Diagnostic performance study on the melanoma automated diagnosis software powered by artificial intelligence technologies

Abstract

INTRODUCTION: The research evaluates a series of publications on the machine recognition efficacy of cutaneous melanoma dermatoscopic images. Some authors report high sensitivity and specificity of automated diagnostics of skin tumors. Significant differences in the published data can be attributed to the use of different algorithms and groups of skin neoplasms to calculate the accuracy rate.

MATERIALS AND METHODS: The diagnostic performance of two automated artificial intelligence systems is compared.

RESULTS: The convolutional neural network algorithm improves the overall diagnostic accuracy by 7% compared to the algorithm without deep learning, while the overall accuracy rate was 78%. An initial set of 100 dermatoscopic images used in the study is published online for the assessment of the applicability of the obtained data when introducing existing artificial intelligence systems.

CONCLUSION: The main limitations and possible ways to further improve the automated diagnosis of skin tumors based on digital dermatoscopy are outlined.

Keywords

artificial intelligence / malignant melanoma / dermatoscopy / neural network automated diagnosis

References

[1] Melerzanov A, Gavrilov D. Melanoma diagnosis using convolutional neural networks of deep learning. Vrach. 2018;29(6):31-3. doi: 10.29296/25877305-2018-06-06 (in Russian)

[2] Мелерзанов А.В., Гаврилов Д.А. Диагностика меланомы кожи с помощью сверточных нейронных сетей глубокого обучения // Врач. 2018;29(6):31-3. doi: 10.29296/25877305-2018-06-06.

[3] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. 2016. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;2818-2826. doi: 10.1109/CVPR.2016.308.

[4] Haenssle H.A., Fink C., Schneiderbauer R., Toberer F., Buhl T., Blum A., 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. doi: 10.1093/annonc/mdy166.

[5] Haenssle HA, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A, 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. doi: 10.1093/annonc/mdy166.

[6] Szegedy C., Vanhoucke V., Ioffe S., Shlens J., Wojna Z. Rethinking the Inception Architecture for Computer Vision. 2016. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;2818-26. doi: 10.1109/CVPR.2016.308.

[7] Haenssle HA, Fink C, Toberer F, Winkler J, Stolz W, Deinlein T, et al. Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Ann Oncol. 2020;31(1):137-43. doi: 10.1016/j.annonc.2019.10.013.

[8] Haenssle H.A., Fink C., Toberer F., Winkler J., Stolz W., Deinlein T., et al. Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Ann Oncol. 2020;31(1):137-43. doi: 10.1016/j.annonc.2019.10.013.

[9] Fink C, Blum A, Buhl T, Mitteldorf C, Hofmann-Wellenhof R, Deinlein T, et al. Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined naevi and melanomas. J Eur Acad Dermatol Venereol. 2020;34(6):1355-61. doi: 10.1111/jdv.16165.

[10] Fink C., Blum A., Buhl T., Mitteldorf C., Hofmann-Wellenhof R., Deinlein T., et al. Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined naevi and melanomas. J Eur Acad Dermatol Venereol. 2020;34(6):1355-61. doi: 10.1111/jdv.16165.

[11] Winkler JK, Sies K, Fink C, Toberer F, Enk A, Deinlein T, et al. Melanoma recognition by a deep learning convolutional neural network-Performance in different melanoma subtypes and localisations. Eur J Cancer. 2020;127:21-9. doi: 10.1016/j.ejca.2019.11.020.

[12] Winkler J.K., Sies K., Fink C., Toberer F., Enk A., Deinlein T., et al. Melanoma recognition by a deep learning convolutional neural network-performance in different melanoma subtypes and localisations. Eur J Cancer. 2020;127:21-9. doi: 10.1016/j.ejca.2019.11.020.

[13] Phillips M, Marsden H, Jaffe W, Matin RN, Wali GN, Greenhalgh J, et al. Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions. JAMA Netw Open. 2019;2(10):e1913436. doi: 10.1001/jamanetworkopen.2019.13436.

[14] Phillips M., Marsden H., Jaffe W., Matin R.N., Wali G.N., Greenhalgh J., et al. Assessment of accuracy of an artificial intelligence algorithm to detect melanoma in images of skin lesions. JAMA Netw Open. 2019;2(10):e1913436. doi: 10.1001/jamanetworkopen.2019.13436.

[15] Cui X, Wei R, Gong L, Qi R, Zhao Z, Chen H, et al. Assessing the effectiveness of artificial intelligence methods for melanoma: A retrospective review. JAAD. 2019;81(5):1176-80. doi: 10.1016/j.jaad.2019.06.042.

[16] Cui X., Wei R., Gong L., Qi R., Zhao Z., Chen H., et al. Assessing the effectiveness of artificial intelligence methods for melanoma: A retrospective review. JAAD. 2019;81(5):1176-80. doi: 10.1016/j.jaad.2019.06.042.

[17] MacLellan AN, Price EL, Publicover-Brouwer P, Matheson K, Ly TY, Pasternak S, et al. The Use of Non-Invasive Imaging Techniques in the Diagnosis of Melanoma: A Prospective Diagnostic Accuracy Study. J Am Acad Dermatol. 2020:S0190-9622(20)30559-4. doi: 10.1016/j.jaad.2020.04.019.

[18] MacLellan A.N., Price E.L., Publicover-Brouwer P., Matheson K., Ly T.Y., Pasternak S., et al. The Use of Non-Invasive Imaging Techniques in the Diagnosis of Melanoma: A Prospective Diagnostic Accuracy Study. J Am Acad Dermatol. 2020:S0190-9622(20)30559-4. doi: 10.1016/j.jaad.2020.04.019.

[19] Sergeeva M, Sergeev V. On the Russian advances in global teledermoscopy. Oral and Poster Presentations from the XII International Congress of Dermatology April 18-22, 2017. Buenos Aires, Argentina. Abst. 0241. Inter J Dermatol. 2017;56:1268-9. doi: 10.1111/ijd.13720.

[20] Sergeeva M., Sergeev V. On the Russian advances in global teledermoscopy. Oral and Poster Presentations from the XII International Congress of Dermatology April 18-22, 2017. Buenos Aires, Argentina. Abst. 0241. Inter J Dermatol. 2017;56:1268-9. doi: 10.1111/ijd.13720.

[21] Neretin EYu, Sergeev VYu. Use of machine vision in the dermatoscopic diagnosis of melanoma. Dermatol Pract Concept. 2015;5(2):137-270.

[22] Neretin E.Yu., Sergeev V.Yu. Use of machine vision in the dermatoscopic diagnosis of melanoma. Dermatol Pract Concept. 2015;5(2):137-270.

[23] Sergeev VYu, Sergeev YuYu, Tamrazova OB, Nikitaev VG, Pronichev AN. On modern methods of automated diagnosis of skin tumors in clinical practice. Medical Alphabet. 2020;(6):76-8. doi: 10.33667/2078-5631-2020-6-76-78 (in Russian).

[24] Сергеев В.Ю., Сергеев Ю.Ю., Тамразова О.Б., Никитаев В.Г., Проничев А.Н. Вопросы внедрения современных методов автоматизированной диагностики новообразований кожи в клиническую практику // Медицинский алфавит. 2020;(6):76-8. doi: 10.33667/2078-5631-2020-6-76-78.

[25] Sergeev VYu, Sergeev YuYu, Tamrazova OB, Nikitaev VG, Pronichev AN. Automated remote diagnosis of dermatological neoplasms. Medical Equipment. 2019;(3):32-3. (in Russian)

[26] Сергеев В.Ю., Сергеев Ю.Ю., Тамразова О.Б., Никитаев В.Г., Проничев А.Н. Автоматизированная диагностика новообразований в дерматологии с применением дистанционных технологий // Медицинская техника. 2019;(3):32-3.

RIGHTS & PERMISSIONS

Eco-Vector