# Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation

arXiv: https://arxiv.org/abs/2304.06968 · HTML: https://mlsanity.com/paper/2304.06968/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 61 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context](https://mlsanity.com/paper/2008.07360/) (2020)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2002.04114/) (2020)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [Domain Divergences: a Survey and Empirical Analysis](https://mlsanity.com/paper/2010.12198/) (2020)
- [Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images](https://mlsanity.com/paper/1806.01357/) (2018)
- [Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images](https://mlsanity.com/paper/2009.04985/) (2020)
- [Recommendations on test datasets for evaluating AI solutions in pathology](https://mlsanity.com/paper/2204.14226/) (2022)

## Built on by (most cited first, 7 of 7)

- [Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2307.03157/) (2023)
- [Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues](https://mlsanity.com/paper/2305.05807/) (2023)
- [Federated and Transfer Learning for Cancer Detection Based on Image Analysis](https://mlsanity.com/paper/2405.20126/) (2024)
- [Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images](https://mlsanity.com/paper/2310.03432/) (2023)
- [Revamping AI Models in Dermatology: Overcoming Critical Challenges for Enhanced Skin Lesion Diagnosis](https://mlsanity.com/paper/2311.01009/) (2023)
- [Enhancing Skin Lesion Classification Generalization with Active Domain Adaptation](https://mlsanity.com/paper/2412.00702/) (2024)
- [Uncertainty-Aware Domain Adaptation for Vitiligo Segmentation in Clinical Photographs](https://mlsanity.com/paper/2512.11791/) (2025)

## Abstract (arXiv)

The limited ability of Convolutional Neural Networks to generalize to images from previously unseen domains is a major limitation, in particular, for safety-critical clinical tasks such as dermoscopic skin cancer classification. In order to translate CNN-based applications into the clinic, it is essential that they are able to adapt to domain shifts. Such new conditions can arise through the use of different image acquisition systems or varying lighting conditions. In dermoscopy, shifts can also occur as a change in patient age or occurence of rare lesion localizations (e.g. palms). These are not prominently represented in most training datasets and can therefore lead to a decrease in performance. In order to verify the generalizability of classification models in real world clinical settings it is crucial to have access to data which mimics such domain shifts. To our knowledge no dermoscopic image dataset exists where such domain shifts are properly described and quantified. We therefore grouped publicly available images from ISIC archive based on their metadata (e.g. acquisition location, lesion localization, patient age) to generate meaningful domains. To verify that these domains are in fact distinct, we used multiple quantification measures to estimate the presence and intensity of domain shifts. Additionally, we analyzed the performance on these domains with and without an unsupervised domain adaptation technique. We observed that in most of our grouped domains, domain shifts in fact exist. Based on our results, we believe these datasets to be helpful for testing the generalization capabilities of dermoscopic skin cancer classifiers.