Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88091Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 周承復 | zh_TW |
| dc.contributor.advisor | Cheng-Fu Chou | en |
| dc.contributor.author | 柯宏穎 | zh_TW |
| dc.contributor.author | Hong-Ying Ke | en |
| dc.date.accessioned | 2023-08-08T16:15:27Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-08 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-13 | - |
| dc.identifier.citation | [1] E. Alsentzer, J. R. Murphy, W. Boag, W.H. Weng, D. Jin, T. Naumann, and M. McDermott. Publicly available clinical bert embeddings. arXiv preprint arXiv:1904.03323, 2019.
[2] F. X. Bosch, J. Ribes, M. Díaz, and R. Cléries. Primary liver cancer: worldwide incidence and trends. Gastroenterology, 127(5):S5–S16, 2004. [3] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014. [4] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova. Bert: Pretraining of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. [5] J. Dong, W. Li, Q. Zeng, S. Li, X. Gong, L. Shen, S. Mao, A. Dong, and P. Wu. Ctguided percutaneous stepbystep radiofrequency ablation for the treatment of carcinoma in the caudate lobe. Medicine, 94(39), 2015. [6] S. Hochreiter and J. Schmidhuber. Long shortterm memory. Neural computation, 9(8):1735–1780, 1997. [7] H. HungChi. Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation based on feature searching and heterogeneous input. Master Thesis, NTU, TPE, 2021. [8] G. N. Ioannou, W. Tang, L. A. Beste, M. A. Tincopa, G. L. Su, T. Van, E. B. Tapper, A. G. Singal, J. Zhu, and A. K. Waljee. Assessment of a deep learning model to predict hepatocellular carcinoma in patients with hepatitis c cirrhosis. JAMA network open, 3(9):e2015626–e2015626, 2020. [9] H. Y. Kim, P. Lampertico, J. Y. Nam, H.C. Lee, S. U. Kim, D. H. Sinn, Y. S. Seo, H. A. Lee, S. Y. Park, Y.S. Lim, et al. An artificial intelligence model to predict hepatocellular carcinoma risk in korean and caucasian patients with chronic hepatitis b. Journal of Hepatology, 76(2):311–318, 2022. [10] S. S. Kulkarni, N. S. Shetty, A. M. Polnaya, A. Janu, S. Kumar, A. Puri, A. Gulia, and V. Rangarajan. Ctguided radiofrequency ablation in osteoid osteoma: result from a tertiary cancer centre in india. Indian Journal of Radiology and Imaging, 27(03):318–323, 2017. [11] I. Lurje, Z. Czigany, J. Bednarsch, C. Roderburg, P. Isfort, U. P. Neumann, and G. Lurje. Treatment strategies for hepatocellular carcinoma—a multidisciplinary approach. International journal of molecular sciences, 20(6):1465, 2019. [12] F. Mosteller and J. W. Tukey. Data analysis, including statistics. Handbook of social psychology, 2:80–203, 1968. [13] C. PoWen. Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation based on machine learning algorithms. Master Thesis, NTU, TPE, 2019. [14] L. Ren, Y. Liu, D. Huang, K. Huang, and C. Yang. Mctan: A novel multichannel temporal attentionbased network for industrial health indicator prediction. IEEE Transactions on Neural Networks and Learning Systems, 2022. [15] M. T. Ribeiro, S. Singh, and C. Guestrin. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016. [16] M. D. Robek, B. S. Boyd, and F. V. Chisari. Lambda interferon inhibits hepatitis b and c virus replication. Journal of virology, 79(6):3851–3854, 2005. [17] B. A. Schaer, A. Maurer, C. Sticherling, P. T. Buser, and S. Osswald. Routine echocardiography after radiofrequency ablation: to flog a dead horse? Europace, 11(2):155–157, 2009. [18] R. L. Siegel, K. D. Miller, N. S. Wagle, and A. Jemal. Cancer statistics, 2023. CA: a cancer journal for clinicians, 73(1):17–48, 2023. [19] B. Van Aken, I. Trajanovska, A. Siu, M. Mayrdorfer, K. Budde, and A. Löser. As sertion detection in clinical notes: Medical language models to the rescue? In Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations, pages 35–40, 2021. [20] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. [21] J. Yin, C. Gan, K. Zhao, X. Lin, Z. Quan, and Z.J. Wang. A novel model for imbalanced data classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 6680–6687, 2020. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88091 | - |
| dc.description.abstract | 肝癌的死亡率多年來位居各癌症前幾名，有一原因就是肝臟沒有神經，早期肝癌大多數都沒有症狀，在手術後復發亦然，除非透過檢驗才會知道。在肝癌復發機會高的情況下，若能從一些影像報告，或其它檢驗與檢體報告中做輔助分析並及早發現復發，早日進行治療，能大幅地降低死亡率。
在肝癌病患中，肝細胞癌佔了七成以上，本篇論文使用的資料是於 20072017 年間，以電燒術與手術作為第一次肝細胞癌治療的病患，兩者會進行比較觀察差異。這份資料集來自臺大醫學院醫研部資料庫，先前有團隊研究了較早期的資料，並且發表數篇研究成果，其涵蓋資料庫建立、提取特徵等領域，但其中有許多資料並沒有良好地與醫生團隊討論與檢查過，在資料不乾淨的情況下所得到的結果也會有比較大的不穩定性。 這篇論文將會著重在資料的前處理，如何從醫研部拿到最原始的資料開始建立新的資料庫，這幾年的研究其間都有定期與醫生做詢問與檢查。在得到資料後再進行模型預測，最後也會著重在我們的模型如何優於先前所使用的，與預測的結果的比較。 | zh_TW |
| dc.description.abstract | The mortality rate of liver cancer has consistently ranked high for many years, one reason being that the liver has no nerves, and early-stage liver cancer often has no symptoms. Even after surgery, there is still a high chance of recurrence, which can only be detected through testing. In situations where the chance of liver cancer recurrence is high, early detection through analysis of imaging reports or other test and specimen reports can significantly reduce the mortality rate by allowing for prompt treatment.
In liver cancer patients, hepatocellular carcinoma accounts for more than 70%. The data used in this paper were collected between 2007 and 2018 from patients who received either radio frequency ablation or surgery as their first treatment for HCC, and the two methods were compared for differences in outcomes. The dataset was obtained from the research database of the National Taiwan University Hospital. Previous research by a team in this field covered the establishment of the database, feature extraction, and other areas. However, many of the data points were not properly discussed or examined with medical teams, and the results obtained under such conditions may be highly unstable. This paper will focus on data preprocessing, starting from obtaining the most raw data from the research department to building a new database, and regularly consulting and examining with medical teams during the past few years of research. After obtaining the data, the paper will also focus on how our model outperforms previous models and compare the predictive results. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-08T16:15:27Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-08T16:15:27Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i
Acknowledgements iii 摘要 v Abstract vii Contents ix List of Figures xiii List of Tables xv Chapter 1 Introduction 1 Chapter 2 Related Work 5 2.1 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 Feature Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.2 Language Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1.3 Imbalance Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 Recurrence Predict Model . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.1 Basic Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.2 Attention Mechanism . . . . . . . . . . . . . . . . . . . . . . . . . 11 Chapter 3 Dataset 15 3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.2 Free Text Report . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2.1 Radiology Report . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 3.2.2 Ultrasound Report . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.2.3 Surgery Report . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.2.4 Admission & Discharge Report . . . . . . . . . . . . . . . . . . . . 20 3.3 Laboratory Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.3.1 Basic Information . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 3.3.2 Laboratory Inspection . . . . . . . . . . . . . . . . . . . . . . . . . 23 3.3.3 Drug History . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 Chapter 4 Method 27 4.1 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 4.1.1 Feature Extracting . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 4.1.1.1 Free Text Report . . . . . . . . . . . . . . . . . . . . . 28 4.1.1.2 Laboratory Data . . . . . . . . . . . . . . . . . . . . . 31 4.1.2 Labeling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.1.3 Data Format . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 4.2 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 4.2.1 Laboratory Inspection Encoder . . . . . . . . . . . . . . . . . . . . 40 4.2.2 Tumor Encoder . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 4.2.3 Basic Information Encoder . . . . . . . . . . . . . . . . . . . . . . 43 4.2.4 Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 4.2.5 Loss Function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 Chapter 5 Experiments 45 5.1 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 5.2 Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 5.3 Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 5.3.1 One Year Recurrence . . . . . . . . . . . . . . . . . . . . . . . . . 49 5.3.2 Three Years Recurrence . . . . . . . . . . . . . . . . . . . . . . . . 49 5.3.3 Hepatitis B and Hepatitis C . . . . . . . . . . . . . . . . . . . . . . 51 5.3.4 Model Explain . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 Chapter 6 Conclusion 59 References 61 | - |
| dc.language.iso | en | - |
| dc.subject | 肝細胞癌 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 文本分析 | zh_TW |
| dc.subject | 時序資料 | zh_TW |
| dc.subject | 射頻灼燒術 | zh_TW |
| dc.subject | Free-Text Analysis | en |
| dc.subject | Deep Learning | en |
| dc.subject | Time Series Data | en |
| dc.subject | HCC | en |
| dc.subject | Radiofrequency Ablation | en |
| dc.title | 基於手術與電燒治療之肝癌復發模型預測系統 | zh_TW |
| dc.title | Prediction System for HCC Recurrence on Surgical and Radiofrequency Ablation Treatments | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 梁嘉德;吳曉光;蔡子傑;呂政修 | zh_TW |
| dc.contributor.oralexamcommittee | Jia-De Liang;Hsiao-Kuang Wu;Tzu-Chieh Tsai;Jenq-Shiou Leu | en |
| dc.subject.keyword | 肝細胞癌,文本分析,深度學習,時序資料,射頻灼燒術, | zh_TW |
| dc.subject.keyword | HCC,Free-Text Analysis,Deep Learning,Time Series Data,Radiofrequency Ablation, | en |
| dc.relation.page | 63 | - |
| dc.identifier.doi | 10.6342/NTU202300885 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2023-07-14 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| dc.date.embargo-lift | 2028-07-13 | - |
| Appears in Collections: | 資訊工程學系 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-111-2.pdf Until 2028-07-13 | 12.34 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.