Skin Disease Segmentation Method Combining Dense Encoder and Dual-Path Attention

doi:10.3778/j.issn.1673-9418.2303122

Abstract

Abstract: Aiming at the problems of different shapes and sizes, discontinuous and blurred boundaries, and high similarity between the lesion area and the background in dermoscopic image lesion areas, a skin lesion segmentation network integrating dense encoder and dual-path attention (DEDA-Net) is proposed. Firstly, the network employs a dense coding module for multi-scale information fusion to enhance network feature extraction capabilities, alleviating blurred edges in dermoscopic images. Skip connection and residual path are used to reduce the semantic gap in the network coding and decoding parts. Secondly, a global normal pooling layer is proposed that weights feature points in the feature map based on their degree of relevance, and a dual-path attention module that extracts feature information in two dimensions, space and channel, is designed to avoid the problem that it is difficult to distinguish the lesion area from the background due to insufficient global information acquisition. Finally, using the idea of an auxiliary loss function, a weighted loss function is employed on both sides of the middle of the network and the final output layer to improve generalization ability of the network. Experimental results show that the algorithm achieves a segmentation accuracy of 96.45%, a specificity of 97.82%, a Dice coefficient of 93.16%, and an IoU of 86.61% on the ISIC2017 dataset, which are 5.93 percentage points, 6.45 percentage points, 6.53 percentage points, and 5.63 percentage points higher than the baseline U-Net, demonstrating the effectiveness of the proposed algorithm in accurately segmenting skin lesion areas.

Key words: dermatology segmentation, multi-scale fusion, dense coding, attention mechanism, global normal pooling

摘要： 针对皮肤镜图像病变区域存在形状大小各异、边界不连续且模糊、病灶区域与背景相似度高的问题，提出了一种融合密集编码器与双路径注意力的皮肤病变分割网络（DEDA-Net）。首先，运用密集编码模块进行多尺度信息融合增强网络特征提取能力，缓解皮肤镜图像中边缘模糊的问题，并采用跳跃连接与残差路径减少网络编解码之间的语义鸿沟；其次，根据特征图内每个特征点关联性程度大小进行加权提出了全局正态池化层，设计了在空间与通道两个维度提取特征信息的双路径注意力模块，避免因全局信息获取不足导致难以区分病灶区域与背景的问题；最后，利用辅助损失函数思想，在网络中间与最后的输出层两侧使用加权损失函数来提升网络泛化能力。实验结果表明，该算法在ISIC2017数据集上分割精度为96.45%，特异性为97.82%，Dice系数为93.16%，IoU为86.61%，比基线U-Net分别提高了5.93个百分点、6.45个百分点、6.53个百分点和5.63个百分点，能够有效分割皮肤病变区域。

关键词: 皮肤病分割, 多尺度融合, 密集编码, 注意力机制, 全局正态池化

WANG Longye, XIAO Yue, ZENG Xiaoli, ZHANG Kaixin, MA Ao. Skin Disease Segmentation Method Combining Dense Encoder and Dual-Path Attention[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(4): 978-989.

王龙业, 肖越, 曾晓莉, 张凯信, 马傲. 王龙业，肖越，曾晓莉，张凯信，马傲[J]. 计算机科学与探索, 2024, 18(4): 978-989.

References

[1] HYUNA S, JACQUES F, REBECCA L S, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA: A Cancer Journal for Clinicians, 2021, 71(3): 209-249.
[2] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Oct 5-9, 2015. Cham: Springer, 2015: 234-241.
[3] 沈怀艳, 吴云. 基于MSFA-Net的肝脏CT图像分割方法[J]. 计算机科学与探索, 2023, 17(3): 646-656.
SHEN H Y, WU Y. Liver CT image segmentation method based on MSFA-Net[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(3): 646-656.
[4] 宋姝洁, 崔振超, 陈丽萍, 等. 多特征融合神经网络的眼底血管分割算法[J]. 计算机科学与探索, 2021, 15(12): 2401-2412.
SONG S J, CUI Z C, CHEN L P, et al. Fundus vessel segmentation algorithm based on multi-feature fusion neural network[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(12): 2401-2412.
[5] 谢娟英, 张凯云. XR-MSF-Unet: 新冠肺炎肺部CT图像自动分割模型[J]. 计算机科学与探索, 2022, 16(8): 1850-1864.
XIE J Y, ZHANG K Y. XR-MSF-Unet: automatic segmentation model for COVID-19 lung CT images[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(8): 1850-1864.
[6] MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 2016 4th International Conference on 3D Vision, Stanford, Oct 25-28, 2016. Washington: IEEE Computer Society, 2016: 565-571.
[7] JAFARI M H, NASR-ESFAHANI E, KARIMI N, et al. Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma[J]. International Journal of Computer Assisted Radiology and Surgery, 2017, 12: 1021-1030.
[8] YUAN Y, CHAO M, YEH-CHI L. Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance[J]. IEEE Transactions on Medical Imaging, 2017, 36(9): 1876-1886.
[9] WANG Y J, SIMON S, JAHOW J, et al. Skin lesion segmentation using atrous convolution via DeepLab v3[J]. arXiv:1807.08891, 2018.
[10] AZAD R, ASADI-AGHBOLAGHI M, FATHY M, et al. Bi-directional ConvLSTM U-Net with densley connected convolutions[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-28,2019. Piscataway: IEEE, 2019: 406-415.
[11] SONG H, WANG W, ZHAO S, et al. Pyramid dilated deeper ConvLSTM for video salient object detection[C]//Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 744-760.
[12] JHA D, RIEGLER M A, JOHANSEN D, et al. DoubleU-Net: a deep convolutional neural network for medical image segmentation[C]//Proceedings of the 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems, Jul 28-30, 2022. Piscataway: IEEE, 2020: 558-564.
[13] PENNSI A, BLOISI D D, SURIANI V, et al. Skin lesion area segmentation using attention squeeze U-Net for embedded devices[J]. Journal of Digital Imaging, 2022, 35(5): 1217-1230.
[14] IBTEHAZ N, RAHMAN M S. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 121: 74-87.
[15] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[16] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[C]//Advances in Neural Information Processing Systems 27, Montreal, Dec 8-13, 2014: 3104-3112.
[17] OKTAY O, SCHLEMPER J, SCHAAP M, et al. Attention U-Net: learning where to look for the pancreas[J]. Medical Image Analysis, 2019, 53: 197-207.
[18] ALOM M Z, HASAN M, YAKOPCIC C, et al. Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation[J]. Journal of Medical Imaging, 2019, 6(1): 6-14.
[19] TANG Y, WANG X, HARRISON A P, et al. Attention-guided curriculum learning for weakly supervised classification and localization of thoracic diseases on chest radiographs[C]//Proceedings of the 9th International Workshop on Machine Learning in Medical Imaging, Granada, Sep 16, 2018.Cham: Springer, 2018: 249-258.
[20] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[J].arXiv:1706.05587, 2017.
[21] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 3-19.
[22] WANG Q, WU B, ZHU P, et al. Supplementary material for ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, Jun 13-19, 2020. Piscataway: IEEE, 2020: 11534-11542.
[23] 王宇航, 周永霞, 吴良武. 基于高斯函数的池化算法[J]. 计算机应用, 2022, 42(9): 2800-2806.
WANG Y H, ZHOU Y X, WU L W. Pooling algorithm based on gaussian function[J]. Journal of Computer Applications, 2022, 42(9): 2800-2806.
[24] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-23, 2018. Piscataway: IEEE, 2018: 7132-7141.
[25] NALEPA J, MARCINKIEWICZ M, KAWULOK M. Data augmentation for brain-tumor segmentation: a review[J]. Frontiers in Computational Neuroscience, 2019, 13: 83.
[26] MENZE B H, JAKAB A, BAUER S, et al. The multimodal brain tumor image segmentation benchmark (BRATS)[J]. IEEE Transactions on Medical Imaging, 2014, 34(10): 1993-2024.
[27] ZHOU Z, RAHMAN SIDDIQUEE M M, TAJBAKSHS N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]//Proceedings of the 4th International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Granada, Sep 20, 2018. Cham: Springer, 2018: 3-11.
[28] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 833-851.