What the evidence says.
A cited synthesis of where dermal scanning and skin imaging stand today... what is diagnostic, what is cosmetic, and what the evidence actually supports.
This page is written for a careful reader, not a practitioner. Every claim below is cited to a source in the reference list at the bottom of the page. If you read only one section, read Section H... it is the one that protects you from confusing a cosmetic tool with a diagnostic one.
Dermoscopy... the original skin scan.
Dermoscopy, also called dermatoscopy, is the use of a handheld optical instrument with polarized or immersion light and magnification (typically 10x) to examine pigmented and non-pigmented skin lesions. In trained hands, it adds meaningful sensitivity over naked-eye examination for the detection of melanoma and other skin cancers.
A landmark Cochrane systematic review concluded that dermoscopy performed by a trained dermatologist, compared to visual inspection alone, improved the accuracy of melanoma detection, with a pooled sensitivity of approximately 92% and improved specificity when dermoscopic algorithms were used.[1] Earlier registry-based work by Carli and colleagues examined the characteristics of melanomas that were missed at a pigmented lesion clinic, finding that a meaningful fraction of missed melanomas had atypical features that a more structured examination approach would have flagged.[14] Simplified scoring systems such as the three-point checklist[2] were developed to make dermoscopic evaluation teachable to non-specialists, including primary care clinicians.
Two editorial takeaways:
- Dermoscopy is a skill-dependent tool. A dermatoscope in an untrained hand is not meaningfully better than the unaided eye.
- Even in expert hands, dermoscopy has limits. Missed melanomas happen. The value of dermoscopy is additive, not absolute.[15]
For high-risk patients, a system... not a snapshot.
Patients with many atypical nevi, or with personal or family history of melanoma, benefit from a surveillance strategy that tracks their skin over time rather than relying on single-visit examinations. The two cornerstone strategies are total body photography (TBP) and sequential digital dermoscopy imaging (SDDI).
TBP captures a patient's entire skin surface across a set of standardized poses to create a baseline photographic record. At subsequent visits, the clinician compares the current skin against the baseline to identify new lesions and changes... an approach often called the "ugly duckling" approach when combined with clinical judgment.[16] SDDI complements TBP by capturing dermoscopic images of specific lesions of concern for side-by-side comparison at follow-up, letting the clinician detect subtle structural change that would be invisible in a single visit.
Evidence supports this approach in high-risk cohorts. Salerni and colleagues reported that in high-risk patients followed with TBP and SDDI, melanomas detected during surveillance were more often thin and in situ than those detected outside such a program.[3] More recent work and society recommendations, including updates from the International Dermoscopy Society and the American Academy of Dermatology, continue to support TBP and SDDI as standard-of-care tools for high-risk surveillance, with the caveat that they are operator-dependent and are not themselves diagnostic... they are monitoring tools that inform the clinician's decision to biopsy or not.[17]
The editorial point is the same as in Section A. These are tools used by a trained clinician to reduce the probability of missing a melanoma over time. They do not remove the need for the clinician.
AI-assisted dermatology and the FDA-cleared devices.
The category of FDA-cleared, AI-assisted lesion evaluation devices is where the field has moved most visibly in the last five years. Two devices anchor this category in the United States.
DermaSensor is a handheld, FDA-cleared device that uses elastic scattering spectroscopy (ESS) combined with an AI-trained algorithm to evaluate a lesion's spectral signature against a database of known malignant and benign lesions. The device is indicated for use in patients aged 40 and above, on lesions a clinician has already assessed as suspicious, to support a referral decision.[18] It is explicitly not intended to be used as a population screening tool and is not intended as a sole diagnostic criterion.
The pivotal DERM-SUCCESS validation study in primary care (1,579 biopsied lesions across 22 sites) reported a device sensitivity of 95.5% for skin cancer overall, with a negative predictive value of 96.6%, and a specificity of 20.7%.[5] In a multi-reader multi-case study, primary care clinicians' false negative rate on concerning lesions was cut roughly in half when they were assisted by the device... from 18.0% without the device to 8.6% with the device.[4] A prospective melanoma validation study in 10 dermatology sites reported device melanoma sensitivity of 95.5%, comparable to the study dermatologists' melanoma sensitivity of 90.9%, with a melanoma negative predictive value of 98.1%.[6] Independent and real-world evaluations have broadly confirmed these findings.[19][20][21][22][23][24]
Two nuances matter for a careful reader:
- The device's high sensitivity and high NPV are the clinically important numbers when the question is "am I going to miss a cancer." The comparatively low specificity (20 to 33%) means the device will produce false positives... lesions it flags that turn out to be benign... and the clinician is expected to integrate the device result with the visual assessment, patient history, and other clinical context.[12][13]
- Device performance in high-volume dermatology practices may not reflect how it performs in a general primary care setting, and vice versa.[6] The indication for use specifies that the device is cleared for non-dermatologist physicians on already-suspicious lesions.
SciBase Nevisense is an FDA-cleared device that uses electrical impedance spectroscopy (EIS) to evaluate the electrical properties of cells within a suspicious pigmented lesion. Multicenter studies have reported melanoma sensitivities of roughly 96 to 97% with specificities in the 24 to 34% range, positioning Nevisense similarly in function to DermaSensor.[7][25][8][26] Like DermaSensor, Nevisense is explicitly intended as an adjunctive tool for lesions already flagged as suspicious, used by trained clinicians, and is not a general screening or self-use tool.
Consumer AI apps. A separate category of consumer-facing mobile "mole-checker" apps has grown rapidly. A systematic review by Freeman and colleagues (2020) evaluated the accuracy of such apps and found them significantly lacking the regulatory and evidentiary standards of cleared devices, with variable and often poor diagnostic performance.[27] A negative result from a smartphone app is not a clinically meaningful reassurance. This is an important reader-level distinction... the presence of "AI" in a skin product's marketing does not imply a shared level of evidence with DermaSensor or Nevisense.
Teledermatology, used well.
Teledermatology extends dermatologic expertise to settings where a specialist is not physically present. In store-and-forward teledermatology, photographs and clinical history are transmitted asynchronously to a reviewing dermatologist. In live-video teledermatology, a specialist consults in real time. Both modalities have accumulated meaningful evidence.
A systematic review by Finnane and colleagues (2017) reported diagnostic concordance rates between teledermatology and in-person evaluation in the 51 to 85% range across studies, with sensitivity for malignancy generally in the 60 to 100% range depending on image quality and study design.[11] Bashshur and colleagues (2015) reported that teledermatology is broadly comparable to in-person care across a range of outcomes, including diagnostic accuracy and appropriateness of management decisions.[10]
The editorial point on teledermatology is that image quality and the workflow around the teleconsultation matter enormously. A well-structured store-and-forward workflow, with dermoscopic images and a good clinical history, performs far better than a single cell-phone photograph of a lesion with no context.
VISIA and the aesthetic skin analysis category.
VISIA (Canfield Scientific) is the dominant aesthetic skin analysis system in dermatology and medical aesthetics practices in the United States and Europe. VISIA uses standardized cross-polarized and UV flash photography, multi-spectral imaging, and software analysis to quantify surface and sub-surface features including spots, pores, wrinkles, texture, porphyrins, UV spots, brown spots (via cross-polarized illumination), and red areas.[9] Comparable systems include Observ (Sylton), Reveal Imager (Canfield), and a growing number of smaller manufacturers.
What VISIA does well, when used in its designed context, is to generate reproducible, quantitative images of surface and sub-surface features that a cosmetic practitioner would otherwise have to assess by eye. The system is useful for cosmetic treatment planning, patient education, and documentation of change after aesthetic treatments. Validation work by Goldsberry and colleagues (2014), and more recent comparative work on aesthetic imaging systems, supports reproducibility of the surface metrics in controlled conditions.[28][29]
What VISIA does not do is diagnose skin cancer. VISIA is not FDA-cleared as a diagnostic device for melanoma, basal cell carcinoma, or squamous cell carcinoma. A VISIA skin analysis performed in a med spa is a cosmetic assessment. If the same person has an atypical mole on their back, the VISIA analysis tells them nothing meaningful about whether that mole is a melanoma.
This is the most commonly misread point in the category, and it is the one the rest of this site is organized around. A cosmetic skin analysis system is not a substitute for a dermatologist's evaluation of a suspicious lesion.
Spectral and hyperspectral imaging, in broad strokes.
Spectral imaging techniques capture information across multiple discrete wavelengths of light, sometimes stretching from the visible into the near-infrared and ultraviolet ranges. Multispectral imaging captures a small number of discrete bands; hyperspectral imaging captures many bands, producing a high-dimensional spectral "cube" for each pixel.
In dermatology, multispectral and hyperspectral imaging have been explored both for diagnostic applications (differentiating benign from malignant lesions) and for characterization of skin conditions ranging from inflammatory disease to burn assessment.[30][31][32][33] The physics are appealing because deeper tissue information is accessible than with standard RGB photography, and algorithmic pattern recognition across dozens of wavelengths can reveal signals a human eye cannot extract.
In practice, most spectral imaging systems in dermatology remain in research or early commercial settings and are not a replacement for the combination of dermoscopy, clinical judgment, and biopsy. Their most mature commercial expression in the US market to date has been in the form of the FDA-cleared devices discussed in Section C, both of which use spectroscopy at the single-point, cellular scale rather than wide-field spectral cubes.
3D skin mapping.
3D skin mapping systems generate a three-dimensional reconstruction of a patient's skin surface, typically using structured light, stereophotogrammetry, or similar depth-capture techniques. Commercial systems in clinical use include 3D total body photography devices such as the Vectra WB360 (Canfield Scientific), which generates a full-body 3D map in a single capture so lesions can be located, measured, and tracked in spatial context.[34][35]
Research in 3D total body photography has explored its role in high-risk melanoma surveillance, particularly for patients with very large nevus counts, where traditional 2D total body photography becomes cumbersome. Early evidence suggests that 3D systems can reduce acquisition time and improve lesion localization over time, and are a natural platform onto which AI-assisted change detection can be layered.[35]
As with every category on this page, the clinical value depends on the operator and the program around the machine.
Screening vs. diagnosis.
Screening and diagnosis are different clinical acts, and "dermal scanning" can refer to either depending on the tool and the context.
Screening is the evaluation of asymptomatic or low-suspicion skin to identify lesions that might warrant further attention. Population-level skin cancer screening is not a settled question. The US Preventive Services Task Force concluded in 2023 that the current evidence is insufficient to assess the balance of benefits and harms of visual skin cancer screening by a clinician in adults without a history of skin cancer.[36] Skin cancer screening is still broadly recommended for patients with established risk factors such as personal or family history of melanoma, many atypical nevi, immunosuppression, or a history of significant sun damage.[37]
Diagnosis is the evaluation of a specific lesion to determine whether it is malignant. Diagnosis, in the dermatology framework, requires a clinician's assessment and, when the lesion is suspicious, a biopsy with histopathology as the reference standard.[4][5][6]
Tools live at different points along this pathway:
- Dermoscopy is a diagnostic adjunct applied at the point of a clinical evaluation.
- Total body photography and sequential digital dermoscopy are surveillance tools that support both change detection (a form of structured follow-up) and eventual diagnosis.
- FDA-cleared AI-assisted devices (DermaSensor, Nevisense) are diagnostic adjuncts explicitly intended for lesions already assessed as suspicious by a clinician, not screening tools.
- Consumer mole-check apps are generally unregulated and should not be treated as screening or diagnostic in any clinically meaningful sense.[27]
- Aesthetic skin analysis systems (VISIA and similar) are cosmetic assessment tools, not screening tools and not diagnostic tools.
References
[1] Dinnes, J., Deeks, J. J., Chuchu, N., Ferrante di Ruffano, L., Matin, R. N., Thomson, D. R., Wong, K. Y., Aldridge, R. B., Abbott, R., Fawzy, M., Bayliss, S. E., Grainge, M. J., Takwoingi, Y., Davenport, C., Godfrey, K., Walter, F. M., & Williams, H. C. (2018). Dermoscopy, with and without visual inspection, for diagnosing melanoma in adults. Cochrane Database of Systematic Reviews, 12, CD011902. https://doi.org/10.1002/14651858.CD011902.pub2
[2] Soyer, H. P., Argenziano, G., Zalaudek, I., Corona, R., Sera, F., Talamini, R., Barbato, F., Baroni, A., Cicale, L., Di Stefani, A., Farro, P., Rossiello, L., Ruocco, E., & Chimenti, S. (2004). Three-point checklist of dermoscopy: A new screening method for early detection of melanoma. Dermatology, 208(1), 27–31. https://doi.org/10.1159/000075042
[3] Salerni, G., Terán, T., Puig, S., Malvehy, J., Zalaudek, I., Argenziano, G., Kittler, H., & International Dermoscopy Society. (2013). Meta-analysis of digital dermoscopy follow-up of melanocytic skin lesions: A study on behalf of the International Dermoscopy Society. Journal of the European Academy of Dermatology and Venereology, 27(7), 805–814. https://doi.org/10.1111/jdv.12032
[4] Ferris, L. K., Jaklitsch, E., Seiverling, E. V., Agresta, T., Cyr, P., Caines, L., Wang, N., & Siegel, D. (2025). DERM-SUCCESS FDA pivotal study: A multi-reader multi-case evaluation of primary care physicians' skin cancer detection using AI-enabled elastic scattering spectroscopy. Journal of Primary Care & Community Health, 16. https://doi.org/10.1177/21501319251342106
[5] Merry, S. P., Croghan, I. T., Dukes, K. A., McCormick, B., Considine, G., Duvall, M., Thompson, C., & Leffell, D. J. (2025). Primary care physician use of elastic scattering spectroscopy on skin lesions suggestive of skin cancer. Journal of Primary Care & Community Health, 16. https://doi.org/10.1177/21501319251344423
[6] Hartman, R. I., Trepanowski, N., Chang, M. S., Tepedino, K., Gianacas, C., McNiff, J. M., Fung, M., Braghiroli, N. F., & Grant-Kels, J. M. (2023). Multicenter prospective blinded melanoma detection study with a handheld elastic scattering spectroscopy device. JAAD International, 15, 24–31. https://doi.org/10.1016/j.jdin.2023.10.011
[7] Braun, R. P., Mangana, J., Goldinger, S., French, L., Dummer, R., & Marghoob, A. A. (2017). Electrical impedance spectroscopy in skin cancer diagnosis. Dermatologic Clinics, 35(4), 489–493. https://doi.org/10.1016/j.det.2017.06.009
[8] Saraç, E., Meiwes, A., Eigentler, T. K., Forchhammer, S., Kofler, L., Häfner, H. M., & Garbe, C. (2020). Diagnostic accuracy of electrical impedance spectroscopy in non-melanoma skin cancer. Acta Dermato-Venereologica, 100(17), adv00328. https://doi.org/10.2340/00015555-3689
[9] Canfield Scientific. (2024). VISIA complexion analysis system: Product literature. Canfield Scientific, Inc. https://www.canfieldsci.com/
[10] Bashshur, R. L., Shannon, G. W., Tejasvi, T., Kvedar, J. C., & Gates, M. (2015). The empirical foundations of teledermatology: A review of the research evidence. Telemedicine Journal and e-Health, 21(12), 953–979. https://doi.org/10.1089/tmj.2015.0146
[11] Finnane, A., Dallest, K., Janda, M., & Soyer, H. P. (2017). Teledermatology for the diagnosis and management of skin cancer: A systematic review. JAMA Dermatology, 153(3), 319–327. https://doi.org/10.1001/jamadermatol.2016.4361
[12] Venkatesh, K. P., Kadakia, K. T., & Gilbert, S. (2024). Learnings from the first AI-enabled skin cancer device for primary care authorized by FDA. npj Digital Medicine, 7, 156. https://doi.org/10.1038/s41746-024-01161-1
[13] Beltrami, E. J., Brown, A. C., Salmon, P. J. M., Leffell, D. J., Ko, J. M., & Grant-Kels, J. M. (2022). Artificial intelligence in the detection of skin cancer. Journal of the American Academy of Dermatology, 87(6), 1336–1342. https://doi.org/10.1016/j.jaad.2022.08.028
[14] Carli, P., Nardini, P., Crocetti, E., De Giorgi, V., & Giannotti, B. (2004). Frequency and characteristics of melanomas missed at a pigmented lesion clinic: A registry-based study. Melanoma Research, 14(5), 403–407. https://doi.org/10.1097/00008390-200410000-00014
[15] Stanganelli, I., Serafini, M., & Bucchi, L. (2000). A cancer-registry-assisted evaluation of the accuracy of digital epiluminescence microscopy associated with clinical examination of pigmented skin lesions. Dermatology, 200(1), 11–16. https://doi.org/10.1159/000018308
[16] Gachon, J., Beaulieu, P., Sei, J. F., Gouvernet, J., Claudel, J. P., Lemaitre, M., Richard, M. A., & Grob, J. J. (2005). First prospective study of the recognition process of melanoma in dermatological practice. Archives of Dermatology, 141(4), 434–438. https://doi.org/10.1001/archderm.141.4.434
[17] Adler, N. R., Kelly, J. W., Guitera, P., Menzies, S. W., Chamberlain, A. J., Fishburn, P., Button-Sloan, A. E., Heal, C., Soyer, H. P., & Thompson, J. F. (2019). Methods of melanoma detection and of skin monitoring for individuals at high risk of melanoma: New Australian clinical practice. Medical Journal of Australia, 210(1), 41–47. https://doi.org/10.5694/mja2.12033
[18] DermaSensor, Inc. (2025). DermaSensor device: Indications for use, clinical evidence summary, and solution overview. DermaSensor, Inc. https://www.dermasensor.com/
[19] Jaklitsch, E., Thames, T., de Campos Silva, T., Coll, P., Oliviero, M., & Ferris, L. K. (2023). Clinical utility of an AI-powered, handheld elastic scattering spectroscopy device on the diagnosis and management of skin cancer by primary care physicians. Journal of Primary Care & Community Health, 14. https://doi.org/10.1177/21501319231205979
[20] Jaklitsch, E., Chang, S., Bruno, S., D'Angelo, N., Tung, J. K., & Ferris, L. K. (2025). Prospective evaluation of an AI-enabled elastic scattering spectroscopy device for triage of patient-identified skin lesions in dermatology clinics. JAAD International, 23, 27–28. https://doi.org/10.1016/j.jdin.2025.07.007
[21] Manolakos, D., Patrick, G., Geisse, J. K., Rabinovitz, H., Buchanan, K., Hoang, P., Rodriguez-Diaz, E., Bigio, I. J., & Cognetta, A. B. (2023). Use of an elastic-scattering spectroscopy and artificial intelligence device in the assessment of lesions suggestive of skin cancer: A comparative effectiveness study. JAAD International, 14, 52–58. https://doi.org/10.1016/j.jdin.2023.08.019
[22] Tepedino, M., Baltazar, D., Hanna, K., Bridges, A., Billot, L., & Zeitouni, N. (2024). Elastic scattering spectroscopy on patient-selected lesions concerning for skin cancer. Journal of the American Board of Family Medicine, 37(3), 427–435. https://doi.org/10.3122/jabfm.2023.230256r2
[23] Markovic, S. N. (2025). Primary care providers versus abnormal skin lesions: Elastic scattering spectroscopy to the rescue. Journal of Primary Care & Community Health, 16. https://doi.org/10.1177/21501319251347905
[24] Goisse, M., & Thomas, B. (2024). Assessing the impact of integrating DermaSensor into primary care for skin cancer detection and management (Asset No. 80-0700.1) [White paper]. DermaSensor, Inc.
[25] Malvehy, J., Hauschild, A., Curiel-Lewandrowski, C., Mohr, P., Hofmann-Wellenhof, R., Motley, R., Berking, C., Grossman, D., Sober, A. J., Ulrich, C., Kelly, J., & Pellacani, G. (2014). Clinical performance of the Nevisense system in cutaneous melanoma detection: An international, multicentre, prospective and blinded clinical trial on efficacy and safety. British Journal of Dermatology, 171(5), 1099–1107. https://doi.org/10.1111/bjd.13121
[26] Liebich, C., von Bruehl, M. L., Schubert, I., Oberhoffer, R., & Sander, C. (2021). Retrospective evaluation of the performance of the electrical impedance spectroscopy system Nevisense in detecting keratinocyte cancers. Skin Research and Technology, 27(5), 723–729. https://doi.org/10.1111/srt.13007
[27] Freeman, K., Dinnes, J., Chuchu, N., Takwoingi, Y., Bayliss, S. E., Matin, R. N., Jain, A., Walter, F. M., Williams, H. C., & Deeks, J. J. (2020). Algorithm based smartphone apps to assess risk of skin cancer in adults: Systematic review of diagnostic accuracy studies. BMJ, 368, m127. https://doi.org/10.1136/bmj.m127
[28] Goldsberry, A., Hanke, C. W., & Hanke, K. E. (2014). VISIA system: A possible tool in the cosmetic practice. Journal of Drugs in Dermatology, 13(11), 1312–1314.
[29] Messaraa, C., Metois, A., Walsh, M., Flynn, J., Doyle, L., Robertson, N., O'Connor, D., & Mavon, A. (2018). Wrinkle and roughness measurement by the Antera 3D and its application for evaluation of cosmetic products. Skin Research and Technology, 24(3), 359–366. https://doi.org/10.1111/srt.12440
[30] Heibel, H. D., Hooey, L., & Cockerell, C. J. (2020). A review of noninvasive techniques for skin cancer detection in dermatology. American Journal of Clinical Dermatology, 21(4), 513–524. https://doi.org/10.1007/s40257-020-00517-z
[31] Ilisanu, M. A., Moldoveanu, F., & Moldoveanu, A. (2023). Multispectral imaging for skin diseases assessment: State of the art and perspectives. Sensors, 23(8), 3888. https://doi.org/10.3390/s23083888
[32] Leon, R., Martinez-Vega, B., Fabelo, H., Ortega, S., Melian, V., Castano, I., Carretero, G., Almeida, P., Garcia, A., Quevedo, E., Hernandez, J. A., Clavo, B., & Callico, G. M. (2020). Non-invasive skin cancer diagnosis using hyperspectral imaging for in-situ clinical support. Journal of Clinical Medicine, 9(6), 1662. https://doi.org/10.3390/jcm9061662
[33] Rey-Barroso, L., Peña-Gutiérrez, S., Yáñez, C., Burgos-Fernández, F. J., Vilaseca, M., & Royo, S. (2021). Optical technologies for the improvement of skin cancer diagnosis: A review. Sensors, 21(1), 252. https://doi.org/10.3390/s21010252
[34] Koh, U., Janda, M., Aitken, J. F., Duffy, D. L., Menzies, S., Sturm, R. A., Schaider, H., Betz-Stablein, B., Prow, T. W., Peyton, A., Lambie, D., Peach, E., Harbord, S., Olsen, C. M., Green, A. C., & Soyer, H. P. (2023). "Mind your moles" study: Protocol of a prospective cohort study of melanocytic naevi. BMJ Open, 13(3), e064130. https://doi.org/10.1136/bmjopen-2022-064130
[35] Primiero, C. A., Yu, H., O'Sullivan, É. D., Bahojb Imani, S., Sharma, A., Smith, K. J., Cheng, G., Betz-Stablein, B., Horsham, C., Mar, V. J., Guitera, P., Menzies, S. W., Janda, M., & Soyer, H. P. (2022). A narrative review: Opportunities and challenges in artificial intelligence skin image analyses using total body photography. Journal of Investigative Dermatology, 142(6), 1613–1621. https://doi.org/10.1016/j.jid.2022.01.015
[36] US Preventive Services Task Force. (2023). Screening for skin cancer: US Preventive Services Task Force recommendation statement. JAMA, 329(15), 1290–1295. https://doi.org/10.1001/jama.2023.4342
[37] American Academy of Dermatology. (2024). Skin cancer screening and surveillance: Position statement. American Academy of Dermatology Association. https://www.aad.org/
[38] Seiverling, E. V., Shah, A., Weinstock, M. A., Grant-Kels, J. M., Falk, N., & Siegel, D. M. (2025). Enhancing diagnostic precision in primary care: A multireader multicase (MRMC) study of an AI-powered handheld elastic scattering spectroscopy device for informed referral decisions in melanoma evaluation. Journal of Clinical and Aesthetic Dermatology, 18(10), 59–65.
Safety and accuracy. AI-based skin scanning devices and apps are adjunctive tools... they support clinical evaluation; they do not replace it. A negative scan does not rule out melanoma. Aesthetic skin analysis systems such as VISIA measure surface and sub-surface features for cosmetic purposes and are not diagnostic. Any lesion that has changed in color, shape, or size, is bleeding, is itching or painful, or is otherwise concerning requires evaluation by a licensed dermatologist.