It is difficult for general registration methods to establish the fine correspondence between images with complex anatomical structures. To overcome the above problem, this work presents SFM-Net, an unsupervised multi-stage semantic feature-based network. In addition to using the pixel-based similarity metrics, we propose a feature operator and emphasize a feature registration to improve the alignment of semantic related areas. Specifically, we design a two-stage training strategy, the intensity image registration stage and the semantic feature registration stage. The former is for valid semantic features learning and intensity-based coarse registration, while the latter is for semantic areas alignment, achieving fine transformation of anatomical structure. The same structure of both stages is composed of a dual-stream feature extraction module (DFEM) and a refined deformation field generation module (RDGM). Unlike the deep learning-based approaches that utilizing down-sampled encoder to extract features, DFEM constructed by dual-stream U-Net structure can capture semantic information in decoder feature for structural alignment. Different with approaches applying cascaded networks to learn deformation field, our proposed RDGM generates multi-scale deformation fields by performing a coarse-to-fine registration within a single network. Experiments on 3D brain MRI and liver CT datasets confirm that the proposed SFM-Net achieves accurate and diffeomorphic registration results, outperforming other state-of-the-art methods.

Deep learning-based image registration (DLIR) meth-ods have achieved remarkable success in deformable im-age registration. We observe that iterative inference can exploit the well-trained registration network to the fullest extent. In this work, we propose a novel Iterative Inference Residual Pyramid Network (IIRP-Net) to enhance registration performance without any additional training costs. In IIRP-Net, we construct a streamlined pyramid registration network consisting of a feature extractor and residual flow estimators (RP-Net) to achieve generalized capabilities in feature extraction and registration. Then, in the inference phase, IIRP-Net employs an iterative inference strategy to enhance RP-Net by iteratively reutilizing residual flow es-timators from coarse to fine. The number of iterations is adaptively determined by the proposed IterStop mecha-nism. We conduct extensive experiments on the FLARE and Mindboggle datasets and the results verify the effectiveness of the proposed method, outperforming state-of-the-art de-formable image registration methods. Our code is available at https://github.com/Torbjorn1997/IIRP-Net.

In deformable image registration, learning-based methods have demonstrated impressive performance. However, previous methods mainly focus on enhancing the capability to predict the deformation field, without fully exploring the optimal ways to update the deformation field. As a result, errors can easily accumulate during the process of updating the deformation field, thus leading to inaccurate registration results. To solve this problem, we propose RC-Block (Refinement Coefficient Block) to find the optimal way to update the deformation field, thus achieving high accuracy registration results. The proposed module introduces a novel refinement coefficient, which can leverage information from the current scale to continuously rectify the previous deformation field. In addition, RC-Block is a plug-and-play module that can be seamlessly and easily integrated into most registration methods. Extensive experimental results show that our module can effectively improve existing advanced methods’ performance with minimal additional burden.

Recommending suitable tags for online textual content is a key building block for better content organization and consumption. In this paper, we identify three pillars that impact the accuracy of tag recommendation: (1) sequential text modeling meaning that the intrinsic sequential ordering as well as different areas of text might have an important implication on the corresponding tag(s) , (2) tag correlation meaning that the tags for a certain piece of textual content are often semantically correlated with each other, and (3) content-tag overlapping meaning that the vocabularies of content and tags are overlapped. However, none of the existing methods consider all these three aspects, leading to a suboptimal tag recommendation. In this paper, we propose an integral model to encode all the three aspects in a coherent encoder-decoder framework. In particular, (1) the encoder models the semantics of the textual content via Recurrent Neural Networks with the attention mechanism, (2) the decoder tackles the tag correlation with a prediction path, and (3) a shared embedding layer and an indicator function across encoder-decoder address the content-tag overlapping. Experimental results on three realworld datasets demonstrate that the proposed method significantly outperforms the existing methods in terms of recommendation accuracy.

Hashtags can greatly facilitate content navigation and improve user engagement in social media. Meaningful as it might be, recommending hashtags for photo sharing services such as Instagram and Pinterest remains a daunting task due to the following two reasons. On the endogenous side, posts in photo sharing services often contain both images and text, which are likely to be correlated with each other. Therefore, it is crucial to coherently model both image and text as well as the interaction between them. On the exogenous side, hashtags are generated by users and different users might come up with different tags for similar posts, due to their different preference and/or community effect. Therefore, it is highly desirable to characterize the users’ tagging habits. In this paper, we propose an integral and effective hashtag recommendation approach for photo sharing services. In particular, the proposed approach considers both the endogenous and exogenous effects by a content modeling module and a habit modeling module, respectively. For the content modeling module, we adopt the parallel co-attention mechanism to coherently model both image and text as well as the interaction between them; for the habit modeling module, we introduce an external memory unit to characterize the historical tagging habit of each user. The overall hashtag recommendations are generated on the basis of both the post features from the content modeling module and the habit influences from the habit modeling module. We evaluate the proposed approach on real Instagram data. The experimental results demonstrate that the proposed approach significantly outperforms the state-of-theart methods in terms of recommendation accuracy, and that both content modeling and habit modeling contribute significantly to the overall recommendation accuracy.

Circular RNAs (circRNAs) are emerging as a new class of endogenous and regulatory noncoding RNAs in latest years. With the widespread application of RNA sequencing (RNA-seq) technology and bioinformatics prediction, large numbers of circRNAs have been identified. However, at present, we lack a comprehensive characterization of all these circRNAs in interested samples. In this study, we integrated 87 935 circRNAs sequences that cover most of circRNAs identified till now represented in circBase to design microarray probes targeting back-splice site of each circRNA to profile expression of those circRNAs. By comparing the circRNA detection efficiency of RNA-seq with this circRNA microarray, we revealed that microarray is more efficient than RNA-seq for circRNA profiling. Then, we found ∼80 000 circRNAs were expressed in cervical tumors and matched normal tissues, and ∼25 000 of them were differently expressed. Notably, many of these circRNAs detected by this microarray can be validated by quantitative reverse transcription polymerase chain reaction (RT-qPCR) or RNA-seq. Strikingly, as many as ∼18 000 circRNAs could be robustly detected in cell-free plasma samples, and the expression of ∼2700 of them differed after surgery for tumor removal. Our findings provided a comprehensive and genome-wide characterization of circRNAs in paired normal tissues and tumors and plasma samples from multiple individuals. In addition, we also provide a rich resource with 41 microarray data sets and 10 RNA-seq data sets and strong evidences for circRNA expression in cervical cancer. In conclusion, circRNAs could be efficiently profiled by circRNA microarray to target their reported back-splice sites in interested samples.