80 citations · 110 across the 15 of their papers we have counts for
9 papers · 1 filter
Reverse Spatio-Temporal Disease Progression Modelling
Ulugbek Shernazarov, Moucheng Xu, Inomjon Ramatov
Deep learning-based spatio-temporal disease progression models commonly overlook the incubation period of progressive diseases, limiting the use of those models in early interventi…
Expectation Maximization Pseudo Labels
Moucheng Xu, Yukun Zhou, Chen Jin +5
In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pse…
Deformably-Scaled Transposed Convolution
Stefano B. Blumberg, Daniele Raví, Mou-Cheng Xu +3
Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers. In this work we revisit transposed convo…
Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation
Mou-Cheng Xu, Yukun Zhou, Chen Jin +5
This paper concerns pseudo labelling in segmentation. Our contribution is fourfold. Firstly, we present a new formulation of pseudo-labelling as an Expectation-Maximization (EM) al…
Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation
Mou-Cheng Xu, Yu-Kun Zhou, Chen Jin +6
We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consi…
MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels
Mou-Cheng Xu, Yukun Zhou, Chen Jin +4
Semi-supervised learning (SSL) is a promising machine learning paradigm to address the issue of label scarcity in medical imaging. SSL methods were originally developed in image cl…
Learning To Pay Attention To Mistakes
Mou-Cheng Xu, Neil P. Oxtoby, Daniel C. Alexander +1
In convolutional neural network based medical image segmentation, the periphery of foreground regions representing malignant tissues may be disproportionately assigned as belonging…
Foveation for Segmentation of Ultra-High Resolution Images
Chen Jin, Ryutaro Tanno, Moucheng Xu +2
Segmentation of ultra-high resolution images is challenging because of their enormous size, consisting of millions or even billions of pixels. Typical solutions include dividing in…
Disentangling Human Error from the Ground Truth in Segmentation of Medical Images
Le Zhang, Ryutaro Tanno, Mou-Cheng Xu +5
Recent years have seen increasing use of supervised learning methods for segmentation tasks. However, the predictive performance of these algorithms depends on the quality of label…