Pansharpening is normally utilized to take full advantage of all the available spectral and spatial information that are derived from a low-spatial-resolution (LR) multispectral (MS) image and its associated high-spatial-resolution (HR) panchromatic (PAN) image, respectively, producing a fused MS image with high spectral and spatial resolutions. Many methods have been recently developed based on convolutional neural networks (CNNs) for the pansharpening task, but most of them still have some drawbacks: 1) The information cannot efficiently flow in their simple stacked convolutional architectures, thereby hindering the representation ability of the networks; 2) They are commonly trained using supervised learning, which does not only require an extra effort to produce the simulated training data, but can also lead to scale-related problems in the fusion results. In this paper, we propose a novel unsupervised CNN-based pansharpening method to overcome these limitations. Specifically, we design an iterative network architecture, in which a PANguided strategy and a set of skip connections (SC) are adopted to continuously extract and fuse the features from the input, thus enhancing the information reuse and transmission. Besides, we propose a new loss function for unsupervised training in which the relationships between the input MS and PAN images and the fused MS image are used to design the spatial constrains and spectral consistency, respectively. The typical quality index with noreference (QNR) is also added to this function to further adjust the spectral and spatial qualities. The designed loss function allows the network to be learned only on input images, without any handcrafted labels (reference HR MS image). We evaluated the effectiveness of our designed network architecture and the combined loss function, and the experiments testify that our unsupervised strategy can also obtain promising results with minor spectral and spatial distortions compared with other traditional and supervised methods.

SUMMARY Recommender systems (RS) exploit user ratings on items and side information to make personalized recommendations. In order to recommend the right products to users, RS must accurately model the implicit preferences of each user and the properties of each product. In reality, both user preferences and item properties are changing dynamically over time, so treating the historical decisions of a user or the received comments of an item as static is inappropriate. Besides, the review text accompanied with a rating score can help us to understand why a user likes or dislikes an item, so temporal dynamics and text information in reviews are important side information for recommender systems. Moreover, compared with the large number of available items, the number of items a user can buy is very limited, which is called the sparsity problem. In order to solve this problem, utilizing item correlation provides a promising solution. Although famous methods like TimeSVD++, TopicMF and CoFactor partially take temporal dynamics, reviews and correlation into consideration, none of them combine these information together for accurate recommendation. Therefore, in this paper we propose a novel combined model called TmRevCo which is based on matrix factorization. Our model combines the dynamic user factor of TimeSVD++ with the hidden topic of each review text mined by the topic model of TopicMF through a new transformation function. Meanwhile, to support our five-scoring datasets, we use a more appropriate item correlation measure in CoFactor and associate the item factors of CoFactor with that of matrix factorization. Our model comprehensively combines the temporal dynamics, review information and item correlation simultaneously. Experimental results on three real-world datasets show that our proposed model leads to significant improvement compared with the baseline methods.

Objective To explore the effect of bone cement distribution, cement leakage, and clinical outcomes with side‐opening cannula for bone cement injection in percutaneous vertebroplasty (PVP) in treatment of Kummell disease. Methods A prospective study of patients with Kummell disease undergoing PVP was conducted from April 2012 to September 2017. In total, 43 patients (11 males, 32 females) with Kummell disease who received bilateral PVP were included in the study. The patients were divided into front‐opening cannulas (FOC) group with front‐opening cannulas and side‐opening cannulas (SOC) group with side‐opening cannulas. All patients were followed up for 6 months. The patient general information such as gender, age, bone density, compression ratio, operative time, and location of fracture vertebrae were recorded. Visual analogue scale (VAS), Oswestry Disability Index (ODI), bone cement distribution, radiation exposure time, bone cement leakage rate and vertebral height, and kyphosis angle were measured and compared for two groups before surgery, 1 day and 6 months after surgery. Results A total of 43 patients were enrolled, including 11 males and 32 females, aged 61–84 years. The bone density (T value) was 2.5 ± 0.6 in FOC group and 2.4 ± 0.6 in SOC group (P > 0.05). The compression ratio and operative time were 36.1% ± 13.0%, 39.3 ± 7.9 min in FOC group and 35.2% ± 13.7%, 40.0 ± 10.7 min in SOC group (P > 0.05). There was no significance between FOC and SOC groups in the location of fracture vertebrae. All patients underwent at least 6 months of follow‐up. At 6 months postoperatively, the VAS and ODI were significantly higher in the FOC group (3.0 ± 0.8, 35.7% ± 2.1%) than in the SOC group (1.3 ± 0.4, 18.6% ± 2.4%) (P < 0.05). The cement leakage rate of the SOC group was 4.8%, which was lower than that of the FOC group (31.8%, P < 0.05), and the bone cement distribution ratio was higher than that of the FOC group (63.1% ± 7.9% vs 40.5% ± 8.6%, P < 0.05). At 6 months after operation, the height of the anterior and posterior vertebral bodies of the patients in the SOC group restored better than the FOC group (anterior SOC: FOC 5.1 ± 0.5 mm vs 4.5 ± 0.5 mm; posterior SOC: FOC 0.6 ± 0.1 mm vs 0.3 ± 0.1 mm, P < 0.05), and the kyphosis correction was more obvious than patients in FOC group (SOC: FOC 8.5° ± 1.4° vs 4.6° ± 0.8°, P < 0.05). Conclusion Percutaneous vertebroplasty with side‐opening cannula is safe and effective in avoiding bone cement leakage, improving bone cement distribution, and restoring vertebral height.