Breast cancer is one of the most common female malignancies, as well as the second leading cause of mortality for women. Early detection and treatment can dramatically decrease the mortality rate. Recently, automated breast volume scanner (ABVS) has become one of the most frequently used diagnose methods for breast tumor screening because of its operator-independent and reproducible advantages. However, it is a challenging job to obtain the tumors’ accurate locations and shapes by reviewing hundreds of ABVS slices. In this paper, a novel computer-aided detection (CADe) system is developed to reduce clinicians’ reading time and improve the efficiency. The CADe system mainly contains three parts: tumor candidate acquisition, false-positive reduction and tumor segmentation. Firstly, a local phase-based approach is built to obtain breast tumor candidates for further recognition. Subsequently, a convolutional neural network (CNN) is applied to reduce false positives (FPs). The introduction of CNN can help to avoid complicated feature extraction as well as elevate the accuracy and efficiency. Finally, superpixel-based segmentation is used to outline the breast tumor. Here, superpixel-based local binary pattern (SLBP) is proposed to assist the segmentation, which improves the performance. The methods were evaluated on a clinical ABVS dataset whose abnormal cases were manually labeled by an experienced radiologist. The experiment results were mainly composed of two parts. At the FP reduction stage, the proposed CNN achieved 100% and 78.12% sensitivity with FPs/case of 2.16 and 0. At the segmentation stage, our SLBP obtained 82.34% true positive, 15.79% false positive and 83.59% Dice similarity. In summary, the proposed CADe system demonstrated promising potential to detect and outline breast tumors in ABVS images.
Three-dimensional (3D) YBO3:Tb3+ flower-like and dense flower-like hierarchitecture constituted of nanoflakes are solvothermally synthesized in the presence of polyborate precursors in the mixture of ethanol and water. The growth process of the YBO3:Tb3+ flowers and dense flowers was explored based on the time-dependent experiment and the results showed that the growth mechanism follows an in situ growth rather than self-assembly process as reported previously. YBO3:Tb3+ morphologies composed of nanoflakes are achieved by controlling the concentration of ethanol and dependence of photoluminescence on morphology was studied. Remarkable photoluminescence enhancement was observed for YBO3:Tb3+ with flower-like morphology demonstrating the potential of the microstructure in future applications as a green phosphor. Such a synthetic method and growth mechanism may be applied to fabricate complex 3D architectures of other materials. 相似文献
The high cost of noble metal catalysts has been a great bottleneck for the catalyst industry. Using the noble metal at a single-atom level for catalytic applications could dramatically decrease the cost. The impacts of single Pt atoms on the photocatalytic performance of Ag3VO4 have been investigated and reported. In this report, single Pt atoms were anchored on the surface of Ag3VO4 (AVO) as a cocatalyst, and the resultant composite photocatalyst has been studied for photocatalytic H2 production from water driven by visible light. The as-prepared AVO particles are hollow nanospheres in the monoclinic phase with a bandgap of 2.20 eV. The light absorption edge of AVO/Pt is slightly red-shifted compared to that of the pristine AVO, indicating more visible light absorption of AVO/Pt. The XPS peaks of Ag, V, and Pt exhibit a significant shift after AVO and Pt get into contact, suggesting the strong interaction between the surface Ag and V atoms, and single Pt atoms. After 3-h illumination, the photocatalytic H2 evolution amount from AVO/Pt is improved up to 1400 μmol, which is 2.8 times that on the bare AVO. Such efficient photocatalytic H2 evolution on AVO/Pt is still maintained after five reaction cycles. The better photocatalytic performance of AVO/Pt has been attributed to the more efficient visible light utilization and the lower interfacial charge transfer resistance, as demonstrated in the DRS and EIS spectra. The presence of the surface Pt atoms also leads to a higher amount of reactive radicals, which could efficiently promote the surface redox reactions. 相似文献
This study addresses the problem of choosing the most suitable probabilistic model selection criterion for unsupervised learning
of visual context of a dynamic scene using mixture models. A rectified Bayesian Information Criterion (BICr) and a Completed
Likelihood Akaike’s Information Criterion (CL-AIC) are formulated to estimate the optimal model order (complexity) for a given
visual scene. Both criteria are designed to overcome poor model selection by existing popular criteria when the data sample
size varies from small to large and the true mixture distribution kernel functions differ from the assumed ones. Extensive
experiments on learning visual context for dynamic scene modelling are carried out to demonstrate the effectiveness of BICr
and CL-AIC, compared to that of existing popular model selection criteria including BIC, AIC and Integrated Completed Likelihood
(ICL). Our study suggests that for learning visual context using a mixture model, BICr is the most appropriate criterion given
sparse data, while CL-AIC should be chosen given moderate or large data sample sizes. 相似文献