• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.418-426
• /
• 2006

This paper proposes a robust and efficient segmentation method for a cardiac ultrasound image taken from a probe inserted into the heart in surgery. The method consists of three steps: initial boundary extraction, whole boundary modification using confidence competition, and local boundary modification using the rolling spoke method. Firstly, the initial boundary is extracted with threshold regions along the global spokes emitted from the center of an ultrasound probe. Secondly, high confidence boundary edges are detected along the global spokes by competing among initial boundary candidate and new candidates achieved by edge and appearance information. finally, the boundary is modified by rolling local spokes along concave regions that are difficult to extract using the global spokes. The proposed method produces promising segmentation results for the ultrasound cardiac images acquired during surgery.

• Journal of radiological science and technology
• /
• v.46 no.6
• /
• pp.475-484
• /
• 2023

This study aimed to compare filters for reducing speckle noise in ultrasound images using clinical liver images. We acquired the clinical liver ultrasound images, and noisy images were obtained by adding 0.01, 0.05, 0.10, and 0.50 intensity levels of speckle noise to the liver images. The Wiener filter, median modified Wiener filter, gamma filter, and Lee filter were designed for the noisy images by setting window sizes at 3×3, 5×5, and 7×7. The coefficient of variation (COV) and contrast to noise ratio (CNR) were calculated to evaluate noise reduction and various filters. Moreover, the filter with the highest image quality was selected and quantitatively compared to a noisy image. As a result, COV and CNR showed the noise improved result when the Lee filter was applied. Furthermore, the Lee filter image with a window size of 7×7 was noted to possess approximately a minimum of 1.28 to a maximum of 3.38 times better COV and a minimum of 2.18 to a maximum of 5.50 times better CNR than the noisy image. In conclusion, we confirmed that the Lee filter was effective in reducing speckle noise and proved that an appropriate window size needs to be set considering blurring.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.876-883
• /
• 2003

In this paper, we propose an algorithm for organ recognition in ultrasound images using log power spectrum. The main procedure of the algorithm consists of feature extraction and feature classification. In the feature extraction, as a translation invariant feature, log power spectrum is used for extracting the information on echo of the organs tissue from a preprocessed input image. In the feature classification, Mahalanobis distance is used as a measure of the similarity between the feature of an input image and the representative feature of each class. Experimental results for real ultrasound images show that the proposed algorithm yields the improvement of maximum 30% recognition rate than the recognition algorithm using power spectrum and Euclidean distance, and results in better recognition rate of 10-40% than the recognition algorithm using weighted quefrency complex cepstrum.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.29 no.4
• /
• pp.292-300
• /
• 1993

Acoustical imaging has made brilliant progress in the medical science field, and has also made much progress in the nondestructive testing and under water acoustics applications since doctor Dussik brother has studied about possibilities of making images of brain by recording variations in the intensity of ultrasonic beam from head in 1937. In this paper an acoustical image is reconstructed with the power spectra analysed by impulse ultrasound wave generated by electrodynamic transducer(EDT). The EDT generates the impulse ultrasound of 77KHz in center frequency and 120KHz in bandwidth at -20dB by 1200V exciter in this experiment. The impulse ultrasound has the dominant frequency components of 47KHz, 177KHz, 110KHz and 155KHz. The U shape object is adopted in making an acoustical image. The resulted spectral acoustical images are different from the optical view of the U shape object. However the image reconstructed from 110KHz spectrum is very similar to the original optical shape of the object. Even KHz level impulse sound of 70$\mu$sec pulse width is found to be useful in reconstructing acoustical imaging improvement.

• Journal of radiological science and technology
• /
• v.39 no.2
• /
• pp.157-161
• /
• 2016

The purpose of this study is that in measures the acoustic propagate characteristics and temperature sensitivity of ultrasound tissue mimicking phantom(TM phantom). TM phantom manufacture according to the International Electronical Committee(IEC) guidelines for acoustic propagate characteristics of soft tissue. TM phantom was observed to have the image brightness and the image depth penetration decreases changes convergence which was the subject of ultrasound image characteristics in accordance with an external temperature that the change is reduced in temperature below $22^{\circ}C$. This study provide a basis t o create another TM Phantom and TM Phantom has been determined that it is appropriate for use in more than $22^{\circ}C$.

• Journal of the Korean Wood Science and Technology
• /
• v.33 no.5 s.133
• /
• pp.21-28
• /
• 2005

For the proper conservation of wooden cultural properties, non-destructive evaluation (NDE) method, which can be used to quantitatively evaluate the internal state of wood members, are needed. In this study, an ultrasonic CT system composed of portable devices was attempted, and the capacity of this system was verified by reconstructing the CT images for two phantoms and two artificially defected specimens. Results from this study showed that the sizes of detected defects were enlarged and the shapes were distorted on the CT images. Also, the positions were shifted somewhat toward the surface of specimen, which is regarded due to the anisotropic property of wood. Compared to the filtered back-projection method, SIRT (simultaneous iterative reconstruction technique) method was determined to be more efficient as the algorithm of image reconstruction for wood. A new ultrasonic CT system is thought to be used as a NDE method for wood. However wood characteristics and wave diffraction within wood made it difficult to accurately evaluate the size, shape and position of defects. To improve the quality of CT image of wood, more research including the relationship between wood and ultrasound is needed, and wood properties should be taken into consideration on the image reconstruction algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.11
• /
• pp.2540-2545
• /
• 2015

In this paper, we propose a novel method to extract appendix from ultrasound image automatically to avoid such subjectivity issue. In the process, we apply a series of image processing algorithms such as Ends_in search stretching for emphasizing brightness contrast and binarization, region labelling, and cubic spline interpolation for extracting lower bound fasicia line that is the base of extracting the appendix. Knowing that the appendix is located at the lower organ area below the bottom fascia line, we conduct a series of image processing techniques to find the fascia line correctly. And then we apply ART2 algorithm to the organ area in order to extract appendix accurately. Through experiment, the effectiveness of the proposed method is verified based on the field experts' evaluations.

• Korean Journal of Agricultural Science
• /
• v.45 no.1
• /
• pp.66-73
• /
• 2018

Hanwoo is an important livestock resource in Korea. Its genetic improvements of economic traits have mainly focused on the steers in the past. However, there is a great necessity to extend the breed improvement programs to the cows as well. Therefore, the objective of this study was to investigate the effects of various environmental factors (person taking the measurement, region, year of measurement, month of measurement, image interpreter, birth-year and birth-year) on ultrasound measured carcass traits. A total of 27,215 ultrasound measurements of carcass traits were recorded between 2004 and 2012 for 22,620 cows born from 1997 to 2011. The ultrasound measures included backfat thickness (BFT), eye muscle area (EMA), and marbling score (MAR). The mean values for the BFT, EMA and MAR were 4.46 mm, $56.24cm^2$, and 4.12 point, respectively. Seven environmental factors, person taking the measurement, region, year of measurement, month of measurement, image interpreter, birth-year and birth-month, were tested to determine if they had a significant effect on the studied traits using the GLM procedure in SAS. All factors were found to significantly affect all the ultrasound carcass traits in this study. Unlike in previous studies, among the environmental effects, the significant effect of the image interpreter on the ultrasound carcass traits was shown for the first time in this study. These results indicate that future genetic evaluations of ultrasound carcass traits of Hanwoo cows should include all of the above environmental factors as well as the effect from people taking the measurements.

• Journal of Biomedical Engineering Research
• /
• v.41 no.1
• /
• pp.48-54
• /
• 2020

In this paper, we deal with a liver fibrosis classification problem using ultrasound B-mode images. Commonly representative methods for classifying the stages of liver fibrosis include liver biopsy and diagnosis based on ultrasound images. The overall liver shape and the smoothness and roughness of speckle pattern represented in ultrasound images are used for determining the fibrosis stages. Although the ultrasound image based classification is used frequently as an alternative or complementary method of the invasive biopsy, it also has the limitations that liver fibrosis stage decision depends on the image quality and the doctor's experience. With the rapid development of deep learning algorithms, several studies using deep learning methods have been carried out for automated liver fibrosis classification and showed superior performance of high accuracy. The performance of those deep learning methods depends closely on the amount of datasets. We propose an enhanced U-net architecture to maximize the classification accuracy with limited small amount of image datasets. U-net is well known as a neural network for fast and precise segmentation of medical images. We design it newly for the purpose of classifying liver fibrosis stages. In order to assess the performance of the proposed architecture, numerical experiments are conducted on a total of 118 ultrasound B-mode images acquired from 78 patients with liver fibrosis symptoms of F0~F4 stages. The experimental results support that the performance of the proposed architecture is much better compared to the transfer learning using the pre-trained model of VGGNet.

• 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.