• Title/Summary/Keyword: Medical Image Segmentation

Search Result 243, Processing Time 0.035 seconds

Definition of Tumor Volume Based on 18F-Fludeoxyglucose Positron Emission Tomography in Radiation Therapy for Liver Metastases: An Relational Analysis Study between Image Parameters and Image Segmentation Methods (간 전이 암 환자의 18F-FDG PET 기반 종양 영역 정의: 영상 인자와 자동 영상 분할 기법 간의 관계분석)

  • Kim, Heejin;Park, Seungwoo;Jung, Haijo;Kim, Mi-Sook;Yoo, Hyung Jun;Ji, Young Hoon;Yi, Chul-Young;Kim, Kum Bae
    • Progress in Medical Physics
    • /
    • v.24 no.2
    • /
    • pp.99-107
    • /
    • 2013
  • The surgical resection was occurred mainly in liver metastasis before the development of radiation therapy techniques. Recently, Radiation therapy is increased gradually due to the development of radiation dose delivery techniques. 18F-FDG PET image showed better sensitivity and specificity in liver metastasis detection. This image modality is important in the radiation treatment with planning CT for tumor delineation. In this study, we applied automatic image segmentation methods on PET image of liver metastasis and examined the impact of image factors on these methods. We selected the patients who were received the radiation therapy and 18F-FDG PET/CT in Korea Cancer Center Hospital from 2009 to 2012. Then, three kinds of image segmentation methods had been applied; The relative threshold method, the Gradient method and the region growing method. Based on these results, we performed statistical analysis in two directions. 1. comparison of GTV and image segmentation results. 2. performance of regression analysis for relation between image factor affecting image segmentation techniques. The mean volume of GTV was $60.9{\pm}65.9$ cc and the $GTV_{40%}$ was $22.43{\pm}35.27$ cc, and the $GTV_{50%}$ was $10.11{\pm}17.92$ cc, the $GTV_{RG}$ was $32.89{\pm}36.8$4 cc, the $GTV_{GD}$ was $30.34{\pm}35.77$ cc, respectively. The most similar segmentation method with the GTV result was the region growing method. For the quantitative analysis of the image factors which influenced on the region growing method, we used the standardized coefficient ${\beta}$, factors affecting the region growing method show GTV, $TumorSUV_{MAX/MIN}$, $SUV_{max}$, TBR in order. The result of the region growing (automatic segmentation) method showed the most similar result with the CT based GTV and the region growing method was affected by image factors. If we define the tumor volume by the auto image segmentation method which reflect the PET image parameters, more accurate and consistent tumor contouring can be done. And we can irradiate the optimized radiation dose to the cancer, ultimately.

DA-Res2Net: a novel Densely connected residual Attention network for image semantic segmentation

  • Zhao, Xiaopin;Liu, Weibin;Xing, Weiwei;Wei, Xiang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.14 no.11
    • /
    • pp.4426-4442
    • /
    • 2020
  • Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

Accuracy evaluation of liver and tumor auto-segmentation in CT images using 2D CoordConv DeepLab V3+ model in radiotherapy

  • An, Na young;Kang, Young-nam
    • Journal of Biomedical Engineering Research
    • /
    • v.43 no.5
    • /
    • pp.341-352
    • /
    • 2022
  • Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

Optimization of Multi-Atlas Segmentation with Joint Label Fusion Algorithm for Automatic Segmentation in Prostate MR Imaging

  • Choi, Yoon Ho;Kim, Jae-Hun;Kim, Chan Kyo
    • Investigative Magnetic Resonance Imaging
    • /
    • v.24 no.3
    • /
    • pp.123-131
    • /
    • 2020
  • Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF's parameters (rpxy, rpz, rsxy, rsz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of rpxy = 10, rpz = 1, rsxy = 3, rsz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.

Segmentation of Mammography Breast Images using Automatic Segmen Adversarial Network with Unet Neural Networks

  • Suriya Priyadharsini.M;J.G.R Sathiaseelan
    • International Journal of Computer Science & Network Security
    • /
    • v.23 no.12
    • /
    • pp.151-160
    • /
    • 2023
  • Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

Survey on Deep Learning-based Panoptic Segmentation Methods (딥 러닝 기반의 팬옵틱 분할 기법 분석)

  • Kwon, Jung Eun;Cho, Sung In
    • IEMEK Journal of Embedded Systems and Applications
    • /
    • v.16 no.5
    • /
    • pp.209-214
    • /
    • 2021
  • Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

Algorithm for Extract Region of Interest Using Fast Binary Image Processing (고속 이진화 영상처리를 이용한 관심영역 추출 알고리즘)

  • Cho, Young-bok;Woo, Sung-hee
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.22 no.4
    • /
    • pp.634-640
    • /
    • 2018
  • In this paper, we propose an automatic extraction algorithm of region of interest(ROI) based on medical x-ray images. The proposed algorithm uses segmentation, feature extraction, and reference image matching to detect lesion sites in the input image. The extracted region is searched for matching lesion images in the reference DB, and the matched results are automatically extracted using the Kalman filter based fitness feedback. The proposed algorithm is extracts the contour of the left hand image for extract growth plate based on the left x-ray input image. It creates a candidate region using multi scale Hessian-matrix based sessionization. As a result, the proposed algorithm was able to split rapidly in 0.02 seconds during the ROI segmentation phase, also when extracting ROI based on segmented image 0.53, the reinforcement phase was able to perform very accurate image segmentation in 0.49 seconds.

Adaptive Active Contour Model: a Localized Mutual Information Approach for Medical Image Segmentation

  • Dai, Shuanglu;Zhan, Shu;Song, Ning
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.9 no.5
    • /
    • pp.1840-1855
    • /
    • 2015
  • Troubles are often met when traditional active contours extract boundaries of medical images with inhomogeneous bias and various noises. Focusing on such a circumstance, a localized mutual information active contour model is discussed in the paper. By defining neighborhood of each point on the level set, mutual information is introduced to describe the relationship between the zero level set and image field. A driving energy term is then generated by integrating all the information. In addition, an expanding energy and internal energy are designed to regularize the driving energy. Contrary to piecewise constant model, new model has a better command of driving the contours without initialization.

Layer Segmentation of Retinal OCT Images using Deep Convolutional Encoder-Decoder Network (딥 컨볼루셔널 인코더-디코더 네트워크를 이용한 망막 OCT 영상의 층 분할)

  • Kwon, Oh-Heum;Song, Min-Gyu;Song, Ha-Joo;Kwon, Ki-Ryong
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.11
    • /
    • pp.1269-1279
    • /
    • 2019
  • In medical image analysis, segmentation is considered as a vital process since it partitions an image into coherent parts and extracts interesting objects from the image. In this paper, we consider automatic segmentations of OCT retinal images to find six layer boundaries using convolutional neural networks. Segmenting retinal images by layer boundaries is very important in diagnosing and predicting progress of eye diseases including diabetic retinopathy, glaucoma, and AMD (age-related macular degeneration). We applied well-known CNN architecture for general image segmentation, called Segnet, U-net, and CNN-S into this problem. We also proposed a shortest path-based algorithm for finding the layer boundaries from the outputs of Segnet and U-net. We analysed their performance on public OCT image data set. The experimental results show that the Segnet combined with the proposed shortest path-based boundary finding algorithm outperforms other two networks.

Segmentation by Contour Following Method with Directional Angle

  • Na, Cheol-Hun;Kim, Su-Yeong;Kang, Seong-Jun
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2012.10a
    • /
    • pp.874-877
    • /
    • 2012
  • This paper proposes the new method based on contour following method with directional angle to segment the cell into the nuclei. The object image was the Thyroid Gland cell image that was diagnosed as normal and abnormal(two types of abnormal : follicular neoplastic cell, and papillary neoplastic cell), respectively. The nuclei were successfully diagnosed as normal and abnormal. this paper, improved method of digital image analysis required in basic medical science for diagnosis of cells was proposed. The object image was the Thyroid Gland cell image with difference of chromatin patterns. To segment the cell nucleus from background, the region segmentation algorithm by edge tracing was proposed. And feature parameter was obtained from discrete Fourier transformation of image. After construct a feature sample group of each cells, experiment of discrimination was executed with any verification cells. As a result of experiment using features proposed in this paper, get a better segmentation rate(70-90%) than previously reported papers, and this method give shape to get objectivity and fixed quantity in diagnosis of cells. The methods described in this paper be used immediately for discrimination of neoplastic cells.

  • PDF