Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns

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.

     

Mechanism of methanol decomposition on the Pd/WC(0001) surface unveiled by first-principles calculations

In this study, the decomposition of methanol into the CO and H species on the Pd/tungsten carbide (WC)(0001) surface is systematically investigated using periodic density functional theory (DFT) calculations. The possible reaction pathways and intermediates are determined. The results reveal that saturated molecules, i.e., methanol and formaldehyde, adsorb weakly on the Pd/ WC(0001) surface. Both CO and H prefer three-fold sites, with adsorption energies of −1.51 and −2.67 eV, respectively. On the other hand, CH₃O stably binds at three-fold and bridge sites, with an adsorption energy of −2.58 eV. However, most of the other intermediates tend to adsorb to the surface with the carbon and oxygen atoms in their sp³ and hydroxyl-like configurations, respectively. Hence, the C atom of CH₂OH preferentially attaches to the top sites, CHOH and CH₂O adsorb at the bridge sites, while COH and CHO occupy the three-fold sites. The DFT calculations indicate that the rupture of the initial C–H bond promotes the decomposition of CH₃OH and CH₂OH, whereas in the case of CHOH, O–H bond scission is favored over the C–H bond rupture. Thus, the most probable methanol decomposition pathway on the Pd/WC(0001) surface is CH₃OH → CH₂OH → trans-CHOH → CHO → CO. The present study demonstrates that the synergistic effect of WC (as carrier) and Pd (as catalyst) alters the CH₃OH decomposition pathway and reduces the noble metal utilization.     

扫描共振频率技术在蓄电池在线修复中的应用

分析了蓄电池组在使用过程受损的原因,介绍了一种蓄电池组在线修复的新技术,即扫描共振频率技术的基本工作原理,并进一步分析、介绍了该在线修复方法所采用的主要新技术和独特的优点。     

双电池系统电源选择器MAX1773/1773A

MAX1773／MAX1773A是用于双电池系统的电源选择器，它允许外部控制器去管理双电池组、适配器输入、电池充电器和系统负载所需的电源连接。文中介绍了MAX1773／1773A的特点、引脚功能、内部结构和工作原理，给出了MAX1773/MAX1773A的典型工作电路。     

橡胶促进剂DM的合成工艺

M氧化生成DM是自由基反应机理，结合微反应器机理，采用分子氧化的反应方式，选用绿色溶剂异丙醇、环境友好型氧化剂H202，一步法制取高品质DM。对反应时间、反应温度、氧化剂用量等因素进行考察，确定最佳工艺条件为：反应时间90min，反应温度55℃，氧化剂不过量，碱过量5％，M—Na溶液M含量30％，加料时N60 min，溶剂用量为M—Na溶液质量的1．5倍，所得产品质量合格，熔点可达180℃。     

共晶碳化物团球化对铸铁激光熔敷层抗裂性的影响

为提高铸铁表面大面积激光熔敷层抗裂性问题，通过冶金因元素控制熔敷层组织形态在熔敷材料中加入碱金属元素钾，研究了在激光快速加热条件下钾对铸铁激光熔敷层组织团球化的影响，进而分析了该球状组织对熔敷层抗裂性的影响，结果表明随熔敷金属内钾含量增多熔敷层内共晶碳化物组织呈球状及孤岛状，这种组织明显提高了熔敷层抗裂性，此外大量的渗碳体组织确保了熔敷层具有较高的耐磨性；获得了无裂纹的大面积搭接熔敷层，其对应合金系统为Fe-C-Si-Ni-K。     

换热站容积式加热器管束失效原因及防护

对换热站容积式加热器管束失效原因进行了分析 ,指出主要是由于汽蚀和电化学腐蚀所致。从操作工艺和采用 12Cr2AlMoV材质两方面进行改进 ,可使管束的使用寿命由 4个月延长到 2年     

中国石油未来油气勘探重点领域分析

根据近几年来的研究认识与勘探成果分析,未来几年中国石油油气勘探主要集中于如下五大重点领域:大面积低渗透岩性油气藏、成熟区复杂隐蔽油气藏、前陆盆地复杂构造油气藏、海相碳酸盐岩油气藏和渤海湾滩海第三系油气藏。     

综合应用地震属性、测井数据反演储层参数

本文研究了样点地震属性的特征提取，利用BP神经网络建立测井声波时差和地震属性的非线性映射关系。采用距离加权平均对研究区所有井的反演结果进行外推。为了提高分辨率和计算结果的准确性，详细分析、研究了适合于地震信号分解和重构的小波，以及测井声波时差和地震波阻抗与层界面的关系。最后，对反演的声波时差资料进行界面影响校正，进而计算出较符合实际情况的孔隙率参数。经已知井和新钻井验证，计算结果和实际情况相一致，效果令人满意。     

星间激光通信技术进展与趋势

较详细地评述了目前国外卫星间光通信技术研究的现状．根据关键单元技术的进展情况，总结了未来星间光通信系统的发展趋势。