• Journal of KIISE
• /
• v.43 no.8
• /
• pp.869-877
• /
• 2016

In this paper, we propose an automated segmentation method of femoral cartilage in knee MR images using multi-atlas-based locally-weighted voting. The proposed method involves two steps. First, to utilize the shape information to show that the femoral cartilage is attached to a femur, the femur is segmented via volume and object-based locally-weighted voting and narrow-band region growing. Second, the object-based affine transformation of the femur is applied to the registration of femoral cartilage, and the femoral cartilage is segmented via multi-atlas shape-based locally-weighted voting. To evaluate the performance of the proposed method, we compared the segmentation results of majority voting method, intensity-based locally-weighted voting method, and the proposed method with manual segmentation results defined by expert. In our experimental results, the newly proposed method avoids a leakage into the neighboring regions having similar intensity of femoral cartilage, and shows improved segmentation accuracy.

• Korean Journal of Computational Design and Engineering
• /
• v.16 no.6
• /
• pp.458-466
• /
• 2011

The morphology of a bone is closely associated with its biomechanical response. Thus, much research has been focused on analyzing the effects of variation of bone morphology with subject-specific models. Subject-specific models, which are generally achieved from 3D imaging devices like CT and MRI, incorporate more of the detailed information that makes a model unique. Hence, it may predict individual responses more accurately. Despite these powerful characteristics, specific models are not easily parameterized to the extent possible with statistical models because of their morphologic complexities. Thus, it is still proven challenging to analyze morphologic variations of subject-specific models across changes due to aging or disease. The aim of this article is to propose a generic and robust parametric morphing method for a subject-specific bone structure. We demonstrate this by using the proposed method on a model of a human proximal femur. Automatic segmentation algorithms are also presented to parameterize the specific model efficiently. A total of 48 femur models were evaluated for defining morphing vector fields. Also, several anatomical and mechanical functions of femur were considered as morphing constraints, and the NURBS interpolating technique was applied in the method to guarantee the generality of our morphed results.

• Journal of Broadcast Engineering
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2012

Recently, medical equipments are developed and used for diagnosis or studies. In addition, demand of techniques which automatically deal with three dimensional medical images obtained from the medical equipments is growing. One of the techniques is automatic bone segmentation which is expected to enhance the diagnosis efficiency of osteoporosis, fracture, and other bone diseases. Although various researches have been proposed to solve it, they are unable to be used in practice since a size of the medical data is large and there are many low contrast boundaries with other tissues. In this paper, we present a fast and accurate automatic framework for bone segmentation based on multi-resolutions. On a low resolution step, a position of the bone is roughly detected using constrained branch and mincut which find the optimal template from the training set. Then, the segmentation and the registration are iteratively conducted on the multiple resolutions. To evaluate the performance of the proposed method, we make an experiment with femur and tibia from 50 test knee magnetic resonance images using 100 training set. The proposed method outperformed the constrained branch and mincut in aspect of segmentation accuracy and implementation time.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• Journal of Korea Multimedia Society
• /
• v.17 no.3
• /
• pp.342-352
• /
• 2014

This paper proposes an automatic segmentation method of cortical bone and trabecular bone and describes an implementation of structural analysis method of trabecular bone in micro-CT images. The proposed segmentation method extract bone region with binarization using a threshold value. Next, it finds adjacent contour lines from outer boundary line into inward direction and sets candidate regions of cortical bone. Next it remove cortical bone region by finding the candidate cortical region of which the average pixel value is maximum. We implemented the method which computes four structural indicators BV/TV, Tb.Th, Tb.Sp, Tb.N by using VTK(Visualization ToolKit) and sphere fitting algorithm. We applied the implemented method to twenty proximal femur of mouses and compared with the manual segmentation method. Experimental result shows that the average error rates between the proposed segmentation method and the manual segmentation method are less than 3% for the four structural indicatiors. This result means that the proposed method can be used instead of the combersome and time consuming manual segmentation method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.439-440
• /
• 2011

최근 의료 장비들이 발전하고 진단 및 연구에 다양하게 이용되면서 이로부터 얻은 3차원 의료 영상들을 자동으로 처리해주는 기술의 수요가 늘고 있다. 자동 뼈 영역화 기법은 이러한 기술들 중 하나로써 골다공증이나 뼈 골절, 골격질환 등의 진단의 효율성을 크게 높여줄 것으로 기대되고 있다. 그러나 현재까지 이를 위한 다양한 연구들이 진행되었음에도 2차원 영상과는 달리 높은 데이터양과 주변 조직과의 모호한 경계들이 많다는 어려움 때문에 실제 진단에는 사용되지 못하고 있다. 이에 따라 본 논문에서는 다중 해상도를 기반으로 하여 영역화와 정합기법을 반복적으로 수행함으로써 3차원 의료 영상 내에서 자동으로 뼈를 영역화 해내는 기법을 제안한다. 낮은 해상도 단계에서 학습된 집합의 뼈 정보들을 이용하여 대략적인 뼈 위치를 검출하고, 이후 해상도를 높여가면서 정합 과정과 영역화 과정을 반복적으로 수행한다. 성능을 확인하기 위해 무릎 자기공명영상(magnetic resonance image)내에서 대퇴골(femur)과 경골(tibia)을 영역화 하는 실험을 진행하였으며 60개의 학습 데이터들을 바탕으로 40개 영상에서의 뼈들을 영역화 하였다.