Chen Qin

White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks

White matter hyperintensities (WMH) are a feature of sporadic small vessel disease also frequently observed in magnetic resonance images (MRI) of healthy elderly subjects. The accurate assessment of WMH burden is of crucial importance for epidemiological studies to determine association between WMHs, cognitive and clinical data; their causes, and the effects of new treatments in randomized trials. The manual delineation of WMHs is a very tedious, costly and time consuming process, that needs to be carried out by an expert annotator (e.g. a trained image analyst or radiologist). The problem of WMH delineation is further complicated by the fact that other pathological features (i.e. stroke lesions) often also appear as hyperintense regions. Recently, several automated methods aiming to tackle the challenges of WMH segmentation have been proposed. Most of these methods have been specifically developed to segment WMH in MRI but cannot differentiate between WMHs and strokes. Other methods, capable of distinguishing between different pathologies in brain MRI, are not designed with simultaneous WMH and stroke segmentation in mind. Therefore, a task specific, reliable, fully automated method that can segment and differentiate between these two pathological manifestations on MRI has not yet been fully identified. In this work we propose to use a convolutional neural network (CNN) that is able to segment hyperintensities and differentiate between WMHs and stroke lesions. Specifically, we aim to distinguish between WMH pathologies from those caused by stroke lesions due to either cortical, large or small subcortical infarcts. The proposed fully convolutional CNN architecture, called uResNet, that comprised an analysis path, that gradually learns low and high level features, followed by a synthesis path, that gradually combines and up-samples the low and high level features into a class likelihood semantic segmentation. Quantitatively, the proposed CNN architecture is shown to outperform other well established and state-of-the-art algorithms in terms of overlap with manual expert annotations. Clinically, the extracted WMH volumes were found to correlate better with the Fazekas visual rating score than competing methods or the expert-annotated volumes. Additionally, a comparison of the associations found between clinical risk-factors and the WMH volumes generated by the proposed method, was found to be in line with the associations found with the expert-annotated volumes.

Pseudo-healthy Image Synthesis for White Matter Lesion Segmentation

White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies. We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T\(_1\) -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.

A Semi-supervised Large Margin Algorithm for White Matter Hyperintensity Segmentation

Precise detection and quantification of white matter hyperintensities (WMH) is of great interest in studies of neurodegenerative diseases (NDs). In this work, we propose a novel semi-supervised large margin algorithm for the segmentation of WMH. The proposed algorithm optimizes a kernel based max-margin objective function which aims to maximize the margin averaged over inliers and outliers while exploiting a limited amount of available labelled data. We show that the learning problem can be formulated as a joint framework learning a classifier and a label assignment simultaneously, which can be solved efficiently by an iterative algorithm. We evaluate our method on a database of 280 brain Magnetic Resonance (MR) images from subjects that either suffered from subjective memory complaints or were diagnosed with NDs. The segmented WMH volumes correlate well with the standard clinical measurement (Fazekas score), and both the qualitative visualization results and quantitative correlation scores of the proposed algorithm outperform other well known methods for WMH segmentation.

Recurrent Neural Networks for Aortic Image Sequence Segmentation with Sparse Annotations

Segmentation of image sequences is an important task in medical image analysis, which enables clinicians to assess the anatomy and function of moving organs. However, direct application of a segmentation algorithm to each time frame of a sequence may ignore the temporal continuity inherent in the sequence. In this work, we propose an image sequence segmentation algorithm by combining a fully convolutional network with a recurrent neural network, which incorporates both spatial and temporal information into the segmentation task. A key challenge in training this network is that the available manual annotations are temporally sparse, which forbids end-to-end training. We address this challenge by performing non-rigid label propagation on the annotations and introducing an exponentially weighted loss function for training. Experiments on aortic MR image sequences demonstrate that the proposed method significantly improves both accuracy and temporal smoothness of segmentation, compared to a baseline method that utilises spatial information only. It achieves an average Dice metric of 0.960 for the ascending aorta and 0.953 for the descending aorta.

Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image.

Accelerating the acquisition of magnetic resonance imaging (MRI) is a challenging problem, and many works have been proposed to reconstruct images from undersampled k-space data. However, if the main purpose is to extract certain quantitative measures from the images, perfect reconstructions may not always be necessary as long as the images enable the means of extracting the clinically relevant measures. In this paper, we work on jointly predicting cardiac motion estimation and segmentation directly from undersampled data, which are two important steps in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In particular, a unified model consisting of both motion estimation branch and segmentation branch is learned by optimising the two tasks simultaneously. Additional corresponding fully-sampled images are incorporated into the network as a parallel sub-network to enhance and guide the learning during the training process. Experimental results using cardiac MR images from 220 subjects show that the proposed model is robust to undersampled data and is capable of predicting results that are close to that from fully-sampled ones, while bypassing the usual image reconstruction stage.

Bayesian Deep Learning for Accelerated MR Image Reconstruction

Recently, many deep learning (DL) based MR image reconstruction methods have been proposed with promising results. However, only a handful of work has been focussing on characterising the behaviour of deep networks, such as investigating when the networks may fail to reconstruct. In this work, we explore the applicability of Bayesian DL techniques to model the uncertainty associated with DL-based reconstructions. In particular, we apply MC-dropout and heteroscedastic loss to the reconstruction networks to model epistemic and aleatoric uncertainty. We show that the proposed Bayesian methods achieve competitive performance when the test images are relatively far from the training data distribution and outperforms when the baseline method is over-parametrised. In addition, we qualitatively show that there seems to be a correlation between the magnitude of the produced uncertainty maps and the error maps, demonstrating the potential utility of the Bayesian DL methods for assessing the reliability of the reconstructed images.

Brain Lesion Segmentation through Image Synthesis and Outlier Detection

Cerebral small vessel disease (SVD) can manifest in a number of ways. Many of these result in hyperintense regions visible on T2-weighted magnetic resonance (MR) images. The automatic segmentation of these lesions has been the focus of many studies. However, previous methods tended to be limited to certain types of pathology, as a consequence of either restricting the search to the white matter, or by training on an individual pathology. Here we present an unsupervised abnormality detection method which is able to detect abnormally hyperintense regions on FLAIR regardless of the underlying pathology or location. The method uses a combination of image synthesis, Gaussian mixture models and one class support vector machines, and needs only be trained on healthy tissue. We evaluate our method by comparing segmentation results from 127 subjects with SVD with three established methods and report significantly superior performance across a number of metrics.