Abstract
Melanoma is one kind of dangerous cancer that has been increasing rapidly in the world. Initial diagnosis is essential to survival, but often the disease is diagnosed in the fatal stage. The rapid growth of skin cancers raises a huge demand for accurate automatic skin lesion segmentation. While deep learning techniques, i.e., convolutional neural network (CNN), have been widely used for precise segmentation, the existing densely connected network (DenseNet) and residual network (ResNet)–based encoder-decoder architectures used non-biomedical features for skin lesion tasks. The complexity of tuned parameters, small information in the pre-trained features, and the lack of multi-scale information degrade the performance of skin lesion segmentation. To address these issues, we present encoder-decoder–based CNN for skin lesion segmentation, based on the widely used UNet architecture. We exploit the benefit of combining DenseNet and ResNet to improve the performance of skin lesion segmentation. In the encoder path, atrous spatial pyramid pooling (ASPP) is used to generate multi-scale features from different dilation rates. We used dense skip connection to combine the feature maps of both encoder and decoder paths. We evaluate our approach on ISIC 2018 dataset and achieve competitive performance as compared to other state-of-the-art approaches. Compared to the previous UNet approaches, our method gains a high Jaccard index, Dice, accuracy, and sensitivity. We think that this progress is mainly due to the combined architecture of DenseNet, ResNet, ASPP, and dense skip connection that preserve the contextual information in the encoder-decoder paths. We utilized the combined benefits of both recent DenseNet and ResNet architectures. We used ASPP to exploit multi-scale contextual information by adopting multiple dilation rates. We also implemented dense skip connections for better recovery of fine-grained information of target objects. In the future, we believe that this approach will be helpful to other medical image segmentation tasks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Pennisi A, Bloisi D, Nardi D, Giampetruzzi A, Mondino C, Facchiano A. Skin lesion image segmentation using delaunay triangulation for melanoma detection. Computerized Medical Imaging and Graphics 2016;52:89–103.
Yu Z, Jiang X, Zhou F, Qin J, Ni D, Chen S, et al. Melanoma recognition in dermoscopy images via aggregated deep convolutional features. IEEE Transactions on Biomedical Engineering 2019; 66(4):1006–1016.
Ghosh S, Das N, Das I, Maulik U. Understanding deep learning techniques for image segmentation. ACM Computing Survey 2019;52(4):1–30. Article No.: 73.
Kooi T, Litjens G, Van Ginneken B, Gubern-Mérida A, Sánchez CI, Mann R, et al. Large scale deep learning for computer aided detection of mammographic lesions. Medical Image Analysis 2017;35:303–312.
Hou B, Kang G, Zhang N, Liu K. Multi-target interactive neural network for automated segmentation of the hippocampus in magnetic resonance imaging. Cognitive Computation 2019;11:630–643.
Jafari MH, Nasr-Esfahani E, Karimi N, Soroushmehr SMR, Samavi S, Najarian K. Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma. International Journal of Computer Assisted Radiology and Surgery 2017;12(6):1021–1030.
Yuan Y, Chao M, Lo YC. Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance. IEEE Trans Medical Imag 2017;36(9):1876–1886.
Li Y, Shen L. Skin lesion analysis towards melanoma detection using deep learning network. Sensors 2018;18(2):556.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention (MICCAI). Cham: Springer International Publishing; 2015. p. 234–241.
Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. UNet++: a nested u-net architecture for medical image segmentation. Deep learning in medical image analysis and multimodal learning for clinical decision support. Cham: Springer International Publishing; 2018. p. 3–11.
Lin BS, Michael K, Kalra S, Tizhoosh HR. Skin lesion segmentation: U-nets versus clustering. IEEE symposium series on computational intelligence (SSCI). IEEE; 2017. p. 1–7.
Qamar S, Jin H, Zheng R, Ahmad P. Multi stream 3D hyper-densely connected network for multi modality isointense infant brain mri segmentation. Multimedia Tools and Applications 2019;78(18): 25807–25828.
Ople JJM, yi Yeh P, Sun SW, Tsai IT, Hua KL. Multi-scale neural network with dilated convolutions for image deblurring. IEEE Access 2020;8:53942–53952.
Holschneider M, Kronland-Martinet R, Morlet J, Tchamitchian P. A real-time algorithm for signal analysis with the help of the wavelet transform. Wavelets. In: Combes JM, Grossmann A, and Tchamitchian P, editors. Berlin: Springer; 1990. p. 286–297.
Yu F, Koltun V, Funkhouser T. Dilated residual networks. IEEE conference on computer vision and pattern recognition (CVPR); 2017. p. 636–644.
Chen LC, Papandreou G, Schroff F, Adam H. 2017. Rethinking atrous convolution for semantic image segmentation. Available from: arXiv:1706.05587.
Jiang F, Zhou F, Qin J, Wang T, Lei B. Decision-augmented generative adversarial network for skin lesion segmentation. IEEE 16th international symposium on biomedical imaging (ISBI 2019); 2019. p. 447–450.
Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, et al. Understanding convolution for semantic segmentation. IEEE winter conference on applications of computer vision (WACV). IEEE; 2018. p. 1451–1460.
Bi L, Feng D, Kim J. 2018. Improving automatic skin lesion segmentation using adversarial learning based data augmentation. Available from: arXiv:1807.08392.
Song Y, Tan EL, Jiang X, Cheng JZ, Ni D, Chen S, et al. Accurate cervical cell segmentation from overlapping clumps in pap smear images. IEEE Trans Medical Imag 2016;36(1):288–300.
Liao S, Gao Y, Oto A, Shen D. Representation learning: a unified deep learning framework for automatic prostate MR segmentation. International conference on medical image computing and computer-assisted intervention (MICCAI). Springer; 2013. p. 254–261.
Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2017;39(4):640–651. Available from: https://doi.org/10.1109/TPAMI.2016.2572683.
Zheng S, Jayasumana S, Romera-Paredes B, Vineet V, Su Z, Du D, et al. Conditional random fields as recurrent neural networks. IEEE international conference on computer vision (ICCV); 2015. p. 1529–1537.
Papandreou G, Chen LC, Murphy KP, Yuille AL. Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. IEEE international conference on computer vision (ICCV); 2015. p. 1742–1750.
Wang Q, Gao J, Li X. Weakly supervised adversarial domain adaptation for semantic segmentation in urban scenes. IEEE Transactions on Image Processing 2019;28(9):4376–4386.
Wang Q, Gao J, Yuan Y. A joint convolutional neural networks and context transfer for street scenes labeling. IEEE Transactions on Intelligent Transportation Systems 2017;19(5):1457–1470.
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence 2017;40(4):834–848.
Zhang K, Zuo W, Gu S, Zhang L. Learning deep CNN denoiser prior for image restoration. IEEE conference on computer vision and pattern recognition (CVPR); 2017. p. 3929–3938.
Yuan Y, Lo YC. Improving dermoscopic image segmentation with enhanced Convolutional-Deconvolutional networks. IEEE Journal of Biomedical and Health Informatics 2019;23:519–526.
Kaul C, Manandhar S, Pears N. Focusnet: an attention-based fully convolutional network for medical image segmentation. IEEE 16th international symposium on biomedical imaging (ISBI 2019); 2019. p. 455–458.
Bissoto A, Perez F, Ribeiro V, Fornaciali M, Avila S, Valle E. 2018. Deep-learning ensembles for skin-lesion segmentation, analysis, classification: RECOD Titans at ISIC Challenge 2018. arXiv:1808.08480.
Shahin AH, Amer K, Alattar MA. Deep convolutional encoder-decoders with aggregated multi-resolution skip connections for skin lesion segmentation. IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019;2019:451–454.
Wu J, Chen EZ, Rong R, Li X, Xu D, Jiang H. Skin lesion segmentation with C-UNet. 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC); 2019. p. 2785–2788.
Chen S, Wang Z, Shi J, Liu B, Yu N. A multi-task framework with feature passing module for skin lesion classification and segmentation. IEEE 15th international symposium on biomedical imaging (ISBI 2018); 2018. p. 1126–1129.
Funding
This research is supported by Natural Science Foundation of China under grant nos. 91959108 and 61672357, the Science and Technology Project of Guangdong Province under grant no. 2018A050501014.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Ethical Approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Saqib Qamar and Parvez Ahmad are contributed equally to this manuscript and should be considered co-first authors.
Rights and permissions
About this article
Cite this article
Qamar, S., Ahmad, P. & Shen, L. Dense Encoder-Decoder–Based Architecture for Skin Lesion Segmentation. Cogn Comput 13, 583–594 (2021). https://doi.org/10.1007/s12559-020-09805-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-020-09805-6