I. J. of Electrical & Electronics Research
Research Article | 
A Novel Medical Image Segmentation Model with Domain Generalization Approach
Author(s) : R Gomathi1 and S Selvakumaran2
Published In : International Journal of Electrical and Electronics Research (IJEER) Volume 10, Issue 2, Special Issue on IEEE-SD
Publisher : FOREX Publication
Published : 30 June 2022
e-ISSN : 2347-470X
Page(s) : 312-319
Abstract
In deep learning-based computing vision for image processing, image segmentation is a prominent issue. There is promising generalisation performance in the medical image segmentation sector for approaches using domain generalisation (DG). Single domain generalisation (SDG) is a more difficult problem than conventional generalisation (DG), which requires numerous source domains to be accessible during network training, as opposed to conventional generalisation (DG). Color medical images may be incorrectly segmented because of the augmentation of the full image in order to increase model generalisation capacity. An arbitrary illumination SDG model for improving generalisation power for colour image segmentation approach for medical images through synthesizing random radiance charts is presented as a first solution to this challenge. Color medical images may be decomposed into reflectivity and illumination maps using retinex-based neural networks (ID-Nets). In order to provide medical colour images under various lighting situations, illumination randomization is used to enhance illumination maps. A new metric, TGCI, called the transfer gradient consistency index was devised to quantify the performance of the breakdown of retinal images by simulating physical lighting. Two of the existing retinal image segmentation tasks are tested extensively in order to assess our suggested system. According to the Dice coefficient, our framework surpasses previous SDGs and image improvement algorithms, outperforming the best SDGs by up to 1.7 per cent.
Keywords: Image segmentation, medical data, machine learning, computer vision, domain generalisation
R Gomathi, Department of ECE, University College of Engineering Dindigul, Tamilnadu, India; Email: gomathiaudece@gmail.com
S Selvakumaran, Department of EEE, PSNA CET, Dindigul, Tamilnadu, India; Email: selvakumaran1977@gmail.com
[1] Bora, “Medical color image enhancement: Problems, challenges & recent techniques,” in Intelligent Multimedia Data Analysis. De Gruyter, 2019, pp. 1–18. [Cross Ref]
[Cross Ref] [2] Parul Datta, Prasenjit Das and Abhishek Kumar (2021), An Integrated Fundus Image Segmentation Algorithm for Multiple Eye Ailments. IJEER 9(4), 125-134. DOI: 10.37391/IJEER.090406.[Cross Ref]
[3] Castrejón, K. Kundu, R. Urtasun, S. Fidler, Annotating object instances with a polygon-RNN, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 4485–4493, doi:10.1109/CVPR.2017.477.[Cross Ref]
[4] Avadhesh Kumar Dixit, Rakesh Kumar Yadav and Ramapati Mishra (2021), Contrast Enhancement of Colour Images by Optimized Fuzzy Intensification. IJEER 9(4), 143-149. DOI: 10.37391/IJEER.090408.[Cross Ref]
[5] Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation, AvXiv Preprint AvXiv: 1706.05587. (2017).[Cross Ref]
[6] Fan, Q. Wang, J. Ke, F. Yang, B. Gong, and M. Zhou, “Adversarially adaptive normalization for single domain generalization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8208–8217.[Cross Ref]
[7] Li, K. Gao, J. Cao, Z. Huang, Y. Weng, X. Mi, Z. Yu, X. Li, and B. Xia, “Progressive domain expansion network for single domain generalization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 224–233.[Cross Ref]
[8] Lin, A. Milan, C. Shen, I. Reid, RefineNet: multi-path refinement networks for high-resolution semantic segmentation, IEEE Trans. Pattern Anal. Mach. Intell. 42 (2020) 1228–1242, doi:10.1109/TPAMI.2019.2893630.[Cross Ref]
[9] Liu, R. Yang, S. Li, Y. Shi, X. Jin, Painting completion with generative translation models, Multimed. Tools Appl. 79 (2020) 14375–14388, doi:10.1007/ s11042-018-6761-3.[Cross Ref]
[10] Liu, Y. Chen, X. Zhu, K. Hou, Image classification using label constrained sparse coding, Multimed. Tools Appl. 75 (2016) 15619–15633, doi:10.1007/s11042-015-2626-1.[Cross Ref]
[11] Qiao, L. Zhao, and X. Peng, “Learning to learn single domain generalization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12 556–12 565.[Cross Ref]
[12] Tajbakhsh, L. Jeyaseelan, Q. Li, J.N. Chiang, Z. Wu, X. Ding, Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation, Med. Image Anal. 63 (2020) 101693, doi:10.1016/j.media.2020.101693.[Cross Ref]
[13] Visin, A. Romero, M. Ciccone, K. Kastner, K. Cho, M. Matteucci, Y. Bengio, A. Courville, ReSeg: a recurrent neural network-based model for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, 2016, pp. 426–433, doi:10.1109/CVPRW.2016.60.[Cross Ref]
[14] Wang, P. Chen, Y. Yuan, D. Liu, Z. Huang, X. Hou, G. Cottrell, Understanding convolution for semantic segmentation, in: Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision, WACV, Institute of Electrical and Electronics Engineers Inc, 2018, pp. 1451–1460, doi:10.1109/WACV.2018.00163. 2018.[Cross Ref]
[15] Wang, Y. Luo, R. Qiu, Z. Huang, and M. Baktashmotlagh, “Learning to diversify for single domain generalization,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 834–843.[Cross Ref]
[16] Wei, W. Wang, W. Yang, and J. Liu, “Deep retinex decomposition for low-light enhancement,” arXiv preprint arXiv:1808.04560, 2018.[Cross Ref]
[17] Xu, Q. Zhu, J. Wang, Generative image completion with image-toimage translation, Neural Comput. Appl. 32 (2020) 7333–7345, doi:10.1007/ s00521-019-04253-2.[Cross Ref]
[18] Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, in: Proceedings of the International Conference on Learning Representations, Caribe Hilton, 2016, pp. 1–4. International Conference on Learning Representations, ICLR.[Cross Ref]
[19] Yu, H. Dong, M. Zhang, J. Zhao, B. Dong, Q. Li, L. Zhang, AF-SEG: an annotation-free approach for image segmentation by self-supervision and generative adversarial network, in: Proceedings of the International Symposium on Biomedical Imaging, IEEE Computer Society, 2020, pp. 1503–1507, doi:10.1109/ISBI45749.2020.9098535.[Cross Ref]
[20] Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid Scene Parsing Network, in: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 6230–6239, doi:10.1109/CVPR.2017.660. 2017. [Cross Ref]
R Gomathi, S Selvankumaran (2022), A Novel Medical Image Segmentation Model with Domain Generalization Approach. IJEER 10(2), 312-319. DOI: 10.37391/IJEER.100242.