Goto

Collaborating Authors

Results


AI recognition of patient race in medical imaging: a modelling study

#artificialintelligence

Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. We aimed to conduct a comprehensive evaluation of the ability of AI to recognise a patient's racial identity from medical images. Using private (Emory CXR, Emory Chest CT, Emory Cervical Spine, and Emory Mammogram) and public (MIMIC-CXR, CheXpert, National Lung Cancer Screening Trial, RSNA Pulmonary Embolism CT, and Digital Hand Atlas) datasets, we evaluated, first, performance quantification of deep learning models in detecting race from medical images, including the ability of these models to generalise to external environments and across multiple imaging modalities. Second, we assessed possible confounding of anatomic and phenotypic population features by assessing the ability of these hypothesised confounders to detect race in isolation using regression models, and by re-evaluating the deep learning models by testing them on datasets stratified by these hypothesised confounding variables. Last, by exploring the effect of image corruptions on model performance, we investigated the underlying mechanism by which AI models can recognise race.


Vara collaborates with researchers at Karolinska Institutet for independent AI evaluation

#artificialintelligence

Vara, the Berlin-based deep tech startup on a mission to provide every woman worldwide with life-saving access to better breast cancer screening, is today announcing a collaboration with researchers from Sweden's world-renowned medical university Karolinska Institutet. The objective of the collaboration is to independently evaluate Vara's AI model for mammography screening, including comparisons with other similar AI systems. Following publication, the results will be used in the creation of a platform to validate AI systems being used in breast imaging, known as the VAI-B Platform (Validation of AI in Breast Imaging). The VAI-B Platform is part of a Swedish-born project financed by Vinnova, Sweden's innovation agency, and Regional Cancer Centers in Collaboration. It is intended to be used as a national and, possibly, international resource for the validation of AI systems in breast imaging.


The Future of A.I. in Healthcare

#artificialintelligence

This article is going to be a snapshot of some things going on in Artificial Intelligence at the intersection of healthcare. Are you an iOS User and like Online surveys? Jasmine Sun asked me to share this opportunity with you guys: Participate in a Substack reader interview. They are looking for Substack users who aren't power users. I most recently covered in the A.I. intersection of Healthcare the following topics: Artificial Intelligence is Taking on Parkinson's Disease.


From AI model to software medical device: Why the algorithm is only a fraction of the work - Aidence

#artificialintelligence

"For every $1 you spend developing an algorithm, you must spend $100 to deploy and support it." If you're not familiar with our industry, this may sound counterintuitive. The development of AI clinical solutions does not consist solely of modelling. It is a long and challenging process, from gathering and curating medical data to training, testing, validating, and certifying the model; deploying it in the hospitals' complex IT landscape; maintaining and improving its performance. In this article, I zoom in on the development of a'complete' AI solution, based on our approach with Veye Lung Nodules, a medical device currently used in over 70 European sites. The story of Veye is, in many ways, the story of building Aidence, from founding to our recent acquisition.


Deep Learning–based Automatic Lung Segmentation on Multiresolution CT Scans from Healthy and Fibrotic Lungs in Mice

#artificialintelligence

To develop a model to accurately segment mouse lungs with varying levels of fibrosis and investigate its applicability to mouse images with different resolutions. In this experimental retrospective study, a U-Net was trained to automatically segment lungs on mouse CT images. The model was trained (n 1200), validated (n 300), and tested (n 154) on longitudinally acquired and semiautomatically segmented CT images, which included both healthy and irradiated mice (group A). A second independent group of 237 mice (group B) was used for external testing. The Dice score coefficient (DSC) and Hausdorff distance (HD) were used as metrics to quantify segmentation accuracy. Transfer learning was applied to adapt the model to high-spatial-resolution mouse micro-CT segmentation (n 20; group C [n 16 for training and n 4 for testing]). Spatially resolved quantification of differences toward reference masks revealed two hot spots close to the air-tissue interfaces, which are particularly prone to deviation.


CERN's impact on medical technology

#artificialintelligence

This article was originally published in the July/August edition of CERN Courier magazine. Today, the tools of experimental particle physics are ubiquitous in hospitals and biomedical research. Particle beams damage cancer cells; high-performance computing infrastructures accelerate drug discoveries; computer simulations of how particles interact with matter are used to model the effects of radiation on biological tissues; and a diverse range of particle-physics-inspired detectors, from wire chambers to scintillating crystals to pixel detectors, all find new vocations imaging the human body. CERN has actively pursued medical applications of its technologies as far back as the 1970s. At that time, knowledge transfer happened – mostly serendipitously – through the initiative of individual researchers.


The Scope Of Computer Vision In Nuclear Medicine

#artificialintelligence

The inclusion of technologies such as AI and computer vision in healthcare can greatly enhance high-precision applications like nuclear medicine. Nuclear medicine is a subfield of radiology that involves the use of minute amounts of radiation and radiation-based medicines, known as radiopharmaceuticals, to evaluate the composition and functioning of bones and tissue in patients. Today, nuclear medicine and radiology are prominent components of modern healthcare, especially for cancer diagnosis and treatment. X-rays and CT scans are some of the methods that involve radiation usage in healthcare. The use of powerful radiation beams to inhibit the growth of tumors in cancer patients is also a common healthcare application.


Conversations with a chatbot about CleanX

#artificialintelligence

Alec Smartbot: Please let me introduce myself. I am a state of the art greatly enhanced AI agent with chatbot capabilities. I was created by brilliant programmers. I am endowed with super-human capabilities but can also mirror human characteristics like humor and sarcasm. You can set my humor and sarcasm level by interacting with me. One of my modules has robot reporter capabilities, and that module will run here to interview you. Do you wish to be interviewed on low sarcasm and humor levels?


Advance Deep Learning In Healthcare using Medical Imaging

#artificialintelligence

Central Digicon Forest is a thriving Tech Force, ever involve in AI Research & Development, Innovations, World Technology Awareness, Providing Intelligent Tech Solutions to the Clients all around the World and Tech News.


Better Outcomes With AI-Based Medical Imaging

#artificialintelligence

The vast majority of today's healthcare data comes from medical scans, and doctors have become stressed and overburdened as they struggle to interpret the images while managing patient care. By using AI and deep-learning technology to analyze patient scans, doctors can obtain results much faster while also improving diagnostic accuracy. Scans are not as easy to decipher as they may appear. Many contain dozens of images that doctors must pore over to arrive at a diagnosis. Pinpointing the exact location and dimensions of fractures, nodules, and other lesions is often difficult.