EDDS-Unet: An Encoder-Decoder Double Skip Connection Scheme for Skin Lesion Segmentation
Main Article Content
Abstract
The paper presents an approach for effective skin lesion segmentation from dermatoscopic images. Aiming at transferring the weights trained from a network originally designed for image classification task, this study proposes to utilize the first layers of EfficientNet as the encoding layers of a U-Net based architecture. Besides, we introduce an encoder-decoder double skip connection scheme, a new skip connection architecture for extracting useful spatial details of skin lesions from the encoding layers. By the double skip scheme, the approach not only fuses information from the encounter layer in the encoder path to the corresponding layer in the decoder path, but also takes into account information of the proceeding encoding layer. In addition, we propose a new decoder network using the Residual blocks and Convolutional Block Attention Module (CBAM) blocks to handle the gradient vanishing problem as well as penalize the weight of each layer. The proposed Encoder-Decoder Double Skip with the Unet architecture, namely EDDS-Unet, has shown promising performance when evaluated on the official ISIC 2017 challenge and the PH2 databases. The proposed method achieves high evaluation scores with the Dice Similarity Coefficients of 0.907 for the ISIC 2017 and 0.950 for the PH2 databases without pre-or post-processing steps.
Keywords
skin lesion segmentation, skip connection, u-net, efficientNet
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
[1] M. Nasir, M. Attique Khan, M. Sharif, I. U. Lali, T. Saba, and T. Iqbal, An improved strategy for skin lesion detection and classification using uniform segmentation and feature selection based approach, Microscopy Rresearch and Technique, vol. 81, pp. 528-543, 2018. https://doi.org/10.1002/jemt.23009
[2] W. Tu, X. Liu, W. Hu, and Z. Pan, Dense-residual network with adversarial learning for skin lesion segmentation, IEEE Access, vol. 7, pp. 77037-77051, 2019. https://doi.org/10.1109/ACCESS.2019.2921815
[3] S. Pathan, K. G. Prabhu, and P. C. Siddalingaswamy, Techniques and algorithms for computer aided diagnosis of pigmented skin lesions-A review, Biomedical Signal Processing Control, vol. 39, pp. 237-262, 2018. https://doi.org/10.1016/j.bspc.2017.07.010
[4] O. Ronneberger, P. Fischer, and T. Brox, U-net: Convolutional networks for biomedical image segmentation, in Proc. of International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
[5] Thi-Thao Tran, Dinh-Thien Vu, Thi Hue Nguyen, and Van-Truong Pham, A CNN-Transformer-based Approach for Medical Image Segmentation, in International Conference on System Science and Engineering (ICSSE), Ho Chi Minh, Vietnam, 2023.
[6] L. Yu, H. Chen, Q. Dou, J. Qin, and P. A. Heng, Automated melanoma recognition in dermoscopy images via very deep residual networks, IEEE Transactions on Medical Imaging, vol. 36, pp. 994- 1004, 2016. https://doi.org/10.1109/TMI.2016.2642839
[7] Y. Yuan, M. Chao, and Y. C. Lo, Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance, IEEE Transactions on Medical Imaging, vol. 36, pp. 1876-1886, 2017. https://doi.org/10.1109/TMI.2017.2695227
[8] Y. Tang, F. Yang, and S. Yuan, A multi-stage framework with context information fusion structure for skin lesion segmentation, in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019, pp. 1407-1410. https://doi.org/10.1109/ISBI.2019.8759535
[9] H. M. Ünver and E. Ayan, Skin lesion segmentation in dermoscopic images with combination of YOLO and grabcut algorithm, Diagnostics, vol. 9, p. 72, 2019. https://doi.org/10.3390/diagnostics9030072
[10] G. Du, X. Cao, J. Liang, X. Chen, and Y. Zhan, Medical image segmentation based on u-net: A review, Journal of Imaging Science and Technology, vol. 64, pp. 20508-1-20508-12, 2020. https://doi.org/10.2352/J.ImagingSci.Technol.2020.64 .2.020508
[11] Thi-Thao Tran and Van-Truong Pham, Fully convolutional neural network with attention gate and fuzzy active contour model for skin lesion segmentation, Multimedia Tools and Applications, vol. 81, pp. 13979-13999, 2022. https://doi.org/10.1007/s11042-022-12413-1
[12] Zahra M., Kumar A., Alceu B., Catarina B., Sandra A., V. Eduardo, et al., A survey on deep learning for skin lesion segmentation, Medical Image Analysis, vol. 88, pp. 1-40, 2023. https://doi.org/10.1016/j.media.2023.102863
[13] M. Tan and Q. V. Le, Efficientnet: Rethinking model scaling for convolutional neural networks, arXiv:1905.11946, 2019.
[14] S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, Cbam: Convolutional block attention module, in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3-19. https://doi.org/10.1007/978-3-030-01234-2_1 [15] K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. https://doi.org/10.1109/CVPR.2016.90 [16] N. Abraham and N. Khan, A novel focal Tversky loss function with improved attention u-net for lesion segmentation, in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019, pp. 683-687. https://doi.org/10.1109/ISBI.2019.8759329
[17] N. Codella, D. Gutman, M. Celebi, B. Helba, M. Marchetti, S. Dusza, et al., Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic), in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 168-172. https://doi.org/10.1109/ISBI.2018.8363547
[18] T. Mendonça, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, PH 2-A dermoscopic image database for research and benchmarking, in 2013 35th annual international conference of the IEEE Engineering In Medicine And Biology Society (EMBC), 2013, pp. 5437-5440. https://doi.org/10.1109/EMBC.2013.6610779
[19] P. Tschandl, C. Sinz, and H. Kittler, Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation, Computers in Biology And Medicine, vol. 104, pp. 111-116, 2019. https://doi.org/10.1016/j.compbiomed.2018.11.010
[20] L. Song, J. Lin, Z. J. Wang, and H. Wang, Denseresidual attention network for skin lesion segmentation, in International Workshop on Machine Learning in Medical Imaging, 2019, pp. 319-327. https://doi.org/10.1007/978-3-030-32692-0_37
[21] K. Zafar, S. O. Gilani, A. Waris, A. Ahmed, M. Jamil, M. N. Khan, et al., Skin lesion segmentation from dermoscopic images using convolutional neural network, Sensors, vol. 20, p. 1601, 2020. https://doi.org/10.3390/s20061601 [22] Y. Xie, J. Zhang, Y. Xia, and C. Shen, A mutual bootstrapping model for automated skin lesion segmentation and classification, IEEE Transactions on Medical Imaging, vol. 39, pp. 2482-2493, 2020. https://doi.org/10.1109/TMI.2020.2972964
[23] M. Jahanifar, N. Z. Tajeddin, N. A. Koohbanani, A. Gooya, and N. Rajpoot, Segmentation of skin lesions and their attributes using multi-scale convolutional neural networks and domain specific augmentations, 2018, arXiv preprint arXiv:1809.10243
[24] L. Bi, J. Kim, E. Ahn, and D. Feng, Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks, 2017, arXiv preprint arXiv:1703.04197.
[25] Y. Xue, T. Xu, H. Zhang, L. R. Long, and X. Huang, SegAN: adversarial network with multi-scale L1 loss for medical image segmentation, Neuroinformatics, vol. 16, pp. 383-392, 2018. https://doi.org/10.1007/s12021-018-9377-x
[2] W. Tu, X. Liu, W. Hu, and Z. Pan, Dense-residual network with adversarial learning for skin lesion segmentation, IEEE Access, vol. 7, pp. 77037-77051, 2019. https://doi.org/10.1109/ACCESS.2019.2921815
[3] S. Pathan, K. G. Prabhu, and P. C. Siddalingaswamy, Techniques and algorithms for computer aided diagnosis of pigmented skin lesions-A review, Biomedical Signal Processing Control, vol. 39, pp. 237-262, 2018. https://doi.org/10.1016/j.bspc.2017.07.010
[4] O. Ronneberger, P. Fischer, and T. Brox, U-net: Convolutional networks for biomedical image segmentation, in Proc. of International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
[5] Thi-Thao Tran, Dinh-Thien Vu, Thi Hue Nguyen, and Van-Truong Pham, A CNN-Transformer-based Approach for Medical Image Segmentation, in International Conference on System Science and Engineering (ICSSE), Ho Chi Minh, Vietnam, 2023.
[6] L. Yu, H. Chen, Q. Dou, J. Qin, and P. A. Heng, Automated melanoma recognition in dermoscopy images via very deep residual networks, IEEE Transactions on Medical Imaging, vol. 36, pp. 994- 1004, 2016. https://doi.org/10.1109/TMI.2016.2642839
[7] Y. Yuan, M. Chao, and Y. C. Lo, Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance, IEEE Transactions on Medical Imaging, vol. 36, pp. 1876-1886, 2017. https://doi.org/10.1109/TMI.2017.2695227
[8] Y. Tang, F. Yang, and S. Yuan, A multi-stage framework with context information fusion structure for skin lesion segmentation, in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019, pp. 1407-1410. https://doi.org/10.1109/ISBI.2019.8759535
[9] H. M. Ünver and E. Ayan, Skin lesion segmentation in dermoscopic images with combination of YOLO and grabcut algorithm, Diagnostics, vol. 9, p. 72, 2019. https://doi.org/10.3390/diagnostics9030072
[10] G. Du, X. Cao, J. Liang, X. Chen, and Y. Zhan, Medical image segmentation based on u-net: A review, Journal of Imaging Science and Technology, vol. 64, pp. 20508-1-20508-12, 2020. https://doi.org/10.2352/J.ImagingSci.Technol.2020.64 .2.020508
[11] Thi-Thao Tran and Van-Truong Pham, Fully convolutional neural network with attention gate and fuzzy active contour model for skin lesion segmentation, Multimedia Tools and Applications, vol. 81, pp. 13979-13999, 2022. https://doi.org/10.1007/s11042-022-12413-1
[12] Zahra M., Kumar A., Alceu B., Catarina B., Sandra A., V. Eduardo, et al., A survey on deep learning for skin lesion segmentation, Medical Image Analysis, vol. 88, pp. 1-40, 2023. https://doi.org/10.1016/j.media.2023.102863
[13] M. Tan and Q. V. Le, Efficientnet: Rethinking model scaling for convolutional neural networks, arXiv:1905.11946, 2019.
[14] S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, Cbam: Convolutional block attention module, in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 3-19. https://doi.org/10.1007/978-3-030-01234-2_1 [15] K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. https://doi.org/10.1109/CVPR.2016.90 [16] N. Abraham and N. Khan, A novel focal Tversky loss function with improved attention u-net for lesion segmentation, in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019, pp. 683-687. https://doi.org/10.1109/ISBI.2019.8759329
[17] N. Codella, D. Gutman, M. Celebi, B. Helba, M. Marchetti, S. Dusza, et al., Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic), in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 168-172. https://doi.org/10.1109/ISBI.2018.8363547
[18] T. Mendonça, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, PH 2-A dermoscopic image database for research and benchmarking, in 2013 35th annual international conference of the IEEE Engineering In Medicine And Biology Society (EMBC), 2013, pp. 5437-5440. https://doi.org/10.1109/EMBC.2013.6610779
[19] P. Tschandl, C. Sinz, and H. Kittler, Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation, Computers in Biology And Medicine, vol. 104, pp. 111-116, 2019. https://doi.org/10.1016/j.compbiomed.2018.11.010
[20] L. Song, J. Lin, Z. J. Wang, and H. Wang, Denseresidual attention network for skin lesion segmentation, in International Workshop on Machine Learning in Medical Imaging, 2019, pp. 319-327. https://doi.org/10.1007/978-3-030-32692-0_37
[21] K. Zafar, S. O. Gilani, A. Waris, A. Ahmed, M. Jamil, M. N. Khan, et al., Skin lesion segmentation from dermoscopic images using convolutional neural network, Sensors, vol. 20, p. 1601, 2020. https://doi.org/10.3390/s20061601 [22] Y. Xie, J. Zhang, Y. Xia, and C. Shen, A mutual bootstrapping model for automated skin lesion segmentation and classification, IEEE Transactions on Medical Imaging, vol. 39, pp. 2482-2493, 2020. https://doi.org/10.1109/TMI.2020.2972964
[23] M. Jahanifar, N. Z. Tajeddin, N. A. Koohbanani, A. Gooya, and N. Rajpoot, Segmentation of skin lesions and their attributes using multi-scale convolutional neural networks and domain specific augmentations, 2018, arXiv preprint arXiv:1809.10243
[24] L. Bi, J. Kim, E. Ahn, and D. Feng, Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks, 2017, arXiv preprint arXiv:1703.04197.
[25] Y. Xue, T. Xu, H. Zhang, L. R. Long, and X. Huang, SegAN: adversarial network with multi-scale L1 loss for medical image segmentation, Neuroinformatics, vol. 16, pp. 383-392, 2018. https://doi.org/10.1007/s12021-018-9377-x