請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51471完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐宏民 | |
| dc.contributor.author | Hsin-Fu Huang | en |
| dc.contributor.author | 黃信輔 | zh_TW |
| dc.date.accessioned | 2021-06-15T13:35:25Z | - |
| dc.date.available | 2018-02-16 | |
| dc.date.copyright | 2016-02-16 | |
| dc.date.issued | 2015 | |
| dc.date.submitted | 2016-01-28 | |
| dc.identifier.citation | [1] M. Balu, K. M. Kelly, C. B. Zachary, R. M. Harris, T. B. Krasieva, K. König, A. J. Durkin, and B. J. Tromberg. Distinguishing between benign and malig- nant melanocytic nevi by in vivo multiphoton microscopy. Cancer research, 74(10):2688–2697, 2014.
[2] K. Busam, C. Charles, C. Lohmann, A. Marghoob, M. Goldgeier, and A. Halpern. Detection of intraepidermal malignant melanoma in vivo by confocal scanning laser microscopy. Melanoma research, 12(4):349–355, 2002. [3] S.-Y. Chen, S.-U. Chen, H.-Y. Wu, W.-J. Lee, Y.-H. Liao, and C.-K. Sun. In vivo virtual biopsy of human skin by using noninvasive higher harmonic generation mi- croscopy. Selected Topics in Quantum Electronics, IEEE Journal of, 16(3):478–492, 2010. [4] S.-Y.Chen,H.-Y.Wu,andC.-K.Sun.Invivoharmonicgenerationbiopsyofhuman skin. Journal of biomedical optics, 14(6):060505–060505, 2009. [5] A. Cruz-Roa, A. Basavanhally, F. González, H. Gilmore, M. Feldman, S. Ganesan, N. Shih, J. Tomaszewski, and A. Madabhushi. Automatic detection of invasive duc- tal carcinoma in whole slide images with convolutional neural networks. In SPIE Medical Imaging, pages 904103–904103. International Society for Optics and Pho- tonics, 2014. [6] A. A. Cruz-Roa, J. E. A. Ovalle, A. Madabhushi, and F. A. G. Osorio. A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection. In Medical Image Computing and Computer- Assisted Intervention–MICCAI 2013, pages 403–410. Springer, 2013. [7] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing sys- tems, pages 1097–1105, 2012. [8] M. Rajadhyaksha, M. Grossman, D. Esterowitz, R. H. Webb, and R. R. Anderson. In vivo confocal scanning laser microscopy of human skin: melanin provides strong contrast. Journal of Investigative Dermatology, 104(6):946–952, 1995. [9] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [10] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Van- houcke, and A. Rabinovich. Going deeper with convolutions. arXiv preprint arXiv:1409.4842, 2014. [11] M.-R. Tsai, Y.-H. Cheng, J.-S. Chen, Y.-S. Sheen, Y.-H. Liao, and C.-K. Sun. Dif- ferential diagnosis of nonmelanoma pigmented skin lesions based on harmonic gen- eration microscopy. Journal of biomedical optics, 19(3):036001–036001, 2014. [12] H. Wang, A. Cruz-Roa, A. Basavanhally, H. Gilmore, N. Shih, M. Feldman, J. Tomaszewski, F. Gonzalez, and A. Madabhushi. Mitosis detection in breast can- cer pathology images by combining handcrafted and convolutional neural network features. Journal of Medical Imaging, 1(3):034003–034003, 2014. [13] W.-H. Weng, M.-R. Tsai, Y.-H. Liao, and C.-K. Sun. Differentiating pigmented skin tumors by the tumor-associated melanocytes based on in vivo third harmonic generation microscopy. In SPIE Photonics West BIOS 2015 Technical Summaries, page 3, 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51471 | - |
| dc.description.abstract | 基底細胞癌是一種最常見的皮膚癌，而傳統上，它必須透過侵入式且耗時的組織學檢測，因此活體內顯影的技術，比如說HGM，被用來當做非侵入式的診斷基礎，但HGM會產生大量的影像導致檢測人員需要花大量的時間去檢測。在這篇論文中，我們最主要集中在如果使用客製化且有效率的CNN模型來去自動偵測BCC的特徵，我們最好的模型可以達到比AlexNet更好的結果，而且只需要AlexNet不到1\%的參數量。而這篇論文的方法也可以套用在其他相似的醫療圖片上。 | zh_TW |
| dc.description.abstract | Diagnosis of basal cell carcinoma (BCC), the most common skin cancer, is made by histologic examination traditionally. Yet the process is invasive and time-consuming. In vivo imaging modalities such as harmonic generation microscopy (HGM) was therefore developed for noninvasive diagnosis of BCC. However the images acquired by HGM are too many for physicians to interpret manually. Thus, in this paper we focus on detecting features of BCC automatically by customizing compact and efficient convolutional neural network (CNN) models on HGM images of BCC. Our best model achieves a better result than AlexNet cite{krizhevsky2012imagenet}, while using less than its 1\% number of parameters. The study indicated the potential solution of using customized CNN to detect the features in similar imaging modalities. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T13:35:25Z (GMT). No. of bitstreams: 1 ntu-104-R02922054-1.pdf: 1448249 bytes, checksum: f1f805bd496d5ba87d96ab665d9d6be7 (MD5) Previous issue date: 2015 | en |
| dc.description.tableofcontents | 誌謝 ii
Acknowledgements iii 摘要 iv Abstract v 1 Introduction 1 1.1 Basal-CellCarcinoma............................ 1 1.2 ConvolutionalNeuralNetworks ...................... 2 2 Dataset 3 2.1 Numberoforiginalimages ......................... 3 2.2 Preprocessing................................ 3 2.2.1 slidingwindows .......................... 3 2.2.2 Subsampling for training and validation set . . . . . . . . . . . . 3 2.2.3 Evaluationfortestingset...................... 4 2.3 Datasetafterpreprocessing......................... 4 3 Methodology 5 3.1 Deepersmallkernels ............................ 5 4 Experiment Results 7 5 Conclusion 9 5.1 Why to design our own model? . . . . . . . . . . . . . . . . . . . . . . . 9 5.2 Guidelineofcustomacompactandefficientmodel . . . . . . . . . . . . 9 Bibliography 10 | |
| dc.language.iso | en | |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 基底細胞癌 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 基底細胞癌 | zh_TW |
| dc.subject | Convolutional Neural Networks | en |
| dc.subject | Basal Cell Carcinoma | en |
| dc.subject | Basal Cell Carcinoma | en |
| dc.subject | Convolutional Neural Networks | en |
| dc.title | 利用卷積神經網路自動化非侵入式基底細胞癌偵測 | zh_TW |
| dc.title | Automated Non-Invasive Basal-Cell Carcinoma Detection by Convolutional Neural Network | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 104-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳文進,孫民,李宏毅 | |
| dc.subject.keyword | 基底細胞癌,卷積神經網路, | zh_TW |
| dc.subject.keyword | Basal Cell Carcinoma,Convolutional Neural Networks, | en |
| dc.relation.page | 11 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2016-01-28 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-104-1.pdf 未授權公開取用 | 1.41 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。