(44.192.112.123) 您好!臺灣時間:2021/03/01 03:36
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:鍾智堅
研究生(外文):Ross Choong Zhi Jian
論文名稱:生成性對抗網絡所生成的合成數據對於原醫學影像數據的模型可視化分析與分類表現的改進
論文名稱(外文):Visual Analytic and Classification Performance Improvement for Medical Imaging Data with Synthetic Data Generated by Generative Adversarial Networks
指導教授:鄭振牟鄭振牟引用關係廖世偉
指導教授(外文):Chen-Mou ChengShih-Wei Liao
口試委員:葉羅堯張富傑
口試日期:2019-07-16
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:電機工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:60
中文關鍵詞:深度學習遷移學習卷積神經網絡醫學影像可視化分析生成式對抗網絡合成數據
DOI:10.6342/NTU201900884
相關次數:
  • 被引用被引用:0
  • 點閱點閱:52
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
大多數的醫學影像的數據集都會面對數據不平衡問題,主要因素是比起正向個案(異常個案),負向個案(正常個案)比較容易收集。更何況,醫學影像數據集都是屬於小型數據,而這些問題都是醫學影像數據集在深度學習領域的分類任務的最大挑戰。另一方面,生成式對抗網絡 (Generative Adversarial Networks, GANs) 已證明其生成的合成數據能在各種領域上使用,如修復影像、超解析度成像以及生成更高質量的影像。生成式對抗網絡所生成的合成數據可以增加原本數據集的數量,成為解決小型數據問題的方案。再加上,基於ImageNet所預訓練的模型是這個實驗模型的基礎訓練模型以得到更好的表現性能。但是,ImageNet數據集的領域與醫學影像的領域相差甚遠,因此透過使用生成式對抗網絡所生成的合成數據能幫助原本分類任務。這個實驗主要有兩大貢獻:提出一個有效提升性能表現的訓練系統、基於Grad-CAM++上進行量的測定以探討有關使用合成數據的影響。為了分析生成式對抗網絡所生成的合成數據對於分類任務的性能,在此使用可視化分析工具——Grad-CAM++並採用量的测定,即交並比 (Intersection over Union, IoU) 以分析深度學習模型在透過分類任務裡學到了什麼。此實驗也比對不同的訓練系統進行分析以從中發現模型如何學習和表現的關鍵。最後,透過Grad-CAM++的交並比結果、測量的準確率 (accuracy) 、精確率 (precision) 、召回率 (recall) 、綜合評價指標 (F1 score)以及曲面下的接收者操作特征 (Area Under the Receiver Operating Characteristics, AUROC)的結果,新的訓練系統——第四方法,會被提出如何合理使用合成數據來提升原本的分類性能。第四方法的訓練系統透過量的測定以驗證其實用性和表現性能,結果上是比其他傳統的訓練系統,在分類性能的整體上進步了許多。在分類性能的測量結果中,進步高達2.0228%;在交並比測量的結果中,進步高達8.2815%。
Most of the medical imaging datasets usually have to deal with imbalance problem, which show that negative case (normal case) is easier to collect and find compare to positive case (abnormal case). This issue and the small-scale medical imaging dataset are the biggest problems in training the deep learning classification task. In the other hand, Generative Adversarial Networks (GANs) has shown that it can generate synthetic data that is useful in various applications, such as reconstructing images, super resolution imaging, generating high quality of images. Synthetic data generated by GANs might be a solution to small-scale issue by increasing the size of dataset. Models pre-trained on ImageNet are used as base models to get better performance. However. the domain of ImageNet dataset is different from the domain of medical imaging. Therefore, the synthetic data generated by GANs based on medical imaging domain can be helpful. This experiment has two main contributions: proposing a effective training pipeline and analyzing the impact of synthetic data through quantity measurement on Grad-CAM++. To analyze the impact of GANs-based synthetic data on the downstream classification performance, quantity measurement: intersection over union (IoU) metric is applied on visual explanation tool: Grad-CAM++, to analyze what deep learning model has learned through the classification task. Various training pipelines are compared to gain insight into how the model learns and performs. From the observation results of both IoU metric measurement in Grad-CAM++ and measurement of accuracy, precision, recall, f1-score, and Area Under the Receiver Operating Characteristics (AUROC), a new training pipeline: method 4 is proposed to handle the synthetic data to improve the overall classification performance. The overall classification performance of the proposed pipeline is improved compare to the other training pipelines. The maximum improvement rate in classification performance is 2.0228%, where the maximum improvement rate in IoU metric is 8.2815%.
口試委員會審審定定書...........................................................i
Acknowledgments....................................................................ii
摘要.........................................................................................iii
Abstract....................................................................................v
List of Figures...........................................................................ix
List of Tables.............................................................................x
Chapter 1 Introduction..........................................................1
Chapter 2 Related Theory.......................................................5
2.1 Dense Convolutional Network......................................5
2.2 Generative Adversarial Networks.................................8
2.3 Grad-CAM++...............................................................11
Chapter 3 Methodology....................................................13
3.1 Dataset.......................................................................14
3.2 Progressive Growing of GAN......................................16
3.3 Training Pipeline..........................................................17
3.4 Evaluation Metrics......................................................21
3.5 Intersection over Union on heatmap.........................23
Chapter 4 Experiment..........................................................26
4.1 Preprocessing Data....................................................27
4.2 Model and Hyperparameters Tuning.........................28
4.3 Analyzing Results of Five Basic Evaluation Metrics….30
4.4 Analyzing Results of IoU............................................38
Chapter 5 Discussion...........................................................47
Chapter 6 Conclusion..........................................................49
Chapter 7 Future Work.......................................................51
7.1 Dataset.....................................................................51
7.2 Synthetic data...........................................................52
7.3 Model........................................................................53
Bibliography...........................................................................54
[1] P. Ruiz, “Understanding and visualizing densenets,” 10 2018.https:// towardsdatascience.com/understanding-and-visualizing-densenets-7f688092391a.
[2] T. Karras, T. Aila, S. Laine, and J. Lehtinen, “Progressive growing of gans for improved quality, stability, and variation,” CoRR, vol. abs/1710.10196, 2017.
[3] RSNA Pneumonia Detection Challenge, “Radiological society of north america.”
https://www.kaggle.com/c/rsna-pneumonia-detection-challenge, 2018.
[4] G. Huang, Z. Liu, and K. Q. Weinberger, “Densely connected convolutional networks,” CoRR, vol. abs/1608.06993, 2016.
[5] H. Pratt, F. Coenen, D. M. Broadbent, S. P. Harding, and Y. Zheng, “Convolutional neural networks for diabetic retinopathy,” Procedia Computer Science, vol. 90, pp. 200 – 205, 2016. 20th Conference on Medical Image Understanding and Analysis (MIUA 2016).
[6] X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, “Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly supervised classification and localization of common thorax diseases,”CoRR,vol. abs/1705.02315, 2017.
[7] P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, D. Ding, A. Bagul, C. Langlotz, K. Shpanskaya, M. P. Lungren, and A. Y. Ng, “Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning,” CoRR, vol. abs/1711.05225, 2017.
[8] Q. Guan, Y. Huang, Z. Zhong, Z. Zheng, L. Zheng, and Y. Yang, “Diagnose like a radiologist: Attention guided convolutional neural network for thorax disease classification,” CoRR, vol. abs/1801.09927, 2018.
[9] R. Poplin, A. V. Varadarajan, K. Blumer, Y. Liu, M. McConnell, G. Corrado, L. Peng, and D. Webster, “Predicting cardiovascular risk factors in retinal fundus photographs using deep learning,” Nature Biomedical Engineering, 2018.
[10] J. D. Fauw, J. R. Ledsam, B. Romera-Paredes, S. Nikolov, N. Tomasev, S. Blackwell, H. Askham, X. Glorot, B. O’Donoghue, D. Visentin, G. van den Driessche, B. Lakshminarayanan, C. Meyer, F. Mackinder, S. Bouton, K. W. Ayoub, R. Chopra, D. King, A. Karthikesalingam, C. O. Hughes, R. A. O. Raine, J. C. Hughes, D. A. Sim, C. A. Egan, A. Tufail, H. Montgomery, D. Hassabis, G. Rees, T. Back, P. T. Khaw, M. Suleyman, J. Cornebise, P. A. Keane, and O. Ronneberger, “Clinically applicable deep learning for diagnosis and referral in retinal disease,” Nature Medicine, vol. 24, pp. 1342–1350, 2018.
[11] J. Son, S. J. Park, and K. Jung, “Retinal vessel segmentation in fundoscopic im-ages with generative adversarial networks,”CoRR, vol. abs/1706.09318, 2017.
[12] A. Shvets, A. Rakhlin, A. A. Kalinin, and V. Iglovikov, “Automatic instrument segmentation in robot-assisted surgery using deep learning,” CoRR, vol. abs/1803.01207, 2018.
[13] X. Zhu, C. Vondrick, C. C. Fowlkes, and D. Ramanan, “Do we need more training data?,” CoRR, vol. abs/1503.01508, 2015.
[14] J. Cho, K. Lee, E. Shin, G. Choy, and S. Do, “Medical image deep learning with hospital PACS dataset,” CoRR, vol. abs/1511.06348, 2015.
[15] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. S. Bernstein, A. C. Berg, and F. Li, “Imagenet large scale visual recognition challenge,” CoRR, vol. abs/1409.0575, 2014.
[16] B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba, “Places: A 10 million image database for scene recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–1, 07 2017.
[17] M. Buda, A. Maki, and M. A. Mazurowski, “A systematic study of the class imbalance problem in convolutional neural networks,” Neural Networks, vol. 106, pp. 249 – 259, 2018.
[18] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair,
A. Courville, and Y. Bengio, “Generative adversarial nets,” in Advances in Neural Information Processing Systems 27 (Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, eds.), pp. 2672–2680, Curran Asso-ciates, Inc., 2014.
[19] M. Mirza and S. Osindero, “Conditional generative adversarial nets,” CoRR, vol. abs/1411.1784, 2014.
[20] A. Odena, C. Olah, and J. Shlens, “Conditional image synthesis with auxiliary classifier GANs,” in Proceedings of the 34th International Conference on Machine Learning (D. Precup and Y. W. Teh, eds.), vol. 70 of Proceedings of Machine Learning Research, (International Convention Centre, Sydney, Australia), pp. 2642–2651, PMLR, 06–11 Aug 2017.
[21] F. Calimeri, A. Marzullo, C. Stamile, and G. Terracina, “Biomedical data augmentation using generative adversarial neural networks,” in Artificial Neural Networks and Machine Learning – ICANN 2017 (A. Lintas, S. Rovetta, P. F. Verschure, and A. E. Villa, eds.), (Cham), pp. 626–634, Springer International Publishing, 2017.
[22] A. Madani, M. Moradi, A. Karargyris, and T. Syeda-Mahmood, “Chest x-ray generation and data augmentation for cardiovascular abnormality classification,” in Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 10574 of Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, p. 105741M, Mar. 2018.
[23] M. Frid-Adar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “Gan-based synthetic medical image augmentation for increased CNN performance in liver lesion classification,” CoRR, vol. abs/1803.01229,2018.
[24] X. Yi, E. Walia, and P. Babyn, “Generative adversarial network in medical imaging: A review,” CoRR, vol. abs/1809.07294, 2018.
[25] T. C. W. Mok and A. C. S. Chung, “Learning data augmentation for brain tumor segmentation with coarse-to-fine generative adversarial networks,” CoRR, vol. abs/1805.11291, 2018.
[26] S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. on Knowl. and Data Eng., vol. 22, pp. 1345–1359, 10 2010.
[27] B. Tan, Y. Zhang, S. J. Pan, and Q. Yang, “Distant domain transfer learning,” in Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, pp. 2604–2610, AAAI Press, 2017.
[28] A. L. Brown, “Domainspecific principles affect learning and transfer in children,” Cognitive Science, vol. 14, pp. 107–133, 01 1990.
[29] Y. Wei, Y. Zhang, and Q. Yang, “Learning to transfer,” CoRR, vol. abs/1708.05629, 2017.
[30] K. Simonyan, A. Vedaldi, and A. Zisserman, “Deep inside convolutional networks: Visualising image classification models and saliency maps.,” CoRR, vol. abs/1312.6034, 2013.
[31] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” CoRR, vol. abs/1512.04150, 2015.
[32] R. R. Selvaraju, A. Das, R. Vedantam, M. Cogswell, D. Parikh, and D. Batra,“Grad-cam: Why did you say that? visual explanations from deep networksvia gradient-based localization,”CoRR, vol. abs/1610.02391, 2016.
[33] A. Chattopadhyay, A. Sarkar, P. Howlader, and V. N. Balasubramanian, “Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks,” CoRR, vol. abs/1710.11063, 2017.
[34] S. Bianco, R. Cadene, L. Celona, and P. Napoletano, “Benchmark analysis of representative deep neural network architectures,” CoRR, vol. abs/1810.00736, 2018.
[35] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein generative adversarial networks,” in Proceedings of the 34th International Conference on Machine Learning (D. Precup and Y. W. Teh, eds.), vol. 70 of Proceedings of Machine Learning Research, (International Convention Centre, Sydney, Australia), pp. 214–223, PMLR, 06–11 Aug 2017.
[36] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, “Improved training of wasserstein gans,” CoRR, vol. abs/1704.00028, 2017.
[37] H. Ravishankar, P. Sudhakar, R. Venkataramani, S. Thiruvenkadam, P. Annangi, N. Babu, and V. Vaidya, “Understanding the mechanisms of deep transfer learning for medical images,” CoRR, vol. abs/1704.06040, 2017.
[38] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A survey on deep transfer learning,” CoRR, vol. abs/1808.01974, 2018.
[39] S. G. Finlayson, H. Lee, I. S. Kohane, and L. Oakden-Rayner, “Towards generative adversarial networks as a new paradigm for radiology education,” CoRR, vol. abs/1812.01547, 2018.
[40] S. Kornblith, J. Shlens, and Q. V. Le, “Do better imagenet models transfer better?,” CoRR, vol. abs/1805.08974, 2018.
[41] A. R. Zamir, A. Sax, W. B. Shen, L. J. Guibas, J. Malik, and S. Savarese, “Taskonomy: Disentangling task transfer learning,” CoRR, vol. abs/1804.08328, 2018.
[42] N. Peng and M. Dredze, “Multi-task multi-domain representation learning for sequence tagging,” CoRR, vol. abs/1608.02689, 2016.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔