• Journal of the Korean Society of Radiology
• /
• v.15 no.7
• /
• pp.999-1005
• /
• 2021

The object of this research is CS, which increases resolution while shortening inspection time, is applied to MRA to compare the quality of images for SENSE and CS techniques and to evaluate SNR and CNR to find out the optimal techniques and to provide them as clinical basic data based on this information. Data were analyzed on 32 patients who performed TOF MRA tests at a university hospital in Chung cheong-do (15 males, 17 females), ICA stenosis:10, M1 Aneurysm:10, and average age 53 ± 4.15). In the inspection, the inspection equipment was Ingenia CX 3.0T, Archieva 3.0T, and 32 channel head coil and 3D gradient echo as a method for equipment data. SNR and CNR of each image were measured by quantitative analysis, and the quality of the image was evaluated by dividing the observer's observation into 5 grades for qualitative evaluation. Imaging evaluation is described as being significant when the p-value is 0.05 or less when the paired T-test and Wilcoxon test are performed. Quantitative analysis of SNR and CNR in TOF MRA images Compared to the SENSE method, the CS method is a method measurement method (p <0.05). As an observer's evaluation, the sharpness of blood vessels: CS (4.45 ± 0.41), overall image quality: CS (4.77 ± 0.18), background suppression of images: CS (4.57 ± 0.18) all resulted in high CS technique (p = 0.000). In conclusion, the Compressed SENSE TOF MRA technique shows superior results when comparing and evaluating the SENSE and Compressed SENSE techniques in increased flow rate magnetic resonance angiography. The results are thought to be the clinical basis material in the 3D TOF MRA examination for brain disease.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.21 no.2
• /
• pp.31-36
• /
• 2017

Purpose Recently, the performance of PET/CT scanner has been improved and various techniques have been developed to increase the image quality such as Sensitivity and Resolution. The purpose of this study is to evaluate the usefulness of Q.Clear (a fully convergent iterative reconstruction) technique of GE Discovery IQ equipment to enhance the image quality. Materials and Methods All scans were acquired by Discovery IQ (GE Healthcare, MI, USA). In NEMA IEC Body Phantom test, Background to Hot-sphere (10 mm, 13 mm, 17 mm, 22 mm) ratio was 1:4 and scan time was 3 minutes. The images were reconstructed by VPHDs (VUE Point High-Definition + SharpIR) and Q.Clear to evaluate each Contrast. We injected 18F-FDG 187 M㏃ to PET/SPECT Performance Phantom. And then it was scanned for 4 minutes to evaluate Resolution and Uniformity. T-test statistical analysis was performed on SUVmax of small lesions less than 2 cm in 100 clinical patients regardless of disease type. Results In the NEMA IEC Body Phantom, the Contrast was $63.6{\pm}5.7%$ (VPHDs) and $75{\pm}4.8%$ (Q.Clear). In the PET/SPECT Performance Phantom, the Resolution was 9.2 mm (VPHDs) and 7.3 mm (Q.Clear). Uniformity of Q.Clear was 10.8% better than VPHDs. T-test statistic of the clinical patients showed a significant difference of p value of 0.021. Conclusion Both the phantom test and the clinical results showed that the quality of the image was improved in Q.Clear was applied. The SUVmax was highly measured in Q.Clear and the lesions were clearly distinguished visually. Therefore Q.Clear can be useful in various aspects such as dose-reduction, patients evaluation and image analysis.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• The Korean Journal of Pain
• /
• v.23 no.3
• /
• pp.202-206
• /
• 2010

Magnetic resonance image (MRI) is the most sensitive imaging test of the spine in routine clinical practice. Unlike conventional x-ray examinations and computed tomography scans, high-quality magnetic resonance images can be assured only if patients are able to remain perfectly still. However, some patients find it uncomfortable to remain still because of pain. In that condition, interlaminar cervical epidural injections can reduce pain and allow the procedure. When using air with the "loss of resistance" technique in epidural injections to identify the epidural space, there is the possibility of injected excessive air epidurally to mimic a herniated disc. We describe a case report of epidural air artifact in a cervical MRI after cervical epidural injections.

• The Journal of Korean Academy of Prosthodontics
• /
• v.43 no.3
• /
• pp.314-321
• /
• 2005

Objectives. The purpose of this study was to compare the shade changes in wet and dry conditions of natural teeth using two different intra-oral colorimeters. Materials and methods. Twenty volunteer subjects have no restorations and fillings in the maxillary central incisors were involved in this clinical study. The color of tooth was measured by two different instruments that were a Shade $Scan^{TM}$ System and a VITA $Easyshade^{(R)}$, Five times consecutive measurements were done for each subject with both instruments. Groups of measurement are an initial wet condition as control, dry in 5 minutes, 15 seconds after re-wetting with saliva, re-wetting after 5minutes and re-wetting after 30 minutes. Using ShadeScan $System^{TM}$, tooth image was captured and converted to the mapping image of Vitapan 3D master. Three main shades were chosen from each subject and calculated the area in Global Lab Image software. Data were analyzed using paired T-Test and Wilcoxon Signed Ranked Test. Using VITA $Easyshade^{(R)}$, color differences($\Delta$E) between measurements were analyzed with one sample T-test. Results. Using ShadeScan $System^{TM}$, there were significant differences between control group and dry(P=.023), dry and re-wetting 15 seconds, 5 minutes, 30 minutes as well(P=.021, P=.017, P=.030) in comparison of primary shade. However, comparing three main shades, there was no significant difference between control and dry(P=.105). Using VITA $Easyshade^{(R)}$, color differences($\Delta$E) between control and dry, dry and re-wetting 30 minutes were statistically different(P=.002, P=.022). Conclusion. Primary shade could be changed in dry and wetting procedure in time, however there was no significant shade changes in overall.

• Journal of Radiation Industry
• /
• v.17 no.4
• /
• pp.397-403
• /
• 2023

The purpose of this study is to obtain brain MRI images through Heavenly T₂ FLAIR and DWI techniques to find out strengths and weaknesses of each image. Data were analyzed on 13 normal people and 17 brain tumor patients. Philips Ingenia 3.0TCX was used as the equipment used for the inspection, and 32 Channel Head Coil was used to acquire data. Using Image J and Infinity PACS Data, 3mm² of gray matter, white matter, cerebellum, basal ganglia, and tumor areas were set and measured. Quantitative analysis measured SNR and CNR as an analysis method, and qualitative analysis evaluated overall image quality, lesion conspicuity, image distortion, susceptibility artifact and ghost artifact on a 5-point scale. The statistical significance of data analysis was that Wilcox-on Signed Rank Test and Paired t-test were executed, and the statistical program used was SPSS ver.22.0 and the p value was less than 0.05. In quantitative analysis, the SNR of gray matter, white matter, cerebellum, basal ganglia, and tumor of Heavily T₂ FLAIR is 41.45±0.13, 40.52±0.45, 41.44±0.51, 40.96±0.09, 35.28±0.46 and the CNR is 15.24±0.13, 16.75±0.23, 16.28±0.41, 15.83±0.17, 16.63±0.51. In DWI, SNR is 32.58±0.22, 36.75±0.17, 30.21±0.19, 35.83±0.11, 43.29±0.08, and CNR is 13.14±0.63, 14.21±0.31, 12.95±0.32, 11.73±0.09, 17.56±0.52. In normal tissues, Heavenly T₂ FLAIR obtained high results, but in disease evaluation, high results were obtained at DWI, b=1000 (p<0.05). In addition, in the qualitative analysis, overall image quality, lesion conspicuity, image distortion, susceptibility artifact and ghost artifact aspects of the Heavily T₂ FLAIR were evaluated, and 3.75±0.28, 2.29±0.24, 3.86±0.23, 4.08±0.21, 3.79±0.22 values were found, respectively, and 2.53±0.39, 4.13±0.29, 1.90±0.20, 1.81±0.21, 1.52±0.45 in DWI. As a result of qualitative analysis, overall image quality, image distortion, susceptibility artifact and ghost artifact were rated higher than DWI. However, DWI was evaluated higher in lesion conspicuity (p<0.05). In normal tissues, the level of Heavenly T₂ FLAIR was higher, but the DWI technique was higher in the evaluation of the disease (tumor). The two results were necessary techniques depending on the normal site and the location of the disease. In conclusion, statistically significant results were obtained from the two techniques. In quantitative and qualitative analysis, the two techniques had advantages and disadvantages, and in normal and disease evaluation, the two techniques produced useful results. These results are believed to be educational data for clinical basic evaluation and MRI in the future.

• Journal of radiological science and technology
• /
• v.44 no.6
• /
• pp.635-643
• /
• 2021

The results of empirical researches on the diagnosis of lung cancer are insufficient, so it is limited to objectively judge the clinical possibility and utilization according to the accuracy of diagnosis. Thus, this study retrospectively analyzed the lung cancer diagnostic performance of PET-MRI (Positron Emission Tomography-Magnetic Resonance Imaging) by using the decision matrix. This study selected and experimented total 165 patients who received both hematological CEA (Carcinoembryonic Antigen) test and hybrid PET-MRI (¹⁸F-FDG, 5.18 MBq/kg / Body TIM coil. VIVE-Dixon). After setting up the result of CEA (positive:>4 ㎍/ℓ. negative:<2.5㎍/ℓ) as golden data, the lung cancer was found in the image of PET-MRI, and then the SUV_max (positive:>4, negative:<1.5) was measured, and then evaluated the correlation and significance of results of relative diagnostic performance of PET-MRI compared to CEA through the statistical verification (t-test, P>0.05). Through this, the PET-MRI was analyzed as 96.29% of sensitivity, 95.23% of specificity, 3.70% of false negative rate, 4.76% of false positive rate, and 95.75% of accuracy. The false negative rate was 1.06% lower than the false positive rate. The PET-MRI that significant accuracy of diagnosis through high sensitivity and specificity, and low false negative rate and false positive rate of lung cancer, could acquire the fusion image of specialized soft tissue by combining the radio-pharmaceuticals with various sequences, so its clinical value and usefulness are regarded as latently sufficient.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• The Journal of Korean Medicine
• /
• v.44 no.4
• /
• pp.136-149
• /
• 2023

Objectives: Facial diagnosis is an important part of clinical diagnosis in traditional East Asian Medicine. In this paper, we proposed a model to quantitatively classify cold sensitivity using a fully automated facial image analysis system. Methods: We investigated cold sensitivity in 452 subjects. Cold sensitivity was determined using a questionnaire and the Cold Pattern Score (CPS) was used for analysis. Subjects with a CPS score below the first quartile (low CPS group) belonged to the cold non-sensitivity group, and subjects with a CPS score above the third quartile (high CPS group) belonged to the cold sensitivity group. After splitting the facial images into train/validation/test sets, the train and validation set were input into a convolutional neural network to learn the model, and then the classification accuracy was calculated for the test set. Results: The classification accuracy of the low CPS group and high CPS group using facial images in all subjects was 76.17%. The classification accuracy by sex was 69.91% for female and 62.86% for male. It is presumed that the deep learning model used facial color or facial shape to classify the low CPS group and the high CPS group, but it is difficult to specifically determine which feature was more important. Conclusions: The experimental results of this study showed that the low CPS group and the high CPS group can be classified with a modest level of accuracy using only facial images. There was a need to develop more advanced models to increase classification accuracy.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.10
• /
• pp.1451-1457
• /
• 2004

Bone density parameters of children, unlike that of adult, might reflect growth effect along longitudinal direction as well as bone mass. The clinical test was performed for 859 male/female children with age 6-16 years. Ultrasonic imaging system was used to measure bone density, and relationship of bone density to age was evaluated. The bone quality index appeared to be highly correlated with age for male/female children. It was found that bone quality index rose rapidly in the first growth period. The bone quality index was then kept almost unchanged in the period of puberty, and slowly rose after puberty. It was also found that growth of female stopped earlier than that of male. Also, if more clinical examinations are performed by applying various sizes of region of interest, relationship between bone density and age is expected to be more reliable.