自動乳房超音波之電腦輔助腫瘤診斷

Computer-Aided Tumor Diagnosis for Automated Breast Ultrasound

盧業達(Yeh-Ta Lu)

指導教授 ： 張瑞峰

國立臺灣大學/電機資訊學院/資訊網路與多媒體研究所/碩士(2016年)

https://doi.org/10.6342/NTU201603097

摘要

乳癌是20-59歲的女性死亡率最高的癌症，及早的治療，可有效降低乳癌的致死率。近年來，乳房超音波影像常用來診斷腫瘤的良惡性，為了提升正確率，大部分研究在腫瘤分類前先做腫瘤切割，切割的結果直接影響到了良惡性腫瘤的判斷。因此，此篇研究主要的目的是使用image matting改善腫瘤的切割結果，進行腫瘤的電腦輔助診斷。首先，從超音波影像取出腫瘤的VOI (volume-of-interest)區域，並透過一連串的影像處理方法進行初步切割，而後將預切割的結果建立成tri-map，接著根據tri-map所畫出的未知區域使用image matting進行腫瘤切割，從切割結果擷取出紋理特徵和形態特徵，最後，利用SVM分類器以及擷取出的特徵進行腫瘤良惡性的分類。在此次研究中採用了80個病例，包含40個良性腫瘤以及40個惡性腫瘤，研究結果顯示，使用image matting確實比不使用image matting有更佳的切割效能，並且在特徵上可得到GLCM (gray-level co-occurrence matrix)、ranklet以及橢圓擬合特徵的組合較具有分辨率，可達到準確率85.0% (68/80)、靈敏性87.5% (35/40)、特異性 82.5% (33/40)，以及ROC曲線面積0.8829。從結果上來看，使用image matting確實能夠改善腫瘤的切割並且得到較為準確的良惡性分類結果。

關鍵字

乳癌 ； image matting ； 電腦輔助診斷

並列摘要

In women aged 20-59 years, breast cancer is the highest mortality. Early treatment can effectively reduce the mortality of breast cancer. In recently, breast ultrasound image is often used to diagnose between benign and malignant tumors. For increasing the accuracy, most researches segment the tumor before classification, and the segmented results directly affect the classification between benign and malignant tumors. Therefore, the purpose of this study is to refine segmented tumors using the image matting method for computer-aided diagnosis. First, the volume-of-interest (VOI) of tumor was extracted from the ultrasound image and pre-segmented by a conventional segmentation method. The tri-map including the background, foreground, and unknown region was created with the pre-segmented tumor, and then the image matting method was applied for refining the segmentation according to the unknown region of tri-map. Texture and morphology features were extracted from refined segmentation result and then the support vector machine was applied with extracted features to classify tumor into benign or malignant tumor. This study was validated with 80 cases including 40 benign and 40 malignant breast lesions. According to the experiment results, applying the image matting method had better performance than not applying the image matting method, and the combination of GLCM, ranklet, and ellipsoid fitting feature set had significant (resolution??. The accuracy, sensitivity, specificity, and the area under ROC achieved 85.0% (68/80), 87.5% (35/40), 82.5% (33/40), and 0.8829, respectively. From the experiment results, the image matting method could actually refine tumor segmentation, and more precise classification between benign and malignant tumor results were obtained.

並列關鍵字

breast cancer ； image matting ； computer-aid diagnosis

參考文獻

[23] Q. Dong, "Largest Connected Component of a k-ary n-cube with Faulty Vertices," Journal of Information Science and Engineering, vol. 29, pp. 777-783, Jul 2013.

[13] Y. Chou, C. Tiu, H. Chiang, S. Chen, H. Chiou, and S. Chiou, "Ultrasound ACR BI-RADSR Categories Applied in an Automated Breast Ultrasound System: Diagnostic Reliability," in Radiological Society of North America scientific assembly and annual meeting program. Oak Brook, Ill: Radiological Society of North America, 2006.

[1] R. L. Siegel, K. D. Miller, and A. Jemal, "Cancer Statistics, 2016," Ca-a Cancer Journal for Clinicians, vol. 66, pp. 7-30, Jan-Feb 2016.

[2] A. Takemura, A. Shimizu, and K. Hamamoto, "Discrimination of breast tumors in ultrasonic images using an ensemble classifier based on the AdaBoost algorithm with feature selection," IEEE Trans Med Imaging, vol. 29, pp. 598-609, Mar 2010.

[3] A. Takemura, A. Shimizu, and K. Hamamoto, "Discrimination of Breast Tumors in Ultrasonic Images Using an Ensemble Classifier Based on the AdaBoost Algorithm With Feature Selection," Ieee Transactions on Medical Imaging, vol. 29, pp. 598-609, Mar 2010.