文章詳目資料

先進工程學刊

  • 加入收藏
  • 下載文章
篇名 結合紋理分析與影像增強技術於電腦斷層影像中輔助診斷急性缺血性腦中風
卷期 4:4
並列篇名 Texture Analysis and Image Enhancement for Aided Diagnosis of Acute Ischemic Stroke in CT Image
作者 黃綠宣李愛先蘇振隆
頁次 385-389
關鍵字 急性缺血性腦中風小波轉換倒傳遞類神經網路影像增強紋理量化分析texture quantizing analysiswavelet transformback propagation neural networkacute ischemic strokeimage enhancement
出刊日期 200910

中文摘要

本論文針對急性缺血性腦中風病發 3 小時內之腦部電腦斷層影像,利用紋理量化分析以及影像增強技術進行分析。以 18 張異常以及 4 張正常中大腦區域影像,使用紋理特徵編碼並擷取紋理特徵值及 t-test統計分析左、右中大腦半球組織參數差異性。系統鑑別病變發生能力評估,準確率由 0.77提高至 0.95、敏感度由0.78提高至 1.00、Kappa Value由 0.40提高至 0.81。此外,藉由 5/3小波轉換將影像分為數個子頻帶,使用多值增強演算法改善局部對比行影像增強;加入增強影像技術後醫師視覺之評估,準確度由 0.63提高至 0.81、敏感度由 0.66提高至 0.84、專一度由 0.50提高至 0.80,病變位置偵測率由 0.40提高至 0.72。

英文摘要

This study used texture quantification and image enhancement technique to
analyze the brain CT images within 3 hours after acute ischemic stroke onset. After calculated texture features of middle cerebral artery (MCA) territory after using texture feature coding method (TFCM) and used t-test to analyze the difference of hemispheres side by side for 18 abnormal and 4 normal images. The accuracy, sensitivity, and kappa
value for system to detect acute cerebral ischemic stroke with/without texture features were 0.95/0.77, 1.00/0.78, and 0.81/0.40, respectively. Brain image was separated into several sub-bands via 5/3 wavelet transform, and then use multi-scale enhancement algorithm to improve local contrast. The accuracy, sensitivity, specificity and ratio of
detected position for physicians were raised from 0.63 to 0.81, 0.66 to 0.84, 0.50 to 0.80, and 0.40 to 0.72, respectively.

本卷期文章目次

相關文獻