GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification

no code implementations • 4 May 2022 • Mayank Golhar, Taylor L. Bobrow, Saowanee Ngamruengphong, Nicholas J. Durr

This study demonstrates that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training data to improve the lesion classification performance of deep learning models.

Classification Data Augmentation +3

Improving colonoscopy lesion classification using semi-supervised deep learning

no code implementations • 7 Sep 2020 • Mayank Golhar, Taylor L. Bobrow, MirMilad Pourmousavi Khoshknab, Simran Jit, Saowanee Ngamruengphong, Nicholas J. Durr

While data-driven approaches excel at many image analysis tasks, the performance of these approaches is often limited by a shortage of annotated data available for training.

Classification Domain Adaptation +3