應用卷積神經網絡於支氣管超音波影像診斷

Endobronchial Ultrasound Images Diagnosis Using Convolutional Neural Network

藍偉任(Wei-Ren Lan)

指導教授 ： 張瑞峰

國立臺灣大學/電機資訊學院/生醫電子與資訊學研究所/碩士(2017年)

https://doi.org/10.6342/NTU201702994

摘要

肺癌在美國是死亡人數最高的癌症，及早的治療，可有效提升肺癌的存活率。支氣管超音波影像由於他的即時性、低輻射、較好的偵測能力，並且可與穿刺搭配常用來做肺部疾病檢查以及肺部病灶的良惡性診斷，近年來成為一個肺癌重要的診斷工具之一。不過目前病灶的支氣管超音波圖像判斷以醫生主觀統整特徵做判斷參考為主。電腦輔助診斷有運用灰階影像特徵做分類，但仍先需有醫生專業從影像上取樣進行分析，屬於半自動化輔助。因此，此篇研究主要的目的是希望藉由卷積神經網路來達成全自動化輔助。首先，調整每張EBUS影像成神經網絡所需的影像輸入尺寸，接著藉由旋轉、翻轉影像做訓練資料數的擴充。欲作為使用的卷積神經網絡CaffeNet 遷移了預先已在ImageNet 訓練過的模型參數，而後再藉由訓練資料訓練來做網絡的參數優化。接著從第七層的全連階層取出 4096 維度的特徵，利用SVM分類器進行病灶的良惡性分類。在此次研究中採用164個病例，包含56個良性病灶以及108個惡性病灶，研究結果顯示，使用遷移學習的卷積神經網絡特徵作為分類使用，比特徵上使用GLCM (gray-level co-occurrence matrix)更較具有分辨率，可達到準確率85.4% (140/164)、靈敏性87.0% (94/108)、特異性 82.1% (46/56)，以及ROC曲線面積0.8705。從結果上來看，使用卷積神經網絡作為支氣管超音波良惡性分類很具有潛力。

關鍵字

肺癌 ； 支氣管超音波 ； 卷積神經網絡 ； 遷移學習

並列摘要

In the United States, lung cancer is the leading cause of cancer death. The survival rate could increase by early detection. In recent years, the endobronchial ultrasonography (EBUS) images have been utilized to differentiate between benign and malignant lesions and guide transbronchial needle aspiration because it is real-time, radiation-free and has better performance. However, the diagnosis depends on the subjective judgement from doctors. There was a study which using the greyscale image textures of the EBUS images to classify the lung lesions but it belonged to semi-automated system which still need the experts to select a part of the lesion first. Therefore, the main purpose of the study was to achieve full automation assistance by using convolution neural network. First of all, the EBUS images resized to the input size of convolution neural network (CNN). And then, the training data were rotated and flipped. The parameters of the model trained with ImageNet previously were transferred to the CaffeNet used to classify the lung lesions. And then, the parameter of the CaffeNet was optimized by the EBUS training data. The features with 4096 dimension were extracted from the 7th fully connected layer and the support vector machine (SVM) was utilized to differentiate benign and malignant. This study was validated with 164 cases including 56 benign and 108 malignant. According to the experiment results, applying the classification by the features from the CNN with transfer learning had better performance than the conventional method with Gray Level Co-Occurrence Matrix (GLCM) features. The accuracy, sensitivity, specificity, and the area under ROC achieved 85.4% (140/164), 87.0% (94/108), 82.1% (46/56), and 0.8705, respectively. From the experiment results, it has potential to diagnose EBUS images with CNN.

並列關鍵字

lung cancer ； EBUS ； convolutional neural network ； transfer learning

參考文獻

[1] R. L. Siegel, K. D. Miller, and A. Jemal, "Cancer statistics, 2016," CA: a cancer journal for clinicians, vol. 66, pp. 7-30, 2016.

[2] R. S. Fontana, D. R. Sanderson, W. F. Taylor, L. B. Woolner, W. E. Miller, J. R. Muhm, et al., "Early Lung Cancer Detection: Results of the Initial (Prevalence) Radiologic and Cytologic Screening in the Mayo Clinic Study 1, 2," American Review of Respiratory Disease, vol. 130, pp. 561-565, 1984.

[3] T. N. L. S. T. R. Team, "Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening," New England Journal of Medicine, vol. 365, pp. 395-409, 2011.

[4] M. Kaneko, K. Eguchi, H. Ohmatsu, R. Kakinuma, T. Naruke, K. Suemasu, et al., "Peripheral lung cancer: screening and detection with low-dose spiral CT versus radiography," Radiology, vol. 201, pp. 798-802, 1996.

[5] E. A. Kazerooni, F. T. Lim, A. Mikhail, and F. J. Martinez, "Risk of pneumothorax in CT-guided transthoracic needle aspiration biopsy of the lung," Radiology, vol. 198, pp. 371-375, 1996.