Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of Prostate Zones and Beyond

by   Anneke Meyer, et al.

Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and peripheral zone (PZ). However, when targeting a fine-grained segmentation of TZ, PZ, distal prostatic urethra (DPU) and the anterior fibromuscular stroma (AFS), the task becomes more challenging and has not yet been solved at the level of human performance. One reason might be the insufficient amount of labeled data for supervised training. Therefore, we propose to apply a semi-supervised learning (SSL) technique named uncertainty-aware temporal self-learning (UATS) to overcome the expensive and time-consuming manual ground truth labeling. We combine the SSL techniques temporal ensembling and uncertainty-guided self-learning to benefit from unlabeled images, which are often readily available. Our method significantly outperforms the supervised baseline and obtained a Dice coefficient (DC) of up to 78.9 obtained results are in the range of human inter-rater performance for all structures. Moreover, we investigate the method's robustness against noise and demonstrate the generalization capability for varying ratios of labeled data and on other challenging tasks, namely the hippocampus and skin lesion segmentation. UATS achieved superiority segmentation quality compared to the supervised baseline, particularly for minimal amounts of labeled data.


page 3

page 14

page 16

page 17


Semi-Supervised Deep Learning for Fully Convolutional Networks

Deep learning usually requires large amounts of labeled training data, b...

Self-semi-supervised Learning to Learn from NoisyLabeled Data

The remarkable success of today's deep neural networks highly depends on...

Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model

Automatic skin lesion segmentation on dermoscopic images is an essential...

SUD: Supervision by Denoising for Medical Image Segmentation

Training a fully convolutional network for semantic segmentation typical...

Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations

A sentence is typically treated as the minimal syntactic unit used for e...

A Non-Parametric Learning Approach to Identify Online Human Trafficking

Human trafficking is among the most challenging law enforcement problems...

Particle Swarm Optimization for Great Enhancement in Semi-Supervised Retinal Vessel Segmentation with Generative Adversarial Networks

Retinal vessel segmentation based on deep learning requires a lot of man...