請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89391完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳文超 | zh_TW |
| dc.contributor.advisor | Wen-Chau Wu | en |
| dc.contributor.author | 李旻哲 | zh_TW |
| dc.contributor.author | Min-Che Lee | en |
| dc.date.accessioned | 2023-09-07T16:48:52Z | - |
| dc.date.available | 2024-09-01 | - |
| dc.date.copyright | 2023-09-11 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-01 | - |
| dc.identifier.citation | Reference
1. McCarthy, C.J., S. McDermott, and M.A. Blake, Adrenal Imaging: Magnetic Resonance Imaging and Computed Tomography. Front Horm Res, 2016. 45: p. 55-69. 2. Johns Hopkins Medicine. Adrenal Glands. 2023; Available from: https://www.hopkinsmedicine.org/health/conditions-and-diseases/adrenal-glands. 3. Turcu, A.F., J. Yang, and A. Vaidya, Primary aldosteronism — a multidimensional syndrome. Nature Reviews Endocrinology, 2022. 18(11): p. 665-682. 4. Kumar, R. and W.S. Wassif, Adrenal insufficiency. J Clin Pathol, 2022. 75(7): p. 435-442. 5. Sherlock, M., et al., Adrenal Incidentaloma. Endocr Rev, 2020. 41(6): p. 775-820. 6. Ilias, I., et al., The optimal imaging of adrenal tumours: a comparison of different methods. Endocrine-Related Cancer Endocr Relat Cancer, 2007. 14(3): p. 587-599. 7. Smith-Bindman, R., et al., Trends in Use of Medical Imaging in US Health Care Systems and in Ontario, Canada, 2000-2016. Jama, 2019. 322(9): p. 843-856. 8. Boland, G.W., Adrenal imaging. Abdom Imaging, 2011. 36(4): p. 472-82. 9. Sarvamangala, D.R. and R.V. Kulkarni, Convolutional neural networks in medical image understanding: a survey. Evolutionary Intelligence, 2022. 15(1): p. 1-22. 10. Choi, R.Y., et al., Introduction to Machine Learning, Neural Networks, and Deep Learning. Transl Vis Sci Technol, 2020. 9(2): p. 14. 11. Su, R., et al., MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation. Frontiers in Genetics, 2021. 12. 12. Luo, G., et al., An optimized two-stage cascaded deep neural network for adrenal segmentation on CT images. Comput Biol Med, 2021. 136: p. 104749. 13. Bashir O, Y.Y., Chieng R, et al., Adrenal gland. 2012. 14. Moulton, J.S. and J.S. Moulton, CT of the adrenal glands. Semin Roentgenol, 1988. 23(4): p. 288-303. 15. Maier-Hein, L., et al., Why rankings of biomedical image analysis competitions should be interpreted with care. Nature Communications, 2018. 9(1): p. 5217. 16. Erickson, B.J., et al., Machine Learning for Medical Imaging. Radiographics, 2017. 37(2): p. 505-515. 17. Seo, H., et al., Machine learning techniques for biomedical image segmentation: An overview of technical aspects and introduction to state-of-art applications. Med Phys, 2020. 47(5): p. e148-e167. 18. Zhou, J., et al., Segmentation of hepatic tumor from abdominal CT data using an improved support vector machine framework. Annu Int Conf IEEE Eng Med Biol Soc, 2013. 2013: p. 3347-50. 19. Kodym, O. and M. Spanel, Semi-automatic CT Image Segmentation using Random Forests Learned from Partial Annotations. BIOIMAGING, 2018. 740: p. 124-131. 20. Held, K., et al., Markov random field segmentation of brain MR images. IEEE Trans Med Imaging, 1997. 16(6): p. 878-86. 21. HEAVY.AI. Feature Engineering. 2022; Available from: https://www.heavy.ai/technical-glossary/feature-engineering. 22. O'Shea, K. and R. Nash, An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458, 2015. 23. Anwar, S.M., et al., Medical Image Analysis using Convolutional Neural Networks: A Review. J Med Syst, 2018. 42(11): p. 226. 24. Ronneberger, O., P. Fischer, and T. Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. Cham: Springer International Publishing. 25. Robinson-Weiss, C., et al., Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT. Radiology, 2023. 306(2): p. e220101. 26. Kim, T.M., et al., Fully automatic volume measurement of the adrenal gland on CT using deep learning to classify adrenal hyperplasia. Eur Radiol, 2022. 27. Pan, S., et al., Abdomen CT multi-organ segmentation using token-based MLP-Mixer. Med Phys, 2022. 28. Zhao, Y., et al., Knowledge-Aided Convolutional Neural Network for Small Organ Segmentation. IEEE J Biomed Health Inform, 2019. 23(4): p. 1363-1373. 29. De Raad, K., et al. The effect of preprocessing on convolutional neural networks for medical image segmentation. in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). 2021. IEEE. 30. Taylor, L. and G. Nitschke. Improving deep learning with generic data augmentation. in 2018 IEEE symposium series on computational intelligence (SSCI). 2018. IEEE. 31. Chlap, P., et al., A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol, 2021. 65(5): p. 545-563. 32. Buslaev, A., et al., Albumentations: Fast and Flexible Image Augmentations. Information, 2020. 11(2): p. 125. 33. Long, J., E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. 34. Sun, S., et al. A comparative study of CNN and FCN for histopathology whole slide image analysis. in Image and Graphics: 10th International Conference, ICIG 2019, Beijing, China, August 23–25, 2019, Proceedings, Part II 10. 2019. Springer. 35. Albawi, S., T.A. Mohammed, and S. Al-Zawi. Understanding of a convolutional neural network. in 2017 international conference on engineering and technology (ICET). 2017. Ieee. 36. Singh, P., P. Raj, and V.P. Namboodiri, EDS pooling layer. Image and Vision Computing, 2020. 98: p. 103923. 37. Nielsen, M.A., Neural networks and deep learning. Vol. 25. 2015: Determination press San Francisco, CA, USA. 38. Hossain, F.A. and Y. Zhang. Development of new efficient transposed convolution techniques for flame segmentation from UAV-captured images. in 2021 3rd International Conference on Industrial Artificial Intelligence (IAI). 2021. IEEE. 39. Liu, F., et al. Rethinking skip connection with layer normalization. in Proceedings of the 28th international conference on computational linguistics. 2020. 40. Szandała, T., Review and comparison of commonly used activation functions for deep neural networks. Bio-inspired neurocomputing, 2021: p. 203-224. 41. Rasamoelina, A.D., F. Adjailia, and P. Sinčák. A review of activation function for artificial neural network. in 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI). 2020. IEEE. 42. Glorot, X., A. Bordes, and Y. Bengio. Deep sparse rectifier neural networks. in Proceedings of the fourteenth international conference on artificial intelligence and statistics. 2011. JMLR Workshop and Conference Proceedings. 43. Maas, A.L., A.Y. Hannun, and A.Y. Ng. Rectifier nonlinearities improve neural network acoustic models. in Proc. icml. 2013. Atlanta, Georgia, USA. 44. He, K., et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. in Proceedings of the IEEE international conference on computer vision. 2015. 45. Du, G., et al., Medical image segmentation based on u-net: A review. Journal of Imaging Science and Technology, 2020. 46. Niyas, S., et al., Medical image segmentation using 3D convolutional neural networks: A review. arXiv preprint arXiv:2108.08467, 2021. 47. Alom, M.Z., et al., Recurrent residual U-Net for medical image segmentation. Journal of Medical Imaging, 2019. 6(1): p. 014006-014006. 48. Zettler, N. and A. Mastmeyer, Comparison of 2D vs. 3D U-Net Organ Segmentation in abdominal 3D CT images. arXiv preprint arXiv:2107.04062, 2021. 49. Çiçek, Ö., et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation. in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. 2016. Springer. 50. Coupeau, P., et al., Patch-based 3D U-Net and transfer learning for longitudinal piglet brain segmentation on MRI. Computer Methods and Programs in Biomedicine, 2022. 214: p. 106563. 51. Lee, B., N. Yamanakkanavar, and J.Y. Choi, Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture. PLOS ONE, 2020. 15(8): p. e0236493. 52. Taha, A.A. and A. Hanbury, Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging, 2015. 15: p. 29. 53. Huang, F., G. Xie, and R. Xiao. Research on ensemble learning. in 2009 International Conference on Artificial Intelligence and Computational Intelligence. 2009. IEEE. 54. Zhou, Z.-H. and Z.-H. Zhou, Ensemble learning. 2021: Springer. 55. Chollet, F., Keras: The python deep learning library. Astrophysics source code library, 2018: p. ascl: 1806.022. 56. Allaire, J.J. and Y. Tang, tensorflow: R Interface to TensorFlow. R package version, 2019. 2(0). 57. Weston, A.D., et al., Complete abdomen and pelvis segmentation using U-net variant architecture. Med Phys, 2020. 47(11): p. 5609-5618. 58. Larsson, M., Y. Zhang, and F. Kahl, Robust abdominal organ segmentation using regional convolutional neural networks. Applied Soft Computing, 2018. 70: p. 465-471. 59. Zhang, J. Self-pretrained V-Net Based on PCRL for Abdominal Organ Segmentation. 2022. Cham: Springer Nature Switzerland. 60. Zhang, M., et al., Value of radiomics features from adrenal gland and periadrenal fat CT images predicting COVID-19 progression. medRxiv, 2021: p. 2021.01.03.21249183. 61. Fan, T., et al., MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation. IEEE Access, 2020. 8: p. 179656-179665. 62. Cai, Y. and Y. Wang, MA-Unet: an improved version of Unet based on multi-scale and attention mechanism for medical image segmentation. 2021 Third International Conference on Electronics and Communication, Network and Computer Technology. Vol. 12167. 2022: SPIE. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89391 | - |
| dc.description.abstract | 腎上腺是人體重要的內分泌器官，分泌過少或過多的激素都可能會引發嚴重的疾病。醫學影像技術，例如電腦斷層掃描（Computed Tomography，CT），因其非侵入性的特點而常被用於診斷腎上腺問題。醫學影像分割可以幫助深入瞭解影像，提取特徵並評估異常或病灶。醫師透過醫學影像解讀可以分析腎上腺的位置和特徵，有助於診斷和治療計劃的制訂。然而，在電腦軟體手動標記腎上腺的位置可能非常耗時，加上每天有大量臨床工作，這無疑造成了醫師龐大的工作負擔。
現今，深度學習由於其高準確性和時間效率，在醫學影像分割上被廣泛應用。但深度學習仍然存在一些困難，特別是在對像腎上腺這種小而形狀不規則的器官進行分割時，模型可能會難以提取特徵。基於上述，我們建立了一個三維U-Net模型，結合了多尺度和集成學習作為訓練方法，來對醫學影像進行腎上腺的自動化分割。本研究以腹部CT影像作為訓練資料集，除了將影像資料的Z軸涵蓋範圍調整成統一的大小之外，不做其他影像前處理，藉以驗證深度學習模型從CT影像中識別和學習腎上腺結構特徵的能力。模型的分割能力使用Dice係數進行評估。 實驗結果顯示，將三維U-Net與多尺度和集成學習結合使用，在腎上腺的分割中可達到66.3%的準確度，值得進一步驗證臨床實用性。 | zh_TW |
| dc.description.abstract | Adrenal glands are vital endocrine organs in the human body, playing a crucial role in hormone production. Imbalances in these hormones can result in serious disorders. With the advantage of minimal noninvasiveness, medical imaging techniques, such as x-ray computed tomography (CT), are commonly used to diagnose adrenal gland disorders. Image segmentation enables feature extraction and evaluation of lesions/abnormalities, and whereby helps diagnosis and treatment planning. However, manual marking of adrenal glands positions on a computer can be time-consuming, posing a significant workload for doctors. Nowadays, deep learning has been widely used for segmentation in medical images due to its high accuracy and time efficiency. However, there are still challenges to overcome, particularly in segmenting small and irregularly shaped organs like adrenal glands in medical images. In light of the above, we built a three-dimensional U-Net in combination with multi-scale and ensemble learning to automatically segment and label adrenal glands on CT images. Except for resizing the tensor size along the z-axis of the data, no other image preprocessing was performed so as to validate the ability of deep learning in identifying and learning the features of adrenal structures from CT images. The segmentation performance of the model was evaluated using the Dice coefficient scores. According to our results, 3D U-Net combined with multi-scale and ensemble learning achieved an average accuracy of 66.3% in adrenal gland segmentation. The proposed method warrants further investigation for its clinical application. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-09-07T16:48:52Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-09-07T16:48:52Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | CONTENTS
Chapter 1 Introduction 1 1.1 Background 1 1.2 Purpose 3 1.3 Literature Review 5 1.3.1 Traditional methods 5 1.3.2 Machine learning 5 1.3.3 Deep learning 8 1.3.4 Deep learning methods applied to adrenal glands segmentation 9 Chapter 2 Material and methods 12 2.1 Datasets 12 2.2 Image preprocessing 15 2.3 Data augmentation 17 2.4 Fully Convolutional Network 19 2.4.1 Convolutional layer 20 2.4.2 Pooling layer 21 2.4.3 Up-sampling 22 2.4.4 Skip connection 23 2.4.5 Activation function 24 2.5 3D U-Net 27 2.6 Patches 29 2.7 Training 30 2.8 Evaluation metrics 32 2.9 Ensemble Learning 33 Chapter 3 Results 34 3.1 Dataset configuration 34 3.2 Research configuration 36 3.2.1 Experimental environment configuration 36 3.2.2 Experimental parameter configuration 36 3.3 Experimental results of 3D U-Net 37 3.4 Parameter analysis of 3D U-Net 38 3.4.1 Model convergence 38 3.4.2 Batch size 39 3.4.3 Learning rate 40 3.5 Visualization results of 3D U-Net 42 3.6 Experimental results of multi-scale 44 3.7 Visualization results of multi-scale 46 3.8 Experimental results of ensemble learning 48 3.9 Visualization results of ensemble learning 50 Chapter 4 Discussion 52 4.1 Visual analysis of 3D U-Net segmentation 52 4.2 Comparison of models for adrenal glands segmentation 53 4.3 Visual analysis of multi-scale segmentation 56 4.4 Comparison of published methods in multi-scale 57 4.5 Visual analysis of ensemble learning 59 4.6 Comparison published methods to ensemble learning results 60 4.7 Analysis of AG segmentation using multi-scale 3D U-Net 63 Chapter 5 Conclusion 65 Reference 67 | - |
| dc.language.iso | en | - |
| dc.subject | 深度學習、三維卷積神經網路、腎上腺、電腦斷層掃描 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | adrenal glands | en |
| dc.subject | 3D convolutional neural network | en |
| dc.subject | computed tomography | en |
| dc.title | 利用多尺度3D U-Net在電腦斷層掃描影像上進行腎上腺的自動化分割 | zh_TW |
| dc.title | Automatic segmentation of adrenal glands on CT images by using multi-scale 3D U-Net | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 鍾孝文;張晉誠; 蔡炳煇;林益如 | zh_TW |
| dc.contributor.oralexamcommittee | Hsiao-Wen Chung;Chin-Cheng Chang;Ping-Huei Tsai;Yi-Ru Lin | en |
| dc.subject.keyword | 深度學習、三維卷積神經網路、腎上腺、電腦斷層掃描, | zh_TW |
| dc.subject.keyword | deep learning, 3D convolutional neural network, adrenal glands, computed tomography, | en |
| dc.relation.page | 70 | - |
| dc.identifier.doi | 10.6342/NTU202302258 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-08-04 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 醫學工程學系 | - |
| 顯示於系所單位： | 醫學工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 2.16 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。