• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2458-2482
• /
• 2023

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, MultiHead Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

• 한국의학물리학회지:의학물리
• /
• 제15권2호
• /
• pp.112-119
• /
• 2004

인체에 대한 표준데이터를 사용하지 않고 실제 한국인의 의료 영상 데이터를 사용하여 인체 모델을 만들고자 하였다. 먼저 CT와 MRI를 통해 획득한 인체의 의료영상에 대한 특징을 분석하였다. 인체의 해부학적인 구성요소에 대해 CT는 gray level로 MR 영상은 펄스시퀀스 별로 분석하여 특징을 추출하였다. 해부학적 구성요소의 특징을 바탕으로 인체 각 부위별로 영상을 얻기 위해 CT와 MR 영상에 대해 영상분할을 수행하였다. 인체의 부위 중 특히 인체의 네 가지 인체 역학적 구조물인 골조직, 근육, 인대, 건 부위를 CT와 MR 영상을 이용하여 구별하였다. 이미지 분할 방법에는 일반적으로 많이 사용되고 있는 경계선 검출(Edge detection), 영역 선택(Region Growing), 문턱치(Intensity Threshold) 방법 등을 선택하여 인체별로 가장 적합한 알고리듬을 적용시켰다. Head/Neck 부위에 대한 영상 분할 결과를 인체 역학적 구성요소별로 3차원 영상으로 재구성하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.269-274
• /
• 2023

In this paper, we proposed a new UNet 3+ model for medical image segmentation. The proposed ensemble(E) UNet 3+ model consists of UNet 3+s of varying depths into one unified architecture. UNet 3+s of varying depths have same encoder, but have their own decoders. They can bridge semantic gap between encoder and decoder nodes of UNet 3+. Deep supervision was used for learning on a total of 8 nodes of the E-UNet 3+ to improve performance. The proposed E-UNet 3+ model shows better segmentation results than those of the UNet 3+. As a result of the simulation, the E-UNet 3+ model using deep supervision was the best with loss function values of 0.8904 and 0.8562 for training and validation data. For the test data, the UNet 3+ model using deep supervision was the best with a value of 0.7406. Qualitative comparison of the simulation results shows the results of the proposed model are better than those of existing UNet 3+.

• 응용통계연구
• /
• 제24권2호
• /
• pp.335-345
• /
• 2011

본 논문에서는 레벨 셋 방법을 이용하여 영상분할을 수행하는데 필요한 새로운 하이브리드 속도함수를 제안한다. 새롭게 제안하는 속도함수는 정확한 분할 결과를 위하여 영상의 객체가 가지고 있는 영역정보와 윤곽선정보를 함께 이용한다. 영역정보는 관심이 있는 물체영상내의 픽셀들의 밝기에 대한 확률분포의 정보를 이용하였고, 윤곽선정보는 영상의 에지의 기울기로부터 주어지는 기울기 벡터장을 이용하였다. 제안된 방법을 이용한 분할결과의 정확성을 확인하기 위하여 가상영상과 실제 사용되는 의료영상에 대하여 다양한 실험을 실시하고, 분할된 결과를 통하여 제안된 방법의 우수성을 입증하였다.

• Journal of International Society for Simulation Surgery
• /
• 제4권1호
• /
• pp.21-23
• /
• 2017

Purpose In this paper, we proposed alternate neighborhood system and reverse spread-direction approach for accurate and fast cellular automata-based image segmentation method. Materials and Methods On the basis of a simple but effective interactive image segmentation technique based on a cellular automaton, we propose an efficient algorithm by using Moore and designed neighborhood system alternately and reversing the direction of the reference pixels for spreading out to the surrounding pixels. Results In our experiments, the GrabCut database were used for evaluation. According to our experimental results, the proposed method allows cellular automata-based image segmentation method to faster while maintaining the segmentation quality. Conclusion Our results proved that proposed method improved accuracy and reduced computation time, and also could be applied to a large range of applications.

• 한국산업융합학회 논문집
• /
• 제27권3호
• /
• pp.563-572
• /
• 2024

Image processing and computer vision technologies are becoming increasingly important in a variety of application fields that require techniques and tools for sophisticated image analysis. In particular, image segmentation is a technology that plays an important role in image analysis. In this study, in order to identify recent research trends on image segmentation techniques, we used the Web of Science(WoS) database to analyze the R&D topography based on the network structure of the author's keyword co-occurrence matrix. As a result, from 2015 to 2023, as a result of the analysis of the R&D map of research articles on image segmentation, R&D in this field is largely focused on four areas of research and development: (1) researches on collecting and preprocessing image data to build higher-performance image segmentation models, (2) the researches on image segmentation using statistics-based models or machine learning algorithms, (3) the researches on image segmentation for medical image analysis, and (4) deep learning-based image segmentation-related R&D. The scientometrics-based analysis performed in this study can not only map the trajectory of R&D related to image segmentation, but can also serve as a marker for future exploration in this dynamic field.

• 대한의용생체공학회:의공학회지
• /
• 제20권3호
• /
• pp.283-290
• /
• 1999

Mr(Magnetic Resonance ) 영상은 인체 기관의 상태에 관한 많은 정보를 가지고 있어 이것을 분석하여 가시화하면 의료 진단에 유용하게 이용될 수 있다. MR 영상의 가시화는 영상의 획득, 전처리, 조직 분류, 보간, 렌더링의 단계로 이루어진다. 이 단계 중 Mr 영상의 불완전성 때문에 현재 조직 분류 및 보간이 문제로 되어 있다. 본 논문에서는 머리 MR 영상을 대상으로 조직 분류 및 보간에 대한 기법을 제안하고 제안된 기법을 바탕으로 뇌를 3차원 가시화한다. 조직 분류 기법에서는 뇌조직 성분 구성 등 임상 실험에 의해 밝혀진 뇌에 대한 구조적인 지식을 단계적으로 이용한다. 보간 기법은 오목 윤곽선에 사용할 수 있게 동적 탄성 보간기법을 개선하였다. 제안한 구조적인 분류 기법 및 보간 기법을 다른 기법과 비교 평가한다.

• Journal of International Society for Simulation Surgery
• /
• 제1권1호
• /
• pp.27-31
• /
• 2014

In this paper, an overview of segmentation and 3D visualization methods are presented. Commonly, the two kinds of methods are used to visualize organs and vessels into 3D from medical images such as CT(A) and MRI - Direct Volume Rendering (DVR) and Iso-surface Rendering (IR). DVR can be applied directly to a volume. It directly penetrates through the volume while it determines which voxels are visualizedbased on a transfer function. On the other hand, IR requires a series of processes such as segmentation, polygonization and visualization. To extract a region of interest (ROI) from the medical volume image via the segmentation, some regions of an object and a background are required, which are typically obtained from the user. To visualize the extracted regions, the boundary points of the regions should be polygonized. In other words, the boundary surface composed of polygons such as a triangle and a rectangle should be required to visualize the regions into 3D because illumination effects, which makes the object shaded and seen in 3D, cannot be applied directly to the points.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.661-669
• /
• 2022

The purpose of this study is to compare and analyze Deep Learning (DL) and Digital Image Processing (DIP) techniques using the results of the glottis segmentation of the two methods followed by the quantification of the asymmetric degree of the vocal cord mucosa. The data consists of 40 normal and abnormal images. The DL model is based on Deeplab V3 architecture, and the Canny edge detector algorithm and morphological operations are used for the DIP technique. According to the segmentation results, the average accuracy of the DL model and the DIP was 97.5% and 94.7% respectively. The quantification results showed high correlation coefficients for both the DL experiment (r=0.8512, p<0.0001) and the DIP experiment (r=0.7784, p<0.0001). In the conclusion, the DL model showed relatively higher segmentation accuracy than the DIP. In this paper, we propose the clinical applicability of this technique applying the segmentation and asymmetric quantification algorithm to the glottal area in the laryngoscopic images.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.