갑상선 초음파 영상의 평활화 알고리즘에 따른 U-Net 기반 학습 모델 평가 Evaluation of U-Net Based Learning Models according to Equalization Algorithm in Thyroid Ultrasound Imaging원문보기
This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after ac...
This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.
This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.
Ma X, Zhang L. Diagnosis of thyroid nodules based？on image enhancement and deep neural networks.？Computational Intelligence and Neuroscience.？2022;2022:5582029. DOI: https://doi.org/10.1155/2022/5582029？
Choi YH. U-net based transfer learning model for？lesion area segmentation on the breast ultrasound？images by optimization of encoder. Kyungpook？National University Graduate School; 2022.？
Shin SY, Lee SH, Han HH. A study on residual u-net？for semantic segmentation based on deep learning.？Journal of Digital Convergence. 2021;19(6):251-8.？DOI: https://doi.org/10.14400/JDC.2021.19.6.251？
Lee J. Using deep learning for image-based superficial femoral artery disease detection. Catholic？University Graduate School; 2022.？
Kim YJ, Park YR, Kim YJ, Ju W, Nam K, Kim KG.？A performance comparison of histogram equalization？algorithms for cervical cancer classification model.？Journal of Biomedical Engineering Research.？2021;42(3):80-5. DOI: https://kiss.kstudy.com/DetailOa/Ar?key52271802#？
Yoshimi Y, Mine Y, Ito S, et al. Image preprocessing？with contrast-limited adaptive histogram equalization improves the segmentation performance of？deep learning for the articular disk of the temporomandibular joint on magnetic resonance images.？Oral Surg Oral Med Oral Pathol Oral Radiol. 2023.？DOI: https://doi.org/10.1016/j.oooo.2023.01.016？
Cho YH. Quality enhancement of medical images by？using nonlinear histogram equalization function.？Journal of the Korean Society of Industry？Convergence. 2010;13(1):23-30. DOI: https://doi.org/10.5391/JKIIS.2010.20.1.030？
Zuiderveld K. Contrast limited adaptive histogram？equalization. In: Heckbert P. ed. Graphics gems IV.？Academic Press; 1994. DOI: https://doi.org/10.1016/B978-0-12-336156-1.50061-6？
https://www.deepphi.ai/？
Son JW, Moon GS, Kim Y. Automatic detection system？of underground pipe using 3D GPR exploration data？and deep convolutional neural networks. Journal of？the Korea Society of Computer and Information.？2021;26(2):27-37. DOI: https://doi.org/10.9708/jksci.2021.26.02.027？
Long J, Shelhamer E, Darrell T. Fully convolutional？networks for semantic segmentation. DOI:？https://doi.org/10.48550/arXiv.1411.4038？
Lee JH, Lee DH, Wang WJ, et al. Left atrial segmentation technique based on u-net. Korea Institute of？Communication Sciences; 2022:139-40.？
Ronneberger O, Fischer P, Brox T. U-net:？Convolutional networks for biomedical image？segmentation. MICCAI. 2015:9351. DOI: https://doi.org/10.48550/arXiv.1505.04597？
Shin SY, Lee SH, Han HH. Atrous residual u-net？for semantic segmentation in street scenes based on？deep learning. Journal of Convergence for Information？Technology. 2021:28;11(10):45-52. DOI: https://doi.org/10.22156/CS4SMB.2021.11.10.045？
Hwang DH, Moon GS, Kim Y. SKU-net: Improved？U-net using selective kernel convolution for retinal？vessel segmentation. Journal of the Korea Society？of Computer and Information. 2021;26(4):29-37.？DOI: https://doi.org/10.9708/JKSCI.2021.26.04.029？
Kim IK, Kim BM, Woo SH, Gwak JH. Contactless？user identification system using multi-channel palm？images facilitated by triple attention u-net and CNN？classifier ensemble models. Journal of the Korea？Society of Computer and Information. 2022;27(3):33-43. DOI: https://doi.org/10.9708/jksci.2022.27.03.033？
Shin HS, Song SH, Lee DH, Park JH. Application？and evaluation of the attention u-net using UAV？imagery for corn cultivation field extraction. Ecology？and Resilient Infrastructure. 2021 Dec 31;8(4):253-65.？DOI: https://doi.org/10.17820/eri.2021.8.4.253？
Oh JY, Jeong EH, Lee JY, et al. Evaluating usefulness of deep learning based left ventricle segmentation in cardiac gated blood pool scan. Journal？of Radiological Science and Technology. 2022;45(2):151-8. DOI: https://doi.org/10.17946/JRST.2022.45.2.151？
Hong JY, Park SH, Jeong YJ. Artificial intelligence？based medical imaging: An overview. Journal of？Radiological Science and Technology. 2020;43(3):195-208. DOI: https://doi.org/10.17946/JRST.2020.43.3.195？
AI-Helper
※ AI-Helper는 부적절한 답변을 할 수 있습니다.