查詢結果分析
來源資料
相關文獻
- 配對搜尋摺積運算於磁振影像左心室目標之自動搜尋
- 懼閉症與磁振影像檢查
- Automatic Tumor Segmentation of Brain in MRI
- 心智模式取向之智慧型電腦輔助診斷學習系統研究成果
- Alagille Syndrome: A Case Report
- 以功能性磁振影像觀察電針刺激光明穴的多樣性腦部表現
- 學習障礙學生網際網路電腦輔助診斷系統雛型之研究與建置
- Diagnosis and Results of Treatment with Radiation Therapy in Gliomatosis Cerebri Patient: Case Report
- 腫瘤影像形狀特徵多變數邏輯式回歸分析應用於乳房固質結節的超音波診斷
- Minimum Variance Distortionless Response Beamforming for Tumor Segmentation in MRI
頁籤選單縮合
題名 | 配對搜尋摺積運算於磁振影像左心室目標之自動搜尋=Automatic Detection of the Left Ventricle in Magnetic Resonance Imaging by a Matching Pursuit-Based Convolution |
---|---|
作者姓名(中文) | 傅家啟; 莊家銘; 蔡志文; | 書刊名 | 大葉學報 |
卷期 | 11:2 2002.12[民91.12] |
頁次 | 頁107-114 |
分類號 | 415.12 |
關鍵詞 | 配對搜尋; 目標偵測; 霍夫變換; 電腦輔助診斷; 磁振影像; Matching pursuit; Object detection; Hough transform; Computer-aided diagnosis; Magnetic resonance imaging; |
語文 | 中文(Chinese) |
中文摘要 | 磁振造影為現今醫學最為強而力之診斷工具之一,磁振造影影像清晰且快速,其非侵入性之造影方式,更廣為受試者接受,然而磁振造影應用於動態器官如心血管系統產生龐大之影像資料,現行所發展之半自動式電腦輔助左心室邊界檢測工具,雖可提供醫師蒐集診斷資訊之功能,但每張影像仍需以手動方式圈選左心室之範圍,以致於輔助診斷效益無法提升,有鑑於此,本論文提出一配對搜尋摺積演算法以自動搜尋左心室之區域,並與傳統配對搜尋演算法及霍夫變換演算法進行績效衡量。 實驗結果顯示本論文所提之配對搜尋摺積演算法,其檢測搜尋速度快、正確率高,大幅改善配對搜尋演算法耗時及霍夫變換演算法偵測搜尋正確率低之缺點,故將本研究所提之配對搜尋摺積演算法應用於現行之電腦輔助診斷系統必可提升輔助診斷效益,達到完全自動化之功能。 |
英文摘要 | Since magnetic resonance imaging (MRI) is noninvasive and generates clear images, it is currently one of the most powerful radiological tools. However, it is time-consuming to quantify the images generated by dynamic organs such as the cardiovascular system. Though a semi-automatic mode can provide information from epicardial and endocardial borders, it still relies on manual input near the region of interest. In this paper, matching pursuit-based convolution algorithm is presented for automatic detection and location of the left ventricule in magnetic resonance imaging. The performance of the proposed algorithm is compared with an original matching pursuit and the Hough transform. Experimental results show that the proposed algorithm is faster and more accurate than conventional methods such as the Hough transform and the original matching pursuit. By applying the matching pursuit-based convolution algorithm, computer-aided diagnostic systems can be fully automated to fulfill the on-line requirements. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。