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

04/08/2021
by   Anneke Meyer, et al.
4

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.

READ FULL TEXT

page 3

page 14

page 16

page 17

03/17/2017

Semi-Supervised Deep Learning for Fully Convolutional Networks

Deep learning usually requires large amounts of labeled training data, b...
11/03/2020

Self-semi-supervised Learning to Learn from NoisyLabeled Data

The remarkable success of today's deep neural networks highly depends on...
08/12/2018

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

Automatic skin lesion segmentation on dermoscopic images is an essential...
10/01/2022

Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentation

Semi-supervised learning has the potential to improve the data-efficienc...
08/04/2019

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

A sentence is typically treated as the minimal syntactic unit used for e...
08/06/2019

Semi-supervised Skin Detection by Network with Mutual Guidance

In this paper we present a new data-driven method for robust skin detect...

Please sign up or login with your details

Forgot password? Click here to reset