請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/77469
標題: | 腹部電腦斷層掃描影像之骨骼肌自動判別與區分方法及臨床應用研究 Automatic Segmentation and Differentiation of Skeletal Muscle at Abdominal CT Images |
作者: | Kai-Ching Hsieh 謝凱靜 |
指導教授: | 陳正剛(Argon Chen) |
關鍵字: | 骨骼肌,自動判別方法,自動區分方法,Canny邊緣偵測, Skeletal muscle,Automatic segmentation,Automatic differentiation,Canny Edge, |
出版年 : | 2018 |
學位: | 碩士 |
摘要: | 骨骼肌指標(Skeletal Muscle Index, SMI)、骨骼肌密度指標是放射科醫師常作為判斷病人身體狀況的重要指標,臨床上,醫師經常需要利用生理測量指標衡量患者是否適合接受手術或化療,其骨骼肌指標相較於其他生理指標較客觀且具有代表性。
人體的骨骼肌含量可經由多種方法測量,如:利用生物電阻抗(BIA)原理檢測身體組成之InBody身體組成分析儀、磁力共振成像(MRI)、利用X射線對人體各器官和組織有不同的穿透率之電腦斷層掃描(CT),其中以影像分析的用途最為廣泛且結果也最為精準。針對腹部電腦斷層掃描橫切面影像之骨骼肌判別,已有一套由學者許(2017)[6]所提出的自動判別方法,由於其方法容易於腹肌部分圈選過厚之骨骼肌,且對於人體區域超出影像邊界無法判別;腰肌內圈,仍有改善空間,因此本研究延續採用腹部電腦斷層掃描橫切面影像,除了改善現有判別方法,使其對於人體區域超出影像邊界之案例,一樣可以自動判別骨骼肌區域,對於內臟與骨骼肌相鄰、腹水之案例,正確的將骨骼肌區域判別出,同時進一步將骨骼肌進行不同部位的區分,再利用自動化判別與區分結果進行臨床研究分析。 本研究參考現有的骨骼肌自動化判別流程,使用Canny邊緣偵測,由外向內搜尋,依序定義皮膚層、骨骼肌外圈、骨骼肌內圈,最後在骨骼肌外圈、內圈之間取得的骨骼肌範圍。不同於現有之方法,本研究透過大津演算法自動尋找腹部電腦斷層影像中人體與非人體區域定義皮膚層,透過皮下脂肪與骨骼肌之位置定義骨骼肌外圈,再修改現有搜尋骨骼肌內圈之方法,定義骨骼肌內圈邊緣。經過自動判別腹部骨骼肌區域後,本研究同時利用骨骼肌之位置、構造特性區分不同部位之骨骼肌,將骨骼肌區分為腹直肌、腹壁肌、豎脊肌以及腰大肌四部分。 為了驗證本研究之自動判別骨骼肌方法,首先利用臺大醫院提供146筆人體腰椎第三節(L3)之CT橫切圖分別與醫師手繪區域內骨骼肌面積進行迴歸相關性分析,結果顯示本研究改善後的自動骨骼肌判別方法之R2較原方法高。利用同組案例驗證骨骼肌不同部位區分方法,發現骨骼肌指標與腹壁肌指標最為相關,其次為豎脊肌指標。當整體骨骼肌總面積增加一單位(〖mm〗^2),有18%來自腰大肌,39%來自豎脊肌,8%還自腹直肌,35%來自腹壁肌。除了比較不同部位骨骼肌之關係,使用Cox Proportional Hazard model Test針對台大醫院所提供的146筆資料進行評估胰臟癌術後健康狀況,分析整體骨骼肌、不同部位骨骼肌面積、指標與胰臟癌病患之存活率相關性,結果顯示不論整體、不同部位之骨骼肌面積、骨骼肌指標、骨骼肌密度,於此案例中,對於存活率皆不顯著,不是影響存活率之重要因素。 Skeletal Muscle Index (SMI) and Skeletal Muscle Density Index are widely used as important indexes to evaluate health condition of patients by radiologists. Clinically, radiologists often use physiological measures to decide whether a patient’s health condition is acceptable for undergoing an operation. Skeletal Muscle Index is more objective and representative than other physiological indicators. The skeletal muscle contained in the human body can be measured by a variety of methods, such asInBody composition analyzer, Magnetic Resonance Imaging (MRI), Computerized Tomography (CT), Dual-energy X-ray Absorptiometryetc (DXA), etc. Among all common evaluation methods, image analysis provides more accurate measurement results and is widely adopted. Hsu (2017) proposes an automatic segmentation method of Skeletal Muscle on abdominal CT images. However, this method still has deficiencies, such as misidentification of the abdominal muscles, inability to handle images with the human body area exceeding the image boundary and problems of segmenting the inner circumference of the lumbar muscles. Therefore, this research is to improve this method for better differentiation of the skeletal muscle region and effective clinical applications. This research follows the steps of Hsu’s automatic segmentation method to identify the margins of tissue layers from the outer part gradually towards the inner part of the human body. That is, the outer margin of the skin layer is first defined by the high contrast between the human body portion and the non-human body portion on the CT images. Then, the search continues to find the outer and inner boundaries of the skeletal muscle. The region of the skeletal muscle is segmented using a proposed edge detection method adapted from the well-known Canny Edge Detection method. Different from Hsu’s method, this research proposes using the Otsu algorithm to automatically search for the skin layer defined by human and non-human areas. To define the outer boundary of skeletal muscle, this research also considers the subcutaneous fat area and finds the interface between the fat and the muscle. The existing method of searching the inner boundary of skeletal muscle is further refined by improving the detection algorithm of skeletal muscle inner edge. After improvement of abdominal skeletal muscle segmentation, in this research the position and structural characteristics of the skeletal muscle are used to distinguish the skeletal muscles of different parts and divide the skeletal muscle into four parts: the rectus abdominis, the abdominal wall muscle, the erector spinae and the psoas muscle. Patients with newly diagnosed pancreatic cancer at National Taiwan University Hospital between October 2013 and October 2016 are used to demonstrate the proposed segmentation method. Body composition is assessed using cross-sectional CT images to calculate the total skeletal muscle (TSM) area and index. The results of automatic segmentation of the skeletal muscle were compared to the results of the skeletal muscle manually circumscribed by a radiologist. Regression analysis is performed and the resulted R2 reaches 0.89 higher than the original method. Using the same case, With the differentiation of skeletal muscle parts, it is found that the skeletal muscle index was most correlated to the abdominal wall muscle index, followed by the erector spinae index. When the total skeletal muscle area is increased by one unit ( ), it is found 18% from the psoas muscle, 39% from the erector spinae, 8% from the rectus abdominis, and 35% from the abdominal wall muscle. In addition to comparing the relationship between subparts of skeletal muscles, Cox proportional hazard ratio with different index of the skeletal muscle are used to compare the effect on overall survival (OS). The results show that regardless of the skeletal muscle area, density or index, the survival rate was not significantly affected by the skeletal muscle. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/77469 |
DOI: | 10.6342/NTU201803394 |
全文授權: | 未授權 |
顯示於系所單位: | 工業工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-R05546003-1.pdf 目前未授權公開取用 | 4.92 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。