AMVC 2020: Artificial intelligence for COVID-19 detection

May 13, 2020
2019 03 04 19 48 5533 2019 03 03 Ecr 2019 Video Ranschaert 400

The outbreak of COVID-19 has created the need for new diagnostic tools to help identify early signs of infection with the novel coronavirus. Could artificial intelligence help?

In this talk from AuntMinnie.com's 2020 Virtual Conference, Dr. Erik Ranschaert, PhD, discusses how artificial intelligence (AI) could be employed in the fight against COVID-19. He provides a brief introduction to AI and the role of AI in COVID-19 detection and discusses how European internet privacy rules could hinder the development of effective strategies.

Ranschaert is a radiologist and AI project leader at Elisabeth-TweeSteden Hospital (ETZ) in the Netherlands. He is also president of the European Society of Medical Imaging Informatics (EuSoMII).

Latest in Clinical News
Group mean C-11 PBR28 SUVR maps of females with ASD (top) and female controls (middle). Statistical map from voxelwise comparison of C-11 PBR28 SUVR between groups, controlled for age and TSPO genotype, shows elevated regional TSPO levels relative to whole brain mean in the midcingulate cortex and splenium of the corpus callosum in ASD (N = 12) compared with controls (N = 10) (Z > 2.3, pcluster) (bottom). TSPO = translocator protein, ASD = autism spectrum disorder, CON = control, SUVR = standardized uptake value ratio, N = number. Image and caption courtesy of Neuropsychopharmacology.
PET/MRI reveals sex differences in patients with autism
April 18, 2024
Doctor Female Young Desk 400
Radiologist consultation improves patients' LCS attitudes
April 18, 2024
We care about what you think.
Sponsored
We care about what you think.
October 30, 2023
Test set images with ground truth (teal, red) and model predictions (green, yellow), with true positives (green), false positives (yellow), and false negatives (red). Predictions from the 6x-YOLOv5 ensemble trained on histogram equalized input images with a y = 0.2 avalanche scheme, achieving 0.536 precision, 0.795 recall, and 0.723 F2 score. Image and caption courtesy of Scientific Reports.
AI proposed to help radiologists detect child abuse injuries
April 17, 2024
Related Stories
2020 08 11 18 03 7274 Sars Co V 2 Spike Coronavirus 400
Artificial Intelligence
Thirona, Smart Reporting team up on COVID-19 software
2019 04 04 21 52 2230 Artificial Intelligence Ai Data 400
Artificial Intelligence
Gender imbalance in AI training datasets lowers results
2020 05 15 18 45 6754 2020 05 15 Ajnr Ct Scans 400
CT
CT angio images show stroke in COVID-19 patient
FREE WEBINAR: Advanced visualization in 2024: Enhancing radiology care
Sponsor Content
FREE WEBINAR: Advanced visualization in 2024: Enhancing radiology care
More in Clinical News
PET/MRI reveals sex differences in patients with autism
By Will Morton
PET/MRI shows that young women with autism spectrum disorder have increased brain metabolism associated with translocator protein (TSPO).
April 18, 2024
Group mean C-11 PBR28 SUVR maps of females with ASD (top) and female controls (middle). Statistical map from voxelwise comparison of C-11 PBR28 SUVR between groups, controlled for age and TSPO genotype, shows elevated regional TSPO levels relative to whole brain mean in the midcingulate cortex and splenium of the corpus callosum in ASD (N = 12) compared with controls (N = 10) (Z > 2.3, pcluster) (bottom). TSPO = translocator protein, ASD = autism spectrum disorder, CON = control, SUVR = standardized uptake value ratio, N = number. Image and caption courtesy of Neuropsychopharmacology.
Radiologist consultation improves patients' LCS attitudes
By Kate Madden Yee
Consulting with a radiologist boosts patients' attitudes toward lung cancer screening (LCS) and their interest in quitting smoking, researchers have reported.
April 18, 2024
Doctor Female Young Desk 400
PET tracer for gliomas under expedited review
By AuntMinnie.com staff writers
The U.S. Food and Drug Administration (FDA) has granted fast-track designation to Telix Pharmaceuticals’ PET radiotracer F-18 floretyrosine (Pixclara) for imaging progressive or recurring gliomas.
April 17, 2024
Gliomas
AI proposed to help radiologists detect child abuse injuries
By Will Morton
A team at Michigan State University has developed an AI model designed to detect rib fractures in children under 3 years old.
April 17, 2024
Test set images with ground truth (teal, red) and model predictions (green, yellow), with true positives (green), false positives (yellow), and false negatives (red). Predictions from the 6x-YOLOv5 ensemble trained on histogram equalized input images with a y = 0.2 avalanche scheme, achieving 0.536 precision, 0.795 recall, and 0.723 F2 score. Image and caption courtesy of Scientific Reports.
Tailored lung cancer screening model helps determine nodule follow-up
By Kate Madden Yee
A personalized lung cancer screening model used with patients with pulmonary nodules identified on low-dose CT helps clinicians determine how to follow up better than rule-based protocols, researchers have found.
April 17, 2024
Lung Cancer
POCUS used widely in lung ultrasound applications
By Amerigo Allegretto
Some of the top domains for users of point-of-care ultrasound (POCUS) incorporate the technology for lung ultrasound applications.
April 17, 2024
Screenshot (1142)
CT-based deep learning identifies patients at further lung cancer risk
By Kate Madden Yee
A CT-based deep learning model can identify individuals with clinical stage IA non-small cell lung cancer (NSCLC) at high risk of further disease, researchers have found.
April 16, 2024
Ai
Deep-learning model determines breast tumor staging
By Amerigo Allegretto
A deep-learning model based on mammographic images can determine tumor staging and sentinel lymph node metastasis in breast cancer patients.
April 16, 2024
Researchers explain the data preparation and structure of a proposed CNN-based deep learning model using mammography features to determine breast tumor staging. The image is available for use under a Creative Commons license: CC BY-NC-ND 4.0 DEED Attribution-NonCommercial-NoDerivs 4.0 International.
FAPI-PET shows promise in patients with lung cancer
By Will Morton
FAPI-PET imaging could emerge as a new tool for assessing patients with single pulmonary tumors, especially in those with negative results on other scans.
April 15, 2024
F-18 FDG and Ga-68 FAPI-46 images of a 51-year-old woman with adenocarcinoma with lepidic growth pattern in right upper lobe. (A) Maximum-intensity-projection PET images. The lesion had F-18 FDG uptake below blood pool level but was strongly Ga-68 FAPI-46-positive. CT-guided biopsy led to pathologic diagnosis of adenocarcinoma, and the patient was treated by stereotactic body radiation therapy because of functional inoperability. Image courtesy of the Journal of Nuclear Medicine.
Can brain MRI for emergency imaging of dizziness be more effective?
By Kate Madden Yee
Predictors for acute conditions such as stroke could make brain MRI more effective in patients who present in the emergency department with dizziness or vertigo, according to recent research.
April 15, 2024
Stroke Mri
RadNet teams up with basketball icon Sheryl Swoopes
By AuntMinnie.com staff writers
RadNet has tapped basketball legend and WNBA superstar Sheryl Swoopes as spokesperson for its nationwide breast cancer screening programs.
April 12, 2024
Mammogramnow
Vision transformer AI model boosts PET/CT imaging of cancer
By Will Morton
A vision transformer AI model outperformed convolutional neural networks when classifying tumors on PET/CT images as benign or malignant.
April 12, 2024
Predictions and Grad-CAMs of ViT-based models on sample PET/CT, PET, and CT test images from the “positive” class. ViT was fine-tuned using training data for each modality. The bounding boxes depicted in the figure indicate malignant lesions. The top row of the Grad-CAMs shows important areas for “positive” predictions, and the bottom row shows areas for “negative” predictions. Image courtesy of Scientific Reports.
Page 1 of 3587
Next Page