請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/3867
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 廖世偉(Shih Wei Liao) | |
dc.contributor.author | Jonathan Ponce Gamero | en |
dc.contributor.author | 彭強森 | zh_TW |
dc.date.accessioned | 2021-05-13T08:37:45Z | - |
dc.date.available | 2018-08-02 | |
dc.date.available | 2021-05-13T08:37:45Z | - |
dc.date.copyright | 2016-08-02 | |
dc.date.issued | 2016 | |
dc.date.submitted | 2016-07-25 | |
dc.identifier.citation | [1] Kreulen TH, Bove AA, McDonough MT, Sands MJ, Spann JF: The evaluation of left ventricular function in man -- a comparison of methods. Circulation 51: 677, 1975
[2] Cohn PF, Gorlin R, Herman MV, Sonnenblick EH, Horn HR, Cohn LH, Collins JJ Jr: Relation between contractile reserve and prognosis in patients with coronary artery disease and a depressed ejection fraction. Circulation 51: 414, 1975 [3] Bartle SH, Sanmarco ME, Dammann JF Jr: Ejection fraction - an index of myocardial function. (abstr) Am J Cardiol 15: 125, 1965 [4] Hood WP Jr, Rackley CE, Rolett EL: Ejection velocity and ejection fraction as indices of ventricular contractility in man. (abstr) Circulation 38 (suppl VI): VI-101, 1968 [5] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. 'Imagenet classification with deep convolutional neural networks.' Advances in neural information processing systems. 2012. [6] Frans, J. Th, et al. 'Multiple gated cardiac blood pool imaging for left ventricular ejection fraction: validation of the technique and assessment of variability.' The American journal of cardiology 43.6 (1979): 1159-1166. [7] Lin, Xiang, Brett R. Cowan, and Alistair A. Young. 'Automated detection of left ventricle in 4D MR images: experience from a large study.' International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer Berlin Heidelberg, 2006. [8] Illingworth, John, and Josef Kittler. 'A survey of the Hough transform.' Computer vision, graphics, and image processing 44.1 (1988): 87-116. [9] Data Science Bowl Cardiac Challenge Data, https://www.kaggle.com/c/second-annualdata-science-bowl/data [10] Data Science Bowl Cardiac Challenge Description, https://www.kaggle.com/c/secondannual-data-science-bowl [11] P.Y. Simard, D. Steinkraus, and J.C. Platt. Best practices for convolutional neural networks applied to visual document analysis. In Proceedings of the Seventh International Conference on Document Analysis and Recognition, volume 2, pages 958–962, 2003. [12] S.C. Turaga, J.F. Murray, V. Jain, F. Roth, M. Helmstaedter, K. Briggman, W. Denk, and H.S. Seung. Convolutional networks can learn to generate affinity graphs for image segmentation. Neural Computation, 22(2):511–538, 2010. [13] Wisneski, J. A., et al. 'Left ventricular ejection fraction calculated from volumes and areas: underestimation by area method.' Circulation 63.1 (1981): 149-151. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/3867 | - |
dc.description.abstract | 基於深度學習之生醫影像分割暨分類 | zh_TW |
dc.description.abstract | Processing of biomedical images is one of the most important tasks that medical institutions such as hospitals and research centers deal with in a day to day basis, but even though this is such an important and basic task technology and current approaches have never been able to be successfully used in practical situations mainly because of their low accuracy, this has started to change in the beginning of 2012 with the use of convolutional neural networks and deep learning to accurately classify and segment a variety of different images, including biomedical images.
Although these new technologies are being widely used with incredible results in many diverse fields, their adoption in the medical community has been slow to say the least, this has been due to many different reasons like the fact that the training data needed to provide a good accuracy model needs to come from a wide variety of patients, hundreds at least, from all around the world, from all age groups and sexes. This in it by itself is a great challenge to put together for a medical institution let alone for an individual, and even after gathering the data, a great deal of effort needs to be put into anonymizing the data. This is extremely important because by law any medical records have to be completely private and cannot be used without the expressive permission of the patient, so in order to facilitate this data many hospitals will anonymize the data so it cannot be tracked down to the patient. The following thesis will try to provide an approach on segmenting and classifying biomedical images, specifically heart MRI images taken by a trained professional, using a series of steps, which include deep learning, to accurately determine the volume of the heart’s left ventricle when it is in diastole, the largest volume of a heart cycle, and systole, the smallest volume of a heart cycle, with this measurement one can calculate the ejection fraction, often described as the most important measurement for early detection of heart disease. As stated before an accuracy high enough to be used in actual medical scenarios will tried to be achieved. The data used for the training for the deep learning model was supplied by Kaggle, an online competition oriented platform designed to solve many of today’s difficult problems. What was also tried to achieve with this research was to create a way to track foreign objects such as cancer and different other diseases, first tracking the object of interest and then using deep learning to either classify, measure or detect the objects main characteristics. | en |
dc.description.provenance | Made available in DSpace on 2021-05-13T08:37:45Z (GMT). No. of bitstreams: 1 ntu-105-R03922147-1.pdf: 1335878 bytes, checksum: 3cefa0ad2b3273a21cf1f63268ec8b61 (MD5) Previous issue date: 2016 | en |
dc.description.tableofcontents | TABLE OF CONTENTS
Acknowledgement and Dedication.........................................................................................ii Abstract..................................................................................................................................iii LIST OF ILLUSTRATIONS ................................................................................................vi LIST OF TABLES ...............................................................................................................vii I. Introduction .....................................................................................................................1 II. Data Set layout ............................................................................................................3 2.1 Heart’s 2 chamber and 4 chamber views ......................................................................4 2.2 Heart’s side axis views .................................................................................................4 III. Step 1: Preprocessing ..................................................................................................5 3.1 Orienting the images .....................................................................................................5 3.2 Separate images ............................................................................................................6 3.3 Normalize different sized images .................................................................................6 IV. Step 2: Fourier transform approach .............................................................................7 V. Step 3: Hough transform and k-means clustering .......................................................8 5.1 Dynamic and local grayscale normalization.................................................................8 5.2 Blob detection ...............................................................................................................9 5.3 K-means clustering .....................................................................................................10 VI. Step 4: Extraction ......................................................................................................11 VII. Step 5: Post processing..............................................................................................13 VIII. Step 6: Temporal measuring and enrichment ........................................................14 8.1 Determining diastole and systole images....................................................................14 8.2 Frustum calculation and enrichment...........................................................................14 IX. Step 7: Deep learning ................................................................................................16 9.1 Setting up the images ..................................................................................................16 9.2 Model ..........................................................................................................................17 X. Results .......................................................................................................................18 XI. Future Work...............................................................................................................19 XII. Libraries Used ...........................................................................................................20 XIII. Conclusion .............................................................................................................20 VI. References .................................................................................................................21 | |
dc.language.iso | en | |
dc.title | 基於深度學習之生醫影像分割暨分類 | zh_TW |
dc.title | Biomedical Image Segmentation and Classification Using
Deep Learning | en |
dc.type | Thesis | |
dc.date.schoolyear | 104-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 蘇中才(Chung Tsai Su),黃維中(Wei Chung Hwang) | |
dc.subject.keyword | 生醫影像,深度學習,左心室,射血分數, | zh_TW |
dc.subject.keyword | Deep Learning,left ventricle,ejection fraction,biomedical images, | en |
dc.relation.page | 22 | |
dc.identifier.doi | 10.6342/NTU201601227 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2016-07-25 | |
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-105-1.pdf | 1.3 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。