請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84291完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳永耀(Yung-Yaw Chen) | |
| dc.contributor.author | Kuan-Chung Wang | en |
| dc.contributor.author | 王冠中 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:07:53Z | - |
| dc.date.copyright | 2022-07-05 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-06-15 | |
| dc.identifier.citation | [1] P. Rawla, T. Sunkara, P. Muralidharan, and J. P. Raj, 'Update in global trends and aetiology of hepatocellular carcinoma,' Contemporary oncology, vol. 22, no. 3, p. 141, 2018. [2] J. Llovet et al., 'Hepatocellular carcinoma nature reviews,' Dis Primers, vol. 7, no. 1, p. 6, 2021. [3] N. Dimitriou, O. Arandjelović, and P. D. Caie, 'Deep Learning for Whole Slide Image Analysis: An Overview,' (in English), Frontiers in Medicine, Mini Review vol. 6, no. 264, 2019-November-22 2019, doi: 10.3389/fmed.2019.00264. [4] Y.-S. Lin, P.-H. Huang, and Y.-Y. Chen, 'Deep Learning-Based Hepatocellular Carcinoma Histopathology Image Classification: Accuracy Versus Training Dataset Size,' IEEE Access, vol. 9, pp. 33144-33157, 2021. [5] A. Kiani et al., 'Impact of a deep learning assistant on the histopathologic classification of liver cancer,' NPJ digital medicine, vol. 3, no. 1, pp. 1-8, 2020. [6] M. Roy et al., 'Convolutional autoencoder based model HistoCAE for segmentation of viable tumor regions in liver whole-slide images,' Scientific Reports, vol. 11, no. 1, pp. 1-10, 2021. [7] H. Tokunaga, B. K. Iwana, Y. Teramoto, A. Yoshizawa, and R. Bise, 'Negative pseudo labeling using class proportion for semantic segmentation in pathology,' in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XV 16, 2020: Springer, pp. 430-446. [8] Y. Liu et al., 'Artificial intelligence–based breast cancer nodal metastasis detection: insights into the black box for pathologists,' Archives of pathology & laboratory medicine, vol. 143, no. 7, pp. 859-868, 2019. [9] S. Khan, N. Islam, Z. Jan, I. U. Din, and J. J. C. Rodrigues, 'A novel deep learning based framework for the detection and classification of breast cancer using transfer learning,' Pattern Recognition Letters, vol. 125, pp. 1-6, 2019. [10] A. Krizhevsky and G. Hinton, 'Learning multiple layers of features from tiny images,' 2009. [11] A. Swanson, M. Kosmala, C. Lintott, R. Simpson, A. Smith, and C. Packer, 'Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna,' Scientific data, vol. 2, no. 1, pp. 1-14, 2015. [12] M. Willi et al., 'Identifying animal species in camera trap images using deep learning and citizen science,' Methods in Ecology and Evolution, vol. 10, no. 1, pp. 80-91, 2019. [13] C. Sun, A. Shrivastava, S. Singh, and A. Gupta, 'Revisiting unreasonable effectiveness of data in deep learning era,' in Proceedings of the IEEE international conference on computer vision, 2017, pp. 843-852. [14] A. Adadi, 'A survey on data‐efficient algorithms in big data era,' Journal of Big Data, vol. 8, no. 1, pp. 1-54, 2021. [15] R. D. Riley et al., 'Calculating the sample size required for developing a clinical prediction model,' Bmj, vol. 368, 2020. [16] R. K. Samala, H.-P. Chan, L. Hadjiiski, M. A. Helvie, C. D. Richter, and K. H. Cha, 'Breast cancer diagnosis in digital breast tomosynthesis: effects of training sample size on multi-stage transfer learning using deep neural nets,' IEEE transactions on medical imaging, vol. 38, no. 3, pp. 686-696, 2018. [17] J. J. Boutilier, T. Craig, M. B. Sharpe, and T. C. Chan, 'Sample size requirements for knowledge‐based treatment planning,' Medical physics, vol. 43, no. 3, pp. 1212-1221, 2016. [18] H. G. Schnack and R. S. Kahn, 'Detecting neuroimaging biomarkers for psychiatric disorders: sample size matters,' Frontiers in psychiatry, vol. 7, p. 50, 2016. [19] J. Cho, K. Lee, E. Shin, G. Choy, and S. Do, 'How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?,' arXiv preprint arXiv:1511.06348, 2015. [20] C. Szegedy et al., 'Going deeper with convolutions,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1-9. [21] C. Luo, X. Li, L. Wang, J. He, D. Li, and J. Zhou, 'How does the data set affect cnn-based image classification performance?,' in 2018 5th International conference on systems and informatics (ICSAI), 2018: IEEE, pp. 361-366. [22] S. Shahinfar, P. Meek, and G. Falzon, '“How many images do I need?” Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring,' Ecological Informatics, vol. 57, p. 101085, 2020. [23] T.-Y. Lin et al., 'Microsoft coco: Common objects in context,' in European conference on computer vision, 2014: Springer, pp. 740-755. [24] 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, 2016, pp. 770-778. [25] O. Russakovsky et al., 'Imagenet large scale visual recognition challenge,' International journal of computer vision, vol. 115, no. 3, pp. 211-252, 2015. [26] L. Hou, D. Samaras, T. M. Kurc, Y. Gao, J. E. Davis, and J. H. Saltz, 'Patch-based convolutional neural network for whole slide tissue image classification,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2424-2433. [27] F. Iandola, M. Moskewicz, S. Karayev, R. Girshick, T. Darrell, and K. Keutzer, 'Densenet: Implementing efficient convnet descriptor pyramids,' arXiv preprint arXiv:1404.1869, 2014. [28] K. Simonyan and A. Zisserman, 'Very deep convolutional networks for large-scale image recognition,' arXiv preprint arXiv:1409.1556, 2014. [29] Y. Sun, A. K. Wong, and M. S. Kamel, 'Classification of imbalanced data: A review,' International journal of pattern recognition and artificial intelligence, vol. 23, no. 04, pp. 687-719, 2009. [30] V. Ganganwar, 'An overview of classification algorithms for imbalanced datasets,' International Journal of Emerging Technology and Advanced Engineering, vol. 2, no. 4, pp. 42-47, 2012. [31] M. P. Paing, C. Pintavirooj, S. Tungjitkusolmun, S. Choomchuay, and K. HAMAMOTO, 'Comparison of sampling methods for imbalanced data classification in random forest,' in 2018 11th Biomedical Engineering International Conference (BMEiCON), 2018: IEEE, pp. 1-5. [32] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' Advances in neural information processing systems, vol. 25, 2012. [33] J. Hu, L. Shen, and G. Sun, 'Squeeze-and-excitation networks,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132-7141. [34] R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, 'Convolutional neural networks: an overview and application in radiology,' Insights into imaging, vol. 9, no. 4, pp. 611-629, 2018. [35] S. Ioffe and C. Szegedy, 'Batch normalization: Accelerating deep network training by reducing internal covariate shift,' in International conference on machine learning, 2015: PMLR, pp. 448-456. [36] A. G. Howard et al., 'Mobilenets: Efficient convolutional neural networks for mobile vision applications,' arXiv preprint arXiv:1704.04861, 2017. [37] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, 'Rethinking the inception architecture for computer vision,' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818-2826. [38] M. Tan and Q. Le, 'Efficientnet: Rethinking model scaling for convolutional neural networks,' in International Conference on Machine Learning, 2019: PMLR, pp. 6105-6114. [39] M. Tan et al., 'Mnasnet: Platform-aware neural architecture search for mobile,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2820-2828. [40] G. vanRossum, 'Python reference manual,' Department of Computer Science [CS], no. R 9525, 1995. [41] A. Paszke et al., 'Pytorch: An imperative style, high-performance deep learning library,' Advances in neural information processing systems, vol. 32, 2019. [42] M. Fatica, 'CUDA toolkit and libraries,' in 2008 IEEE hot chips 20 symposium (HCS), 2008: IEEE, pp. 1-22. [43] G. Bradski, 'The openCV library,' Dr. Dobb's Journal: Software Tools for the Professional Programmer, vol. 25, no. 11, pp. 120-123, 2000. [44] S. Van Der Walt, S. C. Colbert, and G. Varoquaux, 'The NumPy array: a structure for efficient numerical computation,' Computing in science & engineering, vol. 13, no. 2, pp. 22-30, 2011. [45] F. Pedregosa et al., 'Scikit-learn: Machine learning in Python,' the Journal of machine Learning research, vol. 12, pp. 2825-2830, 2011. [46] D. P. Kingma and J. Ba, 'Adam: A method for stochastic optimization,' arXiv preprint arXiv:1412.6980, 2014. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84291 | - |
| dc.description.abstract | 肝細胞癌（Hepatocellular carcinoma）是一種原發性肝臟惡性腫瘤，每年導致全球數十萬人死亡。早期的病理學檢查依靠病理科醫師使用顯微鏡觀察細胞與組織型態進行診斷。隨著科學技術的進步，病理學檢查加入了人工智慧輔助醫生診斷，讓診斷比以往更快、更準確。然而，數位病理切片影像的解析度往往超過數十億像素，因此需要將其切割成數以萬計的補丁（patch）才能應用。實驗室過去的研究主要專注在數位病理切片影像的切片數量如何提高模型對新數位病理切片影像分類的正確率，但沒有探討數位病理切片影像中的補丁數量如何影響模型。本研究探討不同的補丁訓練樣本量對卷積神經網絡模型診斷正確率的影響，希望可以減輕病理科醫師在標註數位病理切片影像工作的負擔。實驗結果顯示可以用少量的醫師標註補丁達成該數位病理切片影像之分類模型訓練並取得相當好的分類正確率（多高於90%以上）。此外，本研究還發現雖然添加數位病理切片影像的數量可以提高模型對新數位病理切片影像進行分類的正確率，但從單張數位病理切片影像中選取更多的補丁進行訓練，並不能有效提高新數位病理切片影像分類的正確率。本論文提供了增進數位病理切片影像分類正確率的方向，同時可以減少病理科醫師於標註資料的負擔，降低分類器訓練之計算時間與成本。 | zh_TW |
| dc.description.abstract | Hepatocellular carcinoma is a primary liver malignancy and causes hundreds of thousands of deaths worldwide each year. Early pathological examination relied on pathologists using microscopes to observe the morphology of cells and tissues to diagnose. As technology advances, the pathological examination has added artificial intelligence to assist pathologists in making diagnoses faster and more accurate. However, digital pathological images often have resolutions in billions of pixels, so they need to be cropped into tens of thousands of patches for application. Our past research has mainly focused on how the number of images improves the model's accuracy for new images but has not explored how the number of patches in an image affects the model's accuracy. This study explores the effect of different training patch sample sizes on the accuracy of convolutional neural network models, hoping to reduce the burden of pathologists on labeling images. The experimental results show that a small number of labeled patches can be used to implement the training of a pathological image classification model, and good classification accuracy (above 90%) can be achieved. In addition, this study also found that while increasing the number of pathological images can improve the accuracy for new images, acquiring more patches from a single pathological image is ineffective in improving the accuracy for new images. This thesis provides directions for improving the pathological image classification accuracy while reducing the burden of pathologists on labeling data and reducing the computation time and cost of classifier training. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:07:53Z (GMT). No. of bitstreams: 1 U0001-2604202219351600.pdf: 4728263 bytes, checksum: 1c032ead7155cac9e7e2b622fed3a1b3 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 口試委員會審訂書 i 誌謝 ii 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES viii LIST OF TABLES xi Chapter 1 Introduction 1 1.1 Motivation 2 1.2 Problem Definition 3 1.3 Previous Approach 4 1.4 Proposed Method 5 1.5 Thesis Structure 6 Chapter 2 Literature Review 7 2.1 The Effect of the Training Sample Size 7 2.1.1 Studies in the Medical Field 7 2.1.2 Studies in Other Fields 10 2.2 Convolutional Neural Network on Pathological Image Classification 13 2.2.1 Patch-based Method for Pathological Image Classification 13 2.2.2 Primary Liver Cancer Image Classification 14 2.2.3 Lung Cancer Image Classification 16 2.2.4 Breast Cancer Image Classification 16 2.3 Summary 18 Chapter 3 Methodology 19 3.1 Problem Formulation 19 3.2 Hepatocellular Carcinoma Dataset Establishment 20 3.2.1 Process for Filtering Out Non-ideal Patches 22 3.2.2 Random Undersampling Method 24 3.2.3 Divide Dataset into Different Training Sample Sizes 28 3.3 Convolutional Neural Network Architecture 29 3.3.1 Convolutional Layer 31 3.3.2 Batch Normalization 32 3.3.3 Squeeze-and-excitation Block 33 3.3.4 Depthwise Separable Convolution 34 3.4 Architecture Comparison on the HCC Dataset 35 Chapter 4 Partial Data Training Experiments 41 4.1 Experimental Setup 42 4.1.1 Specifications of Hardware and Software 42 4.1.2 Hyperparameter Settings 43 4.2 Utilize a Single Image to Train a Model 44 4.2.1 Testing Results for Training Images 44 4.2.2 Predictions of the Regression Model 64 4.3 Utilize Forty Images to Train a Model 70 4.3.1 Testing Results for Training Images 70 4.3.2 Testing Results for New Images 82 4.4 Results and Discussions 85 4.4.1 Results of Models Trained Based on One Image 85 4.4.2 Results of Models Trained Based on Forty Images 89 4.4.3 Results Comparison between 1IMT Models and 40IMT Models 91 4.4.4 Computation Time of Classifier Training 92 Chapter 5 Conclusions and Future Work 94 REFERENCES 95 | |
| dc.language.iso | en | |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 影像分類 | zh_TW |
| dc.subject | 肝細胞癌 | zh_TW |
| dc.subject | 人工智慧 | zh_TW |
| dc.subject | 數位病理影像 | zh_TW |
| dc.subject | artificial intelligence | en |
| dc.subject | image classification | en |
| dc.subject | convolutional neural network | en |
| dc.subject | digital pathological image | en |
| dc.subject | hepatocellular carcinoma | en |
| dc.title | 卷積神經網路訓練樣本量對肝細胞癌病理影像分類的影響 | zh_TW |
| dc.title | The Effect of the Training Sample Size for Convolutional Neural Network on Hepatocellular Carcinoma Pathological Image Classification | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 顏家鈺(Jia-Yush Yen),黃佩欣(Pei-Hsin Huang),林于翔(Yu-Shiang Lin) | |
| dc.subject.keyword | 肝細胞癌,人工智慧,數位病理影像,卷積神經網路,影像分類, | zh_TW |
| dc.subject.keyword | hepatocellular carcinoma,artificial intelligence,digital pathological image,convolutional neural network,image classification, | en |
| dc.relation.page | 100 | |
| dc.identifier.doi | 10.6342/NTU202200726 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-06-20 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-07-05 | - |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2604202219351600.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 4.62 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。