Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.06385 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915203983081472 |
|---|---|
| author | Pope, James Hassanuzzaman, Md Chapman, William Day, Huw Sherpa, Mingmar Emara, Omar Adhikari, Nirmala Joshi, Ayush |
| author_facet | Pope, James Hassanuzzaman, Md Chapman, William Day, Huw Sherpa, Mingmar Emara, Omar Adhikari, Nirmala Joshi, Ayush |
| contents | Background: Many open-source skin cancer image datasets are the result of clinical trials conducted in countries with lighter skin tones. Due to this tone imbalance, machine learning models derived from these datasets can perform well at detecting skin cancer for lighter skin tones. Any tone bias in these models could introduce fairness concerns and reduce public trust in the artificial intelligence health field.
Methods: We examine a subset of images from the International Skin Imaging Collaboration (ISIC) archive that provide tone information. The subset has a significant tone imbalance. These imbalances could explain a model's tone bias. To address this, we train models using the imbalanced dataset and a balanced dataset to compare against. The datasets are used to train a deep convolutional neural network model to classify the images as malignant or benign. We then evaluate the models' disparate impact, based on selection rate, relative to dark or light skin tone.
Results: Using the imbalanced dataset, we found that the model is significantly better at detecting malignant images in lighter tone resulting in a disparate impact of 0.577. Using the balanced dataset, we found that the model is also significantly better at detecting malignant images in lighter versus darker tones with a disparate impact of 0.684. Using the imbalanced or balanced dataset to train the model still results in a disparate impact well below the standard threshold of 0.80 which suggests the model is biased with respect to skin tone.
Conclusion: The results show that typical skin cancer machine learning models can be tone biased. These results provide evidence that diagnosis or tone imbalance is not the cause of the bias. Other techniques will be necessary to identify and address the bias in these models, an area of future investigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06385 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Skin Cancer Machine Learning Model Tone Bias Pope, James Hassanuzzaman, Md Chapman, William Day, Huw Sherpa, Mingmar Emara, Omar Adhikari, Nirmala Joshi, Ayush Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Background: Many open-source skin cancer image datasets are the result of clinical trials conducted in countries with lighter skin tones. Due to this tone imbalance, machine learning models derived from these datasets can perform well at detecting skin cancer for lighter skin tones. Any tone bias in these models could introduce fairness concerns and reduce public trust in the artificial intelligence health field. Methods: We examine a subset of images from the International Skin Imaging Collaboration (ISIC) archive that provide tone information. The subset has a significant tone imbalance. These imbalances could explain a model's tone bias. To address this, we train models using the imbalanced dataset and a balanced dataset to compare against. The datasets are used to train a deep convolutional neural network model to classify the images as malignant or benign. We then evaluate the models' disparate impact, based on selection rate, relative to dark or light skin tone. Results: Using the imbalanced dataset, we found that the model is significantly better at detecting malignant images in lighter tone resulting in a disparate impact of 0.577. Using the balanced dataset, we found that the model is also significantly better at detecting malignant images in lighter versus darker tones with a disparate impact of 0.684. Using the imbalanced or balanced dataset to train the model still results in a disparate impact well below the standard threshold of 0.80 which suggests the model is biased with respect to skin tone. Conclusion: The results show that typical skin cancer machine learning models can be tone biased. These results provide evidence that diagnosis or tone imbalance is not the cause of the bias. Other techniques will be necessary to identify and address the bias in these models, an area of future investigation. |
| title | Skin Cancer Machine Learning Model Tone Bias |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.06385 |