Skin Lesion Detection Using Hand-Crafted and DL-Based Features Fusion and LSTM
Abstract
:1. Introduction
- To propose a novel features fusion-based technique for the early detection of skin cancer. First, images were pre-processed using GF to remove the noise. Second, we extracted features from the images using LBP and Inception V3. Then, we fused these features and employed an LSTM network for the binary classification into malignant and benign. Additionally, we used an Adam optimizer to adjust the learning rate for Inception V3.
- Our proposed model is an efficient technique due to its hybrid architecture that extracts most representative features and employs Long Short-Term Memory (LSTM) for the classification.
- We trained our classifier on 75% dataset and performed various experiments for the assessment of the proposed system, demonstrating its efficacy
- We cross-validated our proposed model, and the experiments showed that it significantly outperformed the existing techniques.
- Our proposed features fusion-based model is simple and easy to execute.
2. Related Work
3. Materials and Methods
3.1. Gaussian Filtering:
3.2. Features Extraction (FE)
3.3. Local Binary Patterns:
3.4. Inception V3 Using Adam Optimization
3.5. Learning Rate Scheduler
3.6. Fusion Process
3.7. Classification Using LSTM
4. Experimental Evaluation
4.1. Dataset
4.2. Metrics
4.3. Environmental Setup
4.4. Results
4.5. Comparison with Segmentation-Based Methods
4.6. Comparison with DL-Based Methods
4.7. Cross-Validation
4.8. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Latif, J.; Xiao, C.; Imran, A.; Tu, S. Medical Imaging Using Machine Learning and Deep Learning Algorithms: A Review. In Proceedings of the 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan, 30–31 January 2019. [Google Scholar]
- Zemouri, R.; Zerhouni, N.; Racoceanu, D. Deep Learning in the Biomedical Applications: Recent and Future Status. Appl. Sci. 2019, 9, 1526. [Google Scholar] [CrossRef]
- Ravishankar, S.; Ye, J.C.; Fessler, J.A. Image reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning. Proc. IEEE 2019, 108, 86–109. [Google Scholar] [CrossRef]
- Qiu, L.; Kantekure, K.; Vitkin, E.; Itzkan, I.; Perelman, L.T.; Zhang, L.; Turzhitsky, V.; Khan, U.; Zakharov, Y.; Pleskow, D.K.; et al. Multispectral Endoscopy with Light Gating for Early Cancer Detection. IEEE J. Sel. Top. Quantum Electron. 2018, 25, 1–9. [Google Scholar] [CrossRef]
- Pardo, A.; Streeter, S.S.; Maloney, B.W.; Gutierrez-Gutierrez, J.A.; McClatchy, D.M.; Wells, W.A.; Paulsen, K.D.; Lopez-Higuera, J.M.; Pogue, B.W.; Conde, O.M. Modeling and Synthesis of Breast Cancer Optical Property Signatures with Generative Models. IEEE Trans. Med. Imaging 2021, 40, 1687–1701. [Google Scholar] [CrossRef]
- Song, H.; Sasada, S.; Masumoto, N.; Kadoya, T.; Okada, M.; Arihiro, K.; Xiao, X.; Kikkawa, T. A Two-Stage Rotational Surface Clutter Suppression Method for Microwave Breast Imaging with Multistatic Impulse-Radar Detector. IEEE Trans. Instrum. Meas. 2020, 69, 9586–9598. [Google Scholar] [CrossRef]
- Song, H.; Sasada, S.; Masumoto, N.; Kadoya, T.; Shiroma, N.; Orita, M.; Arihiro, K.; Okada, M.; Kikkawa, T. Detectability of Breast Tumors in Excised Breast Tissues of Total Mastectomy by IR-UWB-Radar-Based Breast Cancer Detector. IEEE Trans. Biomed. Eng. 2018, 66, 2296–2305. [Google Scholar] [CrossRef] [PubMed]
- Wang, W.; Ye, C.; Zhang, S.; Xu, Y.; Wang, K. Improving Whole-Heart CT Image Segmentation by Attention Mechanism. IEEE Access 2019, 8, 14579–14587. [Google Scholar] [CrossRef]
- Han, Y.; Kim, J.; Ye, J.C. Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal. IEEE Trans. Med. Imaging 2020, 39, 3571–3582. [Google Scholar] [CrossRef]
- Phan, T.-D.-T.; Kim, S.H. Skin Lesion Segmentation by U-Net with Adaptive Skip Connection and Structural Awareness. Appl. Sci. 2021, 11, 4528. [Google Scholar] [CrossRef]
- Marosán-Vilimszky, P.; Szalai, K.; Horváth, A.; Csabai, D.; Füzesi, K.; Csány, G.; Gyöngy, M. Automated Skin Lesion Classification on Ultrasound Images. Diagnostics 2021, 11, 1207. [Google Scholar] [CrossRef] [PubMed]
- Khamparia, A.; Singh, P.K.; Rani, P.; Samanta, D.; Khanna, A.; Bhushan, B. An internet of health things-driven deep learning framework for detection and classification of skin cancer using transfer learning. Trans. Emerg. Telecommun. Technol. 2021, 32, e3963. [Google Scholar] [CrossRef]
- Vidya, M.; Karki, M.V. Skin Cancer Detection using Machine Learning Techniques. In Proceedings of the 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India, 2–4 July 2020; pp. 1–5. [Google Scholar] [CrossRef]
- Jasil, S.P.G.; Ulagamuthalvi, V. Skin Lesion Classification Using Pre-Trained DenseNet201 Deep Neural Network. In Proceedings of the 2021 3rd International Conference on Signal Processing and Communication (ICPSC), Coimbatore, India, 13–14 May 2021. [Google Scholar]
- Setiawan, A.W. Image Segmentation Metrics in Skin Lesion: Accuracy, Sensitivity, Specificity, Dice Coefficient, Jaccard Index, and Matthews Correlation Coefficient. In Proceedings of the 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), Surabaya, Indonesia, 17–18 November 2020. [Google Scholar]
- Ballerini, L.; Fisher, R.B.; Aldridge, B.; Rees, J. A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions. In Color Medical Image Analysis; Springer: Berlin/Heidelberg, Germany, 2013; pp. 63–86. [Google Scholar]
- Cheng, Y.; Swamisai, R.; Umbaugh, S.E.; Moss, R.H.; Stoecker, W.V.; Teegala, S.; Srinivasan, S.K. Skin lesion classification using relative color features. Ski. Res. Technol. 2007, 14, 53–64. [Google Scholar] [CrossRef]
- Silveira, M.; Nascimento, J.C.; Marques, J.S.; Marcal, A.R.S.; Mendonca, T.; Yamauchi, S.; Maeda, J.; Rozeira, J. Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images. IEEE J. Sel. Top. Signal. Process. 2009, 3, 35–45. [Google Scholar] [CrossRef]
- Schaefer, G.; Krawczyk, B.; Celebi, M.E.; Iyatomi, H. An ensemble classification approach for melanoma diagnosis. Memetic Comput. 2014, 6, 233–240. [Google Scholar] [CrossRef]
- Garnavi, R.; Aldeen, M.; Celebi, M.E.; Bhuiyan, A.; Dolianitis, C.; Varigos, G. Automatic segmentation of dermoscopy images using histogram thresholding on optimal color channels. Int. J. Med. Med. Sci. 2010, 1, 126–134. [Google Scholar]
- Akhtar, M.J.; Mahum, R.; Butt, F.S.; Amin, R.; El-Sherbeeny, A.M.; Lee, S.M.; Shaikh, S. A Robust Framework for Object Detection in a Traffic Surveillance System. Electronics 2022, 11, 3425. [Google Scholar] [CrossRef]
- Wei, L.; Ding, K.; Hu, H. Automatic Skin Cancer Detection in Dermoscopy Images Based on Ensemble Lightweight Deep Learning Network. IEEE Access 2020, 8, 99633–99647. [Google Scholar] [CrossRef]
- Hasan, A.H.; Ibrahim, A.A. Hybrid Detection Techniques for Skin Cancer Images. In Proceedings of the 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Istanbul, Turkey, 22–24 October 2020. [Google Scholar]
- Ansari, B.U.; Sarode, T. Skin cancer detection using image processing. Int. Res. J. Eng. Technol. 2017, 4, 2875–2881. [Google Scholar]
- Ibraheem, M.R.; Elmogy, M. A Non-invasive Automatic Skin Cancer Detection System for Characterizing Malignant Melanoma from Seborrheic Keratosis. In Proceedings of the 2020 2nd International Conference on Computer and Information Sciences (ICCIS), Sakaka, Saudi Arabia, 13–15 October 2020. [Google Scholar]
- Rahajeng, A.C.D.; Nuh, M.; Hikmah, N.F. An Evaluation Performance of Kernel on Support Vector Machine to Classify The Skin Tumors in Dermoscopy Image. In Proceedings of the 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), Surabaya, Indonesia, 17–18 November 2020. [Google Scholar]
- Jayalakshmi, G.; Kumar, V.S. Performance analysis of convolutional neural network (CNN) based cancerous skin lesion detection system. In Proceedings of the 2019 International Conference on Computational Intelligence in Data Science (ICCIDS), Chennai, India, 21–23 February 2019. [Google Scholar]
- Rehman, M.U.; Khan, S.H.; Rizvi, S.M.D.; Abbas, Z.; Zafar, A. Classification of skin lesion by interference of segmentation and convolotion neural network. In Proceedings of the 2018 2nd International Conference on Engineering Innovation (ICEI), Bangkok, Thailand, 5–6 July 2018. [Google Scholar]
- Filali, Y.; El Khoukhi, H.; Sabri, M.A.; Yahyaouy, A.; Aarab, A. Texture Classification of skin lesion using convolutional neural network. In Proceedings of the 2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), Fez, Morocco, 3–4 April 2019. [Google Scholar]
- Rezaoana, N.; Hossain, M.S.; Andersson, K. Detection and classification of skin cancer by using a parallel CNN model. In Proceedings of the 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Bhubaneswar, India, 26–27 December 2020. [Google Scholar]
- Barata, C.; Ruela, M.; Francisco, M.; Mendonca, T.; Marques, J.S. Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features. IEEE Syst. J. 2013, 8, 965–979. [Google Scholar] [CrossRef]
- Razzak, I.; Shoukat, G.; Naz, S.; Khan, T.M. Skin lesion analysis toward accurate detection of melanoma using multistage fully connected residual network. In Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 19–24 July 2020. [Google Scholar]
- Daghrir, J.; Tlig, L.; Bouchouicha, M.; Sayadi, M. Melanoma skin cancer detection using deep learning and classical machine learning techniques: A hybrid approach. In Proceedings of the 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia, 2–5 September 2020. [Google Scholar]
- Adegun, A.A.; Viriri, S. Deep Learning-Based System for Automatic Melanoma Detection. IEEE Access 2019, 8, 7160–7172. [Google Scholar] [CrossRef]
- Islam, M.K.; Ali, M.S.; Ali, M.M.; Haque, M.F.; Das, A.A.; Hossain, M.M.; Duranta, D.S.; Rahman, M.A. Melanoma Skin Lesions Classification using Deep Convolutional Neural Network with Transfer Learning. In Proceedings of the 2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA), Riyadh, Saudi Arabia, 6–7 April 2021. [Google Scholar]
- Raut, G.; Raut, A.; Bhagade, J.; Bhagade, J.; Gavhane, S. Deep Learning Approach for Brain Tumor Detection and Segmentation. In Proceedings of the 2020 International Conference on Convergence to Digital World-Quo Vadis (ICCDW), Mumbai, India, 18–20 February 2020. [Google Scholar]
- Alkarakatly, T.; Eidhah, S.; Al-Sarawani, M.; Al-Sobhi, A.; Bilal, M. Skin lesions identification using deep convolutional neural network. In Proceedings of the 2019 International Conference on Advances in the Emerging Computing Technologies (AECT), Al Madinah Al Munawwarah, Saudi Arabia, 10–10 February 2020. [Google Scholar]
- Kondaveeti, H.K.; Edupuganti, P. Skin Cancer Classification using Transfer Learning. In Proceedings of the 2020 IEEE International Conference on Advent Trends in Multidisciplinary Research and Innovation (ICATMRI), Buldhana, India, 30–30 December 2020. [Google Scholar]
- Bi, L.; Kim, J.; Ahn, E.; Kumar, A.; Feng, D.; Fulham, M. Step-wise integration of deep class-specific learning for dermoscopic image segmentation. Pattern Recognit. 2018, 85, 78–89. [Google Scholar] [CrossRef] [Green Version]
- Mahum, R.; Rehman, S.U.; Meraj, T.; Rauf, H.T.; Irtaza, A.; El-Sherbeeny, A.M.; El-Meligy, M.A. A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis. Sensors 2021, 21, 6189. [Google Scholar] [CrossRef] [PubMed]
- Mahum, R.; Rehman, S.U.; Okon, O.D.; Alabrah, A.; Meraj, T.; Rauf, H.T. A Novel Hybrid Approach Based on Deep CNN to Detect Glaucoma Using Fundus Imaging. Electronics 2021, 11, 26. [Google Scholar] [CrossRef]
- Mahum, R.; Munir, H.; Mughal, Z.-U.; Awais, M.; Khan, F.S.; Saqlain, M.; Mahamad, S.; Tlili, I. A novel framework for potato leaf disease detection using an efficient deep learning model. Hum. Ecol. Risk Assess. Int. J. 2022, 1–24. [Google Scholar] [CrossRef]
- Dong, N.; Zhao, L.; Wu, C.; Chang, J. Inception v3 based cervical cell classification combined with artificially extracted features. Appl. Soft Comput. 2020, 93, 106311. [Google Scholar] [CrossRef]
- Albawi, S.; Mohammed, T.A.; Al-Zawi, S. Understanding of a convolutional neural network. In Proceedings of the 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, 21–23 August 2017. [Google Scholar]
- Iranpoor, R.; Mahboob, A.S.; Shahbandegan, S.; Baniasadi, N. Skin lesion segmentation using convolutional neural networks with improved U-Net architecture. In Proceedings of the 2020 6th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS), Mashhad, Iran, 23–24 December 2020. [Google Scholar]
- DermIS, Dermatology Information System. 2020. Available online: https://www.dermis.net/dermisroot/en/home/index.htm (accessed on 25 June 2020).
- Zghal, N.S.; Derbel, N. Melanoma Skin Cancer Detection based on Image Processing. Bentham Sci. 2020, 16, 50–58. [Google Scholar] [CrossRef]
- Goyal, M.; Oakley, A.; Bansal, P.; Dancey, D.; Yap, M.H. Skin Lesion Segmentation in Dermoscopic Images with Ensemble Deep Learning Methods. IEEE Access 2019, 8, 4171–4181. [Google Scholar] [CrossRef]
- Araujo, R.L.; Rabelo, R.D.A.L.; Rodrigues, J.J.P.C.; E Silva, R.R.V. Automatic segmentation of melanoma skin cancer using deep learning. In Proceedings of the 2020 IEEE International Conference on E-health Networking, Application & Services (HEALTHCOM), Shenzhen, China, 1–2 March 2021. [Google Scholar]
- Majumder, S.; Ullah, M.A.; Dhar, J.P. Melanoma diagnosis from dermoscopy images using artificial neural network. In Proceedings of the 2019 5th International Conference on Advances in Electrical Engineering (ICAEE), Dhaka, Bangladesh, 26–28 September 2019. [Google Scholar]
- Waheed, Z.; Waheed, A.; Zafar, M.; Riaz, F. An efficient machine learning approach for the detection of melanoma using dermoscopic images. In Proceedings of the 2017 International Conference on Communication, Computing and Digital Systems (C-CODE), Islamabad, Pakistan, 8–9 March 2017. [Google Scholar]
- Mhaske, H.R.; Phalke, D.A. Melanoma skin cancer detection and classification based on supervised and unsupervised learning. In Proceedings of the 2013 International Conference on Circuits, Controls and Communications (CCUBE), Bengaluru, India, 27–28 December 2013. [Google Scholar]
- Cazzato, G.; Massaro, A.; Colagrande, A.; Lettini, T.; Cicco, S.; Parente, P.; Nacchiero, E.; Lospalluti, L.; Cascardi, E.; Giudice, G.; et al. Dermatopathology of Malignant Melanoma in the Era of Artificial Intelligence: A Single Institutional Experience. Diagnostics 2022, 12, 1972. [Google Scholar] [CrossRef]
- Thapar, P.; Rakhra, M.; Cazzato, G.; Hossain, S. A Novel Hybrid Deep Learning Approach for Skin Lesion Segmentation and Classification. J. Health Eng. 2022, 2022, 1709842. [Google Scholar] [CrossRef]
Ref. | Year | Dataset Used | Classes of Skin Lesion | Activation Function Used | Model | Model Type | Accuracy (%) | Issues |
---|---|---|---|---|---|---|---|---|
[31] | 2013 | 176 dermoscopy images | Binary Classification | - | Gradient Histogram, and BOF | Supervised | 96 | Generalization problem |
[32] | 2020 | ISIC 2019 | NV, DF, MEL, VASC, BCC, AKIEC, BKL | RELU | CNN | Supervised | 96 | Low-level features are not considered |
[33] | 2020 | ISIC | Benign, malignant | - | SVM, KNN, and CNN (Hybrid) | Supervised | KNN:57.3 SVM:71.8 | Less detection accuracy |
[34] | 2019 | ISIC 2017, PH2 | Melanoma, non-melanoma | RELU | CNN | Supervised | 95 | Low-level features are not considered |
[35] | 2021 | HAM10000 | Benign, malignant | SIGMOID | CNN | Supervised | 90.93 | Less detection accuracy |
[36] | 2020 | ISIC2018, HAM10000 | Melanoma, nevus, seborrheic keratosis | SOFTMAX | CNN | Supervised | 86 | Less detection accuracy |
[23] | 2020 | ISIC | Benign, malignant | RELU | CNN | Supervised | 80 | Less detection accuracy |
[37] | 2020 | PH2 | Melanoma, atypical nevus, common nevus | SOFTMAX | CNN | Supervised | 95.0 | Overfitting issue |
[38] | 2020 | HAM1000 | NV, DF, MEL, VASC, BCC, AKIEC, BKL | RELU | CNN | Supervised | 90 | Low precision and accuracy |
[39] | 2019 | SLC 2017, ISBI 2016, and PH2 | Melanoma, non-melanoma | RELU | ResFCN | Supervised | 94.29 | High computational resources |
Type | Learnable | Activation |
---|---|---|
Feature input | - | 7 |
LSTM-1 | Input weights 512 × 7 Recurrent weights 512 × 128 Bias 512 × 1 | 128 |
5 × [Batch Normalization] | Offset 128 × 1 Scale 128 × 1 | 128 |
8 × [RELU] | - | 128 |
addition | - | 128 |
7 × [LSTM-2] | Input weights 512 × 128 Recurrent weights 512 × 128 Bias 512 × 1 | 128 |
Fc_1 | Weights 22 × 128 Bias 22 × 1 | 22 |
Fc_2 | Weights 22 × 22 Bias 22 × 1 | 22 |
SOFTMAX | - | 22 |
Class output | - | 22 |
Hardware | Specifications |
---|---|
Computer | GPU Server |
CPU | Intel Core i5 |
RAM | 16 GB |
GPU | NVIDIA GEFORCE GTX × 4 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Mahum, R.; Aladhadh, S. Skin Lesion Detection Using Hand-Crafted and DL-Based Features Fusion and LSTM. Diagnostics 2022, 12, 2974. https://doi.org/10.3390/diagnostics12122974
Mahum R, Aladhadh S. Skin Lesion Detection Using Hand-Crafted and DL-Based Features Fusion and LSTM. Diagnostics. 2022; 12(12):2974. https://doi.org/10.3390/diagnostics12122974
Chicago/Turabian StyleMahum, Rabbia, and Suliman Aladhadh. 2022. "Skin Lesion Detection Using Hand-Crafted and DL-Based Features Fusion and LSTM" Diagnostics 12, no. 12: 2974. https://doi.org/10.3390/diagnostics12122974