Search

Brain age is considered as an important biomarker for detecting aging-related diseases such as Alzheimer's Disease (AD). Magnetic resonance imaging (MRI) have been widely investigated with deep neural networks for brain age estimation. However, most existing methods cannot make full use of multimodal MRIs due to the difference in data structure. In this paper, we propose a graph transformer geometric learning framework to model the multimodal brain network constructed by structural MRI (sMRI) and diffusion tensor imaging (DTI) for brain age estimation. First, we build a two-stream convolutional autoencoder to learn the latent representations for each imaging modality. The brain template with prior knowledge is utilized to calculate the features from the regions of interest (ROIs). Then, a multi-level construction of the brain network is proposed to establish the hybrid ROI connections in space, feature and modality. Next, a graph transformer network is proposed to model the cross-modal interaction and fusion by geometric learning for brain age estimation. Finally, the difference between the estimated age and the chronological age is used as an important biomarker for AD diagnosis. Our method is evaluated with the sMRI and DTI data from UK Biobank and Alzheimer's Disease Neuroimaging Initiative database. Experimental results demonstrate that our method has achieved promising performances for brain age estimation and AD diagnosis.

It is well known that brain development is very fast and complex in the early childhood with age-based neurological and physiological changes of brain structure and function. The brain maturity is an important indicator for evaluating the normal development of children. In this paper, we propose a multimodal regression framework to combine the features from structural magnetic resonance imaging (sMRI) and diffusion tensor imaging (DTI) data for age prediction of children. First, three types of features are extracted from sMRI and DTI data. Second, we propose to combine the sparse coding and Q-Learning for feature selection from each modality. Finally, the ensemble regression is performed by random forest based on proximity measures to fuse multimodal features for age prediction. The proposed method is evaluated on 212 participants, including 76 young children less than 2 years old and 136 children aged from 2-15 years old recruited from Shanghai Children's Hospital. The results show that integrating multimodal features has achieved the highest accuracies with the root mean squared error (RMSE) of 0.208 years and mean absolute error (MAE) of 0.150 years for age prediction of young children (0-2), and RMSE of 1.666 years and MAE of 1.087 years for older children (2-15). We have shown that the selected features by Q-Learning can consistently improve the prediction accuracy. The comparison of prediction results demonstrates that the proposed method performs better than other competing methods.

Strain relaxation is critical for GeSn alloys transforming from indirect to direct bandgap nature with Sn fraction above 6.5%, but difficult for them grown by molecular beam epitaxy (MBE), in which low temperature has to be set up to avoid Sn segregation. In this work, compressively strained Ge0.935Sn0.065 thin films grown on Si with a Ge buffer layer by MBE are firstly treated by ex-situ rapid thermal annealing, rendering partially strain relaxation in the Ge0.935Sn0.065 by generation of misfit dislocation networks without Sn segregation. Then, secondary epitaxy of Ge0.905Sn0.095 layer is carried out on the thermally annealed Ge0.935Sn0.065 virtual substrate. The secondary epitaxial GeSn layers exhibit partial strain relaxation and strong photoluminescence with red-shift of peak position, compared to that of fully compressive strained GeSn thin films with the same structure grown primary epitaxially. Those results manifest that secondary epitaxy, combining with ex-situ rapid thermal annealing for strain relaxed GeSn virtual substrate, is a practical way to achieve strain relaxed GeSn thin films with direct bandgap nature by MBE.

Product reviews contain a large number of implicit aspects and implicit opinions. However, most of the existing studies in aspect-based sentiment analysis ignored this problem. In this work, we introduce a new task, named Aspect-Category-Opinion-Sentiment (ACOS) Quadruple Extraction, with the goal to extract all aspect-category-opinion-sentiment quadruples in a review sentence and provide full support for aspect-based sentiment analysis with implicit aspects and opinions. We furthermore construct two new datasets, Restaurant-ACOS and Laptop-ACOS, for this new task, both of which contain the annotations of not only aspect-category-opinion-sentiment quadruples but also implicit aspects and opinions. The former is an extension of the SemEval Restaurant dataset; the latter is a newly collected and annotated Laptop dataset, twice the size of the SemEval Laptop dataset. We finally benchmark the task with four baseline systems. Experiments demonstrate the feasibility of the new task and its effectiveness in extracting and describing implicit aspects and implicit opinions. The two datasets and source code of four systems are publicly released at https://github.com/NUSTM/ACOS.

Vitiligo is a common and refractory disease worldwide. The limited efficiency and side effects of the conventional treatment options create demands towards the development of strategies. Excellent repigmentation is demonstrated after several filiform fire needle sessions in the vitiligo lesions. In this observational study, we aimed to observe the response to filiform fire needle therapy in patients with vitiligo, and determine whether there was a difference of efficiency with respect to the type, affected site, and disease duration of vitiligo. Patients received filiform fire needle therapy once every 2 weeks for 12 consecutive weeks. The results of the 77 vitiligo patients were: 34 (44.15%) with an excellent repigmentation rate, 15 (19.48%) with a marked improvement, 15 (19.48%) with a moderate response, 6 (7.79%) with a slight improvement, and 7 (9.09%) with an absent response. Among the vitiligo patients with different affected sites, the most effective location of therapy was the face. Shorter course leads to better therapeutic effect. Two patients developed hypertrophic scars on the lesion site. In conclusion, this study shows filiform fire needle therapy is an effective and relatively safe therapeutic option for vitiligo.