A dramatic shift in R&D toward patient safety has taken place in the CT industry, a shift most clearly seen in efforts to reduce patient radiation dose. Iterative reconstruction algorithms are a prominent fixture at the ISCT meeting this year, as they and their future development are increasingly seen as providing the means to cut dose, while maintaining or even boosting image quality.
A dramatic shift in R&D toward patient safety has taken place in the CT industry, a shift most clearly seen in efforts to reduce patient radiation dose. Iterative reconstruction algorithms are a prominent fixture at the ISCT meeting this year, as they and their future development are increasingly seen as providing the means to cut dose, while maintaining or even boosting image quality.
In the past, vendors have emphasized image quality alone, looking for ways to improve diagnostic confidence or add clinical applications. But with increasing attention being paid to patient dose, vendors have sought to leverage this software to maintain the current benchmark of image quality and reduce dose.
They have documented that iterative reconstruction algorithms can be used to clean up noisy images, producing scans of the same image quality as before, but with less radiation. GE Healthcare pioneered this approach, unveiling the idea at RSNA 2008 with its Adaptive Statistical Iterative Reconstruction product. Dose reductions of 50% or more have since been demonstrated in clinical use, according to the company.
More recently, Siemens and Philips have followed suit, Siemens through its IRIS (Iterative Reconstruction in Image Space) and Philips through its iDose. Toshiba is also developing an iterative reconstruction algorithm. GE is developing a next-generation Model-Based Iterative Reconstruction.
Could AI-Powered Abbreviated MRI Reinvent Detection for Structural Abnormalities of the Knee?
April 24th 2025Employing deep learning image reconstruction, parallel imaging and multi-slice acceleration in a sub-five-minute 3T knee MRI, researchers noted 100 percent sensitivity and 99 percent specificity for anterior cruciate ligament (ACL) tears.
Meta-Analysis Shows Merits of AI with CTA Detection of Coronary Artery Stenosis and Calcified Plaque
April 16th 2025Artificial intelligence demonstrated higher AUC, sensitivity, and specificity than radiologists for detecting coronary artery stenosis > 50 percent on computed tomography angiography (CTA), according to a new 17-study meta-analysis.
Can CT-Based AI Radiomics Enhance Prediction of Recurrence-Free Survival for Non-Metastatic ccRCC?
April 14th 2025In comparison to a model based on clinicopathological risk factors, a CT radiomics-based machine learning model offered greater than a 10 percent higher AUC for predicting five-year recurrence-free survival in patients with non-metastatic clear cell renal cell carcinoma (ccRCC).