• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권2호
• /
• pp.102-110
• /
• 2015

The main source of noise in computed tomography (CT) images is a quantum noise, which results from statistical fluctuations of X-ray quanta reaching the detector. This paper proposes a neural network (NN) based hybrid filter for removing quantum noise. The proposed filter consists of bilateral filters (BFs), a single or multiple neural edge enhancer(s) (NEE), and a neural filter (NF) to combine them. The BFs take into account the difference in value from the neighbors, to preserve edges while smoothing. The NEE is used to clearly enhance the desired edges from noisy images. The NF acts like a fusion operator, and attempts to construct an enhanced output image. Several measurements are used to evaluate the image quality, like the root mean square error (RMSE), the improvement in signal to noise ratio (ISNR), the standard deviation ratio (MSR), and the contrast to noise ratio (CNR). Also, the modulation transfer function (MTF) is used as a means of determining how well the edge structure is preserved. In terms of all those measurements and means, the proposed filter shows better performance than the guided filter, and the nonlocal means (NLM) filter. In addition, there is no severe restriction to select the number of inputs for the fusion operator differently from the neuro-fuzzy system. Therefore, without concerning too much about the filter selection for fusion, one could apply the proposed hybrid filter to various images with different modalities, once the corresponding noise characteristics are explored.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제34권5호
• /
• pp.555-561
• /
• 2008

Purpose: The goal of this study was to develop a technique for creating a computerized composite maxillofacial-dental model, based on point-based surface best fit algorithm and to test its accuracy. The computerized composite maxillofacial-dental model was made by the three dimensional combination of a 3-dimensional (3D) computed tomography (CT) bone model with digital dental model. Materials and Methods: This integration procedure mainly consists of following steps : 1) a reconstruction of a virtual skull and digital dental model from CT and laser scanned dental model ; 2) an incorporation of dental model into virtual maxillofacial-dental model by point-based surface best fit algorithm; 3) an assessment of the accuracy of incorporation. To test this system, CTs and dental models from 3 volunteers with cranio-maxillofacial deformities were obtained. And the registration accuracy was determined by the root mean squared distance between the corresponding reference points in a set of 2 images. Results and Conclusions: Fusion error for the maxillofacial 3D CT model with the digital dental model ranged between 0.1 and 0.3 mm with mean of 0.2 mm. The range of errors were similar to those reported elsewhere with the fiducial markers. So this study confirmed the feasibility and accuracy of combining digital dental model and 3D CT maxillofacial model. And this technique seemed to be easier for us that its clinical applicability can good in the field of digital cranio-maxillofacial surgery.

• 핵의학기술
• /
• 제14권2호
• /
• pp.166-171
• /
• 2010

SPECT/CT는 SPECT의 기능학적 영상과 CT의 해부학적인 영상의 융합(Fusion)을 통하여 기존의 SPECT에서 병소의 위치 및 범위를 감별하는데 어려웠던 문제들을 해결하여 진단적 정보에 도움을 줄수 있다. Infinia Hawkeye 4 (GE Healthcare)의 SPECT/CT 감마카메라 영상과 진단용 CT영상을 융합(Fusion)하여 3D (three Dimension)로 Rendering 할 수 있는 Volumetrix Suite의 유용성을 소개하고자 한다. 본원에 SPECT/CT 검사를 하기 위해 내원한 환자 중, 동일한 검사부위의 진단용 CT영상이 있는 환자(Bone, Venography, Parathyroid, WBC)를 대상으로 Volumetrix Suite (Volumetrix IR, Volumetrix 3D)를 적용하였다. Infinia Hawkeye 4의 SPECT영상과 CT영상을 획득한 후 두 영상을 2D (two Dimension)로 융합(Fusion)하였다. Infinia Hawkeye4 SPECT/CT에서의 CT는 해부학적 정보에 한계가 있어, 3D (three Dimension) Rendering을 하기 위해서는 정보량이 많은 진단용 CT영상을 PACS상에서 DICOM (Digital Imaging and Communications in Medicine) File로 전송하여 Infinia Hawkeye4의 Xeleris Workstation에서 IR (Image Registration)한 후 Intergrating 3D (three Dimension)로 융합(Fusion)하여 2D(two Dimension)영상을 3D (three Dimension)영상으로 Rendering하였다. Volumetrix Suite program을 이용함으로써 Infinia Hawkeye 4의 SPECT/CT 영상과 별도로 촬영한 고해상도 진단용 CT영상을 3D Rendering하여 병소의 위치 및 범위를 감별하는데 좀 더 명확한 해부학적 정보를 얻을 수 있었다. 따라서, 해부학적인 정보가 부족한 핵의학영상을 보완함으로서 더 많은 정보를 제공해 핵의학영상 검사의 진단능력을 향상시킬 수 있을 것이라고 기대된다.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제36권5호
• /
• pp.402-407
• /
• 2010

Introduction: The planning of implant surgery is an important factor for the implant prosthesis. Stereolithographic (SLA) surgical stents based on a computer simulation are quite helpful for clinicians to perform the surgery as planned. Although many clinical and technical trials have been performed for computed tomography (CT)-guided implant stents to improve the surgical procedures and prosthetic treatment, there are still many problems to solve. We developed a system of a surgical guide based on 3 dimensional (3D) CT for implant therapy and achieved satisfactory results in the terms of planning and operation. Materials and Methods: Fifteen patients were selected and 30 implant fixtures were installed. The preoperative CT data for surgical planning were prepared after obtaining informed consent. Surgical planning was performed using the simulation program, Ondemend3D In2Guide. The stents were fabricated based on the simulation data containing information of the residual bone, the location of the nerve, and the expected design of the prostheses. After surgery with these customized stents, the accuracy and reproducibility of implant surgery were evaluated based on the computer simulation. The data of postoperative CT were used to confirm this system using the image fusion technique and compare the implant fixtures between the planned and implanted. Results: The mean error was 1.18 (${\pm}0.73$) mm at the occlusal center, 1.23 (${\pm}0.67$) mm at the apical center, and the axis error between the two fixtures was $3.25^{\circ}C$ (${\pm}3.00$). These stents showed superior accuracy in maxilla cases. The lateral side error at the apical center was significantly different from the error at the occlusal center but there were no significant differences between the premolars, 1st molars and 2nd molars. Conclusion: SLA surgical stents based on a computer simulation have the satisfactory accuracy and are expected to be useful for accurate planning and surgery if some errors can be improved.

• Journal of Korean Neurosurgical Society
• /
• 제59권2호
• /
• pp.129-136
• /
• 2016

Objective : The purpose of this study was to figure out the radiologic findings and risk factors related to adjacent segment degeneration (ASD) after anterior cervical discectomy and fusion (ACDF) using 3-year follow-up radiography, computed tomography (CT), and magnetic resonance image (MRI). Methods : A retrospective matched comparative study was performed for 64 patients who underwent single-level ACDF with a cage and plate. Radiologic parameters, including upper segment range of motion (USROM), lower segment range of motion (LSROM), upper segment disc height (UDH), and lower segment disc height (LDH), clinical outcomes assessed with neck and arm visual analogue scale (VAS), and risk factors were analyzed. Results : Patients were categorized into the ASD (32 patients) and non-ASD (32 patients) group. The decrease of UDH was significantly greater in the ASD group at each follow-up visit. At 36 months postoperatively, the difference for USROM value from the preoperative one significantly increased in the ASD group than non-ASD group. Preoperative other segment degeneration was significantly associated with the increased incidence of ASD at 36 months. However, pain intensity for the neck and arm was not significantly different between groups at any post-operative follow-up visit. Conclusion : The main factor affecting ASD is preoperative other segment degeneration out of the adjacent segment. In addition, patients over the age of 50 are at higher risk of developing ASD. Although there was definite radiologic degeneration in the ASD group, no significant difference was observed between the ASD and non-ASD groups in terms of the incidence of symptomatic disease.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• 대한의용생체공학회:의공학회지
• /
• 제31권5호
• /
• pp.335-343
• /
• 2010

This article presents a review of technologies for an endoscope. The classification according to the clinical applications and the imaging modalities are summarized. The major parts are focused on describing the gastrointestinal endoscope's structures and mechanisms. The details of the image enhanced endoscopic techniques, such as NBI (narrow band imaging), OCT (optical coherence tomography), and EUS (endoscopic ultrasound), are also explained. Finally, the trend of NOTES (natural orifice transluminal endoscopic surgery) which is new fusion technology in the field of endoscopic diagnosis and surgery is introduced.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1996년도 추계학술대회
• /
• pp.301-303
• /
• 1996

A platform is developed for fast and effective functional mapping of human brain, which can allow semi-automatically the whole processes of an image segmentation, a fusion of MR and PET images, and 3-D rendering of volumetric data, including DICOM-based image transfers from PACS archiver within a short period of time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• 한국의학물리학회지:의학물리
• /
• 제14권1호
• /
• pp.34-42
• /
• 2003

World Wide Web (WWW)에서 Virtual Reality Modeling Language (VRML)를 이용하는 3차원 (3D) 디스플레이는 사용자에게 직관적인 정보를 더 효과적으로 제공해 준다. 웹을 기반으로 하는 해부학적 영상과 융합되는 기능적 영상의 3D 가시화는 아직까지 체계적인 방식으로 연구가 활발히 진행되지 않았다. 이 연구의 목적은 2D 영상들과 함께 웹에서 VRML을 이용하여 구현되는 3D 해부학적 표면 영상들과 기능적 표면 영상들을 동시적으로 관찰할 수 있게 하고 VRML을 통해 만들어진 거리 측정 도구를 가지고 관심영역의 공간적인 위치 정보를 제공하는 것이다. 본 연구에서는 한 명의 간질 환자로부터 Magnetic Resonance (MR) 축면 영상과 발작기 및 발작간기 Single Photon Emission Computed Tomography (SPECT) 축면 영상들을 각각 획득하였다. 발작 진원지의 확인을 향상시키기 위해서 subtractionictal SPECT coregistered to MRI (SISCOM)을 수행하였다 SISCOM 결과로 나타난 각 2D 영상들은 모든 voxel들의 평균값 위로 1-표준편차와 2-표준편차에 해당하는 문턱 이상의 영상 값을 갖도록 하였다. SISCOM으로 나타나는 간질 발작 진원지들과 MRI 영상에서 회색질, 백색질 및 뇌척수액의 경계들을 각각 분할하고 marching cube 알고리즘에 의해 VRML 표면 영상들로 나타내었다. 축면 영상에서 실제 거리를 나타내는 x, y축의 길이를 획득하고 z축선의 길이를 계산하였다. VRML을 이용한 거리 측정도구를 만들어 이전의 VRML 표면 영상들과 융합하였다. MRI 영상을 이용하여 3D 표면 영상들의 단면을 나타내고 3D 표면 영상들의 투명도를 설정하기 위해 Java Script 루틴을 사용자 인터페이스 도구로서 삽입하였다 웹 페이지에서 구현되는 3D 표면 영상들의 투명도와 관찰 위치를 조절함에 따라 모델들 사이의 공간적인 정보를 직관적으로 알 수 있었다. 간질 발작 진원지에 대응하는 해부학적 구조를 3D 표면 영상들을 가로지르는 MRI 평면 영상들을 통해서 확인하였다 간질 발작 진원지는 뇌의 오른쪽 측두엽에서 나타났고 공간적으로 발작 진원지의 실제 위치를 VRML 거리 측정 도구에 의해 알 수 있었다. 결론적으로 본 연구에서 제시하는 웹에 근거한 3D 융합 영상의 가시화와 위치 측정은 진단 및 치료 방사선학과 외과학 등의 분야에서 온라인 방식의 연구와 교육에 있어 많은 도움을 줄 것이다.