• 한국멀티미디어학회논문지
• /
• 제17권3호
• /
• pp.342-352
• /
• 2014

본 논문에서는 마이크로 CT 영상에서 치밀뼈와 해면뼈의 자동 분할 방법을 제안하고 분할된 해면뼈의 형태학적 분석 방법의 구현에 대해 기술한다. 제안된 분할 방법에서는 임계값을 이용하여 뼈 영역을 추출한다. 그 다음에는, 뼈의 바깥 경계선부터 안쪽 방향으로 인접한 경계선을 찾아 치밀뼈 후보 영역을 설정한다. 치밀뼈 후보 영역들 중에서 평균 픽셀값이 최대가 되는 지점을 후보 영역을 탐색하여 치밀뼈를 제거한다. 분할된 해면뼈에 BV/TV, Tb.Th, Tb.Sp, Tb.N의 네 가지 형태학적 지표자들을 계산하는 방법을 VTK(Visualization ToolKit)와 구 정합 알고리즘을 이용하여 구현하였다. 구현된 방법을 쥐의 20개 대퇴골 근위부 영상에 적용하였으며 사람이 수작업으로 분할하는 방법과 비교 실험을 수행하였다. 실험 결과 네 가지 형태학적 지표자 모두 수작업으로 분할한 경우와 자동으로 분할한 경우 3% 이내의 평균 오차율을 보여 제안된 방법은 번거로운 수작업 분할 대신 사용될 수 있음을 알 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제28권6호
• /
• pp.713-720
• /
• 2007

In image-guided surgery, automatic bone segmentation of Computed Tomography (CT) images is an important but challenging step. Previous attempts include intensity-, edge-, region-, and deformable curve-based approaches [1], but none claims fully satisfactory performance. Although active contour (AC) techniques possess many excellent characteristics, their applications in CT image segmentation have not worthily exploited yet. In this study, we have evaluated the automaticity and performance of the model of Chan-Vese Multiphase AC Without Edges towards knee bone segmentation from CT images. This model is suitable because it is initialization-insensitive and topology-adaptive. Its segmentation results have been qualitatively compared with those from four other widely used AC models: namely Gradient Vector Flow (GVF) AC, Geometric AC, Geodesic AC, and GVF Fast Geometric AC. To quantitatively evaluate its performance, the results from a commercial software and a medical expert have been used. The evaluation results show that the Chan-Vese model provides superior performance with least user interaction, proving its suitability for automatic bone segmentation from CT images.

• 대한의용생체공학회:의공학회지
• /
• 제28권3호
• /
• pp.332-337
• /
• 2007

In the early twenty-first century, minimally invasive surgery is the mainstay of various kinds of surgical fields. Surgeons gave percutaneously surgical treatment of the screw directly using a fluoroscopic view in the past. The latest date, they began to operate the fractured carpal bone surgery using Computerized Tomography (CT). Carpal bones composed of wrist joint consist of eight small bones which have hexahedron and sponge shape. Because of these shape, it is difficult to grasp the shape of carpal bones using only CT image data. Although several image segmentation studies have been conducted with carpal bone CT image data, more studies about carpal bone using CT data are still required. Especially, to apply the software implemented from the studies to clinical fIeld, the outcomes should be user friendly and very accurate. To satisfy those conditions, we propose modified multi-seed region growing segmentation method which uses simple threshold and the canny edge detector for finding edge information more accurately. This method is able to use very easily and gives us high accuracy and high speed for extracting the edge information of carpal bones. Especially, using multi-seed points, multi-bone objects of the carpal bone are extracted simultaneously.

• 대한의용생체공학회:의공학회지
• /
• 제29권5호
• /
• pp.348-354
• /
• 2008

Segmenting vessels in lower extremity CT images is very difficult because of gray level variation, connection to bones, and their small sizes. Instead of segmenting vessels, we propose an approach that segments bones and subtracts them from the original CT images. The subtracted images can contain not only connected vessel structures but also isolated vessels, which are very difficult to detect using conventional vessel segmentation methods. The proposed method initially grows a 3-dimensional (3D) volume with a seeded region growing (SRG) using an adaptive threshold and then detects junctions and forked branches. The forked branches are classified into either bone branches or vessel branches based on appearance, shape, size change, and moving velocity of the branch. The final volume is re-grown by collecting connected bone branches. The algorithm has produced promising results for segmenting bone structures in several tens of vessel-enhanced CT image data sets of lower extremities.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(3)
• /
• pp.177-180
• /
• 2000

CT images are sequential images that provide medical doctors helpful information for treatment and surgical operation. It is also widely used for the 3D reconstruction of human bone and organs. In the 3D reconstruction, the quality of the reconstructed 3D model heavily depends on the segmentation results. In this paper, we propose an algorithm suitable for the segmentation of teeth and the maxilofacial bone.

• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.139-146
• /
• 2023

Osteoporosis is a disease in which the risk of bone fractures increases due to a decrease in bone density caused by aging. Osteoporosis is diagnosed by measuring bone density in the total hip, femoral neck, and lumbar spine. To accurately measure bone density in the lumbar spine, the vertebral region must be segmented from the lumbar X-ray image. Deep learning-based automatic spinal segmentation methods can provide fast and precise information about the vertebral region. In this study, we used 695 lumbar spine images as training and test datasets for a deep learning segmentation model. We proposed a lumbar automatic segmentation model, CM-Net, which combines the center point of the spine and the modified U-Net network. As a result, the average Dice Similarity Coefficient(DSC) was 0.974, precision was 0.916, recall was 0.906, accuracy was 0.998, and Area under the Precision-Recall Curve (AUPRC) was 0.912. This study demonstrates a high-performance automatic segmentation model for lumbar X-ray images, which overcomes noise such as spinal fractures and implants. Furthermore, we can perform accurate measurement of bone density on lumbar X-ray images using an automatic segmentation methodology for the spine, which can prevent the risk of compression fractures at an early stage and improve the accuracy and efficiency of osteoporosis diagnosis.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1407-1416
• /
• 2018

The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learning model for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice's similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice's similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.

• 방송공학회논문지
• /
• 제17권1호
• /
• pp.73-80
• /
• 2012

최근 의료 장비들이 발전하고 진단 및 연구에 다양하게 이용되면서 이로부터 얻은 3차원 의료 영상들을 자동으로 처리해주는 기술의 수요가 늘고 있다. 자동 뼈 영역화는 이러한 기술들 중 하나로써 골다공증이나 뼈 골절, 골격질환 등의 진단의 효율성을 크게 높여 줄 것으로 기대되고 있다. 현재까지 자동 뼈 영역화를 위한 연구들이 다양하게 진행되었지만 2차원 영상과는 달리 많은 데이터양과 주변 조직과의 모호한 경계들이 많다는 의료영상의 특성 때문에, 실제 진단에 사용할 수 있을만한 성능을 얻지 못하고 있다. 본 논문에서는 이와 같은 문제를 해결하기 위해 다중 해상도를 기반으로 하여 수행속도가 빠르고 영역화 성능이 좋은 자동 뼈 영역화 기법을 제안한다. 낮은 해상도 단계에서는 학습된 집합의 뼈 정보들을 바탕으로 최근 제안된 제한된 브랜치 앤 민컷 기법을 이용하여 대략적인 뼈 위치 및 비슷한 템플릿을 검출하고, 이후 해상도를 높여가면서 정합 과정과 영역화 과정을 반복적으로 수행한다. 제안하는 기법의 성능을 확인하기 위해 무릎 자기공명영상(magnetic resonance image)내에서 대퇴골(femur)과 경골(tibia)을 영역화 하는 실험을 진행하였으며, 100개의 학습 데이터들을 바탕으로 50개 영상에서 뼈들을 영역화 하였다. 제안하는 기법은 정확성 및 수행속도 측면에서 제한된 브랜치 앤 민컷에 비해 향상된 결과를 나타냈다.

• Imaging Science in Dentistry
• /
• 제45권1호
• /
• pp.7-13
• /
• 2015

Purpose: We have developed a new method of segmenting the areas of absorbable implants and bone using region-based segmentation of micro-computed tomography (micro-CT) images, which allowed us to quantify volumetric bone-implant contact (VBIC) and volumetric absorption (VA). Materials and Methods: The simple threshold technique generally used in micro-CT analysis cannot be used to segment the areas of absorbable implants and bone. Instead, a region-based segmentation method, a region-labeling method, and subsequent morphological operations were successively applied to micro-CT images. The three-dimensional VBIC and VA of the absorbable implant were then calculated over the entire volume of the implant. Two-dimensional (2D) bone-implant contact (BIC) and bone area (BA) were also measured based on the conventional histomorphometric method. Results: VA and VBIC increased significantly with as the healing period increased (p<0.05). VBIC values were significantly correlated with VA values (p<0.05) and with 2D BIC values (p<0.05). Conclusion: It is possible to quantify VBIC and VA for absorbable implants using micro-CT analysis using a region-based segmentation method.

• Journal of International Society for Simulation Surgery
• /
• 제2권2호
• /
• pp.67-70
• /
• 2015

We propose an automatic vessel segmentation method of vertebral arteries in CT angiography using combined circular and cylindrical model fitting. First, to generate multi-segmented volumes, whole volume is automatically divided into four segments by anatomical properties of bone structures along z-axis of head and neck. To define an optimal volume circumscribing vertebral arteries, anterior-posterior bounding and side boundaries are defined as initial extracted vessel region. Second, the initial vessel candidates are tracked using circular model fitting. Since boundaries of the vertebral arteries are ambiguous in case the arteries pass through the transverse foramen in the cervical vertebra, the circle model is extended along z-axis to cylinder model for considering additional vessel information of neighboring slices. Finally, the boundaries of the vertebral arteries are detected using graph-cut optimization. From the experiments, the proposed method provides accurate results without bone artifacts and eroded vessels in the cervical vertebra.