Search Results for author: Chengjia Wang

Found 17 papers, 4 papers with code

Explainable unsupervised multi-modal image registration using deep networks

no code implementations3 Aug 2023 Chengjia Wang, Giorgos Papanastasiou

Clinical decision making from magnetic resonance imaging (MRI) combines complementary information from multiple MRI sequences (defined as 'modalities').

Decision Making Image Classification +1

Is attention all you need in medical image analysis? A review

no code implementations24 Jul 2023 Giorgos Papanastasiou, Nikolaos Dikaios, Jiahao Huang, Chengjia Wang, Guang Yang

Attention and Transformer compartments (Transf/Attention) which can well maintain properties for modelling global relationships, have been proposed as lighter alternatives of full Transformers.

CS$^2$: A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Intervention

1 code implementation20 Jun 2022 Xiaodan Xing, Jiahao Huang, Yang Nan, Yinzhe Wu, Chengjia Wang, Zhifan Gao, Simon Walsh, Guang Yang

The destitution of image data and corresponding expert annotations limit the training capacities of AI diagnostic models and potentially inhibit their performance.

Image Generation Segmentation

Unsupervised Image Registration Towards Enhancing Performance and Explainability in Cardiac And Brain Image Analysis

no code implementations7 Mar 2022 Chengjia Wang, Guang Yang, Giorgos Papanastasiou

Moreover, inverse-consistency is a fundamental inter-modality registration property that is not considered in deep learning registration algorithms.

Image Generation Unsupervised Image Registration

Robust Weakly Supervised Learning for COVID-19 Recognition Using Multi-Center CT Images

no code implementations9 Dec 2021 Qinghao Ye, Yuan Gao, Weiping Ding, Zhangming Niu, Chengjia Wang, Yinghui Jiang, Minhao Wang, Evandro Fei Fang, Wade Menpes-Smith, Jun Xia, Guang Yang

The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis.

Computed Tomography (CT) Weakly-supervised Learning

Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling

1 code implementation5 Sep 2020 Haochuan Jiang, Chengjia Wang, Agisilaos Chartsias, Sotirios A. Tsaftaris

Together with the corresponding encoding features, these representations are propagated to decoding layers with U-Net skip-connections.

Management Segmentation

Annealing Genetic GAN for Minority Oversampling

no code implementations5 Aug 2020 Jingyu Hao, Chengjia Wang, Heye Zhang, Guang Yang

In particular, the generator uses different training strategies to generate multiple offspring and retain the best.

Deep Attentive Wasserstein Generative Adversarial Networks for MRI Reconstruction with Recurrent Context-Awareness

no code implementations23 Jun 2020 Yifeng Guo, Chengjia Wang, Heye Zhang, Guang Yang

The performance of traditional compressive sensing-based MRI (CS-MRI) reconstruction is affected by its slow iterative procedure and noise-induced artefacts.

Compressive Sensing MRI Reconstruction

MV-RAN: Multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis

no code implementations1 May 2020 Ming Li, Chengjia Wang, Heye Zhang, Guang Yang

In addition, for a better interpretation of pathophysiological processes, clinical decision-making and prognosis, such cardiac anatomy segmentation and quantitative analysis of various clinical indices should ideally be performed for the data covering the full cardiac cycle.

Anatomy Decision Making +1

Learning to synthesise the ageing brain without longitudinal data

1 code implementation4 Dec 2019 Tian Xia, Agisilaos Chartsias, Chengjia Wang, Sotirios A. Tsaftaris

Our method synthesises images conditioned on two factors: age (a continuous variable), and status of Alzheimer's Disease (AD, an ordinal variable).


Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks

no code implementations12 Aug 2018 Chengjia Wang, Gillian Macnaught, Giorgos Papanastasiou, Tom MacGillivray, David Newby

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images.

Image Generation

A two-stage 3D Unet framework for multi-class segmentation on full resolution image

no code implementations12 Apr 2018 Chengjia Wang, Tom MacGillivray, Gillian Macnaught, Guang Yang, David Newby

Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances.

Image Super-Resolution Segmentation

A Distance Oriented Kalman Filter Particle Swarm Optimizer Applied to Multi-Modality Image Registration

no code implementations20 Mar 2018 Chengjia Wang, Keith A. Goatman, James Boardman, Erin Beveridge, David Newby, Scott Semple

In this paper we describe improvements to the particle swarm optimizer (PSO) made by inclusion of an unscented Kalman filter to guide particle motion.

Benchmarking Image Registration +1

Cannot find the paper you are looking for? You can Submit a new open access paper.