基于自适应感受野机制的颈部淋巴结自动识别算法

doi:10.11772/j.issn.1001-9081.2019061069

计算机应用 ›› 2019, Vol. 39 ›› Issue (12): 3535-3540.DOI: 10.11772/j.issn.1001-9081.2019061069

基于自适应感受野机制的颈部淋巴结自动识别算法

秦品乐¹, 李鹏波¹, 张瑞平², 曾建潮¹, 刘仕杰³, 徐少伟¹

1. 中北大学大数据学院, 太原 030051;
2. 山西白求恩医院, 太原 030001;
3. 山西医科大学第一医院, 太原 030001

收稿日期:2019-06-24 修回日期:2019-08-31 出版日期:2019-12-10 发布日期:2019-10-15
作者简介:秦品乐(1978-),男,山西长治人,副教授,博士,主要研究方向:大数据、机器视觉、三维重建;李鹏波(1995-),男,山西运城人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理;张瑞平(1975-),男,山西太原人,教授,博士生导师,博士,主要研究方向:分子影像学、纳米医学;曾建潮(1963-),男,山西太原人,教授,博士,博士生导师,主要研究方向:复杂系统的维护决策和健康管理;刘仕杰(1990-),男,河北邢台人,硕士研究生,主要研究方向:分子影像学、纳米医学;徐少伟(1995-),男,山西太原人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理。

Automatic recognition algorithm of cervical lymph nodes using adaptive receptive field mechanism

QIN Pinle¹, LI Pengbo¹, ZHANG Ruiping², ZENG Jianchao¹, LIU Shijie³, XU Shaowei¹

1. School of Data Science, North University of China, Taiyuan Shanxi 030051, China;
2. Shanxi Bethune Hospital, Taiyuan Shanxi 030001, China;
3. First Hospital of Shanxi Medical University, Taiyuan Shanxi 030001, China

Received:2019-06-24 Revised:2019-08-31 Online:2019-12-10 Published:2019-10-15
Contact: 曾建潮

摘要/Abstract

摘要： 针对目前应用于医学影像目标检测的深度学习网络模型仅拥有固定的感受野，无法针对形态尺度差异明显的颈部淋巴结进行有效检测的问题，提出了一种新的基于自适应感受野机制的识别算法，将深度学习首次应用于完全三维医学图像的颈部淋巴结自动识别中。首先，采用半随机采样方法对医学序列图像进行裁剪，生成基于网格的局部图像块及对应真值标签；然后，通过局部图像块及标签构建并训练基于自适应感受野机制的DeepNode网络；最后，利用预训练的DeepNode网络模型进行预测，通过输入整体序列图像，可以端到端且快速地获得整体序列对应的颈部淋巴结识别结果。在颈部淋巴结数据集中，采用DeepNode网络识别颈部淋巴结的召回率可达98.13%，精确率可达97.38%，每次扫描的假阳性数量仅为29，同时耗时相对较短。实验结果分析表明，与当前表现优良的二维与三维卷积神经网络相结合的算法、三维通用目标检测算法、基于弱监督定位的识别算法等相比，所提算法可以实现颈部淋巴结的自动识别，并取得最优的识别效果。该算法端到端，简单高效，易于扩展到其他医学图像的三维目标检测任务中，可应用于临床的诊断和治疗。

关键词: 颈部淋巴结检测, 计算机辅助诊断, 注意力机制, 自适应感受野, 三维医学影像

Abstract: Aiming at the problem that the deep learning network model applied to medical image target detection only has a fixed receptive field and cannot effectively detect the cervical lymph nodes with obvious morphological and scale differences, a new recognition algorithm based on adaptive receptive field mechanism was proposed, applying deep learning to the automatic recognition of cervical lymph nodes in complete three-dimensional medical images at the first time. Firstly, the semi-random sampling method was used to crop the medical sequence images to generate the grid-based local image blocks and the corresponding truth labels. Then, the DeepNode network based on the adaptive receptive field mechanism was constructed and trained through the local image blocks and labels. Finally, the trained DeepNode network model was used for prediction. By inputting the whole sequence images, the cervical lymph node recognition results corresponding to the whole sequence was obtained end-to-end and quickly. On the cervical lymph node dataset, the cervical lymph node recognition using the DeepNode network has the recall rate of 98.13%, the precision of 97.38%, and the number of false positives per scan is only 29, and the time consumption is relatively shorter. The analysis of the experimental results shows that compared with current algorithms such as the combination of two-dimensional and three-dimensional convolutional neural networks, the general three-dimensional object detection and the weak supervised location based recognition, the proposed algorithm can realize the automatic recognition of cervical lymph nodes and obtain the best recognition results. The algorithm is end-to-end, simple and efficient, easy to be extended to three-dimensional target detection tasks for other medical images and can be applied to clinical diagnosis and treatment.

Key words: cervical lymph node detection, Computer-Aided Diagnosis (CAD), attention mechanism, adaptive receptive field, three-dimensional medical image

中图分类号:

TP391.41

秦品乐, 李鹏波, 张瑞平, 曾建潮, 刘仕杰, 徐少伟. 基于自适应感受野机制的颈部淋巴结自动识别算法[J]. 计算机应用, 2019, 39(12): 3535-3540.

QIN Pinle, LI Pengbo, ZHANG Ruiping, ZENG Jianchao, LIU Shijie, XU Shaowei. Automatic recognition algorithm of cervical lymph nodes using adaptive receptive field mechanism[J]. Journal of Computer Applications, 2019, 39(12): 3535-3540.

参考文献

[1] PATEL N U, LIND K E, MCKINNEY K, et al. Clinical validation of a predictive model for the presence of cervical lymph node metastasis in papillary thyroid cancer[J]. American Journal of Neuroradiology, 2018, 39(4):756-761.
[2] BEJNORDI B E, VETA M, VAN DIEST P J, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer[J]. Jama, 2017, 318(22):2199-2210.
[3] 魏骏,何凌,车坤,等.CT图像的颈部淋巴结半自动分割算法[J].计算机工程与设计,2015,36(11):3014-3018.(WEI J, HE L, CHE K, et al. Semi-automatic detection and segmentation of neck lymph nodes in CT image[J]. Computer Engineering and Design, 2015, 36(11):3014-3018.)
[4] KAN Y, DONG D, ZHANG Y, et al. Radiomic signature as a predictive factor for lymph node metastasis in early-stage cervical cancer[J]. Journal of Magnetic Resonance Imaging, 2018, 49(1):304-310.
[5] ESTEVES C, ALLEN-BLANCHETTE C, MAKADIA A, et al. Learning SO(3) equivariant representations with spherical CNNs[C]//Proceedings of the 2018 European Conference on Computer Vision, LNCS 11217. Cham:Springer, 2018:54-70.
[6] ELSAYED G F, SHANKAR S, CHEUNG B, et al. Adversarial examples that fool both computer vision and time-limited humans[C]//Proceedings of the 32nd Conference on Neural Information Processing Systems. New York:Curran Associates Inc., 2018:3914-3924.
[7] RAJPURKAR P, IRVIN J, ZHU K, et al. CheXNet:radiologist-level pneumonia detection on chest X-rays with deep learning[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1711.05225.pdf.
[8] RAJPURKAR P, HANNUN A Y, HAGHPANAHI M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1707.01836.pdf.
[9] 秦品乐,李鹏波,曾建潮,等.基于级联全卷积神经网络的颈部淋巴结自动识别算法[J].计算机应用,2019,39(10):2915-2922.(QIN P L, LI P B, ZENG J C, et al. Automatic recognition algorithm of cervical lymph nodes using cascaded fully convolutional neural networks[J]. Journal of Computer Applications, 2019, 39(10):2915-2922.)
[10] 苗光,李朝锋.二维和三维卷积神经网络相结合的CT图像肺结节检测方法[J].激光与光电子学进展,2018,55(5):129-137.(MIAO G, LI C F. Detection of pulmonary nodules CT images combined with two-dimensional and three-dimensional convolution neural networks[J]. Laser and Optoelectronics Progress, 2018, 55(5):129-137.)
[11] DING J, LI A, HU Z, et al. Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks[C]//Proceedings of the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10435. Cham:Springer, 2017:559-567.
[12] ZHU W, VANG Y S, HUANG Y, et al. DeepEM:deep 3D convNets with EM for weakly supervised pulmonary nodule detection[C]//Proceedings of the 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2018:812-820.
[13] TANG H, LIU X, XIE X. An end-to-end framework for integrated pulmonary nodule detection and false positive reduction[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1903.09880.pdf.
[14] TANG H, KIM D R, XIE X. Automated pulmonary nodule detection using 3D deep convolutional neural networks[C]//Proceedings of the IEEE 15th International Symposium on Biomedical Imaging. Piscataway:IEEE, 2018:523-526.
[15] ZHU W, LIU C, FAN W, et al. DeepLung:3D deep convolutional nets for automated pulmonary nodule detection and classification[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1709.05538.pdf.
[16] HAMIDIAN S, SAHINER B, PETRICK N, et al. 3D convolutional neural network for automatic detection of lung nodules in chest CT[C]//Proceedings of the Medical Imaging 2017:Computer-Aided Diagnosis, SPIE 10134. Bellingham, WA:SPIE, 2017:Article No. 1013409.
[17] PEZESHK A, HAMIDIAN S, PETRICK N, et al. 3D convolutional neural networks for automatic detection of pulmonary nodules in chest CT[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(5):2080-2090.
[18] WANG D, KHOSLA A, GARGEYA R, et al. Deep learning for identifying metastatic breast cancer[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1606.05718.pdf.
[19] KHOSRAVAN N, BAGCI U. S4ND:single-shot single-scale lung nodule detection[C]//Proceedings of the 2018 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 11071. Cham:Springer, 2018:794-802.
[20] OZDEMIR O, RUSSELL R L, BERLIN A A. A 3D probabilistic deep learning system for detection and diagnosis of lung cancer using low-dose CT scans[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1902.03233.pdf.
[21] LI X, WANG W, HU X, et al. Selective kernel networks[EB/OL].[2019-05-10]. https://arxiv.org/pdf/1903.06586.pdf.
[22] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2921-2929.
[23] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[EB/OL]. https://arxiv.org/abs/1709.01507.

基于自适应感受野机制的颈部淋巴结自动识别算法

Automatic recognition algorithm of cervical lymph nodes using adaptive receptive field mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[2]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[6]	武维, 李泽平, 杨华蔚, 林川, 王忠德. 融合内容特征和时序信息的深度注意力视频流行度预测模型[J]. 计算机应用, 2021, 41(7): 1878-1884.
[7]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[8]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
[9]	张洋, 江铭虎. 基于注意力机制的文本作者识别[J]. 计算机应用, 2021, 41(7): 1897-1901.
[10]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[11]	刘世泽, 朱奕达, 陈润泽, 罗海勇, 赵方, 孙艺, 王宝会. 基于残差时域注意力神经网络的交通模式识别算法[J]. 计算机应用, 2021, 41(6): 1557-1565.
[12]	李想, 王卫兵, 尚学达. 指针生成网络和覆盖损失优化的Transformer在生成式文本摘要领域的应用[J]. 计算机应用, 2021, 41(6): 1647-1651.
[13]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[14]	赖雪梅, 唐宏, 陈虹羽, 李珊珊. 基于注意力机制的特征融合-双向门控循环单元多模态情感分析[J]. 计算机应用, 2021, 41(5): 1268-1274.
[15]	胡嵽, 冯子亮. 基于深度学习的轻量级道路图像语义分割算法[J]. 计算机应用, 2021, 41(5): 1326-1331.