• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.1-6
• /
• 2024

Recently, various techniques are being applied through the development of medical AI, and research has been conducted on the application of super-resolution AI models. In this study, evaluate the results of the application of the super-resolution AI model to brain CT as the basic data for future research. Acquiring CT images of the brain, algorithm for brain and bone windowing setting, and the resolution was downscaled to 5 types resolution image based on the original resolution image, and then upscaled to resolution to create an LR image and used for network input with the original imaging. The SRCNN model was applied to each of these images and analyzed using PSNR, SSIM, Loss. As a result of quantitative index analysis, the results were the best at 256×256, the brain and bone window setting PSNR were the same at 33.72, 35.2, and SSIM at 0.98 respectively, and the loss was 0.0004 and 0.0003, respectively, showing relatively excellent performance in the bone window setting CT image. The possibility of future studies aimed image quality and exposure dose is confirmed, and additional studies that need to be verified are also presented, which can be used as basic data for the above studies.

• 대한의용생체공학회:의공학회지
• /
• 제42권3호
• /
• pp.71-79
• /
• 2021

Currently, the naked eyes-based diagnosis of bone metastases on CT images relies on qualitative assessment. For this reason, there is a great need for a state-of-the-art approach that can assess and follow-up the bone metastases with quantitative biomarker. Radiomics can be used as a biomarker for objective lesion assessment by extracting quantitative numerical values from digital medical images. In this study, therefore, we evaluated the clinical applicability of non-invasive and objective bone metastases computer-aided diagnosis using radiomics-based biomarkers in CT. We employed a total of 21 approaches consist of three-classifiers and seven-feature selection methods to predict bone metastases and select biomarkers. We extracted three-dimensional features from the CT that three groups consisted of osteoblastic, osteolytic, and normal-healthy vertebral bodies. For evaluation, we compared the prediction results of the classifiers with the medical staff's diagnosis results. As a result of the three-class-classification performance evaluation, we demonstrated that the combination of the random forest classifier and the sequential backward selection feature selection approach reached AUC of 0.74 on average. Moreover, we confirmed that 90-percentile, kurtosis, and energy were the features that contributed high in the classification of bone metastases in this approach. We expect that selected quantitative features will be helpful as biomarkers in improving the patient's survival and quality of life.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.279-280
• /
• 2007

Airway wall thickness is an important bio-marker for evaluation of pulmonary diseases such as stenosis, bronchiectasis. Nevertheless, an image-based analysis of the airway tree can provide precise and valuable airway size information, quantitative measurement of airway wall thickness in CT images involves various sources of error and uncertainty. So we have developed an accurate airway wall measurement technique for small airways with three-dimensional (3-D) approach. To illustrate performance of these techniques, we used airway phantom that consisted of 4 acryl tubes with various inner and outer diameters. Results show that evaluation of interpolation and deconvolution methods of airways in 3-D CT images, and significant improvement over the full-width-half-maximum method for measurement of not only location of the luminal and outer edge of the airway wall but airway wall thickness.

• 한국안전학회지
• /
• 제17권4호
• /
• pp.38-44
• /
• 2002

The application of fractal concept provides an useful method in the study for the quantitative analysis of irregular variations like the fracture surfaces and crack profiles. Fractal curves have characteristics that represents a self-similarity based on the fractal dimension. The fractal dimensions were obtained by the box counting method. In this report, we obtained the nearly stable fractal dimensions of fracture crack profiles for STS316 with CT specimen as the crack advances and the relationships between crack length and fractal dimension. Moreover fractal fracture parameter that corresponds to J-R curve is shown by the relationships between fractal dimension and crack extension. From the results, we concluded that crack extension of high toughness material also shows the fractal characteristics, which can be used in order to evaluate the crack life precisely.

• Journal of Korean Neurosurgical Society
• /
• 제54권5호
• /
• pp.384-389
• /
• 2013

Objective : Use of quantitative computed tomography (CT) to evaluate bone mineral density was suggested in the 1970s. Despite its reliability and accuracy, technical shortcomings restricted its usage, and dual-energy X-ray absorptiometry (DXA) became the gold standard evaluation method. Advances in CT technology have reduced its previous limitations, and CT evaluation of bone quality may now be applicable in clinical practice. The aim of this study was to determine if the Hounsfield unit (HU) values obtained from CT correlate with patient age and bone mineral density. Methods : A total of 128 female patients who underwent lumbar CT for back pain were enrolled in the study. Their mean age was 66.4 years. Among them, 70 patients also underwent DXA. The patients were stratified by decade of life, forming five age groups. Lumbar vertebrae L1-4 were analyzed. The HU value of each vertebra was determined by averaging three measurements of the vertebra's trabecular portion, as shown in consecutive axial CT images. The HU values were compared between age groups, and correlations of HU value with bone mineral density and T-scores were determined. Results : The HU values consistently decreased with increasing age with significant differences between age groups (p<0.001). There were significant positive correlations (p<0.001) of HU value with bone mineral density and T-score. Conclusion : The trabecular area HU value consistently decreases with age. Based on the strong positive correlation between HU value and bone mineral density, CT-based HU values might be useful in detecting bone mineral diseases, such as osteoporosis.

• 대한방사선기술학회지:방사선기술과학
• /
• 제41권6호
• /
• pp.553-560
• /
• 2018

PET-CT and PET-MRI which integrates CT using ionized radiation and MRI using phenomena of magnetic resonance are determined to have the limitation to apply the semi-quantitative index, standardized uptake value (SUV), with the same level due to the fundamental differences of image capturing principle and reorganization, hence, their correlations were analyzed to provide their clinical information. To 30 study subjects maintaining pre-treatment, $^{18}F-FDG$ (5.18 MBq/㎏) was injected and they were scanned continuously without delaying time using $Biograph^{TM}$ mMR 3T (Siemens, Munich) and Biograph mCT 64 (Siemens, Germany), which is an integral type, under the optimized condition except the structural differences of both scanners. Upon the measurement results of $SUV_{max}$ setting volume region of interest with evenly distributed radioactive pharmaceuticals by captured images, $SUV_{max}$ mean values of PET-CT and PET-MRI were $2.94{\pm}0.55$ and $2.45{\pm}0.52$, respectively, and the value of PET-MRI was measured lower by $-20.85{\pm}7.26%$ than that of PET-CT. Also, there was a statistically significant difference in SUVs between two scanners (P<0.001), hence, SUV of PET-CT and PET-MRI cannot express the clinical meanings in the same level. Therefore, in case of the patients who undergo cross follow-up tests with PET-CT and PET-MRI, diagnostic information should be analyzed considering the conditions of SUV differences in both scanners.

• 대한영상의학회지
• /
• 제84권4호
• /
• pp.900-910
• /
• 2023

목적 정상으로 보이는 chest CT를 정량화 분석하여 흡연 및 폐쇄성 폐질환(chronic obstructive pulmonary disease; 이하 COPD) 여부에 따른 차이가 있는지 확인하고자 하였다. 대상과 방법 2013년 1월부터 2014년 12월까지 chest CT가 정상이면서 정량화 분석이 있는 90명의 남자 환자[COPD 없는 비흡연자(n = 38)와 흡연자(n = 45), COPD 흡연자(n = 7)]를 대상으로 하였다. COPD 흡연자 7명을 대상으로 나이를 추출하여 환자-대조군 연구도 하위 분석하였다. Pi10, 왜도, 첨도, 평균감쇠계수, 저감쇠영역%와 같은 정령화 변수를 분석하였다. 결과 COPD가 없는 환자 중에서 흡연자의 Pi10 (4.176 ± 0.282, n = 45)이 비흡연자에 비해 약 0.1 mm 정도 두꺼웠고(4.070 ± 0.191, n = 38, p = 0.047), 흡연자의 왜도와 첨도(2.628 ± 0.484 and 6.448 ± 3.427)가 비흡연자보다 낮았다(2.884 ± 0.624, p = 0.038 and 8.594 ± 4.944, p = 0.027). COPD가 있는 흡연자들의 Pi10 (4.427 ± 0.437, n = 7)이 COPD가 없는 비흡연자들보다 약 0.4 mm 두꺼웠다(4.001 ± 0.108, n = 14, p = 0.005). 그러나 평균감쇠계수와 저감쇠영역%에서는 유의한 차이가 없었다. 결론 정상 chest CT를 보이더라도 QCT로 COPD의 유무와 상관없이 흡연자들의 소기도가 두꺼운 것을 알 수 있으며 이는 폐실질 변화보다 더 선행한다.

• 디지털융복합연구
• /
• 제10권2호
• /
• pp.243-247
• /
• 2012

금속성 치아충전물이 있을 때 PET/CT검사를 시행하면 CT영상에서 선속경화인공음영이 발생한다. CT영상에 발생되는 인공음영에 의해 PET영상에 영향을 미칠 수 있다. 두경부종양이 있는 환자가 치과용 충전물이 있을 경우 CT영상에서 발생하는 선속경화인공음영에 의해 PET영상 및 SUV값에 변화를 줄 수 있다. 따라서 본 연구는 금속성치아충전물에 의한 HU 값의 변화에 따른 SUV값을 정량적으로 측정하여 임상적용에 있어 적절성을 평가 하였다. 연구대상은 2011년 8월에 PET/CT검사를 실시한 환자 47명이었다. 분석을 위해 CT와 PET영상에 2개의 ROI를 그려 이용하였다. 실험결과 충전물이 있을 경우 HU값과 SUV값이 증가 하였고 통계적으로도 유의한 차이를 보였다.(P<0.01) 이 증가 정도는 금속성 치아충전물이 없는 환자의 경우보다 큰 변화는 아니었지만 두경부 종양이 있을 경우 암의 진단시 과대평가가 될 수 있는 가능성이 충분하다. 따라서 임상에서 두경부 종양이 있는 환자를 대상으로 PET/CT 검사를 시행할 경우 판독상의 오류를 범하지 않도록 여러 물리학적, 생물학적인 부분에 대하여 고려를 해야 할 것이다.

• 대한디지털의료영상학회논문지
• /
• 제9권1호
• /
• pp.21-30
• /
• 2007

영상 획득과 재구성 방법에 따라 CT 감약계수는 다양성을 보이고 관심 영역의 노이즈는 정밀도에 영향을 준다. 인체에서 간 실질조직과 위장의 물의 CT 감약계수와 노이즈를 커널에 따라 측정하였다. 다중채널 CT 스캐너를 이용하여 복부를 스캔 하였고, 커널은 B10 (very smooth), B20 (smooth), B30 (medium smooth), B40 (medium), B50 (medium sharp), B60 (sharp), B70 (very sharp), B80 (ultra sharp)으로 재구성하여 간의 실질 조직과 물이 들어 있는 위장 부위를 ROI 기능을 이용하여 평균의 CT감약계수와 표준편차인 노이즈를 측정하여 영상을 비교하였다. 간의 실질 조직에서 CT감약계수는 커널에 따라 60.4에서 69.2 HU사이에서 분포하여 차이가 없었으나, 노이즈는 커널(7.6$\sim$63.8 HU)이 높아질수록 증가하였다. 물의 CT감약계수는 -2.2 HU에서 0.8 HU사이에서 측정되었고, 노이즈는 커널(10.1$\sim$82.4 HU)이 높아질수록 증가하였다. 영상의 질을 높이기 위해서는 검사 부위에 따라 노이즈를 감소하기 위해 적절한 커널을 선택하여 CT 검사를 하여야 한다.

• 한국방사선학회논문지
• /
• 제17권5호
• /
• pp.709-715
• /
• 2023

본 연구의 목적은, U-net 딥러닝 모델을 이용하여 CT 영상에서의 노이즈 감소 효과를 다양한 하이퍼 파라미터를 적용하여 평가하였다. 노이즈가 포함된 입력 영상 생성을 위하여 Gaussian 노이즈를 적용하였고, 총 1300장의 CT 영상에서 train, validation, test 셋의 비율을 8:1:1로 유지하여 U-net 모델을 적용하여 학습하였다. 연구에서 적용된 하이퍼파라미터는 최적화 함수 Adagrad, Adam, AdamW와 학습횟수 10회, 50회, 100회와 학습률 0.01, 0.001, 0.0001을 적용하였으며, 최대 신호 대 잡음비와 영상의 변동계수 값을 계산하여 정량적으로 분석하였다. 결과적으로 U-net 딥러닝 모델을 적용한 노이즈 감소는 영상의 질을 향상시킬 수 있으며 노이즈 감소 측면에서 유용성을 입증하였다.