2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 17 , Issue 1 , PP: 239-254, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Summi Goindi 1 * , Khushal Thakur 2 , Divneet Singh Kapoor 3
Doi: https://doi.org/10.54216/JISIoT.170117
Skin image segmentation serves as a vital undertaking in medical image analysis, specifically in dermatology, since it enables the detection of skin diseases and the assessment of effectiveness of treatments. Segmenting skin lesions from photographs is a crucial step in working towards this patchive. Nevertheless, the work of segmenting skin lesions is difficult due to the existence of both artificial and natural deviations, inherent characteristics like the shape of the lesion), and deviations in the circumstances during which the images are obtained. In recent years, researchers have been investigating the feasibility of utilizing deep-learning models for skin lesion segmentation. Deep learning methodologies have exhibited encouraging outcomes in various image segmentation initiatives, thereby preventing the possibility of automating and enhancing the precision of skin segmentation. This paper introduces a new hybrid method, named the CBi-BERT framework, aimed to improve the results and architectures of medical image segmentation or patch detection tasks. This architecture employs Convolutional Neural Networks (CNNs) for feature extraction as well Bidirectional LSTM-based encoders to process sequence information and BERT based attention collection across the strongest features. Image normalization, resizing and data augmentation techniques are applied in the proposed method to deal with major challenges faced during medical imaging such as rate of image quality differentiation from noise or bias between benign vs. malign features. We evaluate the performance of CBi-BERT to those benchmark datasets and state-of-the-art models, showing that CBi-BERT outperforms them in all relevant metrics such as Intersection over Union (IoU), recall, mean average precision (bin-MAP) DICE coefficient. Specifically, for images sized 256x256 the model achieved IoU =0.9, recall=0.92, mAP=0.89 and Dice coefficient: =0.91 thereby outperforming some advanced state-of-the-art models as ResNet50, VGG16, UNet, EfficientNet-B-01 Our results show that the framework is able to detect and segment important structures in medical images with high precision which makes it a compelling tool for AI based Healthcare solutions.
Skin , Image segmentation , Deep Learning , IOU , Segmentation
[1] L. Liu, Y. Y. Tsui, and M. Mandal, "Skin lesion segmentation using deep learning with auxiliary task," Journal of Imaging, vol. 7, no. 4, p. 67, 2021.
[2] M. M. Stofa, M. A. Zulkifley, and M. A. A. M. Zainuri, "Skin lesions classification and segmentation: a review," International Journal of Advanced Computer Science and Applications, vol. 12, no. 10, 2021.
[3] K. M. Hosny, D. Elshora, E. R. Mohamed, E. Vrochidou, and G. A. Papakostas, "Deep Learning and Optimization-Based Methods for Skin Lesions Segmentation: A Review," IEEE Access, 2023.
[4] A. RP and J. Zacharias, "TLR-Net: Transfer Learning in Residual U-Net for Enhancing Skin Lesion Segmentation," in Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing, 2023, pp. 1-8.
[5] R. Arora, B. Raman, K. Nayyar, and R. Awasthi, "Automated skin lesion segmentation using attention-based deep convolutional neural network," Biomedical Signal Processing and Control, vol. 65, p. 102358, 2021.
[6] S. Garg and J. Balkrishan, "Skin lesion segmentation in dermoscopy imagery," International Arab Journal of Information Technology, vol. 19, no. 1, pp. 29-37, 2022.
[7] F. M. Aydoghmishi, "Skin Cancer Detection by Deep Learning Algorithms," Doctoral dissertation, University of Windsor, Canada, 2023.
[8] M. D. Alahmadi, "Multiscale attention U-Net for skin lesion segmentation," IEEE Access, vol. 10, pp. 59145-59154, 2022.
[9] F. Bagheri, M. J. Tarokh, and M. Ziaratban, "Skin lesion segmentation from dermoscopic images by using Mask R-CNN, Retina-Deeplab, and graph-based methods," Biomedical Signal Processing and Control, vol. 67, p. 102533, 2021.
[10] F. Bagheri, M. J. Tarokh, and M. Ziaratban, "Skin lesion segmentation by using patch detection networks, DeepLab3+, and active contours," Turkish Journal of Electrical Engineering and Computer Sciences, vol. 30, no. 7, pp. 2489-2507, 2022.
[11] S. Baghersalimi et al., "DermoNet: densely linked convolutional neural network for efficient skin lesion segmentation," EURASIP Journal on Image and Video Processing, vol. 2019, no. 1, pp. 1-10, 2019.
[12] R. Ramadan and S. Aly, "CU-net: a new improved multi-input color U-net model for skin lesion semantic segmentation," IEEE Access, vol. 10, pp. 15539-15564, 2022.
[13] R. N. Sharma, "Skin Lesion Detection Using Deep Learning Techniques," Journal of Medical Systems, vol. 45, no. 5, p. 123, 2021.
[14] X. Tong et al., "ASCU-Net: attention gate, spatial and channel attention u-net for skin lesion segmentation," Diagnostics, vol. 11, no. 3, p. 501, 2021.
[15] E. K. Aghdam et al., "Attention swin u-net: Cross-contextual attention mechanism for skin lesion segmentation," in 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), 2023, pp. 1-5.
[16] V. Anand et al., "Modified U-net architecture for segmentation of skin lesion," Sensors, vol. 22, no. 3, p. 867, 2022.
[17] N. Siddique et al., "Recurrent residual U-Net with EfficientNet encoder for medical image segmentation," in Pattern Recognition and Tracking XXXII, vol. 11735, pp. 134-142, 2021.
[18] V. Anand et al., "Fusion of U-Net and CNN model for segmentation and classification of skin lesion from dermoscopy images," Expert Systems with Applications, vol. 213, p. 119230, 2023.
[19] I. Abid et al., "A convolutional neural network for skin lesion segmentation using double u-net architecture," Intelligent Automation & Soft Computing, vol. 33, no. 3, pp. 1407-1421, 2022.
[20] A. Bibi et al., "Skin lesion segmentation and classification using conventional and deep learning-based framework," Computational Materials and Continua, vol. 71, pp. 2477-2495, 2022.
[21] S. Das and D. Das, "Skin lesion segmentation and classification: A deep learning and Markovian approach," in 2021 IEEE Mysore Sub Section International Conference (MysuruCon), 2021, pp. 546-551.
[22] S. Innani et al., "Generative adversarial networks-based skin lesion segmentation," Scientific Reports, vol. 13, no. 1, p. 13467, 2023.
[23] M. A. Khan et al., "Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection," Expert Systems, vol. 39, no. 7, p. e12497, 2022.
[24] S. Barın and G. E. Güraksın, "An automatic skin lesion segmentation system with hybrid FCN-ResAlexNet," Engineering Science and Technology, an International Journal, vol. 34, p. 101174, 2022.
[25] P. Chen, S. Huang, and Q. Yue, "Skin lesion segmentation using recurrent attentional convolutional networks," IEEE Access, vol. 10, pp. 94007-94018, 2022.
[26] T. Thivya et al., "An Improved Network Segmentation Performance in Lesion Segmentation based on Mask R-CNN," in 2022 6th International Conference on Electronics, Communication and Aerospace Technology, 2022, pp. 1192-1198.
[27] N. Nirupama and Virupakshappa, "Enhancing Skin Disease Segmentation with Weighted Ensemble Region-Based Convolutional Network," Engineering Proceedings, vol. 59, no. 1, p. 49, 2023.
[28] Z. Mirikharaji et al., "A survey on deep learning for skin lesion segmentation," Medical Image Analysis, vol. 102863, 2023.
[29] A. A. Adegun, S. Viriri, and M. H. Yousaf, "A probabilistic-based deep learning model for skin lesion segmentation," Applied Sciences, vol. 11, no. 7, p. 3025, 2021.
