結合影像與力學模型分析乳房腫瘤組織硬度及移動性

Analysis of Tumor's Stiffness and Mobility Using Hybrid Tactile Ultrasound Images for Breast Cancer Diagnosis

林靖瑋(Jing-Wei Lin)

指導教授 ： 顏炳郎

國立臺北科技大學/機電學院/自動化科技研究所/碩士(2007年)

摘要

本文旨於以超音波影像與力量資訊，探討乳房腫瘤組織受力時之移動性，實驗方式為以超音波探頭下壓於乳房腫瘤組織，並以其移動性及力量資訊，作為組織特性研究並應用於乳房腫瘤之診斷。本研究以有限元素法建立一乳房力學模型，並經此模型訓練類神經網路，經測試驗證後，再以實際臨床病例中，透過超音波探頭擷取所得之影像及力量感測器所回傳之力量資訊，作為特徵參數，透過倒傳遞類神經網路，預測腫瘤與周圍組織硬度比。本研究經臨床病例驗證，可有效進行腫瘤硬度預測及分群，可作為臨床診斷之輔助參考資訊。

關鍵字

超音波影像 ； 乳房力學模型 ； 影像分割 ； 特徵擷取

並列摘要

Breast cancer is one of deadly diseases of cancers with highest occurrence rate for women in Taiwan. In this study, we analyze the mobility and stiffness of applying external force for model of breast tissue in ultrasound image sequence. We used finite element method to build a model to simulate breast tissue. The image analysis is applied for the continuous 2D US images which are obtained during the probe being pressed .And we got the force and the information of different images, finding out the feature of the tissue. Then we used mobility and force feature for input of ANN and data sets for validation. The result showed that stiffness predictability in breast tumor can be achieved well.

並列關鍵字

Breast Tumor ； Ultrasound image ； image segmentation ； feature extraction

參考文獻

[2]Walaa Khaled , Stefan Reichling, Otto T. Bruhns and Helmut Ermert , "Ultrasonic strain imaging and reconstructive elastography for biological tissue",Ultrasonics, 2006 22 December, Pages e199-e202

[3]Du-Yih TSAI "Classification of Breast Tumors in Mammograms using a Neural Network:Utilization of Selected Features" Proceedings of 1993 International Joint Conference on Neural Networks, pp.967-970.

[4]Ruey-Feng Chang and Dar-Ren Chen, "Solid Breast Masses:Classification with Computer-aided Analysis of Continuous US Images Obtained with robe Compression" Radiology 2005; 236:458–464

[7]Pai-Chi Li, "Pulse Compression for Finite Amplitude Distortion Based Harmonic Imaging Using Coded Waveforms", Ultrasonic Imaging, Vol. 21, pp. 1-16, 1999.

[8]M KASS, A WITKIN, D TERZOPOULOS, "Snakes: active contour models" - International journal of computer vision, 1988, Vol. 1, pp.321-331, 1988.