Modern methods for detecting malignant skin tumors, including the use of mobile applications and artificial intelligence: literature review

• Natalia A. Sivоdedova
• Nikolay N. Karyakin
• Irena L. Shlivko

Abstract

The article analyzes the effectiveness of existing methods for detecting cancer, including the use of mobile applications and artificial intelligence (hereinafter referred to as AI) for identifying malignant skin tumors in countries around the world. An overview of such visual methods as ABCDE, the Ugly duckling sign, the Glasgow system, the use of dermatoscopy, ultrasound diagnostics, reflectance confocal microscopy, and total-body photography is presented. The review also presents and evaluates the effectiveness of AI-based methods for automatic image analysis. The use of AI methods in telemedicine and on mobile platforms in the form of mobile applications opens up new prospects in the early detection of cancer. The article presents examples of mobile applications with various operating algorithms, both for self-diagnosis (Skin Self-Exam, SSE) and for use by specialists.

The purpose of this review is to search in reliable scientific databases for articles on the effectiveness of modern methods for detecting cancer, including the use of mobile applications and artificial intelligence.

Research methods. To search for literature sources, the databases PubMed (Medline), CyberLeninka, and RSCI among English-language and Russian-language publications were used. The study used thematic and semantic methodology for obtaining information. Keyword queries were entered into the search bar: skin, skin malignancies, melanoma, basal cell skin cancer, mobile applications, telemedicine technologies. At the first stage, 1304 articles on the topic of modern diagnostic methods were found, from the received articles the following categories were identified: visual methods, instrumental and methods using information technology, at the second stage queries were entered into these groups, 646 articles were received, duplicates were excluded, description of clinical cases. The review presents 42 articles on methods for diagnosing cancer.

Results and discussion. After searching reliable scientific databases for articles on the effectiveness of modern methods for detecting cancer, including the use of mobile applications and artificial intelligence, the sensitivity of the methods was compared. Despite the advantage of relative ease of use, visual methods show low sensitivity and specificity. Among the achievements of recent years, one can note the use of AI-based tools. Studies based on the analysis of NK images show high sensitivity and specificity. The results obtained may inspire some optimism, but so far the use of such technologies in clinical practice is relatively rare.

The use of mobile applications, both using neural networks and applications for self-diagnosis, is still at the stage of searching for the most effective approaches, despite the fact that in some countries regulatory authorities have approved the use of such solutions in clinical practice, there is a small number of high-quality studies on the effectiveness of these technologies. In certain cases, the use of apps can lead to increased healthcare costs.

Conclusion. Since in recent years there has been an increase in the incidence of cervical cancer, the burden on the healthcare system is increasing, and there is a need to search for and implement new approaches. Along with traditional methods, the search for solutions in the field of using telemedicine technologies, in particular in the form of mobile applications with various algorithms, has wide prospects. Thus, the search and research of effective methods for detecting malignant tumors is becoming one of the most promising tasks for researchers at the intersection of various scientific disciplines and fields of knowledge.

Keywords:skin; malignant neoplasms of the skin; melanoma; basal cell skin cancer; mobile applications; telemedicine technologies

References

1. Chebotarev V.V., Khismatullina Z.R., Zakirova Yu.A. Some aspects of the epidemiology and diagnosis of malignant neoplasms of the skin. Kreativnaya khirurgiya i onkologiya [Creative Surgery and Oncology]. 2020; 10 (1): 65–73. (in Russian)

2. Malignant neoplasms in Russia in 2021 (morbidity and mortality). Collection. In: A.D. Kaprin, V.V. Starinsky, A.O. Shakhzadova (eds). Moscow: MNIOI im. P.A. Gertsena – filial FGBU «NMITs radiologii» Minzdrava Rossii, 2022: 252 p. (in Russian)

3. Arnold M., Singh D., Laversanne M., Vignat J., Vaccarella S., Meheus F., et al. Global burden of cutaneous melanoma in 2020 and projections to 2040. JAMA Dermatol. 2022; 158 (5): 495–503. DOI: https://doi.org/10.1001/jamadermatol.2022.0160 PMID: 35353115; PMCID: PMC8968696.

4. Ermakov A.V. Skin melanomas: modern principles of early diagnosis and prevention. Onkologiya. Zhurnal imeni P.A. Gertsena [Oncology. Journal named after P.A. Gertsen]. 2014; 3 (3): 100–8. (in Russian)

5. Ahnlide I., Bjellerup M., Nilsson F., Nielsen K. Validity of ABCD rule of dermoscopy in clinical practice. Acta Derm Venereol. 2016; 96 (3): 367–72. DOI: https://doi.org/10.2340/00015555-2239 PMID: 26351008.

6. Sokolov D.V., Makhson A.N., Demidov L.V., Vorozhtsov G.N., Kuz’min S.G., Sokolov V.V. Dermatoscopy (epiluminescent surface microscopy): in vivo diagnosis of skin melanoma (literature review). Sibirskiy onkologicheskiy zhurnal [Siberian Journal of Oncology]. 2008; (5): 63–7. (in Russian)

7. Benellii C., Roscetti E., Dal Pozzo V. The dermoscopic (7FFM) versus the clinical (ABCDE) diagnosis of small diameter melanoma. Eur J Dermatol. 2000; 10 (4): 282–7. PMID: 10846255.

8. Demidov L.V., Sokolov D.V., Bulycheva I.V., Shashkov B.V., Makhson A.N., Vorozhtsov G.N., et al. Improvement methods for diagnosing skin melanoma. Vestnik RONTS imeni N.N. Blokhina RAMN [Bulletin of the National Russian Cancer Research Center named after N.N. Blokhin RAMS]. 2007; 18 (1): 36–41. (in Russian)

9. Gaudy-Marqueste C., Wazaefi Y., Bruneu Y., Triller R., Thomas L., Pellacani G., et al. Ugly duckling sign as a major factor of efficiency in melanoma detection. JAMA Dermatol. 2017; 153 (4): 279–84. URL: https://jamanetwork.com/journals/jamadermatology/fullarticle/2600689 (date of access July 15, 2023).

10. Scope A., Dusza S.W., Halpern A.C., et al. The «ugly duckling» sign: agreement between observers. Arch Dermatol. 2008; 144 (1): 58–64. DOI: https://doi.org/10.1001/archdermatol.2007.15

11. Chervonnaya L.V. Pigmented tumors of the skin Moscow: GEOTAR-Media, 2014: 224 p. ISBN: 978-5-9704-2897-9. URL: https://www.rosmedlib.ru/book/ISBN9785970428979.html (date of access July 12, 2023). (in Russian)

12. Gachon J., Beaulieu P., Sei J.F., Gouvernet J., Claudel J.P., Lemaitre M., et al. First prospective study of the recognition process of melanoma in dermatological practice. Arch Dermatol. 2005; 141 (4): 434–8. DOI: https://doi.org/10.1001/archderm.141.4.434 PMID: 15837860.

13. Ebert M.A., Gafton G.I., Zinov’ev G.V., Gafton I.G. Modern view on the diagnosis of skin melanoma. Voprosy oncologii [Problems in Oncology]. 2019; 65 (5): 638–44. EDN PFZQMV. (in Russian)

14. Demidov L.V., Sinel’nikov I.E., Nazarova V.V., Utyashev I.A., Golubev A.V., Doroshenko M.V. Early diagnosis of skin melanoma: the significance and possibilities of using dermatoscopy in the clinical practice of an oncologist. Rossiyskiy onkologicheskiy zhurnal [Russian Journal of Cancer]. 2013; (5): 4–11. (in Russian)

15. Secker L.J., Buis P.A.J., Bergman W., Kukutsch N.A. Effect of a dermoscopy training course on the accuracy of primary care physicians in diagnosing pigmented lesions. Acta Derm Venereol. 2017; 97 (2): 263–5.

16. Jones O., Jurascheck L., van Melle M., Hickman S., Burrows N., Hall P., et al. Dermoscopy for melanoma detection and triage in primary care: a systematic review. BMJ Open. 2019; 9 (8): e027529.

17. Dolianitis C., Kelly J., Wolfe R., Simpson P. Comparative performance of 4 dermoscopic algorithms by nonexperts for the diagnosis of melanocytic lesions. Arch Dermatol. 2005; 141 (8): 1008–14. DOI: https://doi.org/10.1001/archderm.141.8.1008 PMID: 16103330.

18. Annessi G., Bono R., Sampogna F., Faraggiana T., Abeni D. Sensitivity, specificity, and diagnostic accuracy of three dermoscopic algorithmic methods in the diagnosis of doubtful melanocytic lesions: the importance of light brown structureless areas in differentiating atypical melanocytic nevi from thin melanomas. J Am Acad Dermatol. 2007; 56 (5): 759–67. DOI: https://doi.org/10.1016/j.jaad.2007.01.014 Epub 2007 Feb 20. PMID: 17316894.

19. Ulrich J., van Akkooi A.J., Eggermont A.M., Voit C. New developments in melanoma: utility of ultrasound imaging (initial staging, follow-up and pre-SLNB). Expert Rev Anticancer Ther. 2011; 11 (11): 1693–701. DOI: https://doi.org/10.1586/era.11.115 PMID: 22050018.

20. Ultrasound diagnostics of melanocytic skin locations. Sovremennye problemy nauki i obrazovaniya. Elektronniy zhurnal [Modern Problems of Science and Education. Electronic Journal]. URL: https://science-education.ru/ru/article/view?id=19787 (дата обращения: 28.10.2023). (in Russian)

21. Dinnes J., Bamber J., Chuchu N., Bayliss S.E., Takwoingi Y., Davenport C., et al.; Cochrane Skin Cancer Diagnostic Test Accuracy Group. High-frequency ultrasound for diagnosing skin cancer in adults. Cochrane Database Syst Rev. 2018; 12 (12): CD013188. DOI: https://doi.org/10.1002/14651858.CD013188 PMID: 30521683; PMCID: PMC6516989.

22. Agozzino M., Moscarella E., Babino G., Caccavale S., Piccolo V., Argenziano G. The use of in vivo reflectance confocal microscopy for the diagnosis of melanoma. Expert Rev Anticancer Ther. 2019; 19 (5): 413–21. DOI: https://doi.org/10.1080/14737140.2019.1593829 Epub 2019 Mar 28. PMID: 30869538.

23. Rajadhyaksha M., Grossman M., Esterowitz D., Webb R.H., Anderson R.R. In vivo confocal scanning laser microscopy of human skin: melanin provides strong contrast. J Invest Dermatol. 1995; 104 (6): 946–52. DOI: https://doi.org/10.1111/1523-1747.ep12606215 PMID: 7769264.

24. Alarcon I., Carrera C., Palou J., Alos L., Malvehy J., Puig S. Impact of in vivo reflectance confocal microscopy on the number needed to treat melanoma in doubtful lesions. Br J Dermatol. 2014; 170 (4): 802–8. DOI: https://doi.org/10.1111/bjd.12678 PMID: 24124911; PMCID: PMC3984366.

25. Guitera P., Pellacani G., Crotty K.A., Scolyer R.A., Li L.X., Bassoli S., et al. The impact of in vivo reflectance confocal microscopy on the diagnostic accuracy of lentigo maligna and equivocal pigmented and nonpigmented macules of the face. J Invest Dermatol. 2010; 130 (8): 2080–91. DOI: https://doi.org/10.1038/jid.2010.84 Epub 2010 Apr 15. PMID: 20393481.

26. Ghiţă M.A., Căruntu C., Rosca A.E., Căruntu A., Moraru L., Constantin C., et al. Real-time investigation of skin blood flow changes induced by topical capsaicin. Acta Dermatovenerol Croat. 2017; 25 (3): 223–7. PMID: 29252175.

27. Ji-Xu A., Dinnes J., Matin R.N. Total body photography for the diagnosis of cutaneous melanoma in adults: a systematic review and meta-analysis. Br J Dermatol. 2021; 185 (2): 302–12.

28. Hornung A., Steeb T., Wessely A., Brinker T.J., Breakell T., Erdmann M., et al. The value of total body photography for the early detection of melanoma: a systematic review. Int J Environ Res Public Health. 2021; 18 (4): 1726.

29. Soglia S., Pérez-Anker J., Lobos Guede N., Giavedoni P., Puig S., Malvehy J. Diagnostics using non-invasive technologies in dermatological oncology. Cancers. 2022; 14 (23): 5886.

30. Rayner J.E., Laino A.M., Nufer K.L., Adams L., Raphael A.P., Menzies S.W., et al. Clinical perspective of 3D total body photography for early detection and screening of melanoma. Front Med. 2018; 5: 152.

31. Cerminara S.E., Cheng P., Kostner L., Huber S., Kunz M., Maul J.-T., et al. Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: a new era of skin cancer screening? Eur J Cancer. 2023; 190: 112954.

32. Betz-Stablein B., D’Alessandro B., Koh U., Plasmeijer E., Janda M., Menzies S.W., et al. Reproducible naevus counts using 3D total body photography and convolutional neural networks. Dermatology. 2022; 238 (1): 4–11.

33. Truong A., Strazzulla L., March J., Boucher K.M., Nelson K.C., Kim C.C., et al. Reduction in nevus biopsies in patients monitored by total body photography. J Am Acad Dermatol. 2016; 75 (1): 135–43.e5.

34. Ji-Xu A., Dinnes J., Matin R.N. Establishing the use of total body photography among UK dermatologists. Clin Exp Dermatol. 2022; 47 (1): 182–4.

35. Terushkin V., Oliveria S.A., Marghoob A.A., Halpern A.C. Use of and beliefs about total body photography and dermatoscopy among US dermatology training programs: an update. J Am Acad Dermatol. 2010; 62 (5): 794–803.

36. Rice Z.P., Weiss F.J., DeLong L.K., Curiel-Lewandrowski C., Chen S.C. Utilization and rationale for the implementation of total body (digital) photography as an adjunct screening measure for melanoma. Melanoma Res. 2010; 20 (5): 417–21.

37. Cerminara S.E., Cheng P., Kostner L., Huber S., Kunz M., Maul J.T., et al. Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: a new era of skin cancer screening? Eur J Cancer. 2023; 190: 112954. DOI: https://doi.org/10.1016/j.ejca.2023.112954 Epub 2023 Jun 24. PMID: 37453242.

38. Hubel D.H., Wiesel T.N. Receptive fields and functional architecture of monkey striate cortex. J Physiol. 1968; 195 (1): 215–43.

39. The Nobel Prize in Physiology or Medicine 1981. URL: https://www.nobelprize.org/prizes/medicine/1981/summary/ (date of access July 20, 2023).

40. Lecun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998; 86 (11): 2278–324. URL https://ieeexplore.ieee.org/document/726791 (date of access July 12, 2023).

41. Schmidhuber J. Deep learning in neural networks: an overview. Neural Netw. 2015; 61: 85–117.

42. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., et al. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1989; 1 (4): 541–51. URL: https://ieeexplore.ieee.org/document/6795724 (date of access July 12, 2023).

43. Rumelhart D.E., McClelland J.L. (eds). Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations. Cambridge, MA: MIT Press books, 1986: 318–62. URL: https://ieeexplore.ieee.org/document/6302929 (date of access July 12, 2023).

44. Arif M., Philip F.M., Ajesh F., Izdrui D., Craciun M.D., Geman O. Automated detection of nonmelanoma skin cancer based on deep convolutional neural network. J Healthcare Eng. 2022; 2022: 6952304.

45. Zhang L., Gao H.J., Zhang J., Badami B. Optimization of the convolutional neural networks for automatic detection of skin cancer. Open Med (Warsaw, Poland). 2020; 15: 27–37.

46. Öztürk Ş., Özkaya U. Skin lesion segmentation with improved convolutional neural network. J Digit Imaging. 2020; 33 (4): 958–70.

47. Yang C.-H., Ren J.-H., Huang H.-C., Chuang L.-Y., Chang P.-Y. Deep hybrid convolutional neural network for segmentation of melanoma skin lesion. Comput Intell Neurosci. 2021; 2021: 9409508.

48. Sikandar S., Mahum R., Ragab A.E., Yayilgan S.Y., Shaikh S. SCDet: a robust approach for the detection of skin lesions. Diagnostics. 2023; 13 (11): 1824.

49. Afza F., Sharif M., Khan M.A., Tariq U., Yong H.-S., Cha J. Multiclass skin lesion classification using hybrid deep features selection and extreme learning machine. Sensors. 2022; 22 (3): 799.

50. Haenssle H.A., Fink C., Schneiderbauer R., Toberer F., Buhl T., Zalaudek I., 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.

51. Marchetti M.A., Codella N.C.F., Dusza S.W., Gutman D.A., Helba B., Kalloo A., et al. Results of the 2016 International Skin Imaging Collaboration ISBI Challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. J Am Acad Dermatol. 2018; 78 (2): 270–7.e1.

52. 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.

53. Kong F., Horsham C., Rayner J., Simunovic M., O’Hara M., Soyer H.P., et al. Consumer preferences for skin cancer screening using mobile teledermoscopy: a qualitative study. Dermatology. 2020; 236 (2): 97–104.

54. Kong F.W., Horsham C., Ngoo A., Soyer P., Janda M. Review of smartphone mobile applications for skin cancer detection: what are the changes in availability, functionality, and costs to users over time? Int J Dermatol. 2021; 60 (3): 289–308. URL: https://pubmed.ncbi.nlm.nih.gov/32880938 (date of access July 17, 2023).

55. Maier T., Kulichova D., Schotten K., Astrid R., Ruzicka T., Berking C., et al. Accuracy of a smartphone application using fractal image analysis of pigmented moles compared to clinical diagnosis and histological result. J Eur Acad Dermatol Venereol (JEADV). 2015; 29 (4): 663–7.

56. Garanina O.E., Shlivko I.L., Klemenova I.A., Uskova K.A., Mironycheva A.M., Dardyk V.I., et al. Artificial intelligence: how it works and evaluation criteria. Consilium Medicum. 2021; (8): 626–32. URL: https://cyberleninka.ru/article/n/iskusstvennyy-intellekt-kak-rabotaet-i-kriterii-otsenki (date of access July 18, 2023). (in Russian)

57. Ukharov A.O., Shlivko I.L., Klemenova I.A., Garanina O.E., Uskova K.A., Mironycheva A.M., et al. Skin cancer risk self-assessment using AI as a mass screening tool. Inform Med Unlocked. 2023; 38: 101223.

58. Hue L., Makhloufi S., Sall N’Diaye P., Blanchet-Bardon C., Sulimovic L., Pomykala F., et al. Real-time mobile teledermoscopy for skin cancer screening targeting an agricultural population: an experiment on 289 patients in France. J Eur Acad Dermatol Venereol (JEADV). 2016; 30 (1): 20–4.

59. Congalton A.T., Oakley A.M., Rademaker M., Bramley D., Martin R.C.W. Successful melanoma triage by a virtual lesion clinic (teledermatoscopy). J Eur Acad Dermatol Venereol (JEADV). 2015; 29 (12): 2423–8.

60. Kassianos A.P., Emery J.D., Murchie P., Walter F.M. Smartphone applications for melanoma detection by community, patient and generalist clinician users: a review. Br J Dermatol. 2015; 172 (6): 1507–18.

61. Smak Gregoor A.M., Sangers T.E., Bakker L.J., et al. An artificial intelligence based app for skin cancer detection evaluated in a population based setting. NPJ Digit Med. 2023; 6 (1): 90. DOI: https://doi.org/10.1038/s41746-023-00831-w

62. Ryazaeva L.M., Kurkina K.A. Morbidity indicators of the Russian population with the most frequently detected malignant neoplasms for the period 2018–2020. Integral’nye tendentsii v meditsine i obrazovanii [Integrative Trends in Medicine and Education]. 2022; (3): 111–6. (in Russian)