no code implementations • 30 Jan 2024 • Ming Kang, Chee-Ming Ting, Fung Fung Ting, Raphaël Phan
Medical image semantic segmentation techniques can help identify tumors automatically from computed tomography (CT) scans.
no code implementations • 30 Jan 2024 • Chee-Ming Ting, Fuad Noman, Raphaël C. -W. Phan, Hernando Ombao
The low-rank plus sparse (L+S) decomposition model has enabled better reconstruction of dynamic magnetic resonance imaging (dMRI) with separation into background (L) and dynamic (S) component.
1 code implementation • 11 Dec 2023 • Ming Kang, Chee-Ming Ting, Fung Fung Ting, Raphaël C. -W. Phan
We propose a novel Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) which combines spatial and scale features for accurate and fast cell instance segmentation.
1 code implementation • 22 Sep 2023 • Ming Kang, Chee-Ming Ting, Fung Fung Ting, Raphaël C. -W. Phan
You Only Look Once (YOLO)-based object detectors have shown remarkable accuracy for automated brain tumor detection.
1 code implementation • 31 Jul 2023 • Ming Kang, Chee-Ming Ting, Fung Fung Ting, Raphaël C. -W. Phan
With an excellent balance between speed and accuracy, cutting-edge YOLO frameworks have become one of the most efficient algorithms for object detection.
1 code implementation • 26 Jun 2023 • Ming Kang, Chee-Ming Ting, Fung Fung Ting, Raphaël Phan
Blood cell detection is a typical small-scale object detection problem in computer vision.
no code implementations • 8 Jun 2023 • Junn Yong Loo, Ze Yang Ding, Surya G. Nurzaman, Chee-Ming Ting, Vishnu Monn Baskaran, Chee Pin Tan
To address these challenges, we propose a deep Particle Flow Bayes (DPFB) framework for cross-domain soft sensor modeling in the absence of target state labels.
no code implementations • 14 Feb 2023 • Junn Yong Loo, Sin-Yee Yap, Fuad Noman, Raphael CW Phan, Chee-Ming Ting
Recent applications of pattern recognition techniques on brain connectome classification using functional connectivity (FC) neglect the non-Euclidean topology and causal dynamics of brain connectivity across time.
no code implementations • 10 Dec 2022 • Yee-Fan Tan, Chee-Ming Ting, Fuad Noman, Raphaël C. -W. Phan, Hernando Ombao
Despite its remarkable success for Euclidean-valued data generation, use of standard generative adversarial networks (GANs) to generate manifold-valued FC data neglects its inherent SPD structure and hence the inter-relatedness of edges in real FC.
no code implementations • 27 Jul 2021 • Fuad Noman, Chee-Ming Ting, Hakmook Kang, Raphael C. -W. Phan, Brian D. Boyd, Warren D. Taylor, Hernando Ombao
Our new framework demonstrates feasibility of learning graph embeddings on brain networks to provide discriminative information for diagnosis of brain disorders.
1 code implementation • 24 Jan 2021 • Chee-Ming Ting, Jeremy I. Skipper, Steven L. Small, Hernando Ombao
We propose a novel, data-driven approach based on low-rank plus sparse (L+S) decomposition to isolate stimulus-driven dynamic changes in brain functional connectivity (FC) from the background noise, by exploiting shared network structure among subjects receiving the same naturalistic stimuli.
no code implementations • 9 Apr 2020 • Chee-Ming Ting, S. Balqis Samdin, Meini Tang, Hernando Ombao
We present a unified statistical framework for characterizing community structure of brain functional networks that captures variation across individuals and evolution over time.
no code implementations • 21 Mar 2019 • Chun-Ren Phang, Chee-Ming Ting, Fuad Noman, Hernando Ombao
We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ).
no code implementations • 27 Oct 2018 • Fuad Noman, Chee-Ming Ting, Sh-Hussain Salleh, Hernando Ombao
This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats.
no code implementations • 10 Sep 2018 • Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, S. Balqis Samdin, Hernando Ombao, Hadri Hussain
Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure.