Abstract

Skin cancer, a highly prevalent and potentially fatal disease, necessitates accurate and reliable diagnostic tools. This study presents a comprehensive methodology for skin cancer analysis using the International Skin Imaging Collaboration (ISIC)-2017 and ISIC-2019 datasets, through advanced techniques applied across the entire pipeline, from image preprocessing to classification. In the preprocessing phase, a guided filter is employed to reduce image noise, thereby minimizing unwanted artifacts and improving overall image quality. A novel network model, triple modified deep convolutional-UNet (TriMDConv-UNet), is introduced, offering three key innovations over the traditional UNet: (1) modified node connectivity, (2) the use of dilated convolutions instead of standard convolutions, and (3) the incorporation of multi-scale input features along with dense skip connections (DSC) in place of conventional skip connections (SC). For feature extraction, hierarchical relationships are captured using a capsule neural network (CapsNet), which provides more robust and discriminative feature representations. Additionally, a new self-attention network (SANet) based on the ResNet50 architecture, termed kernel attention mechanism (KAM)-SANet is proposed. This model integrates a KAM to enhance classification accuracy. Attention modules are utilized to extract contextual dependencies from images, emphasizing critical features essential for skin cancer detection. In the classification stage, the Eurasian oystercatcher optimiser (EOO) is employed to fine-tune hyperparameters. This nature-inspired optimization algorithm adjusts model parameters to achieve optimal performance in differentiating between benign and malignant skin lesions. The proposed model demonstrates superior performance in both segmentation and classification tasks. For the ISIC-2017 dataset, segmentation accuracy reached 95.03%, while for the ISIC-2019 dataset it was 96.20%. In classification, the model achieved 99.35% accuracy on ISIC-2017 and 99.65% on ISIC-2019. These results indicate that the proposed approach significantly outperforms existing models, delivering improved outcomes in skin cancer analysis.

Keywords

Skin cancer detection, Medical image segmentation, TriMDConv-UNet, Capsule neural network (CapsNet), KAM-SANet, Eurasian oystercatcher optimiser (EOO).

Cite this article

Appadurai JP, Nirmala, Manjunatha, Thirumalraj A. A hybrid TriMDConv-UNet and EOO-based KAM-SANet framework for skin cancer identification. International Journal of Advanced Technology and Engineering Exploration. 2025; 12(130):1414-1431

References

[1] https://platform.who.int/mortality/themes/theme-details/topics/indicator-groups/indicator-group-details/MDB/melanoma-and-other-skin-cancers. Accessed 26 August 2025.

[2] Reis HC, Turk V, Khoshelham K, Kaya S. In SiNet: a deep convolutional approach to skin cancer detection and segmentation. Medical & Biological Engineering & Computing. 2022; 60(3):643-62.

[3] Ali K, Shaikh ZA, Khan AA, Laghari AA. Multiclass skin cancer classification using EfficientNets–a first step towards preventing skin cancer. Neuroscience Informatics. 2022; 2(4):100034.

[4] Xin C, Liu Z, Zhao K, Miao L, Ma Y, Zhu X, et al. An improved transformer network for skin cancer classification. Computers in Biology and Medicine. 2022; 149:105939.

[5] Khan MA, Sharif MI, Raza M, Anjum A, Saba T, Shad SA. Skin lesion segmentation and classification: a unified framework of deep neural network features fusion and selection. Expert Systems. 2022; 39(7):e12497.

[6] Al-Saedi DK, Savaş S. Classification of skin cancer with deep transfer learning method. Computer Science. 2022:202-10.

[7] Kumar KA, Vanmathi C. Optimization driven model and segmentation network for skin cancer detection. Computers and Electrical Engineering. 2022; 103:108359.

[8] Anand V, Gupta S, Altameem A, Nayak SR, Poonia RC, Saudagar AK. An enhanced transfer learning based classification for diagnosis of skin cancer. Diagnostics. 202; 12(7):1-28.

[9] Attique Khan M, Sharif M, Akram T, Kadry S, Hsu CH. A two‐stream deep neural network‐based intelligent system for complex skin cancer types classification. International Journal of Intelligent Systems. 2022; 37(12):10621-49.

[10] Bibi A, Khan MA, Javed MY, Tariq U, Kang BG, Nam Y, et al. Skin lesion segmentation and classification using conventional and deep learning-based framework. Computers, Materials & Continua. 2022; 71(2):2477-95.

[11] Hasan MK, Elahi MT, Alam MA, Jawad MT, Martí R. DermoExpert: skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation. Informatics in Medicine Unlocked. 2022; 28:100819.

[12] Anand V, Gupta S, Koundal D, Nayak SR, Shafi J, Bhoi AK. Segmentation and classification of skin cancer using K-means clustering and EfficientNetB0 model. In advances in communication, devices and networking: proceedings of ICCDN 2021 2022 (pp. 471-481). Singapore: Springer Nature Singapore.

[13] Ahammed M, Al Mamun M, Uddin MS. A machine learning approach for skin disease detection and classification using image segmentation. Healthcare Analytics. 2022; 2:100122.

[14] Tembhurne JV, Hebbar N, Patil HY, Diwan T. Skin cancer detection using ensemble of machine learning and deep learning techniques. Multimedia Tools and Applications. 2023; 82(18):27501-24.

[15] Inthiyaz S, Altahan BR, Ahammad SH, Rajesh V, Kalangi RR, Smirani LK, et al. Skin disease detection using deep learning. Advances in Engineering Software. 2023; 175:103361.

[16] SM J, P M, Aravindan C, Appavu R. Classification of skin cancer from dermoscopic images using deep neural network architectures. Multimedia Tools and Applications. 2023; 82(10):15763-78.

[17] Qureshi AS, Roos T. Transfer learning with ensembles of deep neural networks for skin cancer detection in imbalanced data sets. Neural Processing Letters. 2023; 55(4):4461-79.

[18] Tahir M, Naeem A, Malik H, Tanveer J, Naqvi RA, Lee SW. DSCC_Net: multi-classification deep learning models for diagnosing of skin cancer using dermoscopic images. Cancers. 2023; 15(7):1-28.

[19] Obayya M, Arasi MA, Almalki NS, Alotaibi SS, Al Sadig M, Sayed A. Internet of things-assisted smart skin cancer detection using metaheuristics with deep learning model. Cancers. 2023; 15(20):1-17.

[20] Tabrizchi H, Parvizpour S, Razmara J. An improved VGG model for skin cancer detection. Neural Processing Letters. 2023; 55(4):3715-32.

[21] Gururaj HL, Manju N, Nagarjun A, Aradhya VM, Flammini F. DeepSkin: a deep learning approach for skin cancer classification. IEEE Access. 2023; 11:50205-14.

[22] Kumar MD, Sivanarayana GV, Indira DN, Raj MP. Skin cancer segmentation with the aid of multi-class dilated D-net (MD2N) framework. Multimedia Tools and Applications. 2023; 82(23):35995-6018.

[23] Rahman MA, Bazgir E, Hossain SS, Maniruzzaman M. Skin cancer classification using NASNet. International Journal of Science and Research Archive. 2024; 11(1):775-85.

[24] Sivakumar MS, Leo LM, Gurumekala T, Sindhu V, Priyadharshini AS. Deep learning in skin lesion analysis for malignant melanoma cancer identification. Multimedia Tools and Applications. 2024; 83(6):17833-53.

[25] Desale RP, Patil PS. An efficient multi-class classification of skin cancer using optimized vision transformer. Medical & Biological Engineering & Computing. 2024; 62(3):773-89.

[26] Yao P, Shen S, Xu M, Liu P, Zhang F, Xing J, et al. Single model deep learning on imbalanced small datasets for skin lesion classification. IEEE Transactions on Medical Imaging. 2021; 41(5):1242-54.

[27] Kaur R, GholamHosseini H, Sinha R, Lindén M. Melanoma classification using a novel deep convolutional neural network with dermoscopic images. Sensors. 2022; 22(3):1-15.

[28] Zhu S, Yu Z. Self‐guided filter for image denoising. IET Image Processing. 2020; 14(11):2561-6.

[29] Tran ST, Cheng CH, Nguyen TT, Le MH, Liu DG. Tmd-unet: triple-unet with multi-scale input features and dense skip connection for medical image segmentation. Healthcare. 2021; 9(1):1-19.

[30] Jampour M, Abbaasi S, Javidi M. CapsNet regularization and its conjugation with ResNet for signature identification. Pattern Recognition. 2021; 120:107851.

[31] Al-gaashani MS, Samee NA, Alnashwan R, Khayyat M, Muthanna MS. Using a resnet50 with a kernel attention mechanism for rice disease diagnosis. Life. 2023; 13(6):1-14.

[32] Salim A, Jummar WK, Jasim FM, Yousif M. Eurasian oystercatcher optimiser: new meta-heuristic algorithm. Journal of Intelligent Systems. 2022; 31(1):332-44.