Technical advancements significantly improve earlier diagnosis of cervical cancer, but accurate diagnosis is still difficult due to various factors. We develop an artificial intelligence assistive diagnostic solution, AIATBS, to improve cervical liquid-based thin-layer cell smear diagnosis according to clinical TBS criteria. We train AIATBS with >81,000 retrospective samples. It integrates YOLOv3 for target detection, Xception and Patch-based models to boost target classification, and U-net for nucleus segmentation. We integrate XGBoost and a logical decision tree with these models to optimize the parameters given by the learning process, and we develop a complete cervical liquid-based cytology smear TBS diagnostic system which also includes a quality control solution. We validate the optimized system with >34,000 multicenter prospective samples and achieve better sensitivity compared to senior cytologists, yet retain high specificity while achieving a speed of <180s/slide. Our system is adaptive to sample preparation using different standards, staining protocols and scanners.

No abstract

No abstract

Realistic speech-driven 3D facial animation is a challenging problem due to the complex relationship between speech and face. In this paper, we propose a deep architecture, called Geometry-guided Dense Perspective Network (GDPnet), to achieve speaker-independent realistic 3D facial animation. The encoder is designed with dense connections to strengthen feature propagation and encourage the re-use of audio features, and the decoder is integrated with an attention mechanism to adaptively recalibrate point-wise feature responses by explicitly modeling interdependencies between different neuron units. We also introduce a non-linear face reconstruction representation as a guidance of latent space to obtain more accurate deformation, which helps solve the geometry-related deformation and is good for generalization across subjects. Huber and HSIC (Hilbert-Schmidt Independence Criterion) constraints are adopted to promote the robustness of our model and to better exploit the non-linear and high-order correlations. Experimental results on the public dataset and real scanned dataset validate the superiority of our proposed GDPnet compared with state-of-the-art model. The code is available for research purposes at http:// cic.tju.edu.cn/ faculty/ likun/ projects/ GDPnet.

Rock-filled concrete (RFC) technology is a new type of mass concrete construction technology, which consists of two basic components: the force transfer frame formed by large-size rock accumulation and the matrix formed by self-compacting concrete (SCC) filling. Its unique construction method also distinguishes RFC from ordinary concrete in terms of its force characteristics. In this paper, RFC is considered as a composite material consisting of aggregate and SCC; based on the realistic failure process analysis (RFPA) method, the effects of specimen size and aggregate size on the compressive strength of RFC were studied. Firstly, RFC cube specimens were prepared and uniaxial compression tests were conducted. During the preparation process, in order to eliminate the influence of factors such as shape, spatial distribution state, and volume share of aggregates on the compressive strength, aggregates of different sizes were set as spheres and arranged in simple cubic stacking; then a numerical model of RFC with different specimen sizes and different aggregate sizes was established for uniaxial compression numerical simulation experiments to analyze the variation law and failure pattern of the RFC compressive strength. The results indicate that the compressive strength of RFC exhibits a significant size effect and follows a negative exponential function distribution law; with the same volume fraction of aggregate, the smaller the aggregate size, the higher the compressive strength of the RFC will be, and this increasing trend gradually levels off. Based on the findings of this study, it is recommended that the size effect and the reduction of aggregate size on dam strength be taken into account in the design of RFC dams.