# Dermoscopy, total-body photography & AI skin analysis

Source: https://onco.cc/technologies/dermoscopy-ai/  
OnCo record `dermoscopy-ai` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Magnified skin imaging and whole-body photo mapping, increasingly read by algorithms, to find melanoma early and avoid unnecessary biopsies.

## Summary

Dermoscopy improves diagnostic accuracy over the naked eye; sequential total-body photography tracks change in high-risk patients. Deep-learning classifiers have matched dermatologists on benchmark images and DermaSensor (elastic scattering spectroscopy, FDA 2024) is cleared for primary care. Real-world impact depends on population, skin tone representation in training data, and workflow; no screening RCT has shown mortality benefit.

## Fields

- Kind: Technology
- Status: established
- Last checked: 2026-09-07
- Principle: Polarised or immersion magnification of skin structures; convolutional networks trained on labelled lesion images; spectroscopy of tissue optical properties.
- Strengths: Cheap, non-invasive, repeatable; Reduces benign excisions when used well
- Limitations: Algorithm performance drops on darker skin and rare subtypes; No proven mortality benefit for population screening

## Sources

- Esteva et al., Dermatologist-level classification of skin cancer with deep neural networks (Nature 2017): https://doi.org/10.1038/nature21056

## Connected records

- cancers: [Acral melanoma](https://onco.cc/cancers/acral-melanoma/), [Basal cell carcinoma](https://onco.cc/cancers/basal-cell-carcinoma/), [Bowen's disease (squamous cell carcinoma in situ)](https://onco.cc/cancers/bowens-disease/), [Cutaneous squamous cell carcinoma](https://onco.cc/cancers/cutaneous-scc/), [Melanoma](https://onco.cc/cancers/melanoma/), [Skin cancer (all types)](https://onco.cc/cancers/skin-cancer/), [Stage IIB and IIC melanoma](https://onco.cc/cancers/stage-ii-melanoma/), [Thyroid cancer](https://onco.cc/cancers/thyroid/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Early Detection & Screening](https://onco.cc/fronts/early-detection/)
- technologies: [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [AI-assisted mammography screening](https://onco.cc/technologies/ai-mammography-screening/), [Confocal microscopy and optical coherence tomography for skin (VivaScope, VivoSight, deepLive)](https://onco.cc/technologies/confocal-oct-skin-imaging/), [Skin cancer screening (visual skin examination)](https://onco.cc/technologies/skin-cancer-screening/)
- terms: [Breslow thickness](https://onco.cc/terms/breslow-thickness/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Not enough oncologists, nurses, pathologists, physicists](https://onco.cc/bottlenecks/b-workforce/)
- ideas: [Mandatory subgroup performance reporting for cancer AI](https://onco.cc/ideas/idea-data-subgroup-performance-reporting-mandate/)
- key papers: [Esteva 2017: a deep neural network classifies skin cancer at dermatologist level](https://onco.cc/key-papers/paper-esteva-skin-cancer-deep-learning-nature-2017/)
- companies: [Caliber Imaging and Diagnostics](https://onco.cc/companies/caliber-imaging-diagnostics/), [Canfield Scientific](https://onco.cc/companies/canfield-scientific/), [FotoFinder Systems](https://onco.cc/companies/fotofinder/)

---
JSON: https://onco.cc/api/v1/entities/dermoscopy-ai.json