• Title/Summary/Keyword: Dice Coefficient

Search Result 65, Processing Time 0.027 seconds

Corneal Ulcer Region Detection With Semantic Segmentation Using Deep Learning

  • Im, Jinhyuk;Kim, Daewon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.9
    • /
    • pp.1-12
    • /
    • 2022
  • Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when 'crop & resized' images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.

Convolutional Neural Network-Based Automatic Segmentation of Substantia Nigra on Nigrosome and Neuromelanin Sensitive MR Images

  • Kang, Junghwa;Kim, Hyeonha;Kim, Eunjin;Kim, Eunbi;Lee, Hyebin;Shin, Na-young;Nam, Yoonho
    • Investigative Magnetic Resonance Imaging
    • /
    • v.25 no.3
    • /
    • pp.156-163
    • /
    • 2021
  • Recently, neuromelanin and nigrosome imaging techniques have been developed to evaluate the substantia nigra in Parkinson's disease. Previous studies have shown potential benefits of quantitative analysis of neuromelanin and nigrosome images in the substantia nigra, although visual assessments have been performed to evaluate structures in most studies. In this study, we investigate the potential of using deep learning based automatic region segmentation techniques for quantitative analysis of the substantia nigra. The deep convolutional neural network was trained to automatically segment substantia nigra regions on 3D nigrosome and neuromelanin sensitive MR images obtained from 30 subjects. With a 5-fold cross-validation, the mean calculated dice similarity coefficient between manual and deep learning was 0.70 ± 0.11. Although calculated dice similarity coefficients were relatively low due to empirically drawn margins, selected slices were overlapped for more than two slices of all subjects. Our results demonstrate that deep convolutional neural network-based method could provide reliable localization of substantia nigra regions on neuromelanin and nigrosome sensitive MR images.

Land Cover Classification of Satellite Image using SSResUnet Model (SSResUnet 모델을 이용한 위성 영상 토지피복분류)

  • Joohyung Kang;Minsung Kim;Seongjin Kim;Sooyeong Kwak
    • Journal of IKEEE
    • /
    • v.27 no.4
    • /
    • pp.456-463
    • /
    • 2023
  • In this paper, we introduce the SSResUNet network model, which integrates the SPADE structure with the U-Net network model for accurate land cover classification using high-resolution satellite imagery without requiring user intervention. The proposed network possesses the advantage of preserving the spatial characteristics inherent in satellite imagery, rendering it a robust classification model even in intricate environments. Experimental results, obtained through training on KOMPSAT-3A satellite images, exhibit superior performance compared to conventional U-Net and U-Net++ models, showcasing an average Intersection over Union (IoU) of 76.10 and a Dice coefficient of 86.22.

Classification of Anteroposterior/Lateral Images and Segmentation of the Radius Using Deep Learning in Wrist X-rays Images (손목 관절 단순 방사선 영상에서 딥 러닝을 이용한 전후방 및 측면 영상 분류와 요골 영역 분할)

  • Lee, Gi Pyo;Kim, Young Jae;Lee, Sanglim;Kim, Kwang Gi
    • Journal of Biomedical Engineering Research
    • /
    • v.41 no.2
    • /
    • pp.94-100
    • /
    • 2020
  • The purpose of this study was to present the models for classifying the wrist X-ray images by types and for segmenting the radius automatically in each image using deep learning and to verify the learned models. The data were a total of 904 wrist X-rays with the distal radius fracture, consisting of 472 anteroposterior (AP) and 432 lateral images. The learning model was the ResNet50 model for AP/lateral image classification, and the U-Net model for segmentation of the radius. In the model for AP/lateral image classification, 100.0% was showed in precision, recall, and F1 score and area under curve (AUC) was 1.0. The model for segmentation of the radius showed an accuracy of 99.46%, a sensitivity of 89.68%, a specificity of 99.72%, and a Dice similarity coefficient of 90.05% in AP images and an accuracy of 99.37%, a sensitivity of 88.65%, a specificity of 99.69%, and a Dice similarity coefficient of 86.05% in lateral images. The model for AP/lateral classification and the segmentation model of the radius learned through deep learning showed favorable performances to expect clinical application.

Automatic Segmentation of the Mandible using Shape-Constrained Information in Cranio-Maxillo-Facial CBCT Images (두개악안면 CBCT 영상에서 형상제약 정보를 사용한 하악골 자동 분할)

  • Kim, Joojin;Lee, Min Jin;Hong, Helen
    • Journal of the Korea Computer Graphics Society
    • /
    • v.23 no.5
    • /
    • pp.19-27
    • /
    • 2017
  • In this paper, we propose an automatic segmentation method of the mandible using shape-constrained information in cranio-maxillo-facial CBCT images. The proposed method consists of the following two steps. First, the mandible segmentation based on the global shape information is performed through the statistical shape model generated using the MDCT images. Second, improvement of mandible segmentation is performed considering the local shape information and intensity characteristics of the mandible. To evaluate the performance of the proposed method, the proposed method was evaluated qualitatively and quantitatively based on the results of manual segmentation by expert. Experimental results show that the Dice Similarity Coefficient of the proposed method was 95.64% and 90.97%, respectively, in the mandible body region including the narrow region of large curvature and the condyle region with large positional variance.

Lung Segmentation Considering Global and Local Properties in Chest X-ray Images (흉부 X선 영상에서의 전역 및 지역 특성을 고려한 폐 영역 분할 연구)

  • Jeon, Woong-Gi;Kim, Tae-Yun;Kim, Sung Jun;Choi, Heung-Kuk;Kim, Kwang Gi
    • Journal of Korea Multimedia Society
    • /
    • v.16 no.7
    • /
    • pp.829-840
    • /
    • 2013
  • In this paper, we propose a new lung segmentation method for chest x-ray images which can take both global and local properties into account. Firstly, the initial lung segmentation is computed by applying the active shape model (ASM) which keeps the shape of deformable model from the pre-learned model and searches the image boundaries. At the second segmentation stage, we also applied the localizing region-based active contour model (LRACM) for correcting various regional errors in the initial segmentation. Finally, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by a radiologist. The comparison experiments were performed using 5 lung x-ray images. In our experiment, the Dice coefficient with manually segmented area was $95.33%{\pm}0.93%$ for the proposed method. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for a more accurate early diagnosis and prognosis regarding lung cancer in chest x-ray images.

A Leveling and Similarity Measure using Extended AHP of Fuzzy Term in Information System (정보시스템에서 퍼지용어의 확장된 AHP를 사용한 레벨화와 유사성 측정)

  • Ryu, Kyung-Hyun;Chung, Hwan-Mook
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.19 no.2
    • /
    • pp.212-217
    • /
    • 2009
  • There are rule-based learning method and statistic based learning method and so on which represent learning method for hierarchy relation between domain term. In this paper, we propose to leveling and similarity measure using the extended AHP of fuzzy term in Information system. In the proposed method, we extract fuzzy term in document and categorize ontology structure about it and level priority of fuzzy term using the extended AHP for specificity of fuzzy term. the extended AHP integrates multiple decision-maker for weighted value and relative importance of fuzzy term. and compute semantic similarity of fuzzy term using min operation of fuzzy set, dice's coefficient and Min+dice's coefficient method. and determine final alternative fuzzy term. after that compare with three similarity measure. we can see the fact that the proposed method is more definite than classification performance of the conventional methods and will apply in Natural language processing field.

A New Similarity Measure for Improving Ranking in QA Systems (질의응답시스템 응답순위 개선을 위한 새로운 유사도 계산방법)

  • Kim Myung-Gwan;Park Young-Tack
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.10 no.6
    • /
    • pp.529-536
    • /
    • 2004
  • The main idea of this paper is to combine position information in sentence and query type classification to make the documents ranking to query more accessible. First, the use of conceptual graphs for the representation of document contents In information retrieval is discussed. The method is based on well-known strategies of text comparison, such as Dice Coefficient, with position-based weighted term. Second, we introduce a method for learning query type classification that improves the ability to retrieve answers to questions from Question Answering system. Proposed methods employ naive bayes classification in machine learning fields. And, we used a collection of approximately 30,000 question-answer pairs for training, obtained from Frequently Asked Question(FAQ) files on various subjects. The evaluation on a set of queries from international TREC-9 question answering track shows that the method with machine learning outperforms the underline other systems in TREC-9 (0.29 for mean reciprocal rank and 55.1% for precision).

Study on light extraction efficiency of a side-etched LED (측면 식각된 LED의 광추출 효율에 관한 연구)

  • Noh, Y.K.;Kwon, K.Y.
    • Korean Journal of Optics and Photonics
    • /
    • v.14 no.2
    • /
    • pp.122-129
    • /
    • 2003
  • In the case of a AIGalnP/GaP system rectangular parallelepiped high brightness LED which has side walls etched to be slanted off the vertical direction, we have studied the effects of lossy electrodes and material absorption and etching depth and angle of side walls on its light extraction efficiency. If LEDs have no electrodes, in order to obtain an 80% light extraction efficiency of a TIP (truncated inverted pyramid) LED, the side-etched LEDs should have an etching angle of 22$^{\circ}$~45$^{\circ}$ and an etching depth of 8~17% of a dice height and an absorption coefficient less than 1 $cm^{-1}$ / In case of etching depth of 16~39% of a dice height, we can obtain a 90% light extraction efficiency of a TIP LED. But when LEDs have two electrodes and no absorption loss, in order to obtain an 80% light extraction efficiency of a TIP LEBs, the side-etched LEDs should have an etching angle of 25$^{\circ}$-45$^{\circ}$ and an etching depth of 30~36% of a dice height. In case of etching depth of 57~71% of a dice height, we can obtain a 90% light extraction efficiency of a TIP LED.

Attention Aware Residual U-Net for Biometrics Segmentation (생체 인식 인식 시스템을 위한 주의 인식 잔차 분할)

  • Htet, Aung Si Min;Lee, Hyo Jong
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2022.11a
    • /
    • pp.300-302
    • /
    • 2022
  • Palm vein identification has attracted attention due to its distinct characteristics and excellent recognition accuracy. However, many contactless palm vein identification systems suffer from the issue of having low-quality palm images, resulting in degradation of recognition accuracy. This paper proposes the use of U-Net architecture to correctly segment the vascular blood vessel from palm images. Attention gate mechanism and residual block are also utilized to effectively learn the crucial features of a specific segmentation task. The experiments were conducted on CASIA dataset. Hessian-based Jerman filtering method is applied to label the palm vein patterns from the original images, then the network is trained to segment the palm vein features from the background noise. The proposed method has obtained 96.24 IoU coefficient and 98.09 dice coefficient.