基于深度可分离卷积网络的皮肤镜图像病灶分割方法

doi:10.11959/j.issn.2096-6652.202041

摘要/Abstract

摘要：

针对皮肤镜图像病灶难定位、病灶精准分割难以实现的问题，提出一种基于深度可分离卷积网络的皮肤镜图像病灶分割方法。首先对皮肤镜图像进行黑框移除和毛发移除处理，将图像中有碍确定病灶位置的人工噪声、天然噪声移除；然后在降噪处理的基础上，对图像进行形变、旋转，以扩充数据集；最后构建基于深度可分离卷积、空洞卷积的编解码分割模型，编码部分对图像进行特征提取，解码部分融合特征图，并对图像细节特征进行恢复。实验结果表明，该方法针对皮肤镜图像病灶分割问题可取得较好的分割效果，分割病灶的准确率达到95.24%，与分割模型U-Net相比，准确度提高了6.17%。

关键词: 皮肤镜图像, 病灶分割, 空洞卷积, 深度可分离卷积, 编解码模型

Abstract:

Aiming at the problem of the difficulty in locating the lesions in dermoscopic images and achieving precise segmentation of the lesions, a method of lesion segmentation in dermatological images based on deep separable convolutional network was proposed.Firstly, perform the black frame removal and hair removal processing on the dermoscopic image to remove the artificial and natural noise that hinders the location of the lesion in the image.Then the image after the noise reduction process was deformed and rotated to expand the data set.Finally, a encoder-decoder segmentation model based on depth separable convolution and hole convolution was constructed.The coding part extracts the features of the image, and the decoding part fuses the feature maps and restores the image details.Experimental results show that this method can achieve better segmentation results for the problem of skin disease image lesion segmentation.The accuracy of segmenting lesions reaches 95.24%.Compared with the segmentation model U-Net, the accuracy is improved by 6.17%.

Key words: dermoscopic image, lesion segmentation, hole convolution, deep separable convolution, encoder-decoder model

中图分类号:

TP391.4

崔文成,张鹏霞,邵虹. 基于深度可分离卷积网络的皮肤镜图像病灶分割方法[J]. 智能科学与技术学报, 2020, 2(4): 385-393.

Wencheng CUI,Pengxia ZHANG,Hong SHAO. Dermoscopic image lesion segmentation method based on deep separable convolutional network[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 385-393.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

图11

参考文献 22

[1]	杨国亮, 洪志阳, 许楠 . 基于多尺度编码-解码网络的皮肤病变图像分割[J]. 中国医学物理学杂志, 2019,36(2): 199-204.
	YANG G L , HONG Z Y , XU N . Segmentation of skin lesion image based on multi-scale encoder-decoder network[J]. Chinese Journal of Medical Physics, 2019,36(2): 199-204.
[2]	杨国亮, 洪志阳, 王志元 ,等. 基于改进全卷积网络的皮肤病变图像分割[J]. 计算机工程与设计, 2018,39(11): 3500-3505.
	YANG G L , HONG Z Y , WANG Z Y ,et al. Image segmentation of skin lesions based on improved fully convolution network[J]. Computer Engineering and Design, 2018,39(11): 3500-3505.
[3]	何雪英, 韩忠义, 魏本征 . 基于深度卷积神经网络的色素性皮肤病识别分类[J]. 计算机应用, 2018,38(11): 3236-3240.
	HE X Y , HAN Z Y , WEI B Z . Pigmented skin lesion recognition and classification based on deep convolutional neural network[J]. Journal of Computer Applications, 2018,38(11): 3236-3240.
[4]	LONG J , SHELHAMER E , DARREL T . Fully convolutional networks for semantic segmentation[C]// The IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2015: 3431-3440.
[5]	RONNEBERGER O , FISCHER P , BROX T ,et al. U-Net:convolutional networks for biomedical image segmentation[J]. Medical Image Computing and Computer Assisted Intervention, 2015: 234-241.
[6]	IGLOVIKOV V , SHEVETS A . TernausNet:U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation[J]. arXiv preprint, 2018,arXiv:1801.05746.
[7]	CHAURASIA A , CULURCIELLO E . LinkNet:exploiting encoder representations for efficient semantic segmentation[C]// 2017 IEEE Visual Communications and Image Processing (VCIP). Piscataway:IEEE Press, 2017: 1-4.
[8]	JAHANIFAR M , TAJEDDIN N Z , KOOHBANANI N A ,et al. Segmentation of skin lesions and their attributes using multi-scale convolutional neural networks and domain specific augmentations[J]. arXiv preprint, 2018,arXiv:1809.10243.
[9]	AL-MASNI M A , AL-ANTARI M A , CHOI M ,et al. Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks[J]. Computer Methods and Programs in Biomedicine, 2018,162: 221-231.
[10]	WANG X H , JIANG X D , DING H H ,et al. Bi-directional dermoscopic feature learning and multi-scale consistent decision fusion for skin lesion segmentation[J]. IEEE Transactions on Image Processing, 2019,29: 3039-3051.
[11]	XIE F Y , YANG J W , LIU J ,et al. Skin lesion segmentation using high-resolution convolutional neural network[J]. Computer Methods and Programs in Biomedicine, 2020,186: 105241.
[12]	YU L , CHEN H , DOU Q ,et al. Automated melanoma recognition in dermoscopy images via very deep residual networks[J]. IEEE Transactions on Medical Imaging, 2017,36(4): 994-1004.
[13]	NAVARRO F , ESCUDERO-VI?OLO M , BESCóS J . Accurate segmentation and registration of skin lesion images to evaluate lesion change[J]. IEEE Journal of Biomedical and Health Informatics, 2019,23(2): 501-508.
[14]	KUREK M , JA?KOWSKI W , . Heterogeneous team deep Q-learning in low-dimensional multi-agent environments[C]// The 2016 IEEE Conference on Computational Intelligence and Games (CIG). Piscataway:IEEE Press, 2016: 1-8.
[15]	ZHANG H G , JIANG H , LUO Y H ,et al. Data-driven optimal consensus control for discrete-time multi-agent systems with unknown dynamics using reinforcement learning method[J]. IEEE Transactions on Industrial Electronics, 2017,64(5): 4091-4100
[16]	LEI B Y , XIA Z M , JIANG F ,et al. Skin lesion segmentation via generative adversarial networks with dual discriminators[J]. IEEE Transactions on Industrial Electronics, 2020,64.
[17]	HAWAS A R , GUO Y H , DU C L ,et al. OCE-NGC:a neutrosophic graph cut algorithm using optimized clustering estimation algorithm for dermoscopic skin lesion segmentation[J]. Applied Soft Computing Journal, 2020,86: 105931.
[18]	MU C , ZHAO Q , SUN C ,et al. A novel Q-learning algorithm for optimal tracking control of linear discrete-time systems with unknown dynamics[J]. Applied Soft Computing, 2019,82: 1-13.
[19]	ARULKUMARAN K , DEISENROTH M P , BRUNDAGE M ,et al. Deep reinforcement learning:a brief survey[J]. IEEE Signal Processing Magazine, 2017,34(6): 26-38.
[20]	FOERSTER J N , CHEN R Y , AL-SHEDIVAT M ,et al. Learning with opponent-learning awareness[C]// The 17th International Conference on Autonomous Agents and Multiagent Systems. New York:ACM Press, 2018: 122-130.
[21]	ZHENG Y , MENG Z P , HAO J Y ,et al. Weighted double deep multiagent reinforcement learning in stochastic cooperative environments[C]// The 15th Pacific Rim International Conference on Artificial Intelligence. New York:ACM Press, 2018: 421-429.
[22]	ZHANG K Q , YANG Z R , LIU H ,et al. Fully decentralized multi-agent reinforcement learning with networked agents[C]// The 35th International Conference on Machine Learning. New York:ACM Press, 2018: 5872-5881.

对比项		Epoch
对比项	10	20	40
Batchsize=4	train_ac = 86.71%	train_ac = 90.52%	train_ac = 92.54%
Lr=0.01	test_ac = 85.04%	test_ac = 88.03%	test_ac = 90.45%
Batchsize=4	train_ac = 89.45%	train_ac = 92.14%	train_ac = 94.65%
Lr=0.05	test_ac = 87.60%	test_ac = 91.03%	test_ac = 92.96%
Batchsize=8	train_ac =83.04 %	train_ac = 85.94%	train_ac = 90.81%
Lr=0.01	test_ac = 80.60%	test_ac = 84.36%	test_ac = 89.23%
Batchsize=8	train_ac = 84.57%	train_ac = 92.24%	train_ac = 95.24%
Lr=0.05	test_ac = 83.04%	test_ac = 90.82%	test_ac = 93.82%