Home Health Care Science Article
PDF (9.3 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Original Article | Open Access

SkinSage XAI: An explainable deep learning solution for skin lesion diagnosis

Geetika Munjal (), Paarth Bhardwaj, Vaibhav Bhargava, Shivendra Singh, Nimish Nagpal
Amity School of Engineering and Technology, Amity University Noida, Noida, Uttar Pradesh India
Show Author Information

Graphical Abstract

View original image Download original image
The research was meant to disentangle the difficulties of skin lesion diagnosis using a multimodal approach. Our suggested technique offers unparalleled levels of transparency and interpretability in skin lesion categorization and marks a substantial improvement in the area via methodical methodology and meticulous refining. The research focuses on proposing.

Abstract

Background

Skin cancer poses a significant global health threat, with early detection being essential for successful treatment. While deep learning algorithms have greatly enhanced the categorization of skin lesions, the black‐box nature of many models limits interpretability, posing challenges for dermatologists.

Methods

To address these limitations, SkinSage XAI utilizes advanced explainable artificial intelligence (XAI) techniques for skin lesion categorization. A data set of around 50,000 images from the Customized HAM10000, selected for diversity, serves as the foundation. The Inception v3 model is used for classification, supported by gradient‐weighted class activation mapping and local interpretable model‐agnostic explanations algorithms, which provide clear visual explanations for model outputs.

Results

SkinSage XAI demonstrated high performance, accurately categorizing seven types of skin lesions—dermatofibroma, benign keratosis, melanocytic nevus, vascular lesion, actinic keratosis, basal cell carcinoma, and melanoma. It achieved an accuracy of 96%, with precision at 96.42%, recall at 96.28%, F1 score at 96.14%, and an area under the curve of 99.83%.

Conclusions

SkinSage XAI represents a significant advancement in dermatology and artificial intelligence by bridging gaps in accuracy and explainability. The system provides transparent, accurate diagnoses, improving decision‐making for dermatologists and potentially enhancing patient outcomes.

Keywords

deep learningskin lesionsexplainable artificial intelligenceHAM10000GradCAMLIME

References

1

Tschandl P, Rosendahl C, Kittler H. The HAM10000 dataset, a large collection of multi‐source dermatoscopic images of common pigmented skin lesions. Sci Data. 2018;5:180161. https://doi.org/10.1038/sdata.2018.161

Crossref Google Scholar
2

Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24–9. https://doi.org/10.1038/s41591-018-0316-z

Crossref Google Scholar
3

Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Briefings Bioinf. 2018;19(6):1236–46. https://doi.org/10.1093/bib/bbx044

Crossref Google Scholar
4

Sumithra R, Suhil M, Guru DS. Segmentation and classification of skin lesions for disease diagnosis. Procedia Comput Sci. 2015;45:76–85. https://doi.org/10.1016/j.procs.2015.03.090

Crossref Google Scholar
5
World Health Organization. Radiation: ultraviolet (UV) radiation and skin cancer. Geneva, Switzerland: World Health Organization; 2017.
6

Maglogiannis I, Doukas CN. Overview of advanced computer vision systems for skin lesions characterization. IEEE Trans Inf Technol Biomed. 2009;13(5):721–33. https://doi.org/10.1109/TITB.2009.2017529

Crossref Google Scholar
7
Li X, Wu J, Chen EZ, Jiang H. From deep learning towards finding skin lesion biomarkers. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE; 2019. p. 2797–800. https://doi.org/10.1109/EMBC.2019.8857334
Crossref
8

Olayah F, Senan EM, Ahmed IA, Awaji B. AI techniques of dermoscopy image analysis for the early detection of skin lesions based on combined CNN features. Diagnostics. 2023;13(7):1314. https://doi.org/10.3390/diagnostics13071314

Crossref Google Scholar
9
Ali Ahmed SA, Yanikoglu B, Goksu O, Aptoula E. Skin lesion classification with deep CNN ensembles. In: 2020 28th Signal Processing and Communications Applications Conference (SIU), Gaziantep, Turkey. IEEE; 2020. p. 1–4. https://doi.org/10.1109/siu49456.2020.9302125
Crossref
10

Kassem MA, Hosny KM, Fouad MM. Skin lesions classification into eight classes for ISIC 2019 using deep convolutional neural network and transfer learning. IEEE Access. 2020;8:114822–32. https://doi.org/10.1109/ACCESS.2020.3003890

Crossref Google Scholar
11
Shahin AH, Kamal A, Elattar MA. Deep ensemble learning for skin lesion classification from dermoscopic images. In: 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), Cairo, Egypt. IEEE; 2018.
Crossref
12
Gouda N, Amudha J. Skin cancer classification using ResNet. In: 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA), Greater Noida, India. IEEE; 2020. p. 536–41. https://doi.org/10.1109/ICCCA49541.2020.9250855
Crossref
13

Salido JAA, Ruiz Jr, C. Using deep learning for melanoma detection in dermoscopy images. Int J Mach Learn Comput. 2018;8(1):61–8. https://doi.org/10.18178/ijmlc.2018.8.1.664

Crossref Google Scholar
14

Sherif F, Mohamed WA, Mohra AS. Skin lesion analysis toward melanoma detection using deep learning techniques. Int J Electron Telecommun. 2019;65(4):597–602. https://doi.org/10.24425/ijet.2019.129818

Crossref Google Scholar
15
Demir A, Yilmaz F, Kose O. Early detection of skin cancer using deep learning architectures: ResNet‐101 and inception‐v3. In: 2019 Medical Technologies Congress (TIPTEKNO), Izmir, Turkey. IEEE; 2019. p. 1–4. https://doi.org/10.1109/tiptekno47231.2019.8972045
Crossref
16

Guo S, Yang Z. Multi‐channel‐ResNet: an integration framework towards skin lesion analysis. Inf Med Unlocked. 2018;12:67–74. https://doi.org/10.1016/j.imu.2018.06.006

Crossref Google Scholar
17
Carcagnì P, Leo M, Cuna A, Mazzeo PL, Spagnolo P, Celeste G, et al. Classification of skin lesions by combining multilevel learnings in a DenseNet architecture. In: Image Analysis and Processing—ICIAP 2019: 20th International Conference, Trento, Italy, September 9–13, 2019, Proceedings, Part I 20. Springer International Publishing; 2019. p. 335–44
Crossref
18
Chowdhury T, Bajwa AR, Chakraborti T, Rittscher J, Pal U. Exploring the correlation between deep learned and clinical features in melanoma detection. In: Medical Image Understanding and Analysis: 25th Annual Conference, MIUA 2021, Oxford, United Kingdom, July 12–14, 2021, Proceedings 25. Springer International Publishing; 2021. p. 3–17.
Crossref
19

Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist‐level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–8. https://doi.org/10.1038/nature21056

Crossref Google Scholar
20
Li W, Zhuang J, Wang R, Zhang J, Zheng WS. Fusing metadata and dermoscopy images for skin disease diagnosis. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, USA. IEEE; 2020. p. 1996–2000. https://doi.org/10.1109/isbi45749.2020.9098645
Crossref
21
Sadeghi M, Chilana PK, Atkins MS. How users perceive content‐ based image retrieval for identifying skin images. In: Understanding and Interpreting Machine Learning in Medical Image Computing Applications: First International Workshops, MLCN 2018, DLF 2018, and iMIMIC 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16–20, 2018, Proceedings 1. Springer International Publishing; 2018. p. 141–8.
Crossref
22

Xie Y, Zhang J, Xia Y, Shen C. A mutual bootstrapping model for automated skin lesion segmentation and classification. IEEE Trans Med Imaging. 2020;39(7):2482–93. https://doi.org/10.1109/TMI.2020.2972964

Crossref Google Scholar
23
Ridell P, Spett H. Training set size for skin cancer classification using Google's Inception v3. KTH Royal Institute of Technology; 2017. https://api.semanticscholar.org/CorpusID:211125420
24

Yang J, Xie F, Fan H, Jiang Z, Liu J. Classification for dermoscopy images using convolutional neural networks based on region average pooling. IEEE Access. 2018;6:65130–8. https://doi.org/10.1109/ACCESS.2018.2877587

Crossref Google Scholar
25
Young K, Booth G, Simpson B, Dutton R, Shrapnel S. Deep neural network or dermatologist. In: Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support: Second International Workshop, iMIMIC 2019, and 9th International Workshop, ML‐CDS 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 17, 2019, Proceedings 9. Springer International Publishing; 2019. p. 48–55.
Crossref
26

Brinker TJ, Hekler A, Enk AH, Klode J, Hauschild A, Berking C, et al. Deep learning outperformed 136 of 157 dermatologists in a head‐to‐head dermoscopic melanoma image classification task. Eur J Cancer. 2019;113:47–54. https://doi.org/10.1016/j.ejca.2019.04.001

Crossref Google Scholar
27
Zare R, Pourkazemi A. DenseNet approach to segmentation and classification of dermatoscopic skin lesions images; 2021:2110.04632. https://arxiv.org/abs/2110.04632v1
28

Hosseinzadeh Kassani S, Hosseinzadeh Kassani P. A comparative study of deep learning architectures on melanoma detection. Tissue Cell. 2019;58:76–83. https://doi.org/10.1016/j.tice.2019.04.009

Crossref Google Scholar
29

Ünver HM, Ayan E. Skin lesion segmentation in dermoscopic images with combination of YOLO and GrabCut algorithm. Diagnostics. 2019;9(3):72. https://doi.org/10.3390/diagnostics9030072

Crossref Google Scholar
30
Panati C, Wagner S, Bruggenwirth S. Feature relevance evaluation using Grad‐CAM, LIME and SHAP for deep learning SAR data classification. In: 2022 23rd International Radar Symposium (IRS), Gdansk, Poland. IEEE; 2022. p. 457–62. https://doi.org/10.23919/irs54158.2022.9904989
Crossref
31
Cian D, van Gemert J, Lengyel A. Evaluating the performance of the LIME and Grad‐CAM explanation methods on a LEGO multi‐label image classification task. 2020:2008.01584. https://arxiv.org/abs/2008.01584v1
32
Lamba M, Munjal G, Gigras Y. Prediction of breast cancer grade using explainable machine learning. Lecture notes in networks and systems. Singapore: Springer Nature Singapore; 2024. p. 733–45. https://doi.org/10.1007/978-981-97-3180-0_49
Crossref
33

Bhuiyan MA, Azad I, Uddin MK. Image processing for skin cancer features extraction. Int J Sci Eng Res. 2013;4(2):1–6.

Google Scholar
34

Barata C, Celebi ME, Marques JS. A survey of feature extraction in dermoscopy image analysis of skin cancer. IEEE J Biomed Health Inf. 2019;23(3):1096–109. https://doi.org/10.1109/JBHI.2018.2845939

Crossref Google Scholar
35

van der Velden BHM, Kuijf HJ, Gilhuijs KGA, Viergever MA. Explainable artificial intelligence (XAI) in deep learning‐based medical image analysis. Med Image Anal. 2022;79:102470. https://doi.org/10.1016/j.media.2022.102470

Crossref Google Scholar
36

Nigar N, Umar M, Shahzad MK, Islam S, Abalo D. A deep learning approach based on explainable artificial intelligence for skin lesion classification. IEEE Access. 2022;10:113715–25. https://doi.org/10.1109/ACCESS.2022.3217217

Crossref Google Scholar
37

Akın KD, Gurkan C, Budak A, Karataş H. Classification of monkeypox skin lesion using the explainable artificial intelligence assisted convolutional neural networks. Avrupa Bilim ve Teknoloji Dergisi. 2022;(40):106–10.

Google Scholar
38

Mamun MA, Kabir MS, Akter M, Uddin MS. Recognition of human skin diseases using inception‐v3 with transfer learning. Int J Inf Technol. 2022;14(6):3145–54. https://doi.org/10.1007/s41870-022-01050-4

Crossref Google Scholar
39
Hurtado S, Nematzadeh H, García‐Nieto J, Berciano‐Guerrero MÁ, Navas‐Delgado I. On the use of explainable artificial intelligence for the differential diagnosis of pigmented skin lesions. In: Siebold M, ed. International Work‐Conference on Bioinformatics and Biomedical Engineering, University of Granada, Granada, Spain. Cham: Springer International Publishing; 2022. p. 319–29.
Crossref
40

Hauser K, Kurz A, Haggenmüller S, Maron RC, von Kalle C, Utikal JS, et al. Explainable artificial intelligence in skin cancer recognition: a systematic review. Eur J Cancer. 2022;167:54–69. https://doi.org/10.1016/j.ejca.2022.02.025

Crossref Google Scholar
41

Bharati S, Mondal MRH, Podder P. A review on explainable artificial intelligence for healthcare: why, how, and when. IEEE Trans Artif Intell. 2024;5(4):1429–42. https://doi.org/10.1109/TAI.2023.3266418

Crossref Google Scholar
42

Nunnari FKadir MASonntag DOn the overlap between grad‐CAM saliency maps and explainable visual features in skin cancer images. Lecture notes in computer science. Cham: Springer International Publishing; 2021. p. 241–253. https://doi.org/10.1007/978-3-030-84060-0_16

Crossref
43

Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D, et al. A survey of methods for explaining black box models. ACM Comput Surv. 2019;51(5):1–42. https://doi.org/10.1145/3236009

Crossref Google Scholar
44

Tjoa E, Guan C. A survey on explainable artificial intelligence (XAI): toward medical XAI. IEEE Trans Neural Networks Learn Syst. 2021;32(11):4793–813. https://doi.org/10.1109/TNNLS.2020.3027314

Crossref Google Scholar
45

Zunair H, Ben Hamza A. Melanoma detection using adversarial training and deep transfer learning. Phys Med Biol. 2020;65(13):135005. https://doi.org/10.1088/1361-6560/ab86d3

Crossref Google Scholar
46

Adadi A, Berrada M. Peeking inside the black‐box: a survey on explainable artificial intelligence (XAI). IEEE Access. 2018;6:52138–60. https://doi.org/10.1109/ACCESS.2018.2870052

Crossref Google Scholar
Health Care Science
Volume 3 Issue 6,
December 2024
Pages 438-455
DOI: 10.1002/hcs2.121
Cite this article:
Munjal G, Bhardwaj P, Bhargava V, et al. SkinSage XAI: An explainable deep learning solution for skin lesion diagnosis. Health Care Science, 2024, 3(6): 438-455. https://doi.org/10.1002/hcs2.121
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return