基于深度卷積神經(jīng)網(wǎng)絡的低劑量CT肺部去噪

呂曉琪; 吳涼; 谷宇; 張明; 李菁

doi:10.11999/JEIT170769

基于深度卷積神經(jīng)網(wǎng)絡的低劑量CT肺部去噪

doi: 10.11999/JEIT170769

呂曉琪¹,
吳涼¹,
谷宇¹,
張明¹,
李菁¹

基金項目:

國家自然科學基金(61771266, 61179019)，內蒙古自治區(qū)自然科學基金(2015MS0604)，包頭市科技計劃項目(2015C2006-14)，內蒙古自治區(qū)高等學?？茖W研究項目(NJZY145)

計量
- 文章訪問數(shù): 2027
- HTML全文瀏覽量: 308
- PDF下載量: 337
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-08-01
- 修回日期: 2017-12-01
- 刊出日期: 2018-06-19

Low Dose CT Lung Denoising Model Based on Deep Convolution Neural Network

Funds:

The National Natural Science Foundation of China (61771266, 61179019), The Natural Science Foundation of the Inner Mongolia Autonomous region (2015MS0604), The Science and Technology Plan Projects of Baotou City (2015C2006-14), The Institutions of Higher Learning Scientific Research Projects of the Inner Mongolia Autonomous region (NJZY145)

摘要

摘要: 為了降低低劑量CT肺部噪聲對肺癌篩查后期診斷的影響，該文提出一種基于深度卷積神經(jīng)網(wǎng)絡的低劑量CT肺部去噪算法。以完整的CT肺部圖像作為輸入，池化層對輸入圖像進行降維處理；批規(guī)范化解決隨著網(wǎng)絡深度的增加性能降低的問題；引入殘差學習，學習模型中每一層的殘差，最后輸出去噪圖像。與經(jīng)典去噪算法實驗結果對比，所提方法在解決去噪方面達到了很好的濾波效果，同時也較好地保留了肺部圖像的細節(jié)信息，大大優(yōu)于傳統(tǒng)的去噪算法。
- 卷積神經(jīng)網(wǎng)絡 /
- 診斷 /
- 肺部去噪 /
- 殘差學習 /
- 批規(guī)范化
Abstract: In order to reduce the effect of low dose CT lung noise on the late diagnosis of lung cancer screening, a denoising model of low-dose CT lung based on deep convolution neural network is proposed. The input of the model is the complete CT lung image. The pooling layer reduces the dimension of input. Batch normalization works out the poor performance with the increase of network depth. The residuals of each layer are learned with residual learning. Finally, the denoised image is produced. Compared with classical methods, the proposed method achieves good filtering effect in solving the denoising method, and also retaining the details of lung image information, which is much better than the traditional filtering algorithm.
- Convolution Neural Network (CNN) /
- Diagnosis /
- Lung denoising /
- Residual learning /
- Batch normalization

HTML全文

參考文獻(32)

張云逸. 低劑量CT圖像的質量改善算法研究[D]. [碩士論文],鄭州大學, 2015.

ZHANG Yunyi. Study of image quality improvement algorithm for low-dose CT[D]. [Master dissertation], Zhengzhou University, 2015.

劉光達, 趙立榮. 基于最小均方誤差原理的醫(yī)學X光影像濾波閾值選擇[J]. 光學精密工程, 2001, 9(1): 47-50.

LIU Guangda and ZHAO Lirong. Threshold selection method for medical X-ray images filter based on minimum even- square error[J]. Optics and Precision Engineering, 2001, 9(1): 47-50.

SPERL J, BEQUE D, CLAUS B, et al. Computer-Assisted Scan Protocol and Reconstruction (CASPAR)-reduction of image noise and patient dose[J]. IEEE Transactions on Medical Imaging, 2010, 29(3): 724-732. doi: 10.1109/TMI. 2009.2034515.

代雙鳳, 呂科, 翟銳, 等. 基于3D區(qū)域增長法和改進的凸包算法相結合的全肺分割方法[J]. 電子與信息學報, 2016, 38(9): 2358-2364. doi: 10.11999/JEIT151365.

DAI Shuangfeng, L Ke, ZHAI Rui, et al. Lung segmentation method based on 3D region growing method and improved convex hull algorithm[J]. Journal of Electronics Information Technology, 2016, 38(9): 2358-2364. doi: 10.11999/JEIT151365.

徐玉風. 基于貝葉斯估計的低劑量CT圖像去噪算法[D]. [碩士論文], 鄭州大學, 2016.

XU Yufeng. The denoising algorithm of low-dose CT images based on bayesian estimation[D]. [Master dissertation], Zhengzhou University, 2016.

GREEN M, MAROM E M, KIRYATI N, et al. Efficient Low- Dose CT Denoising by Locally-Consistent Non-Local Means (LC-NLM)[M]. Heidelberg: Springer, 2016: 423-431. doi: 10.1007/978-3-319-46729-9_49.

SHANG Xiaobao, DING Yong, DENG Ruizhe, et al. A three- dimensional denoising method for low-dose computed tomography[J]. Journal of Medical Imaging Health Informatics, 2017, 7(1): 283-287. doi: 10. 1166/jmihi.2017. 2020.

畢一鳴. 低劑量CT圖像恢復算法研究[D]. [碩士論文], 南方醫(yī)科大學, 2010: 12-60.

BI Yiming. Image restoration for low-dose computed tomography[D]. [Master dissertation], Southern Medical University, 2010: 12-60.

ZHANG H, MA J, WANG J, et al. Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Part II: An adaptive approach[J]. Computerized Medical Imaging Graphics the Official Journal of the Computerized Medical Imaging Society, 2015, 43(6): 26-35. doi: 10.1016/j.compmedimag.2015.02.008.

朱永成, 陳陽, 羅立民, 等. 基于字典學習的低劑量X-ray CT圖像去噪[J]. 東南大學學報(自然科學版), 2012, 42(5): 864-868. doi: 10.3969/j.issn.1001-0505.2012.05.013.

ZHU Yongcheng, CHEN Yang, LUO Limin, et al. Dictionary learning based denoising of low-dose X-ray CT image[J]. Journal of Southeast University(Natural Science Edition), 2012, 42(5): 864-868. doi: 10.3969/j.issn.1001-0505.2012.05. 013.

LORE K G, AKINTAYO A, and SARKAR S. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, 2015, 61(1): 650-662. doi: 10.1016/j.patcog.2016.06.008.

LI H M. Deep learning for image denoising[J]. International Journal of Signal Processing Image Processing P, 2014, 3(7): 171-180. doi: 10.14257/ijsip.2014.7.3.14.

XIE J, XU L, and CHEN E. Image denoising and inpainting with deep neural networks[C]. International Conference on Neural Information Processing Systems, Harrahs, 2012, 1: 341-349.

李傳朋, 秦品樂, 張晉京. 基于深度卷積神經(jīng)網(wǎng)絡的圖像去噪研究[J]. 計算機工程, 2017, 43(3): 253-260. doi: 10.3969/j. issn.1000-3428.2017.03.042.

LI Chuanpeng, QIN Pinle, and ZHANG Jinjing. Research on image denoising based on deep convolutional neural network[J]. Computer Engineering, 2017, 43(3): 253-260. doi: 10.3969/j.issn.1000-3428.2017.03.042.

呂永標, 趙建偉, 曹飛龍. 基于復合卷積神經(jīng)網(wǎng)絡的圖像去噪算法[J]. 模式識別與人工智能, 2017, 30(2): 97-105. doi: 10.16451/j.cnki.issn1003-6059.201702001.

L Yongbiao, ZHAO Jianwei, and CAO Feilong. Image denoising algorithm based on composite convolutional neural network[J]. Pattern Recognition and Artificial Intelligence, 2017, 30(2): 97-105. doi: 10.16451/j.cnki.issn1003-6059. 201702001.

ZHANG K, ZUO W, CHEN Y, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising [J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155. doi: 10.1109/TIP.2017.2662206.

周飛燕, 金林鵬, 董軍. 卷積神經(jīng)網(wǎng)絡研究綜述[J]. 計算機學報, 2017, 40(6): 1229-1251. doi: 10.11897/SP.J.1016.2017. 01229.

ZHOU Feiyan, JIN Linpeng, and DONG Jun. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6): 1229-1251. doi: 10.11897/SP.J.1016. 2017.01229.

王華利, 鄒俊忠, 張見, 等. 基于深度卷積神經(jīng)網(wǎng)絡的快速圖像分類算法[J]. 計算機工程與應用, 2017, 53(13): 181-188. doi: 10.3778/j.issn.1002-8331.1601-0435.

WANG Huali, ZOU Junzhong, ZHANG Jian, et al. Fast image classification algorithm based on deep convolutional neural network[J]. Computer Engineering and Applications, 2017, 53(13): 181-188. doi: 10.3778/j.issn.1002-8331.1601- 0435.

HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. IEEE Computer Vision and Pattern Recognition, Las Vegas, 2016: 770-778.

ARMATO S, MCLENNAN G, MCNITT-GRAY M, et al. WE-B-201B-02: The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed public database of CT scans for lung nodule analysis[J]. Medical Physics, 2010, 37(6): 3416-3417. doi: 10.1118/1.3469350.

HENSCHKE C I, MCCAULEY D I, YANKELEVITZ D F, et al. Early lung cancer action project: A summary of the findings on baseline screening[J]. Oncologist, 2001, 6(2): 147-152. doi: 10.1634/theoncologist.6-2-147.

HOR A and ZIOU D. Image quality metrics: PSNR vs. SSIM[C]. 2010 20th IEEE International Conference on Pattern Recognition, Istanbul, 2010: 2366-2369. doi: 10.1109 /ICRP. 2010.579.

施引文獻

資源附件(0)

訪問統(tǒng)計