Computer-Aided Diagnosis of Skin Diseases Using Deep Neural Networks
Source abstract
Abstract
Propensity of skin diseases to manifest in a variety of forms, lack and maldistribution of qualified dermatologists, and exigency of timely and accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD for dermatology by exploring the potential of Deep Learning to classify hundreds of skin diseases, improving classification performance, and utilizing disease taxonomy. We trained state-of-the-art Deep Neural Networks on two of the largest publicly available skin image datasets, namely DermNet and ISIC Archive, and also leveraged disease taxonomy, where available, to improve classification performance of these models. On DermNet we establish new state-of-the-art with 80% accuracy and 98% Area Under the Curve (AUC) for classification of 23 diseases. We also set precedence for classifying all 622 unique sub-classes in this dataset and achieved 67% accuracy and 98% AUC. On ISIC Archive we classified all 7 diseases with 93% average accuracy and 99% AUC. This study shows that Deep Learning has great potential to classify a vast array of skin diseases with near-human accuracy and far better reproducibility. It can have a promising role in practical real-time skin disease diagnosis by assisting physicians in large-scale screening using clinical or dermoscopic images.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · Dermatological and COVID-19 studies · AI in cancer detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Fachbereich Informatik, Technische Universität Kaiserslautern, 67663 Kaiserslautern, Germany
German Research Center for Artificial Intelligence GmbH (DFKI), 67663 Kaiserslautern, Germany
College of Engineering, Osaka Prefecture University, Naka, Sakai, Osaka 599-8531, Japan
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST), H-12, Islamabad 46000, Pakistan
Deep Learning Laboratory, National Center of Artificial Intelligence, Islamabad 46000, Pakistan
Department of Dermatology, University Hospital Münster, Von-Esmarch-Str 58, 48149 Münster, Germany
Department of Dermatology, University Hospital Düsseldorf, Moorenstr. 5, 40225 Düsseldorf, Germany
Funding
National University of Science and Technology, Pakistan · Bundesministeriums für Bildung und Forschung · NVIDIA AI Lab
References (48)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
3. Advances in natural language processing10.1126/science.aaa8685 ↗
4. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
5. Identification of Marek’s disease virus nuclear antigen in latently infected lymphoblastoid cells10.1128/jvi.62.10.3764-3771.1988 ↗
6. Malignancy detection on mammography using dual deep convolutional neural networks and genetically discovered false color input enhancement10.1007/s10278-017-9993-2 ↗
7. Bajwa, M.N., Malik, M.I., Siddiqui, S.A., Dengel, A., Shafait, F., Neumeier, W., and Ahmed, S. (2019). Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Med. Inform. Decis. Mak., 19.10.1186/s12911-019-0842-8 ↗
8. Bajwa, M.N., Taniguchi, Y., Malik, M.I., Neumeier, W., Dengel, A., and Ahmed, S. (2019, January 24–26). Combining Fine-and Coarse-Grained Classifiers for Diabetic Retinopathy Detection. Proceedings of the Annual Conference on Medical Image Understanding and Analysis, Liverpool, UK.10.1007/978-3-030-39343-4_21 ↗
9. Automated critical test findings identification and online notification system using artificial intelligence in imaging10.1148/radiol.2017162664 ↗
10. Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology10.1046/j.1365-2133.2003.05023.x ↗
11. Validity and reliability of dermoscopic criteria used to differentiate nevi from melanoma: A web-based international dermoscopy society study10.1001/jamadermatol.2016.0624 ↗
12. Masood, A., and Ali Al-Jumaily, A. (2013). Computer aided diagnostic support system for skin cancer: A review of techniques and algorithms. Int. J. Biomed. Imaging, 2013.10.1155/2013/323268 ↗
13. Argenziano, G., Soyer, H., De Giorgi, V., Piccolo, D., Carli, P., and Delfino, M. (2020, March 05). Interactive Atlas of Dermoscopy (Book and CD-ROM). Available online: http://www.dermoscopy.org/atlas/order_cd.asp.
14. Ballerini, L., Fisher, R.B., Aldridge, B., and Rees, J. (2013). A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions. Color Medical Image Analysis, Springer.10.1007/978-94-007-5389-1_4 ↗
15. MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images10.1016/j.eswa.2015.04.034 ↗
16. Mendonça, T., Ferreira, P.M., Marques, J.S., Marcal, A.R., and Rozeira, J. (2013, January 3–7). PH 2-A dermoscopic image database for research and benchmarking. Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan.10.1109/EMBC.2013.6610779 ↗
17. A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data. Medical Imaging 2012: Image Perception, Observer Performance, and Technology Assessment
18. Sato, I., Nishimura, H., and Yokoi, K. (2015). Apac: Augmented pattern classification with neural networks. arXiv.
19. Graham, B. (2014). Fractional max-pooling. arXiv.
20. Lee, C.Y., Gallagher, P.W., and Tu, Z. (2016). Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree. Artif. Intell. Stat., 464–472.
21. Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L.J., Fei-Fei, L., Yuille, A., Huang, J., and Murphy, K. (2018, January 8–14). Progressive neural architecture search. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01246-5_2 ↗
22. Kawahara, J., BenTaieb, A., and Hamarneh, G. (2016, January 13–16). Deep features to classify skin lesions. Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic.10.1109/ISBI.2016.7493528 ↗
23. Ge, Z., Demyanov, S., Bozorgtabar, B., Abedini, M., Chakravorty, R., Bowling, A., and Garnavi, R. (2017, January 18–21). Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging. Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, Australia.10.1109/ISBI.2017.7950681 ↗
24. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
25. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists10.1093/annonc/mdy166 ↗
26. Gutman, D., Codella, N.C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv.
27. Li, Y., Esteva, A., Kuprel, B., Novoa, R., Ko, J., and Thrun, S. (2017, January 4–5). Skin cancer detection and tracking using data synthesis and deep learning. Proceedings of the Workshops at the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.
28. Li, Y., and Shen, L. (2018). Skin lesion analysis towards melanoma detection using deep learning network. Sensors, 18.10.3390/s18020556 ↗
29. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
30. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
31. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
32. Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18–23). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00907 ↗
33. Liao, H. (2016). A Deep Learning Approach to Universal Skin Disease Classification, University of Rochester Department of Computer Science, CSC.
34. Cıcero, F.M., Oliveira, A.H.M., Botelho, G.M., and da Computaçao, C.d.C. (2016, January 4–7). Deep learning and convolutional neural networks in the aid of the classification of melanoma. Proceedings of the Conference on Graphics, Patterns and Images, SIBGRAPI, Sao Paulo, Brazil.
35. Prabhu, V., Kannan, A., Ravuri, M., Chablani, M., Sontag, D., and Amatriain, X. (2018). Prototypical Clustering Networks for Dermatological Disease Diagnosis. arXiv.
36. Codella, N.C., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., and Kittler, H. (2018, January 4–7). 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). Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363547 ↗
37. Codella, N., Rotemberg, V., Tschandl, P., Celebi, M.E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., and Marchetti, M. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv.
38. Menegola, A., Fornaciali, M., Pires, R., Bittencourt, F.V., Avila, S., and Valle, E. (2017, January 18–21). Knowledge transfer for melanoma screening with deep learning. Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, Australia.10.1109/ISBI.2017.7950523 ↗
39. Nasr-Esfahani, E., Samavi, S., Karimi, N., Soroushmehr, S.M.R., Jafari, M.H., Ward, K., and Najarian, K. (2016, January 17–20). Melanoma detection by analysis of clinical images using convolutional neural network. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.10.1109/EMBC.2016.7590963 ↗
40. Automated melanoma recognition in dermoscopy images via very deep residual networks10.1109/TMI.2016.2642839 ↗
41. Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., and Smith, J.R. (2015, January 5). Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. Proceedings of the International Workshop on Machine Learning in Medical Imaging, Munich, Germany.10.1007/978-3-319-24888-2_15 ↗
42. Effective features to classify skin lesions in dermoscopic images10.1016/j.eswa.2017.05.003 ↗
43. Lopez, A.R., Giro-i Nieto, X., Burdick, J., and Marques, O. (2017, January 20–21). Skin lesion classification from dermoscopic images using deep learning techniques. Proceedings of the 2017 13th IASTED International Conference on Biomedical Engineering (BioMed), Innsbruck, Austria.
44. Computer-aided model for skin diagnosis using deep learning10.18178/joig.4.2.122-129 ↗
45. Skin cancer classification using convolutional neural networks: Systematic review10.2196/11936 ↗
46. Automated dermatological diagnosis: Hype or reality?10.1016/j.jid.2018.04.040 ↗
47. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm10.1016/j.jid.2018.01.028 ↗
48. Interpretation of the Outputs of a Deep Learning Model Trained with a Skin Cancer Dataset10.1016/j.jid.2018.05.014 ↗