• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1167-1187
• /
• 2020

With the development of medical imaging technology, image registration has been widely used in the field of disease diagnosis. The registration between different modal images of brain magnetic resonance (MR) is particularly important for the diagnosis of brain diseases. However, previous registration methods don't take advantage of the prior knowledge of bilateral brain symmetry. Moreover, the difference in gray scale information of different modal images increases the difficulty of registration. In this paper, a multimodal medical image registration method based on image segmentation and symmetric self-similarity is proposed. This method uses modal independent self-similar information and modal consistency information to register images. More particularly, we propose two novel symmetric self-similarity constraint operators to constrain the segmented medical images and convert each modal medical image into a unified modal for multimodal image registration. The experimental results show that the proposed method can effectively reduce the error rate of brain MR multimodal medical image registration with rotation and translation transformations (average 0.43mm and 0.60mm) respectively, whose accuracy is better compared to state-of-the-art image registration methods.

• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.693-701
• /
• 2011

Image registration is an essential process to analyze the time series of satellite images for the purpose of image fusion and change detection. The Mutual Information (MI) is commonly used as similarity measure for image registration because of its robustness to noise. Due to the radiometric differences, it is not easy to apply MI to multi-temporal satellite images using directly the pixel intensity. Image features for MI are more abundantly obtained by employing a Gabor filter which varies adaptively with the filter characteristics such as filter size, frequency and orientation for each pixel. In this paper we employed Bidirectional Gabor Filter Energy (BGFE) defined by Gabor filter features and applied the BGFE to similarity measure calculation as an image feature for MI. The experiment results show that the proposed method is more robust than the conventional MI method combined with intensity or gradient magnitude.

• 대한의용생체공학회:의공학회지
• /
• 제26권4호
• /
• pp.231-241
• /
• 2005

New methods to register multiple hemispheric slices of the postmortem brain to anatomically corresponding in-vivo MRI slices within a 3D volumetric MRI are presented. Gel-embedding and fiducial markers are used to reduce geometrical distortions in the postmortem brain volume. The registration algorithm relies on a recursive extraction of warped MRI slices from the reference MRI volume using a modified non-linear polynomial transformation until matching slices are found. Eight different voxel similarity measures are tested to get the best co-registration cost and the results show that combination of two different similarity measures shows the best performance. After validating the implementation and approach through simulation studies, the presented methods are applied to real data. The results demonstrate the feasibility and practicability of the presented co­registration methods, thus providing a means of MR signal analysis and histological examination of tissue lesions via co­registered images of postmortem brain slices and their corresponding MRI sections. With this approach, it is possible to investigate the pathology of a disease through both routinely acquired MRls and postmortem brain slices, thus improving the understanding of the pathological substrates and their progression.

• 한국지능시스템학회논문지
• /
• 제22권3호
• /
• pp.287-293
• /
• 2012

본 논문에서는 영상의 다차원 명암도 증감에 기반을 둔 유사도 측정에 의한 효율적인 영상정합 방법을 제안하였다. 여기서 다차원 명암도는 영상의 4방향을 고려한 유사성 판정으로 영상이 가지는 속성을 더욱 더 많이 반영하기 위함이고, 명암도 증감은 인접 픽셀간의 밝기변화를 고려함으로써 좀 더 포괄적으로 유사성을 측정하기 위함이다. 또한 측정된 4방향 각각의 명암도 증감에 대한 정규상호상관계수를 구하고, 그 각각에 바탕을 둔 전체 정규상호상관계수, 각 방향의 상관계수에 대한 산술평균과 단순 곱 및 최대값으로 정규화된 상관계수의 산술평균과 단순 곱으로 정의된 유사도 계수로 각각 정합을 측정하였다. 제안된 방법을 22개의 243*243 픽셀 얼굴영상과 9개의 500*500 픽셀 인물영상을 대상으로 각각 실험한 결과, 영상의 속성을 잘 반영한 우수한 정합성능이 있음을 확인하였다. 특히 각 방향의 상관계수에 대한 산술평균 유사도가 가장 우수한 신뢰성을 가지는 정합척도임을 알 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1960-1969
• /
• 2016

In this paper, we propose an automatic hierarchical organ segmentation method on abdominal CT images. First, similar atlases are selected using bone-based similarity registration and similarity of liver, kidney, and pancreas area. Second, each abdominal organ is roughly segmented using image-based similarity registration and intensity-based locally weighted voting. Finally, the segmented abdominal organ is refined using mask-based affine registration and intensity-based locally weighted voting. Especially, gallbladder and pancreas are hierarchically refined using location information of neighbor organs such as liver, left kidney and spleen. Our method was tested on a dataset of 12 portal-venous phase CT data. The average DSC of total organs was $90.47{\pm}1.70%$. Our method can be used for patient-specific abdominal organ segmentation for rehearsal of laparoscopic surgery.

• 한국차세대컴퓨팅학회논문지
• /
• 제15권5호
• /
• pp.64-74
• /
• 2019

비강체 정합은 임상적 필요성은 높으나 계산 복잡도가 높고, 정합의 정확성 및 강건성을 확보하기 어려운 분야이다. 본 논문은 비지도 학습 환경에서 3차원 뇌 자기공명 영상 데이터에 딥러닝 네트워크를 이용한 비강체 정합 기법을 제안한다. 서로 다른 환자의 두 영상을 입력받아 네트워크를 통하여 두 영상 간의 특징 벡터를 생성하고, 변위 벡터장을 만들어 기준 영상에 맞추어 다른 쪽 영상을 변형시킨다. 네트워크는 U-Net 형태를 기반으로 설계하여 정합 시 두 영상의 전역적, 지역적인 차이를 모두 고려한 특징 벡터를 만들 수 있고, 손실함수에 균일화 항을 추가하여 3차원 선형보간법 적용 후에 실제 뇌의 움직임과 유사한 변형 결과를 얻을 수 있다. 본 방법은 비지도 학습을 통해 임의의 두 영상만을 입력으로 받아 단일 패스 변형으로 비강체 정합을 수행한다. 이는 반복적인 최적화 과정을 거치는 비학습 기반의 정합 방법들보다 빠르게 수행할 수 있다. 실험은 50명의 뇌를 촬영한 3차원 자기공명 영상을 가지고 수행하였고, 정합 전·후의 Dice Similarity Coefficient 측정 결과 평균 0.690으로 정합 전과 비교하여 약 16% 정도의 유사도 향상을 확인하였다. 또한, 비학습 기반 방법과 비교하여 유사한 성능을 보여주면서 약 10,000배 정도의 속도 향상을 보여주었다. 제안 기법은 다양한 종류의 의료 영상 데이터의 비강체 정합에 활용이 가능하다.

• Radiation Oncology Journal
• /
• 제35권2호
• /
• pp.101-111
• /
• 2017

The number of imaging data sets has significantly increased during radiation treatment after introducing a diverse range of advanced techniques into the field of radiation oncology. As a consequence, there have been many studies proposing meaningful applications of imaging data set use. These applications commonly require a method to align the data sets at a reference. Deformable image registration (DIR) is a process which satisfies this requirement by locally registering image data sets into a reference image set. DIR identifies the spatial correspondence in order to minimize the differences between two or among multiple sets of images. This article describes clinical applications, validation, and algorithms of DIR techniques. Applications of DIR in radiation treatment include dose accumulation, mathematical modeling, automatic segmentation, and functional imaging. Validation methods discussed are based on anatomical landmarks, physical phantoms, digital phantoms, and per application purpose. DIR algorithms are also briefly reviewed with respect to two algorithmic components: similarity index and deformation models.

• Journal of Computing Science and Engineering
• /
• 제6권1호
• /
• pp.1-11
• /
• 2012

Computed tomography (CT) images are widely used for the analysis of the temporal evaluation or monitoring of the progression of a disease. The follow-up examinations of CT scan images of the same patient require a 3D registration technique. In this paper, an automatic and robust registration is proposed for the rigid registration of 3D CT images. The proposed method involves two steps. Firstly, the two CT volumes are aligned based on their principal axes, and then, the alignment from the previous step is refined by the optimization of the similarity score of the image's voxel. Normalized cross correlation (NCC) is used as a similarity metric and a downhill simplex method is employed to find out the optimal score. The performance of the algorithm is evaluated on phantom images and knee synthetic CT images. By the extraction of the initial transformation parameters with principal axis of the binary volumes, the searching space to find out the parameters is reduced in the optimization step. Thus, the overall registration time is algorithmically decreased without the deterioration of the accuracy. The preliminary experimental results of the study demonstrate that the proposed method can be applied to rigid registration problems of real patient images.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권1호
• /
• pp.36-41
• /
• 2015

This paper is proposed a wavelet-based MCDT(Mask Coefficient Differential and Threshold) method of image registration of Multi-images contaminated with visible image and infrared image. The method for ensure reliability of the image registration is to the increase statistical corelation as getting the common feature points between two images. The method of threshold the wavelet coefficients using derivatives of the wavelet coefficients of the detail subbands was proposed to effectively registration images with distortion. And it can define that the edge map. Particularly, in order to increase statistical corelation the method of the normalized mutual information. as similarity measure common feature between two images was selected. The proposed method is totally verified by comparing with the several other multi-image and the proposed image registration.

• 대한원격탐사학회지
• /
• 제30권5호
• /
• pp.547-557
• /
• 2014

본 논문에서는 영상 등록을 위한 유사도 계산에 사용되는 원형 템플릿의 설계 방법을 제안한다. 원형 템플릿은 영상의 이동 및 회전 변환에 불변한 성질을 가지고 있어 기준 영상 및 관측 영상 사이에 이동 및 회전 변환이 존재하더라도 영상 등록 제어점을 정확하게 정합하는 장점이 있다. 기준 영상의 제어점을 중심으로 일정한 거리 이내에 다수의 원주를 구성하고 각 원주 위에 일정한 간격으로 위치하는 화소들로 이루어지는 원형 템플릿을 생성하고 이를 이차원 이산 극좌표 행렬(Discrete Polar Coordinate Matrix, DPCM)으로 구성한다. 관측 영상에서도 동일한 형태의 원형 템플릿을 생성하고 탐색 범위 내의 각 위치에서 관측 영상의 원형 템플릿을 0도에서 360도 범위 내에서 일정 각도 간격으로 회전시키면서 극좌표 행렬을 생성하고 기준 영상의 극좌표 행렬과의 유사도를 Mutual Information을 이용해서 계산한다. 탐색 범위 내의 각 위치와 회전 각도에 대한 Mutual Information이 최대가 되는 화소를 정합쌍으로 결정한다. 제안한 알고리즘은 서로 다른 두 시기에 촬영한 KOMPSAT-2 영상에 적용하여 영상의 회전 변화 조건하에서 우수한 정합 성능을 보임을 확인하였다.