An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures

Gökçen Çetinel; Bekir Murat Aydın; Sevda Gül; Devrim Akgün; Rabia Öztaş Kara

doi:10.35377/saucis...1543993

EN

An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures

Abstract

Skin lesion segmentation for recognizing and defining the boundaries of skin lesions in images is proper for automated analysis of skin lesion images, especially for the early diagnosis and detection of skin cancers. Deep learning architectures are an efficient way to implement segmentation once a skin lesion dataset is provided with ground truth images. This study evaluates deep learning architectures on a hybrid dataset, including a private dataset collected from a hospital and a public ISIC dataset. Four different test cases exist in the analysis where the combinations of public and private datasets are used as train and test datasets. Experimental results include Unet, Unet++, DeepLabV3, DeepLabV3++, and FPN segmentation architectures. According to the comparative evaluations, mixed datasets, where public and private datasets were used together, provided the best results. The evaluations also show that the collected dataset with ground truth images provided promising results.

Keywords

Supporting Institution

TÜBİTAK

Project Number

122E629

Thanks

The authors thanks to TÜBİTAK for their supports

References

S. Spanos et al., “Measuring the quality of skin cancer management in primary care: A scoping review,” Australas. J. Dermatol., vol. 64, no. 2, pp. 177–193, May 2023, doi: 10.1111/AJD.14023.
R. Javed, M. S. M. Rahim, T. Saba, and A. Rehman, “A comparative study of features selection for skin lesion detection from dermoscopic images,” Netw. Model. Anal. Heal. Informatics Bioinforma., vol. 9, no. 1, pp. 1–13, Dec. 2020, doi: 10.1007/S13721-019-0209-1/TABLES/5.
M. Zafar, M. I. Sharif, M. I. Sharif, S. Kadry, S. A. C. Bukhari, and H. T. Rauf, “Skin Lesion Analysis and Cancer Detection Based on Machine/Deep Learning Techniques: A Comprehensive Survey,” Life 2023, Vol. 13, Page 146, vol. 13, no. 1, p. 146, Jan. 2023, doi: 10.3390/LIFE13010146.
Z. Mirikharaji et al., “A survey on deep learning for skin lesion segmentation,” Med. Image Anal., vol. 88, p. 102863, Aug. 2023, doi: 10.1016/J.MEDIA.2023.102863.
N. C. F. Codella 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),” Proc. - Int. Symp. Biomed. Imaging, vol. 2018-April, pp. 168–172, Oct. 2017, doi: 10.1109/ISBI.2018.8363547.
N. Codella et al., “Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC),” Feb. 2019, Accessed: Jul. 12, 2024. [Online]. Available: https://arxiv.org/abs/1902.03368v2.
C. Hernández-Pérez et al., “BCN20000: Dermoscopic Lesions in the Wild,” Sci. Data, vol. 11, no. 1, Aug. 2019, doi: 10.1038/s41597-024-03387-w.
P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Sci. Data 2018 51, vol. 5, no. 1, pp. 1–9, Aug. 2018, doi: 10.1038/sdata.2018.161.

O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
N. J. Singh and K. Nongmeikapam, “Semantic Segmentation of Satellite Images Using Deep-Unet,” Arab. J. Sci. Eng., vol. 48, no. 2, pp. 1193–1205, Feb. 2023, doi: 10.1007/S13369-022-06734-4/TABLES/2.
L. Zhang, J. Shen, and B. Zhu, “A research on an improved Unet-based concrete crack detection algorithm,” Struct. Heal. Monit., vol. 20, no. 4, pp. 1864–1879, Jul. 2021, doi: 10.1177/1475921720940068/ASSET/IMAGES/10.1177_1475921720940068-IMG1.PNG.
D. Harrison, F. C. De Leo, W. J. Gallin, F. Mir, S. Marini, and S. P. Leys, “Machine Learning Applications of Convolutional Neural Networks and Unet Architecture to Predict and Classify Demosponge Behavior,” Water 2021, Vol. 13, Page 2512, vol. 13, no. 18, p. 2512, Sep. 2021, doi: 10.3390/W13182512.
D.-Y. Chen et al., “Building Extraction and Number Statistics in WUI Areas Based on UNet Structure and Ensemble Learning,” Remote Sens. 2021, Vol. 13, Page 1172, vol. 13, no. 6, p. 1172, Mar. 2021, doi: 10.3390/RS13061172.
Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, “Unet++: A nested u-net architecture for medical image segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11045 LNCS, pp. 3–11, 2018, doi: 10.1007/978-3-030-00889-5_1/FIGURES/3.
L. C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11211 LNCS, pp. 833–851, Feb. 2018, doi: 10.1007/978-3-030-01234-2_49.
O. Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” Apr. 2018, Accessed: Jul. 12, 2024. [Online]. Available: https://arxiv.org/abs/1804.03999v3.
X. Yi, E. Walia, and P. Babyn, “Generative adversarial network in medical imaging: A review,” Med. Image Anal., vol. 58, p. 101552, Dec. 2019, doi: 10.1016/J.MEDIA.2019.101552.
V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, Nov. 2015, doi: 10.1109/TPAMI.2016.2644615.
E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 4, pp. 640–651, Nov. 2014, doi: 10.1109/TPAMI.2016.2572683.
M. Z. Alom, M. Hasan, C. Yakopcic, T. M. Taha, and V. K. Asari, “Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation,” Feb. 2018, Accessed: Jul. 12, 2024. [Online]. Available: https://arxiv.org/abs/1802.06955v5.
F. Milletari, N. Navab, and S. A. Ahmadi, “V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation,” Proc. - 2016 4th Int. Conf. 3D Vision, 3DV 2016, pp. 565–571, Jun. 2016, doi: 10.1109/3DV.2016.79.
N. Ibtehaz and M. S. Rahman, “MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation,” Neural Networks, vol. 121, pp. 74–87, Feb. 2019, doi: 10.1016/j.neunet.2019.08.025.
H. Sharen, M. Jawahar, L. Jani Anbarasi, V. Ravi, N. Saleh Alghamdi, and W. Suliman, “FDUM-Net: An enhanced FPN and U-Net architecture for skin lesion segmentation,” Biomed. Signal Process. Control, vol. 91, p. 106037, May 2024, doi: 10.1016/J.BSPC.2024.106037.
Sweta Jain, Pruthviraj Choudhari, Mahesh Gour, Pulmonary Lung Nodule Detection from Computed Tomography Images Using Two-Stage Convolutional Neural Network, The Computer Journal, Volume 66, Issue 4, April 2023, Pages 785–795.
He, X., Wang, Y., Poiesi, F., Song, W., Xu, Q., Feng, Z., & Wan, Y. (2023). Exploiting multi-granularity visual features for retinal layer segmentation in human eyes. Frontiers in Bioengineering and Biotechnology, 11, 1191803.
Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., Glocker, B., & Rueckert, D. (2018). Attention U-Net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.
Yi, X., Walia, E., & Babyn, P. (2019). Generative adversarial network in medical imaging: A review. Medical Image Analysis, 58, 101552. https://doi.org/10.1016/j.media.2019.101552
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
M. K. Hasan, M. A. Ahamad, C. H. Yap, and G. Yang, “A survey, review, and future trends of skin lesion segmentation and classification,” Comput. Biol. Med., vol. 155, p. 106624, Mar. 2023, doi: 10.1016/J.COMPBIOMED.2023.106624.
M. Strzelecki, M. Kociołek, M. Strąkowska, M. Kozłowski, A. Grzybowski, and P. M. Szczypiński, “Artificial intelligence in the detection of skin cancer: State of the art,” Clin. Dermatol., vol. 42, no. 3, pp. 280–295, May 2024, doi: 10.1016/J.CLINDERMATOL.2023.12.022.
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature Pyramid Networks for Object Detection,” Dec. 2016, Accessed: Jul. 12, 2024. [Online]. Available: https://arxiv.org/abs/1612.03144v2.
R. L. Araújo, F. H. D. d. Araújo, and R. R. V. e. Silva, “Automatic segmentation of melanoma skin cancer using transfer learning and fine-tuning,” Multimed. Syst., vol. 28, no. 4, pp. 1239–1250, Aug. 2022, doi: 10.1007/S00530-021-00840-3/TABLES/8.
R. Mohakud and R. Dash, “Skin cancer image segmentation utilizing a novel EN-GWO based hyper-parameter optimized FCEDN,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 10, pp. 9889–9904, Nov. 2022, doi: 10.1016/J.JKSUCI.2021.12.018.

Details

Primary Language

English

Subjects

Software Testing, Verification and Validation

Journal Section

Research Article

Authors

Gökçen Çetinel
0000-0002-1999-2797
Türkiye

Bekir Murat Aydın
0000-0002-5965-0687
Türkiye

Sevda Gül ^*
0000-0002-7040-7952
Türkiye

Devrim Akgün
0000-0002-0770-599X
Türkiye

Rabia Öztaş Kara
0000-0003-1828-5844
Türkiye

Early Pub Date

December 25, 2024

Publication Date

December 31, 2024

Submission Date

September 5, 2024

Acceptance Date

November 20, 2024

Published in Issue

Year 1970 Volume: 7 Number: 3

DOI

https://doi.org/10.35377/saucis...1543993

IZ

https://izlik.org/JA57RG26DG

Cite

RIS / Bibtex

APA

Çetinel, G., Aydın, B. M., Gül, S., Akgün, D., & Öztaş Kara, R. (2024). An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures. Sakarya University Journal of Computer and Information Sciences, 7(3), 449-459. https://doi.org/10.35377/saucis...1543993

AMA

1.Çetinel G, Aydın BM, Gül S, Akgün D, Öztaş Kara R. An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures. SAUCIS. 2024;7(3):449-459. doi:10.35377/saucis.1543993

Chicago

Çetinel, Gökçen, Bekir Murat Aydın, Sevda Gül, Devrim Akgün, and Rabia Öztaş Kara. 2024. “An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures”. Sakarya University Journal of Computer and Information Sciences 7 (3): 449-59. https://doi.org/10.35377/saucis. 1543993.

EndNote

Çetinel G, Aydın BM, Gül S, Akgün D, Öztaş Kara R (December 1, 2024) An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures. Sakarya University Journal of Computer and Information Sciences 7 3 449–459.

IEEE

[1]G. Çetinel, B. M. Aydın, S. Gül, D. Akgün, and R. Öztaş Kara, “An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures”, SAUCIS, vol. 7, no. 3, pp. 449–459, Dec. 2024, doi: 10.35377/saucis...1543993.

ISNAD

Çetinel, Gökçen - Aydın, Bekir Murat - Gül, Sevda - Akgün, Devrim - Öztaş Kara, Rabia. “An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures”. Sakarya University Journal of Computer and Information Sciences 7/3 (December 1, 2024): 449-459. https://doi.org/10.35377/saucis. 1543993.

JAMA

1.Çetinel G, Aydın BM, Gül S, Akgün D, Öztaş Kara R. An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures. SAUCIS. 2024;7:449–459.

MLA

Çetinel, Gökçen, et al. “An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures”. Sakarya University Journal of Computer and Information Sciences, vol. 7, no. 3, Dec. 2024, pp. 449-5, doi:10.35377/saucis. 1543993.

Vancouver

1.Gökçen Çetinel, Bekir Murat Aydın, Sevda Gül, Devrim Akgün, Rabia Öztaş Kara. An Evaluation of Skin Lesion Segmentation Using Deep Learning Architectures. SAUCIS. 2024 Dec. 1;7(3):449-5. doi:10.35377/saucis. 1543993