透過您的圖書館登入
IP:3.128.171.246
  • 學位論文

全乳房超音波電腦輔助偵測之臨床應用分析

Clinical Utility of Computer-aided Detection in Whole Breast Ultrasound

指導教授 : 張瑞峰

摘要


隨著乳癌發病率在世界各地不斷地增加,乳癌篩檢更顯得格外的重要;作為輔助乳房攝影的角色,手持式超音波雖然可有效且相對容易使用於乳癌篩檢,但在臨床使用上卻因操作者相依性過高與無法重製結果之因素而有所受限。因此,全乳房超音波與三維自動乳房超音波被發展來克服此問題。然而,一個三維自動乳房超音波影像往往包含數百張二維乳房超音波影像,對於醫師來說,判讀數百張二維乳房超音波影像是相當耗時且容易因疲勞導致誤判。為了幫助醫師減少誤判以及加快判讀流程,電腦輔助偵測系統已被開發用於協助醫師進行三維自動乳房超音波影像判讀。截至目前為止,大多數已提出的全乳房超音波與三維自動乳房超音波電腦輔助偵測系統皆在其病例資料集中具有極優異的效能表現,但缺乏臨床有效性與臨床效用評估。在這篇論文研究中,將會進一步針對全乳房超音波與三維自動乳房超音波電腦輔助偵測系統分別進行臨床應用評估。在第一個研究中,提出一個適用於手持式超音波的電磁定位全乳房超音波系統並進行臨床應用評估;在第二個研究中,針對三維自動乳房超音波電腦輔助偵測系統,利用多讀者多案例之臨床回顧性分析進行臨床應用調查。實驗結果顯示,全乳房超音波可做為乳房腫瘤篩檢的臨床工具,並在臨床使用上有望可取代價格較高的三維自動乳房超音波系統;電腦輔助偵測系統則有潛力成為一個有效的第二讀者,藉此協助醫師在三維自動乳房超音波影像中偵測腫瘤。

並列摘要


The incidence of breast cancer is increasing worldwide, reinforcing the importance of breast screening. Conventional hand-held ultrasound (HHUS) for breast screening is efficient and relatively easy to perform; however, limited by operator dependency and non-reproducible results. Thus, whole-breast ultrasound (WBUS) and 3-D automated breast ultrasound (ABUS) were developed to overcome these problems. However, reviewing hundreds of slices in a 3-D ABUS image to find suspicious is time-consuming. To reduce the midsection and accelerate the reviewing procedure by physicians, computer-aided detection (CADe) systems were proposed to assist physicians in interpretation of ABUS images. Most of the previous studies for development of WBUS and CADe system have excellent performance in their data sets, but lack of clinical validity and clinical utility assessment. In the thesis, two clinical utility studies for WBUS and CADe system were proposed. In the first study, an electromagnetic tracking-based whole-breast ultrasound system was investigated to facilitate the use of HHUS for breast screening. Subsequently, a multi-reader multi-case (MRMC) clinical retrospective reader study of CADe for ABUS was investigated. The results showed that WBUS is a practical clinical tool for breast screening that can be used instead of the often unavailable and costly ABUS, and the CADe system has the potential to be an effective second reader for detecting breast tumors in ABUS images.

參考文獻


[1] F. Kamangar, G. M. Dores, and W. F. Anderson, "Patterns of cancer incidence, mortality, and prevalence across five continents: Defining priorities to reduce cancer disparities in different geographic regions of the world," Journal of Clinical Oncology, vol. 24, pp. 2137-2150, May 10 2006.
[2] L. A. Torre, F. Bray, R. L. Siegel, J. Ferlay, J. Lortet-Tieulent, and A. Jemal, "Global Cancer Statistics, 2012," Ca-a Cancer Journal for Clinicians, vol. 65, pp. 87-108, Mar-Apr 2015.
[3] R. L. Siegel, K. D. Miller, and A. Jemal, "Cancer Statistics, 2016," Ca-a Cancer Journal for Clinicians, vol. 66, pp. 7-30, Jan-Feb 2016.
[4] A. Takemura, A. Shimizu, and K. Hamamoto, "Discrimination of Breast Tumors in Ultrasonic Images Using an Ensemble Classifier Based on the AdaBoost Algorithm With Feature Selection," Ieee Transactions on Medical Imaging, vol. 29, pp. 598-609, Mar 2010.
[5] M. S. Soo, E. L. Rosen, J. A. Baker, T. T. Vo, and B. A. Boyd, "Negative predictive value of sonography with mammography in patients with palpable breast lesions," American Journal of Roentgenology, vol. 177, pp. 1167-1170, Nov 2001.

延伸閱讀