Histopathological Domain Adaptation with Generative Adversarial Networks - Bridging the Domain Gap Between Thyroid Cancer Histopathology Datasets
Dee, W.; Alaaeldin Ibrahim, R.; Marouli, E.
Show abstract
Deep learning techniques are increasingly being used to classify medical imaging data with high accuracy. Despite this, due to often limited training data, these models can lack sufficient generalizability to predict unseen test data, produced in a different domain, with comparable performance. This study focuses on thyroid histopathology image classification and investigates whether a Generative Adversarial Network (GAN), trained with just 156 patient samples, can produce high quality synthetic images to sufficiently augment training data and improve overall model generalizability. Utilizing a StyleGAN2-ADA approach, the generative network produced images with an FID score of 5.05, matching state-of-the-art GAN results in non-medical domains with comparable dataset sizes. Augmenting the training data with these GAN-generated images increased model generalizability significantly when tested on external data, improving overall accuracy and F1 scores by 36% and 42% respectively. Most importantly, this performance improvement was observed on minority class images, tumour subtypes which are known to suffer from high levels of inter-observer variability when classified by trained pathologists.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Classification performance bias between training and test sets in a limited mammography dataset 94%
- Enhancing Semantic Segmentation in Chest X-Ray Images through Image Preprocessing: ps-KDE for Pixel-wise Substitution by Kernel Density Estimation 93%
- Identifying Transcriptomic Correlates of Histology using Deep Learning 93%
Similar papers in this journal
- Generating synthetic data in digital pathology through diffusion models: a multifaceted approach to evaluation 96%
- Reproducible And Clinically Translatable Deep Neural Networks For Cervical Screening 95%
- ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.