Accurate and automated gland segmentation on histology tissue images is an essential but challenging task in the computer-aided diagnosis of adenocarcinoma. Despite their prevalence, deep learning models always require a myriad number of densely anno
tated training images, which are difficult to obtain due to extensive labor and associated expert costs related to histology image annotations. In this paper, we propose the pairwise relation-based semi-supervised (PRS^2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net). The S-Net is trained on labeled data for segmentation, and PR-Net is trained on both labeled and unlabeled data in an unsupervised way to enhance its image representation ability via exploiting the semantic consistency between each pair of images in the feature space. Since both networks share their encoders, the image representation ability learned by PR-Net can be transferred to S-Net to improve its segmentation performance. We also design the object-level Dice loss to address the issues caused by touching glands and combine it with other two loss functions for S-Net. We evaluated our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset. Our results not only demonstrate the effectiveness of the proposed PR-Net and object-level Dice loss, but also indicate that our PRS^2 model achieves the state-of-the-art gland segmentation performance on both benchmarks.
MPTCP is a new transport protocol that enables mobile devices to use multiple physical paths simultaneously through several network interfaces, such as WiFi and Cellular. However, wireless path capacities change frequently in the mobile environments,
causing challenges for path selection. For example, WiFi associated paths often become poor as devices walk away, since WiFi has intermittent connectivity caused by the short signal coverage and stochastic interference. MPTCPs native decision based on hysteretic TCP-layer estimation will miss the real switching point of wireless quality, which may cumulate packets on the broken path and causes serious packets reinjection. Through analyzing a unique dataset in the wild, we quantitatively study the impact of MAC-layer factors on the aggregated performance of MPTCP. We then propose a decision tree approach for cross-layer path selection that decides which path to carry the incoming packets dynamically according to the prior learned schemes. A prototype of the path selection system named SmartPS, which proactively probes the wireless environments, is realized and deployed in Linux and Android. Evaluation results demonstrate that our SmartPS can efficiently utilize the faster path, with goodput improvements of up to 29%.
In this paper, we propose a fast method for array response adjustment with phase-only constraint. This method can precisely and rapidly adjust the array response of a given point by only varying the entry phases of a pre-assigned weight vector. We sh
ow that phase-only array response adjustment can be formulated as a polygon construction problem, which can be solved by edge rotation in complex plain. Unlike the existing approaches, the proposed algorithm provides an analytical solution and guarantees a precise phase-only adjustment without pattern distortion. Moreover, the proposed method is suitable for an arbitrarily given weight vector and has a low computational complexity. Representative examples are presented to demonstrate the effectiveness of the proposed algorithm.
This paper presents a novel array response control algorithm and its application to array pattern synthesis. The proposed algorithm considers how to flexibly and precisely adjust the array responses at multiple points, on the basis of one given weigh
t vector. With the principle of adaptive beamforming, it is shown that the optimal weight vector for array response control can be equivalently obtained with a different manner, in which a linear transformation is conducted on the quiescent weight. This new strategy is utilized to realize multi-point precise array response control from one given weight vector, and it obtains a closed-form solution. A careful analysis shows that the response levels at given points can be independently, flexibly and accurately adjusted by simply varying the parameter vector, and that the uncontrolled region remains almost unchanged. By applying the proposed algorithm, an effective pattern synthesis approach is devised. Simulation results are provided to demonstrate the performance of the proposed algorithm.
