설진 영상의 혀 영역 자동 분할을 위한 U-Net 기반 딥러닝 알고리즘
A Deep Learning Algorithm Based on U-Net for Automatic Tongue Region Segmentation from Images Acquired through a Computerized Tongue Image Acquisition System
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Research on improving the accuracy of tongue region segmentation in the deep learning process of Korean medicine's tongue diagnosis is actively ongoing. This study aims to propose a segmentation model based on the U-Net using Convolutional Neural Networks (cNN). Binary mask images representing the tongue region were created, and the dataset was randomly divided into an 8:2 ratio for the train and test set. To prevent overfitting, the changes in validation loss were monitored at each epoch. Finally, Dice similarity coefficient (DSC) and Jaccard index (JI) were computed to measure the accuracy of the segmentation model in identifying the target regions. The modified U-Net network showed a significant level of accuracy in tongue region segmentation and minimal overfitting despite a small number of training data sets. The accuracy in the train set reached 0.997 and in the test set the accuracy was 0.993. The Dice similarity coefficient (DSC) score on the test dataset was 0.981 ± 0.017 and the Jaccard index (JI) score was 0.964 ± 0.031. The proposed model based on U-Net for tongue region extraction is anticipated to be effective for practical applications such as computerized tongue analysis systems.
Abstract
Research on improving the accuracy of tongue region segmentation in the deep learning process of Korean medicine's tongue diagnosis is actively ongoing. This study aims to propose a segmentation model based on the U-Net using Convolutional Neural Networks (cNN). Binary mask images representing the tongue region were created, and the dataset was randomly divided into an 8:2 ratio for the train and test set. To prevent overfitting, the changes in validation loss were monitored at each epoch. Finally, Dice similarity coefficient (DSC) and Jaccard index (JI) were computed to measure the accuracy of the segmentation model in identifying the target regions. The modified U-Net network showed a significant level of accuracy in tongue region segmentation and minimal overfitting despite a small number of training data sets. The accuracy in the train set reached 0.997 and in the test set the accuracy was 0.993. The Dice similarity coefficient (DSC) score on the test dataset was 0.981 ± 0.017 and the Jaccard index (JI) score was 0.964 ± 0.031. The proposed model based on U-Net for tongue region extraction is anticipated to be effective for practical applications such as computerized tongue analysis systems.
참고문헌 (27)
- Kim KH, "Tongue diagnosis method for extraction of effective region and classification of tongue coating", Proceedings of the 1st Workshops on Image Processing Theory, Tools and Applications, pp.1~7 (2008), IEEE
- Wu WJ, "Method of tongue image segmentation based on luminance and roughness information", Journal of System Simulation, 18(S1), pp.374~376 (2006)
- Zhang ZS, "Tongue extraction algorithm based on dynamic thresholds and correction model", Computer and Modernization, (11), pp.49~52 (2014)
- Li DX, "Tongue image segmentation method based on adaptive thresholds", Computer Technology and Development, 21(9), pp.63~65 (2011)
- Zhi L, "Tongue shape detection based on b-spline", Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, pp.3829~3832 (2006), IEEE
- Li X, "Automatic tongue image segmentation based on histogram projection and matting", Proceedings of the 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp.76~81 (2014), IEEE
- Wang YQ, "A knowledge-based arithmetic for automatic tongue segmentation", Acta Electronica Sinica, 32(3), pp.489~491 (2004)
- Jang MS, "Improved snakes algorithm for tongue image segmentation in Oriental tongue diagnosis", The Journal of the Institute of Internet, Broadcasting and Communication, 16(4), pp.125~131 (2016)
- Liu B, "Application of an Improved Grab Cut method in tongue image segmentation. Intelligent Computing Methodologies", ICIC 2018 (2018), Springer
- Jeong JW, "Demonstration of a deep learning model for extracting tongue image regions using SegNet convolutional neural networks", Sangji Korean Medical Journal, 9(1), pp.11~23 (2021)
- Badrinarayanan V, "SegNet : A deep convolutional encoder-decoder architecture for image segmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), pp.2481~2495 (2017)
- Rhee S, "Tongue area segmentation and tongue cracks detection using CNN", J Korean Inst Intell Syst, 30, pp.258~264 (2020)
- Hu J, "Classification of fissured tongue images using deep neural networks", Technology and Health Care, 30, pp.271~283 (2022)
- Ronneberger O, "U-Net: Convolutional networks for biomedical image segmentation", Medical image computing and computer-assisted intervention-MICCAI 2015. Lecture Notes in Computer Science (2015), Springer
- Zhang Z, "Cracked tongue extraction model based on improved U-Net Method", IEEE Access, 11, pp.126352~126364 (2023)
- Ding J, "A multichannel deep neural network for retina vessel segmentation via a fusion mechanism", Front Bioeng Biotechnol, 9, pp.697915~ (2021)
- Zhang N, "Lung nodule segmentation and recognition algorithm based on multiposition U-Net", Comput Math Methods Med, 2022, pp.5112867~ (2022)
- Wang H, "Multilevel attention Unet segmentation algorithm for lung cancer based on CT images", Computers, Materials & Continua, 78(2), pp.1569~1589 (2024)
- Ni B, "Segmentation of ultrasound image sequences by combing a novel deep siamese network with a deformable contour model", Neural Computing and Applications, 35(20), pp.14535~14549 (2023)
- Hou S, "Teeth U-Net : A segmentation model of dental panoramic X-ray images for context semantics and contrast enhancement", Computers in Biology and Medicine, 152, pp.106296~ (2023)
- Rehman F, "A Region-based deep level set formulation for vertebral bone segmentation of osteoporotic fractures", J Digit Imaging, 33(1), pp.191~203 (2020)
- Li B, "Fast segmentation of vertebrae CT image based on the SNIC algorithm", Tomography, 8(1), pp.59~76 (2022)
- Zhang H, "Study on TCM tongue image segmentation model based on convolutional neural network fused with superpixel", Evid Based Complement Alternat Med, 2022, pp.3943920~ (2022)
- Liu W, "Tongue image segmentation and tongue color classification based on deep learning", Digital Chinese Medicine, 5(3), pp.253~263 (2022)
- Chen H, "Research on tongue segmentation based on convolutional neural network", Doctor, Department of Computer Engineering, pp.2021
- Ahn IK, "Tongue image segmentation using CNN and various image augmentation techniques", Journal of Biomedical Engineering Research, 42(5), pp.201~210 (2021)
- Li YJ, "Tongue segmentation using the receptive field diversification of U-net", Journal of the Korea Society of Computer and Information, 26(9), pp.37~47 (2021)