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.

     

Effective Excitation of Magnetoelectric Voltage Harmonics in a Ferromagnet–Piezoelectric Structure by Current Passing through the Magnetic Layer

Technical Physics Letters - The magnetoelectric (ME) effect in a planar amorphous ferromagnet–piezoelectric lead zirconate titanate (PZT) composite structure can be effectively excited by...     

Simulation of a Terahertz Laser in the Bloch Oscillation Mode

Technical Physics Letters - Possible designs of a terahertz laser that use the effect of Bloch oscillations in SiC natural superlattices have been considered. It has been proposed to use as a...     

Shaping the Toroidal Section of End Mills

The shaping of the toroidal cutting section of end mills is considered. Methods are devised for selecting the positional parameters in shaping the helical rake surface on the toroidal section. Relations are established between the geometric parameters of the end mill in the toroidal section.     

Volumetric out-of-furnace heat treatment of 3600-M3 decomposers

Specifications require that all the welds in 12-m-diam. decomposers with a capacity of 3600 m³ be subjected to high-temperature tempering before going into service in order to alleviate the stresses from the welding operation. Specialists at the organizations VNIIPTkhimnefteapparatury and VNIImontazhspetsstroi have proposed out-of-furnace volumetric (complete) of the assembled decomposer with the use of special heaters. The use of this heating method has shortened assembly operations while providing the welds with a highquality heat treatment and reducing the stresses overall (including welding stresses, stresses from assembly of the decomposer, etc.) The technology ensures uniform heating of the housing of the decomposer and provides for close control over the process. The experience gained in heat-treating decomposers can also be used in the construction of other containers that come into contact with corrosive media. __________ Translated from Metallurg, No. 3, pp. 61–64, March, 2006.