使用多尺度強度的紋理切割與分類在胸腔X光影像進行自動病理檢測之研究

Automatic Pathology Detection for Chest X-ray Images Using Multiscale Intensity Texture Segmentation and classification

曾詠智(Yong-Zhi Zeng)

指導教授 ： 吳憲珠

國立臺中科技大學/資訊與流通學院/資訊管理系碩士班/碩士(2017年)

摘要

在胸部的X光影像中許多可能危及生命的疾病的診斷對醫療部門來說相當重要的，而其中醫學影像處理已經從過去的數十年中發揮了許多貢獻。因此輔助診斷肺部疾病發生狀況是重要的，而本篇論文提出了兩個部分，第一個方法是先針對肺部是否具有病變進行分類，主要採用局部二值模式(LBP)運算來進行特徵提取，並透過SVM來進行訓練與分類對於具有病變與不具病變的肺部。而第二個方法則是針對具有病變的肺部進行病變區域的切割。其切割的方法首先為去除背景和雜訊，之後將肺部區域進行紋理變化的分析找出病變區域。而在容易造成影響的肋骨邊界區域則是先針對肺部進行邊緣運算找出肋骨的上下邊界。最後再將不易切割的肋骨邊界區域，透過與病變區域所相鄰的邊界區域給補足來獲得更完整的疾病區域。

關鍵字

醫學影像切割 ； 胸腔X光 ； 肺部疾病 ； 局部紋理

並列摘要

Digital image processing has been applied in medical domain widely, but the multitude still needs to manual processing. Automatic image segmentation and features analysis can assist doctor treatment and diagnose diseases more accurately, reduce the time of diagnosing and improve efficiency. Automatic medical image segmentation is difficult in that the image quality varied by equipment and dosage. In this thesis, the automatic method employed image multiscale intensity texture analysis and segmentation to surmount this problem. The proposed method automatically recognize and classify abnormal region without manual segmentation. Generally, automatic identification is based on the difference of the texture and organ shape, or any pathological changes of lung area. Therefore, the important features could be retained to identify abnormal areas.
In this thesis, the chest x-ray images for finding whether lung region is healthy or not. The first proposed identifying common pneumothorax is based on SVM to classification method. Features are extracted from the lung image by the local binary pattern. Then, classification of pneumothorax lung is determined by support vector machines. The second proposed automatic pneumothorax detection is based on multiscale intensity texture segmentation. Remove the background and noises in the chest images for segmenting the lung of abnormal region. The segmenting the abnormal region. is used texture transforms from computing multiple overlapping blocks. Because the ribs boundaries are affected easily, the rib boundaries are identified by using Sobel edge detection. Finally, in order to obtain a complete disease region, the rib boundary is filled up in the rib boundary located between the abnormal regions.

並列關鍵字

Medical image segmentation ； texture ； chest ； lung pathology

參考文獻

[1] M. Noppen & T. De Keukeleire, Pneumothorax. Respiration, Vol. 76(2), 2008, pp. 121-127.

[2] A. MacDuff & A. Arnold & J. Harvey, Management of spontaneous pneumothorax: British Thoracic Society pleural disease guideline 2010. Thorax, Vol. 65(Suppl 2), 2010, pp. ii18-ii31.

[3] A. P. Wakai, Spontaneous pneumothorax. BMJ clinical evidence, 2011.

[4] N. Bellaviti & F. Bini & L. Pennacchi & G. Pepe & B. Bodini & R. Ceriani & C. D'Urbano & A. Vaghi, Increased Incidence of Spontaneous Pneumothorax in Very Young People: Observations and Treatment. CHEST Journal, Vol. 150(4_S), 2016, pp. 560A-560A.

[7] K. Doi & S. Sanada, Method and system for automatic detection of ribs and pneumothorax in digital chest radiographs. U.S. Patent No. 5,668,888. 1997.