithm can be applied on resource-constrained platforms. This paper applies the data augmentation module to an end-to-end multi-scale patchmatch algorithm and adopts adaptive evaluation propagation, avoiding the substantial memory resource consumption characterizing traditional region matching algorithms. Extensive experiments on the DTU and Tanks and Temples datasets show that our algorithm is very competitive in completeness, speed and memory. [ABSTRACT FROM AUTHOR]

Background: Minimally invasive surgical techniques such as robotic surgical platforms have provided favourable outcomes for patients, but the impact on surgeons is not well described. This systematic review aims to synthesize and evaluate the physical and mental impact of robotic surgery on surgeons compared to standard laparoscopic or open surgery. Methods: A search strategy was developed to identify peer-reviewed English articles published from inception to end of December 2019 on the following databases: MEDLINE, PubMed, PsycINFO and Embase. The articles were assessed using a modified Newcastle–Ottawa tool. Results: Of the 6563 papers identified, 30 studies were included in the qualitative synthesis of this review. Most of the included studies presented a high risk of bias. A total of 13 and 21 different physical and mental tools, respectively, were used to examine the impact on surgeons. The most common tool used to measure physical and mental demand were surface electromyography (N = 9) and the NASA Task Load Index (NASA-TLX; N = 8), respectively. Majority of studies showed mixed results for physical (N = 10) and mental impact (N = 7). This was followed by eight and six studies favouring RS over other surgical modalities for physical and mental impact, respectively. Conclusion: Most studies showed mixed physical and mental outcomes between the three surgical modalities. There was a high risk of bias and methodological heterogeneity. Future studies need to correlate mental and physical stress with long-term impact on the surgeons. [ABSTRACT FROM AUTHOR]

Herein, a dual-branch semantic segmentation model based on depth-separable convolution and attention mechanism is proposed for the real-time and accuracy requirement of semantic segmentation. The proposed approach overcomes the problems of poor segmentation effect and over-simplification of feature fusion arising from the constant downsample operations in semantic segmentation. The network is divided into spatial detail and semantic information paths. The spatial detail path utilizes a smaller downsample multiplier to maintain resolution and efficiently extract spatial information. The semantic information path is constructed by a non-bottleneck residual unit with dilated convolution; it extracts semantic features. For the feature aggregation problem, the feature-guided fusion module is designed to assign different weights to the parts of the two paths and fuse them to obtain the final output. The proposed algorithm achieves a segmentation accuracy of 69.6% and speed of 70 fps on the Cityscapes dataset, with a model parameter count of only 0.76 M, thus indicating some advantages over recent real-time semantic segmentation algorithms. The proposed method with depth separable convolution and attention mechanism can effectively extract features and compensate for the loss of accuracy caused by downsampling. The experiments demonstrate that the proposed fusion module outperforms other methods in fusing different features. [ABSTRACT FROM AUTHOR]

When training deep learning models, data augmentation is an important technique to improve the performance and alleviate overfitting. In natural language processing (NLP), existing augmentation methods often use fixed strategies. However, it might be preferred to use different augmentation policies in different stage of training, and different datasets may require different augmentation policies. In this paper, we take dynamic policy scheduling into consideration. We design a search space over augmentation policies by integrating several common augmentation operations. Then, we adopt a population based training method to search the best augmentation schedule. We conduct extensive experiments on five text classification and two machine translation tasks. The results show that the optimized dynamic augmentation schedules achieve significant improvements against previous methods. [ABSTRACT FROM AUTHOR]

Histopathological diagnosis is the golden standard for cancer diagnosis and grading. The past decade has witnessed great successes of vision‐based deep learning in computer‐aided cancer diagnosis. However, fully‐supervised methods require collecting large amounts of annotated data, which is a major challenge. In this research, we propose RMIL, a novel registration‐enhanced multiple instance learning pipeline, for cervical cancer biopsy grading of whole slide images as well as patch‐level regions. It requires only slide‐level annotations and a small amount of patch‐level annotations for training. To enhance it, an efficient registration method is implemented to generate more labeled patches with discriminative local features as data augmentations. In addition, attention mechanisms and self‐supervised learning are introduced to enhance feature extraction. Experiments showed that its classification accuracy is increased by 11.11%, compared to the vanilla multiple instance learning methods. The method has great potential for transferring to other scenarios. [ABSTRACT FROM AUTHOR]