Multi-View Contouring for Breast Tumor on Magnetic Resonance Imaging

• Main Authors: Yao-Wen Chang, 張耀文
• Other Authors: Yu-Len Huang
• Format: Others
• Language: en_US
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/56558620996466043322

碩士 === 東海大學 === 資訊工程學系 === 103 === The shape and contour of the lesion is shown to be effective features for physicians to identify the breast tumor as benign or malignant. The region of the lesion is created by the physician according their clinical experience. Contouring tumors on breast magnetic resonance imaging (MRI) is difficult and time-consuming. For this purpose, automatic contouring for breast tumors may assist physicians in making correct diagnoses. As breast MRI becomes more widespread used, a functional automatic contouring method is essential and its clinical application is becoming urgent. This study presents a multi-view segmentation method for detecting contours of breast tumors in MRI. The preprocessing of the proposed method reduces the any amount of noises but preserves the shape and contrast of breast tumor. The two-dimensional (2D) level-set segmentation method extracts precise contours of breast tumors from transverse, coronal and sagittal planes. This study evaluates ten malignant tumor cases. The simulation results show that the proposed contouring method could save much of the time required to sketch a precise contour.