Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
C2FResMorph: A high-performance framework for unsupervised 2D medical image registration
AbstractDeformable medical image registration is an important precursor task for surgical automation, while enhancing the registration performance of 2D medical images remains a challenging work. Existing methods primarily minimize the similarity loss ...
Highlights- C2FResMorph is a two-stage framework for accurate 2D medical image registration.
- A ResMorph registration network effectively improves registration performance.
- Residual structured loss enhances generalization for 2D image ...
- research-articleMarch 2024
A cascaded framework with cross-modality transfer learning for whole heart segmentation
AbstractAutomatic and accurate segmentation of the whole heart structure from 3D cardiac images plays an important role in helping physicians diagnose and treat cardiovascular disease. However, the time-consuming and laborious manual labeling of the ...
Graphical abstractDisplay Omitted
Highlights- The CM-TranCaF framework improves heart segmentation, transferring MRI to CT while preserving heart shape using the MTN module. MAUNet addresses class imbalances and boundary clarity, and SCN module uses spatial relations to boost ...
- research-articleFebruary 2024
Hyperspectral image classification using Second-Order Pooling with Graph Residual Unit Network
- Kwabena Sarpong,
- Zhiguang Qin,
- Rajab Ssemwogerere,
- Rutherford Agbeshi Patamia,
- Asha Mzee Khamis,
- Enoch Opanin Gyamfi,
- Favour Ekong,
- Chiagoziem C. Ukwuoma
Expert Systems with Applications: An International Journal (EXWA), Volume 238, Issue PDhttps://doi.org/10.1016/j.eswa.2023.122202AbstractConvolutional Neural Networks (CNNs) have become increasingly popular for hyperspectral image (HSI) classification due to their ability to capture spatial and spectral information using fixed square filters. However, CNNs are less effective than ...
Highlights- We propose a SOPGRU model for hyperspectral image classification.
- We propose a CSFA mechanism to eliminate noisy spectral–spatial features.
- We leverage the SOP to capture higher-order statistics of the image features.
- We ...
- research-articleApril 2024
Differentiable Attention Unet-like Nerual Architecture Search for Multimodal Magnetic Resonance Imaging-based Glioma Segmentaion DAUNAS for Multimodal MRI-based Glioma Segmentation
ISAIMS '23: Proceedings of the 2023 4th International Symposium on Artificial Intelligence for Medicine SciencePages 14–19https://doi.org/10.1145/3644116.3644119The utilization of artificial intelligence has had a profound impact on diverse areas within the medical field day by day. Specifically, the identification and management of gliomas, a specific category of brain tumors characterized by a challenging ...
- research-articleOctober 2023
Backdoor Attack on Deep Learning-Based Medical Image Encryption and Decryption Network
IEEE Transactions on Information Forensics and Security (TIFS), Volume 19Pages 280–292https://doi.org/10.1109/TIFS.2023.3322315Medical images often contain sensitive information, and one typical security measure is to encrypt medical images prior to storage and analysis. A number of solutions, such as those utilizing deep learning, have been proposed for medical image encryption ...
-
- research-articleAugust 2023
MFNet:Real-Time Motion Focus Network for Video Frame Interpolation
IEEE Transactions on Multimedia (TOM), Volume 26Pages 3251–3262https://doi.org/10.1109/TMM.2023.3308442As a popular research topic in computer vision, video frame interpolation is widely used in video processing tasks. However, this task is often limited by slow processing speed or high memory consumption in practical applications. To address these ...
- research-articleJuly 2023
Interpreting Universal Adversarial Example Attacks on Image Classification Models
IEEE Transactions on Dependable and Secure Computing (TDSC), Volume 20, Issue 4Pages 3392–3407https://doi.org/10.1109/TDSC.2022.3202544Mitigating adversarial deep learning attacks remains challenging, partly because of the ease and low cost in carrying out such attacks. Therefore, in this article, we focus on the understanding of universal adversarial example attack on image ...
- research-articleDecember 2022
Dual_Pachi: Attention-based dual path framework with intermediate second order-pooling for Covid-19 detection from chest X-ray images
- Chiagoziem C. Ukwuoma,
- Zhiguang Qin,
- Victor K. Agbesi,
- Bernard M. Cobbinah,
- Sophyani B. Yussif,
- Hassan S. Abubakar,
- Bona D. Lemessa
Computers in Biology and Medicine (CBIM), Volume 151, Issue PAhttps://doi.org/10.1016/j.compbiomed.2022.106324AbstractNumerous machine learning and image processing algorithms, most recently deep learning, allow the recognition and classification of COVID-19 disease in medical images. However, feature extraction, or the semantic gap between low-level ...
Highlights- Dual_Pachi, an End-to-End framework that generalizes COVID-19, Pneumonia, Lung opacity and Normal images, is proposed for COVID-19 identification.
- research-articleNovember 2022
Maximal activation weighted memory for aspect based sentiment analysis
AbstractThe vast diffusion of social networks has made an unprecedented amount of user-generated data available, increasing the importance of Aspect Based Sentiment Analysis(ABSA) when extracting sentiment polarity. Although recent research efforts favor ...
Highlights- Aspect Based Sentiment Analysis.
- Activation weighted memory.
- Bidirectional Encoder Representations from Transformers.
- Memory decay.
- research-articleNovember 2022
LCSB-inception: Reliable and effective light-chroma separated branches for Covid-19 detection from chest X-ray images
- Chiagoziem C. Ukwuoma,
- Zhiguang Qin,
- Victor Kwaku Agbesi,
- Chukwuebuka J. Ejiyi,
- Olusola Bamisile,
- Ijeoma A. Chikwendu,
- Bole W Tienin,
- Md Altab Hossin
Computers in Biology and Medicine (CBIM), Volume 150, Issue Chttps://doi.org/10.1016/j.compbiomed.2022.106195AbstractAccording to the World Health Organization, an estimate of more than five million infections and 355,000 deaths have been recorded worldwide since the emergence of the coronavirus disease (COVID-19). Various researchers have developed interesting ...
Highlights- We proposed an inception-based Dual-Paths light-weight deep CNN with less memory and computational complexity.
- A Global second-order pooling replaced the traditional Maxpooling at the last two Conv. blocks for comprehensive extraction ...
- research-articleMay 2022
Constructing secure‐channel free identity‐based encryption with equality test for vehicle‐data sharing in cloud computing
Transactions on Emerging Telecommunications Technologies (TETT), Volume 33, Issue 5https://doi.org/10.1002/ett.3896AbstractWith the rapid rise of connected vehicles on the road, there is an exponential growth in vehicle‐related data (vehicle‐data) generated and accumulated by connected vehicles. Taking advantage of cloud computing, enabling a vehicle‐data sharing ...
System model of vehicle‐data sharing via SCF‐IBEET scheme. image image
- research-articleMay 2022
Oblivious transfer with hidden access control and outsourced decryption from deterministic finite automata‐based functional encryption for an in‐vehicle sensor database system
Transactions on Emerging Telecommunications Technologies (TETT), Volume 33, Issue 5https://doi.org/10.1002/ett.3870AbstractVehicle sensors are continuously observing the state of the vehicle, collecting and transmitting data from/to surrounding road users. The sensors data are then processed and stored in an in‐vehicle sensor database in the form of records. These ...
- research-articleMay 2022
Segmentation mask and feature similarity loss guided GAN for object-oriented image-to-image translation
Information Processing and Management: an International Journal (IPRM), Volume 59, Issue 3https://doi.org/10.1016/j.ipm.2022.102926AbstractWhile image-to-image translation has been extensively studied, there are a number of limitations in existing methods designed for transformation between instances of different shapes from different domains. In this paper, a novel ...
Highlights- Proposed object-level image-to-image translation model to learn cross-domain mappings
- research-articleMarch 2022
Generic network for domain adaptation based on self-supervised learning and deep clustering
Neurocomputing (NEUROC), Volume 476, Issue CPages 126–136https://doi.org/10.1016/j.neucom.2021.12.099AbstractDomain adaptation methods train a model to find similar feature representations between a source and target domain. Recent methods leverage self-supervised learning to discover the analogous representations of the two domains. However, ...
- research-articleJanuary 2022
Facial expression recognition via coarse-grained and fine-grained feature representation
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 43, Issue 4Pages 3947–3959https://doi.org/10.3233/JIFS-212022Recognizing facial expressions rely on facial parts’ movement (action units) such as eyes, mouth, and nose. Existing methods utilize complex subnetworks to learn part-based facial features or train neural networks with an extensively perturbed dataset. ...
- research-articleJanuary 2022
Privacy-Preserving Task Distribution Mechanism with Cloud-Edge IoT for the Mobile Crowdsensing
Mobile crowdsensing under big data provides an efficient, win-win, and low-budget data collection solution for IoT applications such as the smart city. However, its open and all access scenarios raise the threat of data security and user privacy during ...
- review-articleJanuary 2022
Traditional and Hybrid Access Control Models: A Detailed Survey
- Thippa Reddy G,
- Muhammad Umar Aftab,
- Ali Hamza,
- Ariyo Oluwasanmi,
- Xuyun Nie,
- Muhammad Shahzad Sarfraz,
- Danish Shehzad,
- Zhiguang Qin,
- Ammar Rafiq
Access control mechanisms define the level of access to the resources among specified users. It distinguishes the users as authorized or unauthorized based on appropriate policies. Several traditional and hybrid access control models have been proposed in ...
- research-articleJanuary 2022
Attention Augmented Convolutional Neural Network for Fine-Grained Plant Disease Classification and Visualization Using Stochastic Sample Transformations
ICAIP '21: Proceedings of the 5th International Conference on Advances in Image ProcessingPages 13–19https://doi.org/10.1145/3502827.3502836Deep convolutional neural network (DCNN) image analysis improved plant health management. DCNN methods require train samples with diverse feature distribution and discriminative features for the models to generalize well on unseen categories. The limited ...
- research-articleNovember 2021
Spatial self-attention network with self-attention distillation for fine-grained image recognition
Journal of Visual Communication and Image Representation (JVCIR), Volume 81, Issue Chttps://doi.org/10.1016/j.jvcir.2021.103368AbstractThe underlining task for fine-grained image recognition captures both the inter-class and intra-class discriminate features. Existing methods generally use auxiliary data to guide the network or a complex network comprising multiple ...
Highlights- Spatial self-attention learns discriminate features for fine-grained recognition.
- research-articleOctober 2021
ToStaGAN: An end-to-end two-stage generative adversarial network for brain tumor segmentation
Neurocomputing (NEUROC), Volume 462, Issue CPages 141–153https://doi.org/10.1016/j.neucom.2021.07.066AbstractBrain tumor segmentation using MRI data remains challenging for some reasons. Hence, how to accurately segment the brain tumor is kept as a significant topic in the area of medical image segmentation. To follow the idea of “coarse-to-...