Moucheng Xu

Understanding the progression trajectories of diseases is crucial for early diagnosis and effective treatment planning. This is especially vital for life-threatening conditions such as Idiopathic Pulmonary Fibrosis (IPF), a chronic, progressive lung disease with a prognosis comparable to many cancers. Computed tomography (CT) imaging has been established as a reliable diagnostic tool for IPF. Accurately predicting future CT scans of early-stage IPF patients can aid in developing better treatment strategies, thereby improving survival outcomes. As inspired by the recent success of world models in generating video-based virtual physical worlds, we present the first world model for IPF, to synthesize realistic scans of early-stage IPF patients at any time point. We term our model 4D Vector Quantised Generative Adversarial Networks (4D-VQ-GAN). Our model is trained using a two-stage approach. In the first stage, a 3D-VQ-GAN is trained to reconstruct CT volumes. In the second stage, a Neural Ordinary Differential Equation (ODE) model is trained to capture the temporal dynamics of the quantised embeddings, which are generated by the encoder trained in the first stage. For clinical validation, we conduct survival analysis using imaging biomarkers derived from generated CT scans and achieve a C-index either better than or comparable to that of biomarkers derived from the real CT scans. The survival analysis results suggest the potential clinical utility inherent to generated longitudinal CT scans, showing that they can reliably predict survival outcomes.

Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders1. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications2. Here, we present RETFound, a foundation model for retinal images that learns generalizable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in several applications. Specifically, RETFound is trained on 1.6 million unlabelled retinal images by means of self-supervised learning and then adapted to disease detection tasks with explicit labels. We show that adapted RETFound consistently outperforms several comparison models in the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction with fewer labelled data. RETFound provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinical AI applications from retinal imaging.

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) algorithm for clear statistical interpretation. Secondly, we propose a semi-supervised medical image segmentation method purely based on the original pseudo labelling, namely SegPL. We demonstrate SegPL is a competitive approach against state-of-the-art consistency regularisation based methods on semi-supervised segmentation on a 2D multi-class MRI brain tumour segmentation task and a 3D binary CT lung vessel segmentation task. The simplicity of SegPL allows less computational cost comparing to prior methods. Thirdly, we demonstrate that the effectiveness of SegPL may originate from its robustness against out-of-distribution noises and adversarial attacks. Lastly, under the EM framework, we introduce a probabilistic generalisation of SegPL via variational inference, which learns a dynamic threshold for pseudo labelling during the training. We show that SegPL with variational inference can perform uncertainty estimation on par with the gold-standard method Deep Ensemble.

We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consists of an encoder and a two-head decoders. One decoder learns positive attention to the foreground regions of interest (RoI) on unlabelled images thereby generating dilated features. The other decoder learns negative attention to the foreground on the same unlabelled images thereby generating eroded features. We then apply a consistency regularisation on the paired predictions. MisMatch outperforms state-of-the-art semi-supervised methods on a CT-based pulmonary vessel segmentation task and a MRI-based brain tumour segmentation task. In addition, we show that the effectiveness of MisMatch comes from better model calibration than its supervised learning counterpart.