• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.134-136
• /
• 2021

Research related to early diagnosis of breast cancer using artificial intelligence algorithms has been actively conducted in recent years. Although various algorithms that classify breast cancer based on a few publicly available ultrasound breast cancer images have been published, these methods show various limitations such as, processing speed and accuracy suitable for the user's purpose. To solve this problem, in this paper, we propose a multi-stage transfer learning where ResNet model trained on ImageNet is transfer learned to microscopic cancer cell line images, which was again transfer learned to classify ultrasound breast cancer images as benign and malignant. The images for the experiment consisted of 250 breast cancer ultrasound images including benign and malignant images and 27,200 cancer cell line images. The proposed multi-stage transfer learning algorithm showed more than 96% accuracy when classifying ultrasound breast cancer images, and is expected to show higher utilization and accuracy through the addition of more cancer cell lines and real-time image processing in the future.

• Journal of radiological science and technology
• /
• v.46 no.1
• /
• pp.15-21
• /
• 2023

This study was purpose to assessment of the resolution characteristics by using ATS 535H Basic quality assurance (QA) phantom for ultrasound. The ultrasound equipment was used Logiq P6 (Ultrasound, GE Healthcare System, Chicago, IL, USA). And the ultrasound transducer were used Convex 4C (4~5.5 MHz), Linear 11L (10~13 MHz), Sector 3SP (3~5.5 MHz) probe. As for the noise power spectrum (NPS) comparison results by using ATS 535H Basic QA ultrasound phantom and Convex 4C, Linear 11L, Sector 3SP probe. The NPS value of the Convex 4C probe image was 0.0049, Linear 11L probe image was 0.0049, Sector 3SP probe image was 0.1422 when the frequency is 1.0 mm^-1. The modulation transfer function (MTF) comparison results by using ATS 535H Basic QA ultrasound phantom and Linear 11L probe the MTF value of the 3 cm focus image was 0.7511 and 4 cm focus image was 0.9001 when the frequency is 1.0 mm^-1. This study was presented characteristics of spatial resolution a quantitative evaluation methods by using ultrasound medical images for QA of ultrasound medical QA phantom. The quality control (QC) for equipment maintenance can be efficiently used in the clinic due to the quantitative evaluation of the NPS and MTF as the standard methods. It is meaningful in that it is applied mutatis mutandis and presented the results of physical resolution characteristics of the ultrasound medical image.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.5
• /
• pp.373-380
• /
• 1998

The prediction of bone strength by ultrasound velocity and broadband ultrasound attenuation was examined. Ultrasound velocity and broadband attenuation were measured for sixty specimens of human trabecular bone. Samples were divided into two equal groups and loaded in compression at the strain rates of $0.0004\;s^{-1}$ and of $0.08\;s^{-1}$. The ultimate strength was determined for each specimen. Specimens tested at $0.08\;s^{-1}$ had a mean value of strength 63% higher than the specimens tested at $0.0004\;s^{-1}$. Ultrasound velocity and broadband attenuation were significantly associated with compressive strength at both strain rates. Mechanical strength was also correlated strongly with a linear combination of ultrasound velocity and broadband attenuation for both the low and high loading rates. The use of ultrasound parameters may provide good clinical means for assessing the resistance of trabecular bone to both low and high energy trauma.

• Journal of Animal Science and Technology
• /
• v.65 no.2
• /
• pp.365-376
• /
• 2023

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

• Journal of Mechanical Science and Technology
• /
• v.19 no.5
• /
• pp.1116-1122
• /
• 2005

A finite element method was used to simulate the wave propagation of laser-generated ultrasound and its interaction with surface breaking cracks in an elastic material. Thermoelastic laser line source on the material surface was approximated as a shear dipole and loaded as nodal forces in the plane-strain finite element (FE) model. The shear dipole- FE model was tested for the generation of ultrasound on the surface with no defect. The model was found to generate the Rayleigh surface wave. The model was then extended to examine the interaction of laser generated ultrasound with surface-breaking cracks of various depths. The crack-scattered waves were monitored to size the crack depth. The proposed model clearly reproduced the experimentally observed features that can be used to characterize the presence of surface-breaking cracks.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1038-1048
• /
• 2022

Ultrasound is one of the effective methods for skin treatment. The skin penetration depth of the ultrasound depends on the ultrasonic frequency, that is, when the ultrasonic frequency is high, the depth is shallow. We have developed a transducer which can generate effectively 3 different ultrasonic frequencies removing interference between 3 types of frequencies according to impedance matching technology. The generated powers of transducer are 40.67W at 3.MHz, 17.46W at 11.7 MHz, and 14.79W at 21.5 MHz. The signal interference between the three frequencies is designed so that they do not interfere with each other by separating the signals using the SPDT (Single Pole, Double Throw) switch. The developed hybrid ultrasound transducer can be applied in skin care or skin treatment and beauty therapy.

• Korean Journal of Food Science and Technology
• /
• v.43 no.1
• /
• pp.30-38
• /
• 2011

Effects of depolymerization treatments of a carbohydrase mixture (CM), ultrasound, and irradiation on the physical properties of defatted mustard meal-based edible films (DMM films) were investigated. DMM hydrocolloids were added to CM (0.42% (w/w solution)), treated by ultrasound (500-700 W, 10-30 min) or ${\gamma}$-ray (40-100 kGy) to prepare film-forming solutions. Films were formed by drying. The CM treatment at 0.42% (w/w), pH 5.5, and 40-$50^{\circ}C$ with a 0.5 hr incubation time resulted in the highest colloidal stability in the film-forming solution. The depolymerization treatments did not dramatically change the water vapor permeability of the films. The solubility of the film decreased up to 53.1% by the CM treatment. The ultrasound treatment (700 W-30 min) decreased tensile strength and elongation. The ultrasound treatment (600 W-20 min) resulted in more compact and uniform structures of the films. Flavor profiles were differentiated by the power level and the time of the ultrasound treatment.

• Advances in nano research
• /
• v.2 no.2
• /
• pp.121-133
• /
• 2014

Polymer nanocomposites are advanced nanomaterials which exhibit dramatic improvements in various mechanical, thermal and barrier properties as compared with the neat polymer. Polystyrene/ alumina nanocomposites were prepared by an ultrasound-assisted solution casting method at filler loadings ranging from 0.2 to 2% and also at different ultrasonic frequencies, viz. 58 kHz, 192/58 kHz, 430 kHz, 470 kHz and 1 MHz. The composites were subjected to mechanical property tests (tensile and impact tests) and cavitation erosion tests to study the enhancement in functional properties. Filler dispersion in the polymer matrix was observed by SEM analysis. The effect of frequency on filler dispersion in the matrix was studied by SEM analysis and functional property enhancement of the composite material. The composites prepared at dual (high/ low) frequency (192/58 kHz) were found to show better property enhancement at low filler loadings as compared with neat polymer and also with composites prepared without ultrasound, thus reinforcing the finding that ultrasound-assisted synthesis is a promising method for the synthesis of nanocomposites.

• Journal of radiological science and technology
• /
• v.41 no.1
• /
• pp.53-60
• /
• 2018

The purpose of this study was investigating the effect of 3D printing technology that changes the speed of sound (SOS) and the broadband ultrasound attenuation (BUA) by controlling the density of the media phantom. We used 3D printers which called additive manufacturing (AM) by using material with polylactic acid (PLA). The inside of the medium phantom was filled crossly with 100%, 90%, 80%, 70%, 60%, and 50% of the material. The ultrasonic instrument measured the SOS and the BUA using a 0.55 MHz ultrasound output in opposing mode with a pair of transducers. As a result, the density of the medium phantoms with the SOS showed very high correlation (r = 0.944), but the SOS showed very low correlation (r = 0.500). It is expecting that the manufacturing and measurement method of the medium phantom using 3D printing technology will be used as basic data for ultrasonic bone mineral density.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.307-310
• /
• 2021

In the recent years, studies using Computer-Aided Diagnostics(CAD) have been actively conducted, such as signal and image processing technology using breast ultrasound images, automatic image optimization technology, and automatic detection and classification of breast masses. As computer diagnostic technology is developed, it is expected that early detection of cancer will proceed accurately and quickly, reducing health insurance and test ice for patients, and eliminating anxiety about biopsy. In this paper, a quantitative analysis of tumors was conducted in ultrasound images using a gray level co-occurrence matrix(GLCM) to experiment with the possibility of use for computer assistance diagnosis.