Enterprise Imaging

Enterprise imaging brings together all imaging exams, patient data and reports from across a healthcare system into one location to aid efficiency and economy of scale for data storage. This enables immediate access to images and reports any clinical user of the electronic medical record (EMR) across a healthcare system, regardless of location. Enterprise imaging (EI) systems replace the former system of using a variety of disparate, siloed picture archiving and communication systems (PACS), radiology information systems (RIS), and a variety of separate, dedicated workstations and logins to view or post-process different imaging modalities. Often these siloed systems cannot interoperate and cannot easily be connected. Web-based EI systems are becoming the standard across most healthcare systems to incorporate not only radiology, but also cardiology (CVIS), pathology and dozens of other departments to centralize all patient data into one cloud-based data storage and data management system.

Tablet projecting metaphorical medical hologram

AI model identifies radiologist-recommended follow-up imaging in reports, has potential for widespread use

New data published in the American Journal of Roentgenology details the performance of a deep learning model known as BERT, short for Bidirectional Encoder Representations from Transformers.

April 19, 2023
Growing Tree

Decreasing energy consumption in radiology: How one hospital reduced use and saved big

Energy consumption reduction tactics could decrease greenhouse gas emissions owed to radiology while also saving departments tens of thousands of dollars every year. 

April 18, 2023
Example of the four types of breast tissue density. The density of fibroglandular tissue inside the breast impacts the ability to easily see cancers. Cancers are very easy to spot in fatty breasts, but are almost impossible to find in extremely dense breasts. These examples show craniocaudal mammogram findings characterized as almost entirely fatty (far left), scattered areas of fibroglandular density (second from left), heterogeneously dense (second from right), and extremely dense (far right). RSNA

Experts developed a deep learning model that can estimate breast density

When tested, the model achieved a performance comparable to that of human experts.

April 10, 2023
pulmonary embolism on CT pulmonary angiography

AI work list prioritization tool significantly decreases PE turnaround times

The FDA-approved tool works by reprioritizing CTPA exams to the top of a radiologist’s work list when the scan is positive for PE.

April 5, 2023

Follow-up adherence affected by how and when imaging orders are placed

These are factors that healthcare systems can and should control, experts recently suggested in a new JACR paper.

April 5, 2023
Chest X-ray. Using an explainable artificial intelligence (AI) model, researchers were recently able to accomplish highly accurate labeling on large datasets of publicly available chest radiograph X-rays.. 

Radiologists develop point-of-care AI for chest X-rays

Radiologists used an AI tool-building platform to create their model(s), which allows clinicians the opportunity to develop AI models without any prior training in data sciences or computer programming. 

April 3, 2023
Consult

Structured reports with a 'forcing function' for recommendations improve follow-up adherence

In a study that included hundreds of radiologist recommendations for additional imaging, there was a threefold increase in follow-up adherence when radiologists utilized a voluntary closed-loop communication tool that required structured recommendations. 

March 31, 2023
ai.jpg

'Quite impressive': ChatGPT generates a nuclear medicine report

The generated report included indication, findings laid out numerically, TNM stage, impression and follow-up recommendations.

March 27, 2023

Around the web

The newly approved AI models are designed to improve the detection of pulmonary embolisms and strokes in patients who undergo CT scans.

"I see, at least for the next decade, this being a SPECT and PET world, not one or the other," explained Tim Bateman, MD.

The FDA-approved technology developed by HeartFlow can predict a patient's long-term risk of target vessel failure as well as more invasive treatments performed inside a cath lab. 

Trimed Popup
Trimed Popup