• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.523-530
• /
• 2019

The purpose of this study was to obtain the K-edge images using a spectral CT system based on a photon-counting detector and implement the 3D fusion imaging using the conventional and spectral CT images. Also, we evaluated the clinical feasibility of the 3D fusion images though the quantitative analysis of image quality. A spectral CT system based on a CdTe photon-counting detector was used to obtain K-edge images. A pork phantom was manufactured with the six tubes including diluted iodine and gadolinium solutions. The K-edge images were obtained by the low-energy thresholds of 35 and 52 keV for iodine and gadolinium imaging with the X-ray spectrum, which was generated at a tube voltage of 100 kVp with a tube current of $500{\mu}A$. We implemented 3D fusion imaging by combining the iodine and gadolinium K-edge images with the conventional CT images. The results showed that the CNRs of the 3D fusion images were 6.76-14.9 times higher than those of the conventional CT images. Also, the 3D fusion images was able to provide the maps of target materials. Therefore, the technique proposed in this study can improve the quality of CT images and the diagnostic efficiency through the additional information of target materials.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.6
• /
• pp.42-48
• /
• 2007

In x-ray imaging system, two kinds of noises are involved. First, the charge generated from the radiation interaction with the detector during exposure. Second, the signal is then added by readout electronics noise. But, x-ray images are not modeled by Gaussian noise but as the realization of a Poisson process. In this paper, we apply a new approach to remove Poisson noise from medical X-ray image in the wavelet domain, the applied methods shows more excellent results in cone-beam CT.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.72-74
• /
• 1997

We have developed a 3-D image processing and display technique that include image resampling, modification of MIP, and fusion of MIP image and volumetric rendered image. This technique facilitates the visualization of the three-dimensional spatial relationship between vasculature and surrounding organs by overlapping the MIP image on the volumetric rendered image of the organ. We applied this technique to a MR brain image data to produce an MRI angiogram that is overlapped with 3-D volume rendered image of brain. MIP technique was used to visualize the vasculature of brain, and volume rendering was used to visualize the other structures of brain. The two images are fused after adjustment of contrast and brightness levels of each image in such a way that both the vasculature and brain structure are well visualized either by selecting the maximum value of each image or by assigning different color table to each image. The resultant image with this technique visualizes both the brain structure and vasculature simultaneously, allowing the physicians to inspect their relationship more easily. The presented technique will be useful for surgical planning for neurosurgery.

• Journal of Biomedical Engineering Research
• /
• v.26 no.5
• /
• pp.283-294
• /
• 2005

The Center for Imaging Human Structures (CIH) was established in December 2002 to develop new diagnostic imaging techniques and to make them available to the greater community of biomedical and clinical researchers at Sungkyunkwan University. CIH has been involved in 5 specific activities to provide solutions for early diagnosis and improved treatment of human diseases. The five area goals include: 1) development of a digital mammography system with computer aided diagnosis (CAD); 2) development of digital radiological imaging techniques; 3) development of unified medical solutions using 3D image fusion; 4) development of multi-purpose digital endoscopy; and, 5) evaluation of new imaging systems for clinical application

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• Journal of Magnetics
• /
• v.18 no.2
• /
• pp.142-149
• /
• 2013

We aim to monitor vascularization of early bone perfusion following rabbit lumbar intertransverse bone graft fusion surgery using magnetic resonance imaging assessment. Correlation with graft survival status was evaluated by histological method. Experimental animals were randomly divided into three groups and the model was established by operating bilateral lumbar intertransverse bone graft with different types of bone graft substitute material. The lumbar intertransverse area of three groups of rabbits was scanned via MRI. In addition, histological examinations were performed at the $6^{th}$ week after surgery and the quantitative analysis of the osteogenesis in different grafted area was carried out by an image analysis system. The MRI technique can be used for early postoperative evaluation of vascularized bone graft perfusion after transplantation of different bone materials, whereas histological examination allows direct visualization of the osteogenesis process.

• Journal of Computing Science and Engineering
• /
• v.4 no.4
• /
• pp.368-387
• /
• 2010

We propose a novel method for the registration of 3D CT scans to 2D endoscopic images during the image-guided medialization laryngoplasty. This study aims to allow the surgeon to find the precise configuration of the implant and place it into the desired location by employing accurate registration methods of the 3D CT data to intra-operative patient and interactive visualization tools for the registered images. In this study, the proposed registration methods enable the surgeon to compare the outcome of the procedure to the pre-planned shape by matching the vocal folds in the CT rendered images to the endoscopic images. The 3D image fusion provides an interactive and intuitive guidance for surgeon by visualizing a combined and correlated relationship of the multiple imaging modalities. The 3D Magic Lens helps to effectively visualize laryngeal anatomical structures by applying different transparencies and transfer functions to the region of interest. The preliminary results of the study demonstrated that the proposed method can be readily extended for image-guided surgery of real patients.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.450-453
• /
• 2002

In radiotherapy treatment planning, it is critical to deliver the radiation dose to tumor and protect surrounding normal tissue. Recent developments in functional imaging and radiotherapy treatment technology have been raising chances to control tumor saving normal tissues. A brain phantom which could be used for image registration technique of CT-MR and CT-SPECT images using surface matching was developed. The brain phantom was specially designed to obtain imaging dataset of CT, MR, and SPECT. The phantom had an external frame with 4 N-shaped pipes filled with acryl rods, Pb rods for CT, MR, and SPECT imaging, respectively. 8 acrylic pipes were inserted into the empty space of the brain phantom to be imaged for geometric evaluation of the matching. For an optimization algorithm of image registration, we used Downhill simplex algorithm suggested as a fast surface matching algorithm. Accuracy of image fusion was assessed by the comparison between the center points of the section of N-shaped bars in the external frame and the inserted pipes of the phantom and minimized cost functions of the optimization algorithm. Technique with partially transparent, mixed images using color on gray was used for visual assessment of the image registration process. The errors of image registration of CT-MR and CT-SPECT were within 2mm and 4mm, respectively. Since these errors were considered within a reasonable margin from the phantom study, the phantom is expected to be used for conventional image registration between multimodal image datasets..

• Journal of the Korean Society of Radiology
• /
• v.12 no.5
• /
• pp.549-555
• /
• 2018

The medical imaging technique images the contrast formed based on the difference in absorption coefficient of X-rays which changes according to the composition and thickness of the object. At this time, not only primary rays entering the image detector but also scattered rays greatly affect the image quality. Therefore, in this paper, Forward scattering rate and Scattered to primary ratio analysis were performed through Monte Carlo simulation in order to consider influence of scattered ray generated according to object thickness and radiation exposure area change on image quality. In the study, the Forward scattering rate corresponding to the thickness of the object was analyzed at a maximum of 15.3%p and the Scattered to primary ratio was analyzed at 2.00 to 4.54, but it was analyzed as maintaining a constant value for radiation exposure area change. Based on these results, the thickness of the object should be considered as a factor influencing the quality of the image, but radiation exposure area verified that it is a factor that does not affect the image quality. We believe that the results of this research can be utilized as basic information of scattered radiation to improve image quality.