Background:We developed a computational model integrating clinical data and imaging features extracted from contrast-enhanced computed tomography (CECT) images, to predict lymph node (LN) metastasis in patients with pancreatic ductal adenocarcinoma (PDAC).Methods: This retrospective study included 159 patients with PDAC (118 in the primary cohort and 41 in the validation cohort) who underwent preoperative contrast-enhanced computed tomography examination between 2012 and 2015. All patients underwent surgery and lymph node status was determined. A total of 2041 radiomics features were extracted from venous phase images in the primary cohort, and optimal features were extracted to construct a radiomics signature. A combined prediction model was built by incorporating the radiomics signature and clinical characteristics selected by using multivariable logistic regression. Clinical prediction models were generated and used to evaluate both cohorts. Results: Fifteen features were selected for constructing the radiomics signature based on the primary cohort. The combined prediction model for identifying preoperative lymph node metastasis reached a better discrimination power than the clinical prediction model, with an area under the curve of 0.944 vs. 0.666 in the primary cohort, and 0.912 vs. 0.713 in the validation cohort.Conclusions: This pilot study demonstrated that a noninvasive radiomics signature extracted from contrastenhanced computed tomography imaging can be conveniently used for preoperative prediction of lymph node metastasis in patients with PDAC.

Despite the recent success of convolutional neural networks for computer vision applications, unconstrained face recognition remains a challenge. In this work, we make two contributions to the field. Firstly, we consider the problem of face recognition with partial occlusions and show how current approaches might suffer significant performance degradation when dealing with this kind of face images. We propose a simple method to find out which parts of the human face are more important to achieve a high recognition rate, and use that information during training to force a convolutional neural network to learn discriminative features from all the face regions more equally, including those that typical approaches tend to pay less attention to. We test the accuracy of the proposed method when dealing with real-life occlusions using the AR face database. Secondly, we propose a novel loss function called batch triplet loss that improves the performance of the triplet loss by adding an extra term to the loss function to cause minimisation of the standard deviation of both positive and negative scores. We show consistent improvement in the Labeled Faces in the Wild (LFW) benchmark by applying both proposed adjustments to the convolutional neural network training.

An efficient quantum secure direct communication protocol is presented over the amplitude damping channel. The protocol encodes logical bits in two-qubit noiseless states, and so it can function over a quantum channel subjected to collective amplitude damping. The feature of this protocol is that the sender encodes the secret directly on the quantum states, the receiver decodes the secret by performing determinate measurements, and there is no basis mismatch. The transmission's safety is ensured by the nonorthogonality of the noiseless states traveling forward and backward on the quantum channel. Moreover, we construct the efficient quantum circuits to implement channel encoding and information encoding by means of primitive operations in quantum computation.quantum secure direct communication, amplitude damping, quantum cryptography Quantum cryptography [1] is one of the most remarkable applications of quantum information. Since the pioneering work [2] , various protocols based on different quantum features are proposed, such as quantum key distribution (QKD) [3,4] , quantum secret sharing (QSS) [5,6] , quantum secure direct communication (QSDC) [7,8] and so on. QSDC is a novel branch which allows that the secret is transmitted between users directly without creating a private key in advance. As it is useful in some urgent circumstances, many efforts have been made on the research of QSDC [9][10][11][12][13][14][15][16][17][18][19][20][21] . For example, Deng et al. proposed four criteria for secure QSDC [12] and gave two secure QSDC protocols [10,12] , Cai et al. presented two efficient QSDC schemes with entangled states [9] and single qubit [11] , respectively.In contrast to classical cryptography, the security of quantum cryptography is guaranteed by the principles of quantum mechanics, and therefore the unconditional security can be achieved. Properly speaking, according to quantum physics principles, Eve's eavesdropping will inevitably disturb the carrier states and induce errors in the process of checking eavesdropping. Higher error rate results in lower information transmission rate, and once it becomes too large, no secure message can be transmitted and the communications will have to abort. Therefore, building a viable quantum cryptographic system depends on ensuring that the error rate is low. However in practice, quantum states are very fragile and easily destroyed by decoherence due to unwanted coupling with the environment, and errors are induced in the eavesdropping detection inevitably. It has been one of the major obstacles to implementing quantum cryptography protocols in real physical systems. To solve the effects of such interactions, some strategies, such as quantum error correction code [22,23] and quantum error-rejection code [24][25][26][27] have been proposed.Considering the specific types of coupling with the

No abstract