This repository contains the source code of the paper Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of the Prostate Zones and Beyond, accepted in Artificial Intelligence in Medicine Journal.
- A deep semi-supervised method named uncertainty-aware temporal self-learning (UATS) is proposed for segmentation.
- UATS leverages performance gains from temporal ensembling (Laine and Aila) and uncertainty-guided self-learning.
- UATS surpasses fully supervised performance on prostate zone segmentation and achieves human observer quality.
- Further experiments demonstrate its generalizability on the following benchmark biomedical datasets:
- pip install -r requirements.txt
- Experiment and dataset-related changes to be made in the file: utility/config.py
- The UATS model could be trained: python dataset_specific/prostate/expts/prostate_uats_softmax.py