查詢結果分析
來源資料
相關文獻
- Automatic Tumor Segmentation of Brain in MRI
- Minimum Variance Distortionless Response Beamforming for Tumor Segmentation in MRI
- 下頜腺腫瘤--本土病例低惡性率之臨床意義
- Germline RET Proto-Oncogene Mutations in Two Taiwanese Families with Multiple Endocrine Neoplasia Type 2A
- Correlation between Urinary and Serum Prostate--Specific Antigen
- Renal Cell Carcinoma Presented as a Traumatic Ruptured Kidney
- 惡性肺癌轉移至牙周組織之病例報告
- A Patient of Primary Hyperparathyroidism with Full-Blown Bone Changes Simulating Malignancy
- Concomitant Measurement of CA 125 and CA19-9 in Detecting Ovarian Malignancy: A Review Study of 64 Cases
- 二氧化碳顯影電腦斷層與二氧化碳顯影超音波於肝臟腫瘤之比較
頁籤選單縮合
題 名 | Automatic Tumor Segmentation of Brain in MRI=大腦磁振影像的自動腫瘤分割技術之研究 |
---|---|
作 者 | 王圳木; 楊勝智; 劉昭勇; | 書刊名 | 勤益學報 |
卷 期 | 17 1999.11[民88.11] |
頁 次 | 頁127-136 |
分類號 | 414.93 |
關鍵詞 | 抑制能量最小化法; 磁振影像; 分類法; 大腦影像; 腫瘤; Constrained energy minimization; CEM; Magnetic resonance imaging; Classification; Brain images; Tumor; MRI; |
語 文 | 英文(English) |
中文摘要 | 在這篇論文中,我們提出了一個新方法,可使腫瘤從腦部的多頻譜磁振影像 (Magnetic Resonance,MR) 內給分類出來, 這些磁振影像的組成是由三個磁振參數,質子 密度 (Proton Density,PD),T1 分量 (Weighted) 和 T2 分量影像,經過多頻譜分析所處 理出來的。 我們提出的這個方法, 稱為抑制能旦最小化法 (Constrained Energy Minimization,CEM),被研發於 [12] 內,認為在所知道的領域中,把期望的特徵給分類出 來, 這方法所使用的基礎,就是矩陣運算申的最小化變異數無雜訊響應 (MinimumVariance Distortionless Response, MVDR),CEM 將多頻譜 MR 影像視為一個矩陣處理的問題,在這 問題中的每一個觀察值都代表一個頻譜頻帶 (Spectral Band),再使用有限脈衝響應濾波器 (Finite Impulse Response,FIR) 將輸出功率做最小化處理, 使期望的特徵被強制到一個 特定的增益。此方法已經由數個實驗所得證,實驗結果顯示出大腦組織正確地被分割為四張 影像, 腦瘤 (Tumor)、 灰質 (Gray Matter)、 白質 (White Matter) 以及腦脊髓液 (Cerebral Spinal Fluid,CSF),這些都象徵了這個方法是非常有用的。 另外,對於計算所 花的時間而言,實驗結果也顯示出繁雜計算的改進處。 |
英文摘要 | In this paper, we present a new method to classify tumor in multispect magnetic resonance (MR) images of the human brain. The MRI's consist of three magnetic resonance parameters proton density, T1-weighted, and T2-weighted images, which are processed with multispectral analysis. The proposed approach, called Constrained Energy Minimization (CEM) was developed in [12] where only the knowledge of the desired signature to be classified was required. It was derived based on the Minimum Variance Distortion less Response (MVDR) in array processing. CEM considers an MR image classification problem as an array-processing problem where each sensor represents one spectral band. It uses a finite impulse response (FIR) filter to minimize the output power while the desired signature is constrained to a specific gain. The method has been evaluated through several experiments. Results show that the cerebral tissue was segmented accurately into four images, tumor, gray matter, white matter and cerebral spinal fluid indicating the possible usefulness of this method. As far ascomputing saving is concerned, the experimental results also show computational complexity improvement. |
本系統中英文摘要資訊取自各篇刊載內容。