中文摘要

在眾多診斷乳癌的程序中，醫學超音波乳癌影像診斷為接受度最高的及時診斷工具，因此超音波掃描儀成為臨床上醫生早期診斷乳癌的利器。然而，由於超音波腫瘤影像含有大量的斑點、 雜訊及組織紋理，容易因為不同廠牌型號的超音波掃描儀輸出的影像相異，或因操作的醫師經驗差異產生不同診斷結果的情形，進而導致醫療資源的濫用。因此近年來，本計畫主持人與多位學者及醫師合作完成數個乳房超音波腫瘤電腦輔助診斷系統，得到了卓越的診斷結果，但是此系統所輸入之影像資料需要醫師手動擷取腫瘤的區域，為了降低系統的應用門檻，協助臨床醫生快速描繪腫瘤的正確輪廓，於是結合紋路分析技術、分水嶺轉換(Watershed Transformation)與主動式輪廓模型(Active Contour Model)自動描繪乳房腫瘤的輪廓，使系統可自動描繪出近似於豐富經驗的醫師所描繪之腫瘤輪廓。由於上述此主題深具實用性，可造福更多婦女同胞，所以在本計畫中，將針對乳癌超音波電腦輔助診斷系統設計一自動乳房腫瘤輪廓切割法，以期完成全自動電腦輔助診斷系統。
在本計畫中，我們將使用數位影像加強技術減低不同廠牌型號的超音波掃描儀之輸出差異，加強腫瘤影像紋理之特徵，再簡化分水嶺轉換輪廓描繪法之複雜度，以超音波影像紋路為主軸，探討乳房超音波影像內的組織差異，利用不同組織的影像特性來合併腫瘤內部的過度切割區域，並以主動式輪廓模型加強腫瘤輪廓描繪的精確性，提供自動擷取的腫瘤區域做為乳房腫瘤電腦輔助診斷系統的輸入。

關鍵詞：乳房超音波、紋路分析、分水嶺轉換、主動式輪廓模型、腫瘤輪廓描繪、電腦輔助診斷系統

Abstract

Medical ultrasound is a certified convenient tool for detecting and diagnosing breast tumors, particularly palpable tumors. Due to the ultrasonic examination would not cause any side effect upon patients’ body. The cost-effectiveness and portability of this facility are particularly important in hospitals, in which the equipment is useful in conducting complex medical imaging in a timely manner. The ultrasonic image is also an efficient instrument of the clinical physicians to diagnose the breast tumors at an earlier stage. However, speckles, noise, and tissue-related textures always consist in ultrasonic images, physicians without clinical experience may make a miscarriage of diagnoses. We have proposed a number of computer aided diagnosis (CAD) systems for breast ultrasound and given remarkable results. In these systems, the region of interesting (ROI) in the ultrasonic image is manual sketched by the experienced physicians. However, the automatic contouring may assist physicians without experience in making a correct diagnosis. Textural analysis, watershed transformation, and active contour model techniques were employed to automatically identify the contour of breast tumors.
In this project, image enhancement techniques will used to make no difference between sonographic images that acquire form diverse ultrasound equipments. Then, the watershed transform will be performed to identify tumor’s contour in the ultrasound textural image. A texture-based region merging method absorbs the regions in a tumor according to the textural similarity function. The active contour model will be used to achieve the final contour for a breast tumor. We will try to identify the similar contour with the physician for the breast ultrasonic images more effectively.

Keywords: Breast ultrasound, Texture analysis, Watershed transform, Active contour model, Tumor contour approximation, computer aided diagnosis