請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96139完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林澤 | zh_TW |
| dc.contributor.advisor | Che Lin | en |
| dc.contributor.author | 張舜程 | zh_TW |
| dc.contributor.author | Shun-Cheng Chang | en |
| dc.date.accessioned | 2024-11-15T16:07:51Z | - |
| dc.date.available | 2024-11-16 | - |
| dc.date.copyright | 2024-11-15 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-10-24 | - |
| dc.identifier.citation | [1] D. J. Araújo, M. R. Verdelho, A. Bissoto, J. C. Nascimento, C. Santiago, and C. Barata. Key patches are all you need: A multiple instance learning framework for robust medical diagnosis, 2024.
[2] S.A.ArmstrongandA.R.He.Immuno-oncologyforhepatocellularcarcinoma:The present and the future. Clinics in Liver Disease, 24(4):739–753, 2020. [3] W. D. Bidgood Jr, S. C. Horii, F. W. Prior, and D. E. Van Syckle. Understanding and using dicom, the data interchange standard for biomedical imaging. Journal of the American Medical Informatics Association, 4(3):199–212, 1997. [4] P. Bilic, P. Christ, H. B. Li, E. Vorontsov, A. Ben-Cohen, G. Kaissis, A. Szeskin, C. Jacobs, G. E. H. Mamani, G. Chartrand, et al. The liver tumor segmentation benchmark (lits). Medical Image Analysis, 84:102680, 2023. [5] M.-A. Carbonneau, V. Cheplygina, E. Granger, and G. Gagnon. Multiple instance learning: A survey of problem characteristics and applications. Pattern Recognition, 77:329–353, 2018. [6] S. Chang, P. Wang, W. Wang, T. Su, J. Kao, and C. Lin. A bclc staging system for hepatocellular carcinoma using swin transformer and ct imaging. In 2024 46rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2024. [7] H.Dong,Y.Iwamoto,X.Han,L.Lin,H.Hu,X.Cai,andY.-W.Chen.Casediscrim- ination: Self-supervised feature learning for the classification of focal liver lesions. In Innovation in Medicine and Healthcare: Proceedings of 9th KES-InMed 2021, pages 241–249. Springer, 2021. [8] Z.Dong,B.Xu,J.Shi,andL.Zheng.Localandglobalfeatureinteractionnetworkfor endoscope image classification. In International Conference on Image and Graphics, pages 412–424. Springer, 2023. [9] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. ICLR, 2021. [10] M. Fang, M. Fu, B. Liao, X. Lei, and F.-X. Wu. Deep integrated fusion of local and global features for cervical cell classification. Computers in Biology and Medicine, 171:108153, 2024. [11] S. Fu, F. Sun, J. Yang, S. Zhang, Y. Lian, and L. Jiang. Clinical risk predication for hepatocellular carcinoma based on swin transformer. In Proceedings of the 2023 2nd International Conference on Algorithms, Data Mining, and Information Technology, pages 202–206, 2023. [12] J. Guo, K. Han, H. Wu, Y. Tang, X. Chen, Y. Wang, and C. Xu. Cmt: Convolutional neural networks meet vision transformers, 2022. [13] Z. Han, B. Wei, Y. Hong, T. Li, J. Cong, X. Zhu, H. Wei, and W. Zhang. Accurate screening of covid-19 using attention-based deep 3d multiple instance learning. IEEE Transactions on Medical Imaging, 39(8):2584–2594, 2020. [14] A. Hatamizadeh, Y. Tang, V. Nath, D. Yang, A. Myronenko, B. Landman, H. Roth, and D. Xu. Unetr: Transformers for 3d medical image segmentation, 2021. [15] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [16] Health Promotion Administration, Ministry of Health and Welfare, Taiwan. Cancer registry annual report, 2019, taiwan. https://www.hpa.gov.tw/File/Attach/ 14913/File_18302.pdf, 2019. Accessed: 2022-11-25. [17] T. Heimann, B. Van Ginneken, M. A. Styner, Y. Arzhaeva, V. Aurich, C. Bauer, A. Beck, C. Becker, R. Beichel, G. Bekes, et al. Comparison and evaluation of meth- ods for liver segmentation from ct datasets. IEEE transactions on medical imaging, 28(8):1251–1265, 2009. [18] X. Huo, G. Sun, S. Tian, Y. Wang, L. Yu, J. Long, W. Zhang, and A. Li. Hifuse: Hier- archical multi-scale feature fusion network for medical image classification. Biomed- ical Signal Processing and Control, 87:105534, 2024. [19] M. Ilse, J. Tomczak, and M. Welling. Attention-based deep multiple instance learn- ing. In International conference on machine learning, pages 2127–2136. PMLR, 2018. [20] F. Isensee, P. F. Jaeger, S. A. Kohl, J. Petersen, and K. H. Maier-Hein. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2):203–211, 2021. [21] H. Lee, H. Lee, H. Hong, H. Bae, J. S. Lim, and J. Kim. Classification of focal liver lesions in ct images using convolutional neural networks with lesion information augmented patches and synthetic data augmentation. Medical physics, 48(9):5029– 5046, 2021. [22] W. Li, C. Qu, X. Chen, P. R. Bassi, Y. Shi, Y. Lai, Q. Yu, H. Xue, Y. Chen, X. Lin, et al. Abdomenatlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking. Medical Image Anal- ysis, 97:103285, 2024. [23] X. Li, P. S. Morgan, J. Ashburner, J. Smith, and C. Rorden. The first step for neu- roimaging data analysis: Dicom to nifti conversion. Journal of neuroscience meth- ods, 264:47–56, 2016. [24] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo. Swin trans- former: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021. [25] Z. Liu and L. Shen. Cect: controllable ensemble cnn and transformer for covid-19 image classification by capturing both local and global image features, 2023. [26] M. Y. Lu, B. Chen, A. Zhang, D. F. Williamson, R. J. Chen, T. Ding, L. P. Le, Y.-S. Chuang, and F. Mahmood. Visual language pretrained multiple instance zero-shot transfer for histopathology images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 19764–19775, 2023. [27] O. N. Manzari, H. Ahmadabadi, H. Kashiani, S. B. Shokouhi, and A. Ayatollahi. Medvit: A robust vision transformer for generalized medical image classification. Computers in Biology and Medicine, 157:106791, May 2023. [28] S. Mehta and M. Rastegari. Mobilevit: Light-weight, general-purpose, and mobile- friendly vision transformer, 2022. [29] A. W. Moawad, A. Morshid, A. M. Khalaf, M. M. Elmohr, J. D. Hazle, D. Fuentes, M. Badawy, A. O. Kaseb, M. Hassan, A. Mahvash, et al. Multimodality annotated hepatocellular carcinoma data set including pre-and post-tace with imaging segmen- tation. Scientific Data, 10(1):33, 2023. [30] M.Reig,A.Forner,J.Rimola,J.Ferrer-Fàbrega,M.Burrel,Á.Garcia-Criado,R.K. Kelley, P. R. Galle, V. Mazzaferro, R. Salem, et al. Bclc strategy for prognosis prediction and treatment recommendation: The 2022 update. Journal of hepatology, 76(3):681–693, 2022. [31] S. Shah, R. Mishra, A. Szczurowska, and M. Guziński. Non-invasive multi-channel deep learning convolutional neural networks for localization and classification of common hepatic lesions. Polish Journal of Radiology, 86:e440, 2021. [32] Z. Shao, H. Bian, Y. Chen, Y. Wang, J. Zhang, X. Ji, et al. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Ad- vances in neural information processing systems, 34:2136–2147, 2021. [33] A. L. Simpson, M. Antonelli, S. Bakas, M. Bilello, K. Farahani, B. Van Ginneken, A. Kopp-Schneider, B. A. Landman, G. Litjens, B. Menze, et al. A large annotated medical image dataset for the development and evaluation of segmentation algo- rithms. arXiv preprint arXiv:1902.09063, 2019. [34] J. Song, H. Dong, Y. Chen, L. Lin, H. Hu, and Y.-W. Chen. Deep neural network- based classification of focal liver lesions using phase-shuffle prediction pre-training. In International KES Conference on Innovation in Medicine and Healthcare, pages 235–243. Springer, 2023. [35] T.-H. Su, C.-H. Wu, T.-H. Liu, C.-M. Ho, and C.-J. Liu. Clinical practice guidelines and real-life practice in hepatocellular carcinoma: A taiwan perspective. Clinical and Molecular Hepatology, 29(2):230, 2023. [36] H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians, 71(3):209–249, 2021. [37] Y. Tang, D. Yang, W. Li, H. R. Roth, B. Landman, D. Xu, V. Nath, and A. Hatamizadeh. Self-supervised pre-training of swin transformers for 3d medi- cal image analysis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 20730–20740, 2022. [38] Z. Tu, H. Talebi, H. Zhang, F. Yang, P. Milanfar, A. Bovik, and Y. Li. Maxvit: Multi-axis vision transformer. ECCV, 2022. [39] E. Vorontsov, A. Tang, C. Pal, and S. Kadoury. Liver lesion segmentation informed by joint liver segmentation. In 2018 IEEE 15th International Symposium on Biomed- ical Imaging (ISBI 2018), pages 1332–1335. IEEE, 2018. [40] C.-S. Wei. A BCLC staging system for hepatocellular carcinoma using Ensemble Learning and Multi-phase abdominal CT. Master’s thesis, National Taiwan University, Graduate Institute of Clinical Medicine, Taipei, 2023. Retrieved from: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89122. [41] T. Xiao, M. Singh, E. Mintun, T. Darrell, P. Dollár, and R. Girshick. Early convo- lutions help transformers see better, 2021. [42] Y. Zhang, C. Peng, L. Peng, H. Huang, R. Tong, L. Lin, J. Li, Y.-W. Chen, Q. Chen, H. Hu, and Z. Peng. Multi-phase liver tumor segmentation with spatial aggregation and uncertain region inpainting, 2021. [43] C. Zheng, X. Deng, Q. Fu, Q. Zhou, J. Feng, H. Ma, W. Liu, and X. Wang. Deep learning-based detection for covid-19 from chest ct using weak label. MedRxiv, pages 2020–03, 2020. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96139 | - |
| dc.description.abstract | 深度學習已經徹底改變了醫學影像領域，提供了更先進的方法來進行精確的診斷和治療計劃。BCLC 分期系統在分期高死亡率的肝細胞癌（HCC）中具有重要作用。自動化的 BCLC 分期系統可以顯著提升診斷和治療計劃的效率。本研究中，我們發現 BCLC 分期與多實例學習（MIL）框架的原理高度契合，這主要是因為 BCLC 分期直接關聯到肝臟腫瘤的大小和數量。為了有效利用這一框架，我們提出了一種新的預處理技術，稱為遮蔽裁剪和填充（MCP），該技術解決了肝臟體積變異性問題，並確保輸入尺寸的一致性。這一技術能夠保留肝臟的結構完整性，從而促進更有效的學習。
此外，我們引入了一種名為 ReViT 的全新混合模型，該模型結合了卷積神經網絡（CNN）的局部特徵提取能力與視覺變換器（ViT）的全局上下文建模能力。該模型在 MIL 框架內充分利用了這兩種架構的優勢，從而提供了一種穩健且精確的 BCLC 分期方法。通過採用 Top-K 池化策略，模型能夠聚焦於最具信息量的實例，有效地探索了性能與可解釋性之間的權衡。我們的方法在 BCLC 分期方面表現出比傳統方法更優越的性能和穩健性。這一創新不僅提升了診斷的準確性，還提供了更高的臨床可解釋性，承諾將改善患者的治療結果。 | zh_TW |
| dc.description.abstract | Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. In this study, we uncovered that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively utilize the framework, we proposed a new preprocessing technique called Masked Cropping and Padding (MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced ReViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks with the global context modeling of Vision Transformers (ViTs). This model leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. By employing Top-K Pooling strategies, it focuses on the most informative instances within each bag, effectively exploring the trade-off between performance and interpretability. Our approach demonstrates superior performance and robustness in BCLC staging compared to traditional methods. This innovation not only enhances diagnostic accuracy but also offers greater clinical interpretability, promising improved patient outcomes. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-11-15T16:07:51Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-11-15T16:07:51Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements ii 摘要 iv Abstract v Contents vii List of Figures xi List of Tables xiii Chapter 1: Introduction 1 Chapter 2: Related Works 5 • 2.1 Deep Learning in Liver Cancer Classification 5 • 2.2 Advances in CNN and ViT for Medical Imaging 6 • 2.3 Multiple Instance Learning 7 Chapter 3: Datasets 8 • 3.1 MSD 10 • 3.2 TCIA-TACE-Seg 11 • 3.3 OP 12 Chapter 4: Methods 14 • 4.1 Data Preprocessing 14 • 4.1.1 Data Acquisition 14 • 4.1.2 Data Preprocessing 15 • 4.1.3 Masked Cropping and Padding 17 • 4.1.4 Data Augmentation 18 • 4.2 Overall Framework 20 • 4.2.1 Segmentation Model 21 • 4.2.2 Cube Encoder Block 23 • 4.2.2.1 CNN Encoder 25 • 4.2.2.2 ViT Encoder 27 • 4.2.2.3 ReViT 29 • 4.2.3 MIL Pooling Block 31 • 4.2.3.1 Global Average Pooling 31 • 4.2.3.2 Top-K Pooling 32 • 4.3 Loss Function 33 Chapter 5: Experiment Setting 35 • 5.1 Baseline Models 35 • 5.2 Performance Metrics 38 • 5.2.1 Accuracy 38 • 5.2.2 Recall 39 • 5.2.3 Precision 39 • 5.2.4 Macro-F1 Score 40 • 5.3 Implementation Details 40 Chapter 6: Results & Discussions 42 • 6.1 Performance Comparison of Different Preprocessing Methods and Models 42 • 6.1.1 Statistical Analysis of Preprocessing Methods on Model Performance 44 • 6.1.2 Statistical Comparison of Model Architectures Using MCP Preprocessing 45 • 6.2 Impact of Pooling Strategies on Model Performance 46 • 6.3 Impact of Pooling Strategies on Model Explainability 48 • 6.4 Applications of the Proposed Methods 49 • 6.5 Limitations of the Segmentation Model and Rule-Based BCLC Staging 51 • 6.6 The Impact of Data Distribution 52 Chapter 7: Limitations and Future Work 55 • 7.1 Limitations 55 • 7.1.1 Dataset Variability 55 • 7.1.2 Limited Sample Size 56 • 7.2 Future Work 57 • 7.2.1 Data Expansion 57 • 7.2.2 Integration of Multiphase Imaging 58 • 7.2.3 Handling Missing Phases 59 • 7.2.4 Future Expansion to Advanced Staging and Multimodal Integration 59 • 7.2.5 Enhancing the Capability of the Segmentation Model 60 Chapter 8: Conclusion 62 References 65 | - |
| dc.language.iso | en | - |
| dc.title | 基於多實例學習框架下之混合視覺模型方法實現肝細胞癌 BCLC 分期系統 | zh_TW |
| dc.title | A Hybrid Vision Model Under the MIL Framework for BCLC Staging of Hepatocellular Carcinoma Using 3D CT | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 蘇東弘;郭柏志;王偉仲;戴邇立 | zh_TW |
| dc.contributor.oralexamcommittee | Tung-Hung Su;Po-Chih Kuo;Wei-Chung Wang;Thierry Blu | en |
| dc.subject.keyword | 醫學影像,肝細胞癌,BCLC 分期,卷積神經網絡,視覺變換器,多實例學習, | zh_TW |
| dc.subject.keyword | Medical Imaging,Hepatocellular Carcinoma,BCLCstaging,Convolutional Neural Network,Vision Transformer,Multiple Instance Learning, | en |
| dc.relation.page | 71 | - |
| dc.identifier.doi | 10.6342/NTU202404487 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-10-24 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電信工程學研究所 | - |
| dc.date.embargo-lift | 2029-10-23 | - |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 目前未授權公開取用 | 25.05 MB | Adobe PDF | 檢視/開啟 |
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。