• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.434-440
• /
• 2022

Liver transplantation is a critical used treatment method for patients with end-stage liver disease. The number of cases of living donor liver transplantation is increasing due to the imbalance in needs and supplies for brain-dead organ donation. As a result, the importance of the accuracy of the donor's suitability evaluation is also increasing rapidly. To measure the donor's liver volume accurately is the most important, that is absolutely necessary for the recipient's postoperative progress and the donor's safety. Therefore, we propose liver segmentation in abdominal CT images from pre-operation, POD 7, and POD 63 with a two-dimensional U-Net. In addition, we introduce an algorithm to measure the volume of the segmented liver and measure the hepatectomy rate and regeneration rate of pre-operation, POD 7, and POD 63. The performance for the learning model shows the best results in the images from pre-operation. Each dataset from pre-operation, POD 7, and POD 63 has the DSC of 94.55 ± 9.24%, 88.40 ± 18.01%, and 90.64 ± 14.35%. The mean of the measured liver volumes by trained model are 1423.44 ± 270.17 ml in pre-operation, 842.99 ± 190.95 ml in POD 7, and 1048.32 ± 201.02 ml in POD 63. The donor's hepatectomy rate is an average of 39.68 ± 13.06%, and the regeneration rate in POD 63 is an average of 14.78 ± 14.07%.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.53-59
• /
• 2011

Purpose: To evaluate the dosimetry and image of very low does CT attenuation correction for phantom using pediatric PET/CT. Materials and methods: three PET / CT scanners (Discovery STe, BiographTruepoint 40, Discovery 600) as a child-size acrylic phantom and ion chamber dosimeter (Unfous Xi CT, Sweden) using a CT image acquisition parameters (10, 20, 40, 80, 100, 160 mA; 80, 100, 120, 140 kVp) by varying the depth dose and evaluate $CTDI_{vol}$ value. And each attenuation corrected PET/CT images used NEMA PET Phantom$^{TM}$ (NU2-1994) was evaluated by SUV. Results: Abdominal diagnosis CT dose in general pediatric (about 10 ages) parameter (100 kVp, 100 mA) than very low dose CT parameter (80 kVp, 10 mA) at the depth dose was reduced approximately 92%, $CTDI_{vol}$ was reduced to about 88%. Each CT attenuation corrected parameters PET images showed no change in the value of SUV. Conclusion: for pediatric patients, PET/CT scan can be obtained with very low dose attenuation correction CT (80 kVp, 10 mA), and such attenuation correction CT dose was reduced 100 fold than diagnosis CT dose. PET / CT scan used very low dose CT attenuation correction in pediatric patients can be helpful in reducing radiation dose.

• Journal of Veterinary Clinics
• /
• v.30 no.4
• /
• pp.273-277
• /
• 2013

This study was performed to compare clinical and diagnostic imaging features between asymptomatic and symptomatic extrahepatic portosystemic shunts in dogs. The data of thirty patients diagnosed with extrahepatic PSS by multi-detector CT were reviewed, and the dogs were divided into asymptomatic (9/30) and symptomatic (21/30) groups. Signalments, hematologic results, liver size, morphologic classifications and main portal vein to abdominal aortic ratio (PV/AO) at the porta hepatis level from CT images were evaluated in two groups. Shih-tzu (5/9) was the most frequent breed in asymptomatic group, and various breeds were presented in symptomatic group. Mean age of asymptomatic group ($9.2{\pm}3.2$ years) was significantly higher than that of symptomatic group ($4.5{\pm}3.2$ years). The most morphologic form of shunt vessel was the splenophrenic shunt (16/30). PV/AO of asymptomatic group ($1.1{\pm}0.19$) was significantly higher than the values of symptomatic group ($0.55{\pm}0.19$). Clinical signs, hematologic results and diagnostic imaging findings of asymptomatic PSS are too nonspecific to suspect PSS. Therefore, considering of patient's age and CT examination with application of PV/AO ratio could be useful for the diagnosis of asymptomatic PSS.

• Journal of Biomedical Engineering Research
• /
• v.38 no.1
• /
• pp.49-55
• /
• 2017

The prevalence of obesity has noticeably increased worldwide over several decades with various complication. Even though anti-obesity drug treatments have been spotlighted by resulting in effective mean weight losses, its adverse effects cannot be overlooked. Thus, this study aimed to evaluate the effects of multi-frequency whole body vibration, one of the mechanical stimulus, as a countermeasure against obesity. Thirty-two-6-week-old C57BL/6J male mice were equally assigned to four groups: the Control group (CON, n = 8), the Sham group (Sham, n = 8), the sham with single frequency whole body vibration (S+V, n = 8), and the sham with multi frequency whole body vibration (S+MV, n = 8). After 4 weeks, morphologic changes in the adipose tissue were evaluated from three-dimensional images using in vivo micro-computed tomography. At 4 weeks, the volume of the abdominal adipose tissue, which had the highest value in Sham group, noticeably reduced in S+MV group compared to it in S+V group. These results implied that the accumulation of abdominal adipose tissue can be effectively reduced through applying multi-frequency whole body vibration.

• The Journal of the Korea Contents Association
• /
• v.2 no.4
• /
• pp.23-29
• /
• 2002

This paper suggest the image compression that is needed to process PACS in medical information system. The image decoding method is used Linear-predictor and Lloyd-Max quantizer(quantization) in the Wavelet transform domain. Wavelet Transform Method is processed the multi-resolution by dividing image into 10 sub-bands of 3 levels. Low frequency domain that is sensitive to human visual characteristic is encoded by DPCM which is lossless encoding methods, and Lloyed-Max quantizer, the optimal quantizer for reducing ringing and aliasing in the image of inter sub-band, is used in the remaining high frequency domain of sub-band. The examination verifies that decompressed images are superior by the result that PSNR is 28.53dB on the input image, 512$\times$152 abdominal CT image and Chest image.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.103-111
• /
• 2020

Liver cancer is the most fatal cancer that occurs worldwide. In order to diagnose liver cancer, the patient's physical condition was checked by using a CT technique using radiation. Segmentation was needed to diagnose the liver on the patient's abdominal CT scan, which the radiologists had to do manually, which caused tremendous time and human mistakes. In order to automate, researchers attempted segmentation using image segmentation algorithms in computer vision field, but it was still time-consuming because of the interactive based and the setting value. To reduce time and to get more accurate segmentation, researchers have begun to attempt to segment the liver in CT images using CNNs, which show significant performance in various computer vision fields. The pixel value, or numerical value, of the CT image is called the Hounsfield Unit (HU) value, which is a relative representation of the transmittance of radiation, and usually ranges from about -2000 to 2000. In general, deep learning researchers reduce or limit this range and use it for training to remove noise and focus on the target organ. Here, we observed that the range of HU values was limited in many studies but different in various liver segmentation studies, and assumed that performance could vary depending on the HU range. In this paper, we propose the possibility of considering HU value range as a hyper parameter. U-Net and ResUNet were used to compare and experiment with different HU range limit preprocessing of CHAOS dataset under limited conditions. As a result, it was confirmed that the results are different depending on the HU range. This proves that the range limiting the HU value itself can be a hyper parameter, which means that there are HU ranges that can provide optimal performance for various models.

• Journal of the Korean Society of Radiology
• /
• v.83 no.5
• /
• pp.1182-1188
• /
• 2022

We call hemangiomatosis if hemangioma arises multifocally from single or multiple organs. It develops predominantly on liver, and there are just few cases of hemangiomatosis from greater omentum and mesentery. Herein, we present the imaging and histopathological findings including CT and MRI images of a 62-year-old male patient with a hemangiomatosis on liver, greater omentum and mesentery.

• Journal of radiological science and technology
• /
• v.38 no.2
• /
• pp.107-114
• /
• 2015

The purpose is reducing radiation dose while maintaining of image quality in liver dynamic CT(LDCT) scan, by protocols generally used and the tube voltage set at a low level protocol compared to the radiation dose and image quality. The target is body mass index, 18.5~24 patients out of 40 patients who underwent the ACT(abdominal CT). Group A(tube voltage : 120kVp, SAFIRE strength 1) of 20 people among 40 people, to apply the general abdominal CT scan protocol, group B(tube voltage : 100kVp, apply SAFIRE strength 0~5) was 20 people, set a lower tube voltage. Image quality evaluation was setting a region of interest(ROI) in the liver parenchyma, aorta, superior mesenteric artery (SMA), celiac trunk, visceral fat of arterial phase. In the ROI were compared by measuring the noise, signal to noise ratio(SNR), contrast to noise ratio(CNR), CT number. In addition, qualitative assessments to evaluate two people in the rich professional experience in Radiology by 0-3 points. We compared the total radiation dose, dose length product(DLP) and effective dose, volume computed tomography dose index(CTDIvol). The higher SAFIRE in the tube voltage 100 kVp, noise is reduced, CT number was increased. Thus, SNR and CNR was increased higher the SAFIRE step. Compared with the tube voltage 120kVp, noise, SNR, CNR was most similar in SAFIRE strength 2 and 3. Qualitative assessment SAFIRE strength 2 is the most common SAFIRE strength 2 the most common qualitative assessment, if the tube voltage of 100kVp when the quality of the images better evaluated was SAFIRE strength 1. Dose was reduced from 21.69%, in 100kVp than 120kVp. In the case of a relatively high BMI is not LDCT scan, When it is shipped from the factory tube voltage is set higher, unnecessary radiation exposure when considering the reality that is concerned, when according to the results of this study, set a lower tube voltage and adjust the SAFIRE strength to 1 or 2, the radiation without compromising image quality amount also is thought to be able to be reduced.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.187-201
• /
• 2024

Osteoporosis is a major health issue globally, often remaining undetected until a fracture occurs. To facilitate early detection, deep learning (DL) models were developed to classify osteoporosis using abdominal computed tomography (CT) scans. This study was conducted using retrospectively collected data from 3,012 contrast-enhanced abdominal CT scans. The DL models developed in this study were constructed for using image data, demographic/clinical information, and multi-modality data, respectively. Patients were categorized into the normal, osteopenia, and osteoporosis groups based on their T-scores, obtained from dual-energy X-ray absorptiometry, into normal, osteopenia, and osteoporosis groups. The models showed high accuracy and effectiveness, with the combined data model performing the best, achieving an area under the receiver operating characteristic curve of 0.94 and an accuracy of 0.80. The image-based model also performed well, while the demographic data model had lower accuracy and effectiveness. In addition, the DL model was interpreted by gradient-weighted class activation mapping (Grad-CAM) to highlight clinically relevant features in the images, revealing the femoral neck as a common site for fractures. The study shows that DL can accurately identify osteoporosis stages from clinical data, indicating the potential of abdominal CT scans in early osteoporosis detection and reducing fracture risks with prompt treatment.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.