• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.189-194
• /
• 2021

The purpose of this study was to investigate the effect of reducing noise and streaking artefacts by applying the Boost3D algorithm in the case of noise and streaking artifacts generated during computed tomography of the shoulder joint. A phantom study using a thoracic phantom including shoulder joint and clinical evaluation were conducted through shoulder joint images of 35 patients who underwent computed tomography of the shoulder joint from September 2020 to October 2020. The evaluation was divided into groups before and after the application of the Boost3D algorithm, and the noise values, signal to noise ratio, and mean to standard deviation ratio values were analyzed. Both noise values and mean to standard deviation ratio values analyzed in phantom image evaluation and clinical image evaluation were statistically significantly lower in the group after Boost3D was applied (p<0.05). Through this study, it was found that noise and streak artifacts were reduced through the application of Boost3D, and the mean to standard deviation ratio was high, which can be judged as an excellent image. If the Boost3D algorithm is used for computed tomography of the shoulder joint, it is thought that excellent images can be obtained with reduced noise and streaking artifacts that may occur in the shoulder joint area.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.17-18
• /
• 2024

악성 흉수의 진단은 세포학적 검사로 암세포를 확인하는 것이 필수적이며 진단율은 50~80%로 나타난다. 양성자 단층 촬영은 비침습적으로 암 병기를 평가하는 유용한 방법이다. 하지만 암이 아닌 다른 원인으로 인한 포도당 대사로 인하여 양전자 단층 촬영만으로 악성 흉수를 진단하는 데 어려움이 있다. 악성 흉수 자동 진단 모델은 암세포를 진단하는데 있어서 보조적인 역할이 가능하다. 이에 따라 본 연구는 컨볼루션 신경망 기반의 딥러닝 모델을 개발하여 악성 흉수 진단 성능을 확인하고 진단의 보조적 목적으로써 딥러닝의 사용 가능성을 확인하고자 하였다. 결과적으로 모델 전반적으로 accuracy 0.7~0.86의 높은 성능을 보였다. 본 연구의 결과를 통해 실제 의료 환경에서 악성 흉수를 진단하는데 딥러닝 모델이 보조적인 역할을 할 수 있을 것으로 기대된다.

• Journal of Veterinary Clinics
• /
• v.30 no.5
• /
• pp.390-393
• /
• 2013

This case study describes the imaging features of radiography and computed tomography (CT) in four small breed dogs with lung lobe torsion. The medical records, thoracic radiographs and CT images of four dogs with confirmed lung lobe torsion were retrospectively reviewed. Pleural effusion and increased lobar opacity/density were seen on all CT and thoracic radiography in all four dogs. CT revealed narrowed/collapsed bronchus in all four dogs, while this was only appreciated on one thoracic radiography. The vesicular emphysema pattern was seen on four CT but only on three radiographic examinations. The specific findings of lung lobe torsion were vesicular emphysema and a narrowed/collapsed bronchus. These findings were more easily recognized on CT than with thoracic radiographs.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.295-301
• /
• 2023

In addition to protocol adjustments during CT examinations, the height of the CT table can also affect image quality. Therefore, this study aimed to investigate the change in image quality depending on the height of the table in brain CT, which accounts for a large proportion of CT examinations, by measuring signal to contrast to noise ratio (CNR) and noise power spectrum (NPS) using the head phantom and evaluating them. The head phantom images were acquired using Philips Brilliance iCT 256. When the image was acquired, the table height was adjusted to 815, 865, 915, 965, 1015, and 1030 mm, respectively, and each scan was performed 3 times for each height. The CNR result showed the highest value at 965 mm, which is the height adjacent to the center of the head phantom. NPS showed the lowest NPS at 915 mm, the center of the head phantom in the low frequency region. From these results, it can be seen that the height of the table in CT examination is closely related to the image quality, and it can be seen the characteristics of image quality according to CT table through quantitative evaluation methods such as CNR and NPS.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.11-16
• /
• 2005

Recently, there are a lot of endeavor to implement a fuzzy theory to artificial neural network. Goh proposed the fuzzy single layer perceptron algorithm and advanced fuzzy perceptron based on the generalized delta rule to solve the XOR Problem and the classical Problem. However, it causes an increased amount of computation and some difficulties in application of the complicated image recognition. In this paper, we propose an enhanced fuzzy single layer Perceptron using the dynamic adjustment of threshold. This method is applied to the XOR problem, which used as the benchmark in the field of pattern recognition. The method is also applied to the recognition of digital image for image application. In a result of experiment, it does not always guarantee the convergence. However, the network show improved the learning time and has the high convergence rate.

• Progress in Medical Physics
• /
• v.24 no.4
• /
• pp.303-314
• /
• 2013

Image quality of computed tomography (CT) is very vulnerable to metal artifacts. Recently, the thickness and background normalization techniques have been introduced. Since they provide flat sinograms, it is easy to determine metal traces and a simple linear interpolation would be enough to describe the missing data in sinograms. In this study, we have developed a theory describing two normalization methods and compared two methods with respect to various sizes and numbers of metal inserts by using simple numerical simulations. The developed theory showed that the background normalization provide flatter sinograms than the thickness normalization, which was validated with the simulation results. Numerical simulation results with respect to various sizes and numbers of metal inserts showed that the background normalization was better than the thickness normalization for metal artifact corrections. Although the residual artifacts still existed, we have showed that the background normalization without the segmentation procedure was better than the thickness normalization for metal artifact corrections. Since the background normalization without the segmentation procedure is simple and it does not require any users' intervention, it can be readily installed in conventional CT systems.

• Journal of Veterinary Clinics
• /
• v.31 no.3
• /
• pp.241-245
• /
• 2014

A miniature pinscher and two Maltese dogs were present with dyspnea, and radiography and computed tomography (CT) were performed. All dogs were diagnosed with giant bullous emphysema of the massive, hyperexpanded, and hypoattenuating bulla causing contralateral mediastinal shift. Giant bullous emphysema, the rarest form of bullous lung disease, is defined as a bulla that fills more than 30% of the hemithorax, and multi-detector CT scanning could provide the useful information to confirm a diagnosis of giant bullous emphysema in older dogs. The radiographic and computed tomographic features for giant bullous emphysema were described.

• Journal of the Korean Society of Radiology
• /
• v.10 no.6
• /
• pp.443-450
• /
• 2016

In this study, we are using a computer tomography image of the abdomen, as an experimental linear research for the image of the fatty liver patients texture features analysis and computer-aided diagnosis system of implementation using the ROC curve analysis, from the computer tomography image. We tried to provide an objective and reliable diagnostic information of fatty liver to the doctor. Experiments are usually a fatty liver, via the wavelet transform of the abdominal computed tomography images are configured with the experimental image section, shows the results of statistical analysis on six parameters indicating a feature value of the texture. As a result, the entropy, average luminance, strain rate is shown a relatively high recognition rate of 90% or more, the control also, flatness, uniformity showed relatively low recognition rate of about 70%. ROC curve analysis of six parameters are all shown to 0.900 (p = 0.0001) or more, showed meaningful results in the recognition of the disease. Also, to determine the cut-off value for the prediction of disease six parameters. These results are applicable from future abdominal computed tomography images as a preliminary diagnostic article of diseases automatic detection and eventual diagnosis.

• Journal of Veterinary Clinics
• /
• v.27 no.5
• /
• pp.588-592
• /
• 2010

A 15-year-old neutered male Yorkshire terrier was presented with a gait disorder of the pelvic limbs. For differential diagnosis of neural disease, magnetic resonance imaging (MRI) and computed tomography (CT) scan were performed. CT showed bone defect in the 4th lumbar vertebra and adjacent soft tissue mass. MRI revealed a mass in left side of the 4th lumbar vertebra. The mass was uniformly enhanced on contrast-enhanced T1-weighted imaging (T1W1). Excision of the mass alleviated back pain. Vertebral osteosarcoma was identified by the histopathological examination. Therefore, CT and MRI were helpful to diagnose vertebral osteosarcoma in the dog and to plan surgical excision of the mass.

• Journal of Chest Surgery
• /
• v.36 no.1
• /
• pp.39-42
• /
• 2003

Endobronchial lipomas are rare benign tumors that arise from the lung. They partially or totally obstruct the bronchial lumen, producing a variable degree of collapse, irreversible bronchiectasis, and pulmonary damage. Although bronchoscope, CT and MR are reported to be helpful in establishing the diagnosis, CT is highly specific and sensitive in detecting fatty tumor. They may be removed by endoscope or thoracotomy or lobectomy. We present a case of endobronchial lipoma completely obstructing the right middle lobe and postobstructive irreversible pulmonary change with review of literatures.