Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914966651535360 |
|---|---|
| author | Mekala, Rohan Reddy Pahde, Frederik Baur, Simon Chandrashekar, Sneha Diep, Madeline Wenzel, Markus Wisotzky, Eric L. Yolcu, Galip Ümit Lapuschkin, Sebastian Ma, Jackie Eisert, Peter Lindvall, Mikael Porter, Adam Samek, Wojciech |
| author_facet | Mekala, Rohan Reddy Pahde, Frederik Baur, Simon Chandrashekar, Sneha Diep, Madeline Wenzel, Markus Wisotzky, Eric L. Yolcu, Galip Ümit Lapuschkin, Sebastian Ma, Jackie Eisert, Peter Lindvall, Mikael Porter, Adam Samek, Wojciech |
| contents | In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-quality annotated datasets have hampered the accuracy and generalizability of machine learning models. We propose an innovative unsupervised augmentation solution that harnesses Generative Adversarial Network (GAN) based models and associated techniques over their latent space to generate controlled semiautomatically-discovered semantic variations in dermatoscopic images. We created synthetic images to incorporate the semantic variations and augmented the training data with these images. With this approach, we were able to increase the performance of machine learning models and set a new benchmark amongst non-ensemble based models in skin lesion classification on the HAM10000 dataset; and used the observed analytics and generated models for detailed studies on model explainability, affirming the effectiveness of our solution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization Mekala, Rohan Reddy Pahde, Frederik Baur, Simon Chandrashekar, Sneha Diep, Madeline Wenzel, Markus Wisotzky, Eric L. Yolcu, Galip Ümit Lapuschkin, Sebastian Ma, Jackie Eisert, Peter Lindvall, Mikael Porter, Adam Samek, Wojciech Computer Vision and Pattern Recognition Artificial Intelligence In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-quality annotated datasets have hampered the accuracy and generalizability of machine learning models. We propose an innovative unsupervised augmentation solution that harnesses Generative Adversarial Network (GAN) based models and associated techniques over their latent space to generate controlled semiautomatically-discovered semantic variations in dermatoscopic images. We created synthetic images to incorporate the semantic variations and augmented the training data with these images. With this approach, we were able to increase the performance of machine learning models and set a new benchmark amongst non-ensemble based models in skin lesion classification on the HAM10000 dataset; and used the observed analytics and generated models for detailed studies on model explainability, affirming the effectiveness of our solution. |
| title | Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.05114 |