DALSA launches image processor

AuntMinnie.com staff writers

Nov 30, 2009

Canadian digital imaging developer DALSA introduced at this week's RSNA meeting its XRI-1600 digital imaging processor intended for use with x-ray imaging.

XRI-1600 is designed to handle a wide range of resolutions, pixel depths, and frame rates, according to the Waterloo, Ontario-based firm.

XRI-1600 incorporates DALSA's Image Processing Engine (IPE) that performs real-time digital image processing in three dynamic stages, and comes bundled with easy-to-use software application development tools and utilities, the company said.

Related Reading

DALSA unveils new sensors, November 26, 2008

DALSA debuts High Quanta sensors, December 6, 2007

DALSA receives CMOS order, November 6, 2007

DALSA debuts new DR camera at RSNA, November 26, 2006

DALSA Coreco debuts image processor, September 12, 2005

Copyright © 2009 AuntMinnie.com

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

Transgender Heart

Bone health appears normal in transgender youth on hormone therapy

April 5, 2024

Abortion care limitations raise medicolegal concerns in IR

April 3, 2024

(a) Raw example of a dynamic digital radiograph. (b) Contrast equalization using contrast-limited adaptive equalization shows improved anatomical visualization. (c) Training data is generated through manually labeling using SLEAP’s graphical user interface. (d-e) Neural network detection schematic. For each quadrant a series of two networks were used. The first identifies the quadrant center, the second using input of the first, then identifies individual anatomical landmarks within a quadrant. (d) Four neural networks were trained, each with the objective of identifying a chest quadrant centroid. The four separate quadrants are visualized as colored boxes (right upper quadrant, green; right lower quadrant, blue; left upper quadrant, red; left lower quadrant, yellow). (e) Serial centroid then anatomical identification. Two quadrant examples showing confidence maps of trained neural networks identifying quadrant centroids (left) and then anatomical confidence maps (right). Image and caption courtesy of Chest Pulmonary.

Can AI help chest DDR achieve clinical adoption?

April 1, 2024

AI proposed to help radiologists detect child abuse injuries

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.

Bone health appears normal in transgender youth on hormone therapy

Bone mineral density is only slightly below the normal average among transgender youth undergoing gender-affirming hormone therapy.

April 5, 2024

Transgender Heart

Abortion care limitations raise medicolegal concerns in IR

Interventional radiology (IR) specialists should be aware of shifting individual state laws on abortion so as to not be blindsided when called on to provide care to pregnant patients.

April 3, 2024

Can AI help chest DDR achieve clinical adoption?

Chest dynamic digital radiography (DDR) may have received a boost toward clinical use in patients with lung disorders, with researchers developing AI to perform time-consuming analysis involved in the technology.

April 1, 2024

(a) Raw example of a dynamic digital radiograph. (b) Contrast equalization using contrast-limited adaptive equalization shows improved anatomical visualization. (c) Training data is generated through manually labeling using SLEAP’s graphical user interface. (d-e) Neural network detection schematic. For each quadrant a series of two networks were used. The first identifies the quadrant center, the second using input of the first, then identifies individual anatomical landmarks within a quadrant. (d) Four neural networks were trained, each with the objective of identifying a chest quadrant centroid. The four separate quadrants are visualized as colored boxes (right upper quadrant, green; right lower quadrant, blue; left upper quadrant, red; left lower quadrant, yellow). (e) Serial centroid then anatomical identification. Two quadrant examples showing confidence maps of trained neural networks identifying quadrant centroids (left) and then anatomical confidence maps (right). Image and caption courtesy of Chest Pulmonary.

Powering down idle IR systems can reduce environmental impact

Powering down idle interventional radiology (IR) imaging systems can substantially decrease carbon emissions and electricity costs.

March 21, 2024

Mercedes-Benz employs x-ray technology in crash tests

Mercedes-Benz said it has performed the world's first crash with a real car using x-ray imaging technology.

March 21, 2024

An image illustrating the use of novel x-ray technology in crash tests.

Hysterectomies may be averted with UAE

A minimally invasive treatment called uterine artery embolization (UAE) may be a promising alternative to hysterectomy in women due to severe bleeding after childbirth.

March 20, 2024

Training technique in AI helps preserve patient privacy

The privacy of patient data in AI models trained on chest x-rays can be guaranteed – importantly, without significantly reducing the accuracy of models on large “real-world” data sets.

March 18, 2024

AI flags rare humeral bone tumors on chest x-rays

An AI algorithm can help identify rare tumors on upper arm bones in patients undergoing chest x-rays – findings not typically identified in daily reading practice.

March 13, 2024

The tumor localization/visualization results obtained by the proposed AI algorithm. Original chest x-ray images with a lesion (red circle = radiologists’ annotation of the lesion location) and AI's lesion localization result. These examples demonstrate that the proposed technique can successfully detect humeral tumors. Image and caption courtesy of Radiology: Artificial Intelligence.

Dark-field chest x-ray takes step forward

German developers of dark-field chest x-ray appear to have overcome a technical limitation of the technology – namely, adjusting for photon scattering caused by interferometers used in the experimental system.

March 12, 2024

Study calls for continuous improvement of AI algorithms

An external validation study conducted in a primary care clinic in Spain has demonstrated the value – as well as important limitations – of AI software for interpreting chest x-rays in clinical practice.

March 8, 2024

Image of patient (upper-left) in which, according to the radiologist's report, there is only consolidation, but the algorithm detects an abnormal rib (upper-right), consolidation (lower-left), and two nodules (lower-right). It is worth noting the confusion of a consolidation with mammary tissue and of two nodules with the two mammary areolae. Image courtesy of Scientific Reports.

Using deep learning with CT helps predict hip fractures

By Kate Madden Yee

A deep-learning model that includes digital x-rays reconstructed from 3D hip CT images shows promise for predicting subsequent fractures in patients with a relatively recent hip break, researchers have found.

January 31, 2024

Page 1 of 373