DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909081543901184 |
|---|---|
| author | Chiu, Ming-Chang Wang, Yingfei Kuo, Yen-Ju Chen, Pin-Yu |
| author_facet | Chiu, Ming-Chang Wang, Yingfei Kuo, Yen-Ju Chen, Pin-Yu |
| contents | Skin tone as a demographic bias and inconsistent human labeling poses challenges in dermatology AI. We take another angle to investigate color contrast's impact, beyond skin tones, on malignancy detection in skin disease datasets: We hypothesize that in addition to skin tones, the color difference between the lesion area and skin also plays a role in malignancy detection performance of dermatology AI models. To study this, we first propose a robust labeling method to quantify color contrast scores of each image and validate our method by showing small labeling variations. More importantly, applying our method to \textit{the only} diverse-skin tone and pathologically-confirmed skin disease dataset DDI, yields \textbf{DDI-CoCo Dataset}, and we observe a performance gap between the high and low color difference groups. This disparity remains consistent across various state-of-the-art (SoTA) image classification models, which supports our hypothesis. Furthermore, we study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13280 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection Chiu, Ming-Chang Wang, Yingfei Kuo, Yen-Ju Chen, Pin-Yu Computer Vision and Pattern Recognition Computational Engineering, Finance, and Science Skin tone as a demographic bias and inconsistent human labeling poses challenges in dermatology AI. We take another angle to investigate color contrast's impact, beyond skin tones, on malignancy detection in skin disease datasets: We hypothesize that in addition to skin tones, the color difference between the lesion area and skin also plays a role in malignancy detection performance of dermatology AI models. To study this, we first propose a robust labeling method to quantify color contrast scores of each image and validate our method by showing small labeling variations. More importantly, applying our method to \textit{the only} diverse-skin tone and pathologically-confirmed skin disease dataset DDI, yields \textbf{DDI-CoCo Dataset}, and we observe a performance gap between the high and low color difference groups. This disparity remains consistent across various state-of-the-art (SoTA) image classification models, which supports our hypothesis. Furthermore, we study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection. |
| title | DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection |
| topic | Computer Vision and Pattern Recognition Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2401.13280 |