• 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
• /
• 제7권4호
• /
• pp.579-591
• /
• 2004

본 논문에서는 직선과 곡선으로 구성된 단순한 도면으로부터 곡선을 검출한 다음에 곡선을 원형 아크로 분할하는 방법을 제안한다. 본 논문의 방법에서는 먼저 선의 중심점을 찾은 다음에 연결된 중심점을 추적하여 선분을 검출한다. 그 다음에는 선분의 양 끝에서 선분의 방향을 이용하여 이웃한 선분을 검출하여 선분을 확장해 나간다. 선분을 확장한 다음에는 직선을 제거하고 곡선만 남긴 다음에 재귀적 분할 방법을 이용하여 곡선을 아크들의 집합으로 분할한다. 본 논문에서는 기존의 벡터화 소프트웨어와 벡터 기반 아크 분할 방법과 비교 실험을 수행하였다. 실험 결과에 의하면 본 논문에서 제안된 방법이 기존의 방법에 비하여 교차점을 가지는 곡선에 대하여 보다 정확하게 아크로 분할하였다.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• Investigative Magnetic Resonance Imaging
• /
• 제21권1호
• /
• pp.9-19
• /
• 2017

Background: Normalized cerebral blood volume (nCBV) can be measured using manual or semiautomatic segmentation method. However, the difference in diagnostic performance on brain tumor differentiation between differently measured nCBV has not been evaluated. Purpose: To compare the diagnostic performance of manually obtained nCBV to that of semiautomatically obtained nCBV on glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) differentiation. Materials and Methods: Histopathologically confirmed forty GBM and eleven PCNSL patients underwent 3T MR imaging with dynamic susceptibility contrast-enhanced perfusion MR imaging before any treatment or biopsy. Based on the contrast-enhanced T1-weighted imaging, the mean nCBV (mCBV) was measured using the manual method (manual mCBV), random regions of interest (ROIs) placement by the observer, or the semiautomatic segmentation method (semiautomatic mCBV). The volume of enhancing portion of the tumor was also measured during semiautomatic segmentation process. T-test, ROC curve analysis, Fisher's exact test and multivariate regression analysis were performed to compare the value and evaluate the diagnostic performance of each parameter. Results: GBM showed a higher enhancing volume (P = 0.0307), a higher manual mCBV (P = 0.018) and a higher semiautomatic mCBV (P = 0.0111) than that of the PCNSL. Semiautomatic mCBV had the highest value (0.815) for the area under the curve (AUC), however, the AUCs of the three parameters were not significantly different from each other. The semiautomatic mCBV was the best independent predictor for the GBM and PCNSL differential diagnosis according to the stepwise multiple regression analysis. Conclusion: We found that the semiautomatic mCBV could be a better predictor than the manual mCBV for the GBM and PCNSL differentiation. We believe that the semiautomatic segmentation method can contribute to the advancement of perfusion based brain tumor evaluation.

• 한국정보처리학회논문지
• /
• 제7권2호
• /
• pp.542-551
• /
• 2000

본 논문에서는 MR 영상의 3차원 가시화 및 분석을 위한 단일 채널 MR 영상의 자동 뇌영역 분할 방법을 제안한다. 이 방법은 4단계의 2차원 및 3차원 처리에 의하여 뇌윤곽을 찾아낸다. 1,2단계에서는 곡선 적합을 이용한 자동 문턱치화에 의하여 머리마스크와 초기 뇌마스크를 생성한다. 3단계에서 입방보간으로 초기 뇌마스크의 3차원 볼륨을 생성하여 형태학적 연산, 연결부위 레이블링에 의하여 중기 뇌마스크를 생성한다. 최종적으로 곡선 적합에 의한 자동 문턱치화를 이용하여 뇌마스크를 정련한다. 제안한 알고리즘은 영상의 슬라이스 방향을 고려할 필요가 없고 영상이 뇌 전체를 포함하지 않아도 되며, T1, T2, PD, SPGR등 다양한 종류의 MR 영상의 자동적인 뇌영역의 분할에 유용하다. 실험에서 20세트 MR 영상에 대하여 수동분할을 기준으로 0.97 이상의 유지도를 보였다.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.435-441
• /
• 2021

Objective: To evaluate the usefulness of the ventricular volume percentage quantified using three-dimensional (3D) brain computed tomography (CT) data for interpreting serial changes in hydrocephalus. Materials and Methods: Intracranial and ventricular volumes were quantified using the semiautomatic 3D threshold-based segmentation approach for 113 brain CT examinations (age at brain CT examination ≤ 18 years) in 38 patients with hydrocephalus. Changes in ventricular volume percentage were calculated using 75 serial brain CT pairs (time interval 173.6 ± 234.9 days) and compared with the conventional assessment of changes in hydrocephalus (increased, unchanged, or decreased). A cut-off value for the diagnosis of no change in hydrocephalus was calculated using receiver operating characteristic curve analysis. The reproducibility of the volumetric measurements was assessed using the intraclass correlation coefficient on a subset of 20 brain CT examinations. Results: Mean intracranial volume, ventricular volume, and ventricular volume percentage were 1284.6 ± 297.1 cm³, 249.0 ± 150.8 cm³, and 19.9 ± 12.8%, respectively. The volumetric measurements were highly reproducible (intraclass correlation coefficient = 1.0). Serial changes (0.8 ± 0.6%) in ventricular volume percentage in the unchanged group (n = 28) were significantly smaller than those in the increased and decreased groups (6.8 ± 4.3% and 5.6 ± 4.2%, respectively; p = 0.001 and p < 0.001, respectively; n = 11 and n = 36, respectively). The ventricular volume percentage was an excellent parameter for evaluating the degree of hydrocephalus (area under the receiver operating characteristic curve = 0.975; 95% confidence interval, 0.948-1.000; p < 0.001). With a cut-off value of 2.4%, the diagnosis of unchanged hydrocephalus could be made with 83.0% sensitivity and 100.0% specificity. Conclusion: The ventricular volume percentage quantified using 3D brain CT data is useful for interpreting serial changes in hydrocephalus.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.430-433
• /
• 1996

The shape of an object plays a very important role in pattern analysis and classification. Roughly, the researches on this topic can be classified into three fields, i.e. (i) edge detection, (ii) dominant points extraction, and (iii) shape recognition and classification. Many works have been done in these three fields. However, it is very seldom to see the research that discusses the connection relationship of objects. This problem is very important in robot assembly systems. Therefore, here we focus on this problem and discuss how to recover the connection relationship of planar objects. Our method is based on the partial curve identification algorithm. The experiment results show the efficiency and validity of this method.

• 전기전자학회논문지
• /
• 제11권4호
• /
• pp.307-314
• /
• 2007

In this paper, we propose an image contrast enhancement algorithm for an LCD TV. The proposed algorithm consists of two processes: the image segmentation process and the tone curve control process. The first process uses an automatic threshold technique to decompose an input image into two regions and then utilizes a hierarchical structure for real-time processing. The second process generates a gray level tone curve for contrast enhancement using a weighted sum of average tone curves for two segmented regions. Experimental result shows that the proposed algorithm outperforms the conventional contrast enhancement methods for an LCD TV.

• 융합신호처리학회논문지
• /
• 제1권1호
• /
• pp.23-31
• /
• 2000

본 논문에서는 물체의 경계나 형태 추출을 위하여 레벨 세트 이론을 바탕으로 한 새로운 곡선 전개방법을 제안한다. 특히 전처리 과정에서 잡음의 효과적 처리를 위하여 기존의 필터 방식들이 가지는 단점인 경계 부분의 bluning 현상을 줄이고 정확한 에지 위치를 보존할 수 있는 비등방성 확산 필터(anisotropic diffusion filter)를 사용한다. 기존의 레벨 세트 방식이 수축이나 팽창 중 단지 한가지의 방식만 적용되어지는 반면, 제안한 방법은 물체의 경계 추출시 팽창과 수축이 통시에 가능하므로 특히 초기 곡선이 여러 물체에 걸쳐져 있는 경우에도 정확한 형태 추출이 가능하였다. 아울러 초기 곡선의 설정이 위치나 형태에 거의 제한을 받지 않기 때문에 추출을 원하는 영역이 아주 조금만 포함되어 있어도 정화한 형태 추출이 가능하였다.

• 한국컴퓨터정보학회논문지
• /
• 제23권4호
• /
• pp.57-64
• /
• 2018

In this paper, we propose the automatic detection method for individual region separation using panorama image. Finding areas that contain individual teeth is one of the most important tasks in automating 3D models through individual tooth separation. In the conventional method, the maxillary and mandibular teeth regions are separated using a straight line or a specific CT slide, and the tooth regions are separated using a straight line in the vertical direction. In the conventional method, since the teeth are arranged in a curved shape, there is a problem that each tooth region is incorrectly detected in order to generate an accurate tooth region. This is a major obstacle to automating the creation of individual tooth models. In this study, we propose a method to find the correct tooth curve by using the jawbone curve which is very similar to the tooth curve in order to overcome the problem of finding the area containing the existing tooth. We have proposed a new method to accurately set individual tooth regions using the feature that individual teeth are arranged in a direction similar to the normal direction of the tooth alignment curve. In the proposed method, the maxillary and mandibular teeth can be more precisely separated than the conventional method, and the area including the individual teeth can be accurately set. Experiments using real dental CT images demonstrate the superiority of the proposed method.