Human–computer collaboration for skin cancer recognition

Abstract

Mailings and social media posts of the International Dermoscopy Society were used to recruit targeted groups. The recruitment was focused on medical personell interested in the diagnosis of skin cancer. It is possible that recruitment of raters is influenced by self-selection bias and therefore biased towards the selection of motivated and skilled raters. Skill level was included as a covariate in the interaction experiments. Each rater had to perform multiple screening tests to ensure that the self-reported experience matched actual skills. Because of self selection bias, the generalisability of our results to a less motivated group of readers may be limited. Ethics oversightEthics review board of the Medical University of Vienna Note that full information on the approval of the study protocol must also be provided in the manuscript.

Use of artificial intelligence in skin cancer diagnosis and management

“…This approach could dramatically improve clinician workload and timely access to specialist care for people requiring urgent attention. Alternatively, artificial intelligence consulted following an examination by the clinician may act as a second opinion to improve diagnostic sensitivity and reduce unnecessary biopsies . The latter is more closely aligned with current clinical workflows and therefore likely to be preferred while the field matures.…”

“…A secondary support system may provide the clinician with a diagnosis or a management decision. Doctors are more likely to change their minds if they are uncertain of a diagnosis and an algorithm provides a conflicting result . It is thus important to consider how an algorithm might convey uncertainty to avoid false guidance.…”

“…However, this retrieval system may fail for rare or unseen cases and does not provide a decision‐making process. While the black box phenomenon remains, there are two potentially negative implications for clinical practice: first, clinicians may have difficulty upskilling by following the algorithms’ outputs; and second, there exists the potential for deskilling and underperforming due to an over‐reliance on technology . The effect of a faulty system has been explored by manipulating a previously trusted algorithm to generate incorrect classifications and found that doctors of all experience levels were susceptible to being misled by the recommendation …”

“…Several studies have now shown that CNNs trained on retrospective image data collected at a single time point are capable of classifying skin cancer with sensitivities and specificities equal or superior to that of dermatologists (Box 1), and clinicians with less experience gain most from AI support under experimental conditions . Hypomelanotic and acral melanoma can be more challenging to diagnose clinically, and this could potentially present a challenge for automated classification.…”

Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases

“…Recently Wu et al did show an impressive 95% overall diagnostic accuracy in classifying atopic dermatitis, eczema and psoriasis on selected image material (13). Studies comparing the accuracy of CAD models to clinicians are generally based on image classification equivalent to retrospective analysis, though some head to head studies were conducted with prospective collected image material (12,14,15).…”