Derm Cases · Dermatology / Pigmented lesions / Skin cancer triage
OSCE — dermoscopy image-based diagnosis: two-step algorithm, acral ridge, and monitor-vs-biopsy
An 8-minute OSCE on handheld dermoscopy decision-making: two-step algorithm, chaos-and-clues biopsy threshold, vessel/pattern dictionary pearls, acral parallel ridge red flag, facial/nail special-site awareness, and appropriate use of digital monitoring versus immediate excision; AI as assist only.
On this page
Study tools
Target exams
NEET-PGINICETPLABMRCPFRCDerm
Prompt
An 8-minute OSCE on handheld dermoscopy decision-making: two-step algorithm, chaos-and-clues biopsy threshold, vessel/pattern dictionary pearls, acral parallel ridge red flag, facial/nail special-site awareness, and appropriate use of digital monitoring versus immediate excision; AI as assist only.
Brief (to candidate)
Skin lesion clinic. Patient 1: chaotic pigmented back lesion. Patient 2: pigmented sole macule. Patient 3: asks for “AI photo diagnosis and monitoring” of a pink nodule. In 8 minutes, demonstrate image-based decision logic.
[5]Candidate instructions
- State two-step algorithm and one instrument mode pearl (polarised vs immersion).
- Apply chaos and clues to Patient 1 → biopsy plan.
- Interpret acral ridge vs furrow for Patient 2.
- Reject unsafe monitoring for a nodular / red-flag lesion; mention when digital monitoring is acceptable.
- Position AI as assistive, not a substitute for red-flag excision/histology.
Examiner checklist (mark each domain / 10)
| Domain | Key actions expected |
|---|---|
| Two-step | Melanocytic criteria → then benign vs suspicious within melanocytic lesions[1] |
| Chaos/clues | Disorder + melanoma clues → tissue diagnosis[2] |
| Acral | Parallel ridge concerning for melanoma; furrow/lattice/fibrillar often benign when classic[3] |
| Vessels/patterns | At least one correct classic match (e.g. arborising–BCC) |
| Monitoring | Only selected flat low-suspicion lesions with follow-up; not nodules/red flags[5] |
| AI | May approach specialist accuracy on curated tasks; does not replace biopsy of red flags[4] |
| Safety-net | Clear plan, histology gold standard for excised tissue |
Model key actions
- Patient 1: excise/biopsy with full-thickness approach if melanoma plausible.[1][2]
- Patient 2: ridge → urgent specialist pathway; not “benign acral freckle” default.[3]
- Patient 3: pink nodule with atypical vessels → tissue, not AI monitor.
Common errors
- Monitoring parallel ridge acral lesions.
- Using trunk network rules on face/sole without site algorithms.
- Declaring AI “rules out melanoma.”
- Shave-only plan when melanoma staging depth matters.
References5ShowHide
- [1]Yélamos O, Braun RP, Liopyris K, et al. Dermoscopy and dermatopathology correlates of cutaneous neoplasms. Journal of the American Academy of Dermatology, 2019.PMID 30321581
- [2]Rosendahl C, Cameron A, McColl I, Wilkinson D. Dermatoscopy in routine practice - 'chaos and clues'. Australian Family Physician, 2012.PMID 22762066
- [3]Saida T, Koga H, Uhara H. Key points in dermoscopic differentiation between early acral melanoma and acral nevus. Journal of Dermatology, 2011.PMID 21175752
- [4]Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017.PMID 28117445
- [5]Zenone M, Zocchi L, Moccia C, et al. Digital dermoscopy monitoring of melanocytic lesions: Two novel calculators combining static and dynamic features to identify melanoma. Journal of the European Academy of Dermatology and Venereology, 2022.PMID 34862986