A5070739732- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Cancer Immunotherapy and Biomarkers
- Immunotherapy and Immune Responses
- Cell Image Analysis Techniques
- Automated Road and Building Extraction
- Remote-Sensing Image Classification
- Remote Sensing and LiDAR Applications
- Artificial Intelligence in Healthcare and Education
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Atherosclerosis and Cardiovascular Diseases
- Digital Imaging for Blood Diseases
- Colorectal Cancer Screening and Detection
Queen's University Belfast
2020-2024
University of Boumerdes
2018
Biomarkers identify patient response to therapy. The potential immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS), expressed on regulating activation and involved in adaptive immune responses, is of great interest. We have previously shown that open-source software for digital pathology image analysis can be used detect quantify ICOS using cell detection algorithms based traditional processing techniques. Currently, artificial intelligence (AI) deep learning methods...
In this paper, we propose a convolutional neural network, which is based on down sampling followed by up architecture for the purpose of road extraction from aerial images. Our model consists layers only. The proposed encoder-decoder structure allows our network to retain boundary information, critical feature identification. This usually lost when dealing with other CNN models. design also less complex in terms depth, number parameters, and memory size. It, therefore, uses fewer computer...
Integrating artificial intelligence (AI) tools in the tissue diagnostic workflow will benefit pathologist and, ultimately, patient. The generation of such AI has two parallel and yet interconnected processes, namely definition pathologist’s task to be delivered silico, software development requirements. In this review paper, we demystify process, from a viewpoint that joins experienced pathologists data scientists, by proposing general pathway describing core steps build an digital pathology...
Rapid and accurate detection of COVID-19 is a crucial step to control the virus. For this purpose, authors designed web-based detector using efficient dual attention networks, called 'EDANet'. The EDANet architecture based on inverted residual structures reduce model complexity mechanism with position channel blocks enhance discriminant features from different layers network. Although has only 4.1 million parameters, experimental results demonstrate that it achieves state-of-the-art COVIDx...
Abstract Detecting the Kirsten Rat Sarcoma Virus ( KRAS ) gene mutation is significant for colorectal cancer (CRC) patients. The encodes a protein involved in epidermal growth factor receptor (EGFR) signaling pathway, and mutations this can negatively impact use of monoclonal antibodies anti-EGFR therapy affect treatment decisions. Currently, commonly used methods like next-generation sequencing (NGS) identify but are expensive, time-consuming, may not be suitable every patient sample. To...
In this article, we propose ICOSeg, a lightweight deep learning model that accurately segments the immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS) protein in colon cancer from immunohistochemistry (IHC) slide patches. The proposed relies on MobileViT network includes two main components: convolutional neural (CNN) layers for extracting spatial features; and transformer block capturing global feature representation IHC patch images. ICOSeg uses an encoder decoder...
Abstract Introduction - Seminal work from Galon et al [PMID: 16371631], found immunohistochemical (IHC) quantification of the immune response to be prognostic in colorectal cancer (CRC). Although numerous systems for scoring T-cell subsets have been published [reviewed PMID: 35758208] and this type is acknowledged as a bona fide diagnostic test 32320495], it not commonly used general routine. Our group reported recently that digital pathology (DP) approach CD3/CD4/CD8 more than 1,500...