研究生: |
陳冠維 Guan-Wei Chen |
---|---|
論文名稱: |
巨量影像雲端資料庫之設計與建立 The Design and Implementation of Large-Scale Image Cloud Database |
指導教授: |
王靖維
Ching-Wei Wang |
口試委員: |
王靖維
Ching-Wei Wang 白孟宜 Meng-Yi Bai 趙載光 Tai-Kuang Chao |
學位類別: |
碩士 Master |
系所名稱: |
應用科技學院 - 醫學工程研究所 Graduate Institute of Biomedical Engineering |
論文出版年: | 2019 |
畢業學年度: | 107 |
語文別: | 中文 |
論文頁數: | 47 |
中文關鍵詞: | 數位病理切片 、醫學影像 、巨量影像 、雲端資料庫 |
外文關鍵詞: | Digital pathology section, Medical imaging, Large-scale image, Cloud database |
相關次數: | 點閱:280 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年體外診斷的智慧化發展日益飛快,尤其是病理診斷領域部分,為解決病理科的人力缺口以及提升人工判讀的效率,數位病理已成為各國注目的焦點。數位病理切片藉由顯示器呈現病理變化的效果比顯微鏡好,顯示器可透過像素呈現病理切片完整的病理現象。然而,數位化病理切片需要一個能夠儲存、調閱與管理的系統,方能使數位病理學更完善。
我們利用Python Flask作為架設雲端系統模組,並利用JSON和MariaDB作為資料庫的管理系統,個別設計出一套不同資料庫管理系統的雲端資料庫系統,兩套系統皆包含儲存、調閱和管理的功能。由於本系統結合了雲端運算服務,因此使用者可藉由電腦、手機或平板等裝置透過網際網路連接系統平台取得服務,使用者可將數位化病理切片上傳至系統,系統將會把上傳的影像儲存於雲端資料庫,使用者也可以透過平台直接調閱及管理雲端資料庫,以便使用者可以有效率的調閱、管理與分析影像。
本研究所提出的雲端資料庫系統不僅僅只侷限於數位病理切片,亦可應用到CT、MRI等醫學影像,甚至可以應用於學術或產業領域。本系統是透過網際網路為溝通媒介,因此可藉由網際網路打破距離的限制,當病理科醫師之間需要討論時,即使身處不同地方,也能夠及時的討論,甚至需要尋求第二意見時,不再被距離所侷限,藉此提高醫療保健的品質。
In recent years, the intelligentize progress of in vitro diagnosis has become more and more rapid, especially in the pathology field. In order to solve the manpower gap of pathology and improve the efficiency of manual interpretation, the digital pathology has become the focus of all countries. Because the digital monitor has better presentation than light microscope, the digital monitor can display all the pathological features by the pixels. However, the digital pathology requires a system that can store, access, and manage to make digital pathology more perfect.
We uses Python Flask as the cloud system module, and uses JSON and MariaDB as the database management system to design the cloud database system with different management systems. Both systems' features include storage, access and Management. Since the system combines the cloud computing, the user can obtain the service from system platform through a device such as a computer, a mobile phone or a tablet. The user can upload the digital pathological section to the system, and the system will store the image in the cloud database, and the user also can directly access and manage the cloud database through the platform, so that the user can efficiently access, manage and analyze images.
The large-scale image cloud database proposed by this study is not only limited to digital pathological section, but also can be applied to medical images such as CT and MRI, and even applied to academic or industrial fields. This system uses the Internet as a communication medium, so it can break the distance limitation by the Internet. When the pathologists need to discuss, even if they are in different places, they can discuss in time. When you need second opinion, you are no longer limited by distance. Thereby improving the quality of health care.
[1] Pantanowitz L. Farahani N., Parwani A. Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine
International, 2015:7:23–33, June 2015.
[2] Lee G. Madabhushi A. Image analysis and machine learning in digital pathology:
Challenges and opportunities. Medical Image Analysis, 33:170–175, October 2016.
[3] Yang L. Xing F. Robust nucleus/cell detection and segmentation in digital pathology
and microscopy images: A comprehensive review. IEEE Reviews in Biomedical
Engineering, 9:234 – 263, January 2016.
[4] William D. Binder et al. Jonathan D. Eisenberg, Andrew T. Reisner. Role of ct in the
diagnosis of nonspecific abdominal pain: A multicenter analysis. American Journal
of Roentgenology, 208(3), March 2017.
[5] S.Sumera et al. H.R.Hixsona, C.LeivaSalinasa. Utilizing dual energy ct to improve
ct diagnosis of posterior fossa ischemia. Journal of Neuroradiology, 43:346 – 352,
October 2016.
[6] Bhavik N. Patel et al. Stephanie T. Chang, R. Brooke Jeffrey. Preoperative multidetector ct diagnosis of extrapancreatic perineural or duodenal invasion is associated
with reduced postoperative survival after pancreaticoduodenectomy for pancreatic
adenocarcinoma: Preliminary experience and implications for patient care. The New
England Journal of Medicine, 281(3), July 2016.
[7] Jimmy Espinoza. Fetal mri and prenatal diagnosis of congenital heart defects. The
Lancet, 393:1574 – 1576, April 2019.
[8] Palumbo P. et al. Bruno F., Arrigoni F. New advances in mri diagnosis of degenerative osteoarthropathy of the peripheral joints. La radiologia medica, February
2019.
[9] Antti S. Rannikko et al. Veeru Kasivisvanathan, M.R.C.S. Mritargeted or standard biopsy for prostatecancer diagnosis. The New England Journal of Medicine,
378:1767 – 1777, May 2018.
[10] Health at a glance 2015 oecd indicators. http://apps.who.int/medicinedocs/
documents/s22177en/s22177en.pdf.
[11] 吳其勳. 徹底了解 Cloud Computing 部署模式. https://www.ithome.com.tw/
article/93013.
[12] Gang Li et al. Junnan Wu, Robert James Taylor. Cloudbased medical image processing system with tracking capability. https://patents.google.com/patent/
US10078727B2/en, Feburary 2012.