Computational neural network in melanocytic lesions diagnosis: artificial intelligence to improve diagnosis in dermatology?
Tóm tắt
Diagnosis in dermatology is largely based on contextual factors going far beyond the visual and dermoscopic inspection of a lesion. Diagnostic tools such as the different types of dermoscopy, confocal microscopy and optical coherence tomography (OCT) are available and all of these have shown their importance in improving the dermatologist’s ability, especially in the diagnosis of skin cancer. Their use, however, remains limited and time consuming, and optimizing their practice appears to be difficult, requiring extensive pre-processing, lesion segmentation and extraction of domain-specific visual features before classification. Over the last two decades, image recognition has been a matter of interest in a large part of our society and in industry, leading to the development of several techniques such as convolutional processing combined with artificial intelligence or neural networks (CNN/ANN). The aim of the present manuscript is to provide a short overview of the most recent data about CNN in the field of dermatology, mainly in skin cancer detection and its diagnosis.
Tài liệu tham khảo
Russo T, Piccolo V, Lallas A, et al. Dermoscopy of malignant skin tumours: what’s new? Dermatology 2017; 233(1): 64–73.
Witkowski AM, Ludzik J, Arginelli F, et al. Improving diagnostic sensitivity of combined dermoscopy and reflectance confocal microscopy imaging through double reader concordance evaluation in telemedicine settings: a retrospective study of 1000 equivocal cases. PLoS One 2017; 12(11): e0187748.
Levine A, Wang K, Markowitz O. Optical coherence tomography in the diagnosis of skin cancer. Dermatol Clin 2017; 35(4): 465–88.
Haroon A, Shafi S, Rao BK. Using reflectance confocal microscopy in skin cancer diagnosis. Dermatol Clin 2017; 35(4): 457–64.
Wolner ZJ, Yelamos O, Liopyris K, Rogers T, Marchetti MA, Marghoob AA. Enhancing skin cancer diagnosis with dermoscopy. Dermatol Clin 2017; 35(4): 417–37.
LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient–based learning applied to document recognition. In: Proceedings of the IEEE, 1998.
Ronneberger O, Fischer P, Brox T, editors. U–net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer–assisted intervention. Springer, 2015.
Chen L–C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Semantic image segmentation with deep convolutional nets and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 2018; 40: 834–48.
Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder–decoder architecture for image segmentation. 2015 (arXiv preprint arXiv: 151100561) available on https: //arxiv.org/abs/1511.0056; last accessed 01 february 2019.
Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). 2919658. IEEE Computer Society, 2015, p. 1520–8.
Long J, Shelhamer E, Darrell T, editors. Fully convolutional networks for semantic segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Ren S, He K, Girshick R, Zhang X, Sun J. Object detection networks on convolutional feature maps. IEEE Trans Pattern Anal Mach Intell 2017; 39(7): 1476–81.
Itchhaporia D, Snow PB, Almassy RJ, Oetgen WJ. Artificial neural networks: current status in cardiovascular medicine. J Am Coll Cardiol 1996; 28(2): 515–21.
Esteva A, Kuprel B, Novoa RA, et al. Dermatologist–level classification of skin cancer with deep neural networks. Nature 2017; 542(7639): 115–8.
Haenssle HA, Fink C, Schneiderbauer R, et al. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol 2018; 29(8): 1836–42.
Yu C, Yang S, Kim W, et al. Acral melanoma detection using a convolutional neural network for dermoscopy images. PLoS One 2018; 13(3): e0193321.
Han SS, Kim MS, Lim W, Park GH, Park I, Chang SE. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J Invest Dermatol 2018; 138(7): 1529–38.
Bi L, Kim J, Ahn E, Kumar A, Fulham M, Feng D. Dermoscopic image segmentation via multistage fully convolutional networks. IEEE Trans Biomed Eng 2017; 64(9): 2065–74.
Yuan Y, Chao M, Lo YC. Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 2017; 36(9): 1876–86.
Roffman D, Hart G, Girardi M, Ko CJ, Deng J. Predicting nonmelanoma skin cancer via a multi–parameterized artificial neural network. Sci Rep 2018; 8(1): 1701.
Pang S, Yu Z, Orgun MA. A novel end–to–end classifier using domain transferred deep convolutional neural networks for biomedical images. Comput Methods Programs Biomed 2017; 140: 283–93.
Tkaczyk E. Innovations and developments in dermatologic noninvasive optical imaging and potential clinical applications. Acta Derm Venereol 2017 July 5.
Saha S. A comprehensive guide to convolutional neural networks–the ELI5 way. 2018 (available from: https: //towardsdatascience. com/a–comprehensive–guide–to–convolutional–neural–networks–the–eli5–way–3bd2b1164a53; last accessed 25 February 2019).