A deep learning-enhanced ultra-fast bpMRI protocol offered similar sensitivity for csPCa as mpMRI with an 80 percent reduction in scan time, according to research findings presented at the European Congress of Radiology (ECR) conference.
Ultra-fast biparametric magnetic resonance imaging (bpMRI) may provide a viable alternative to multiparametric MRI (mpMRI) for the detection of clinically significant prostate cancer (csPCa), according to new study findings presented at the European Congress of Radiology (ECR) conference.
For the prospective study, researchers compared mpMRI and deep learning-assisted ultra-fast bpMRI for detection of csPCa in 123 biopsy-naïve patients. Two radiologists, with four and three years of experience, respectively, offered PI-RADS v2.1 assessments as well as PI-QUAL scores for image quality, according to the study.
The researchers found that the ultra-fast bpMRI protocol offered similar sensitivity (91 percent vs. 94 percent) and negative predictive value (NPV) (95 percent vs. 96 percent) for csPCa detection as mpMRI.
In a study recently presented at the European Congress of Radiology (ECR) conference, researchers found that a deep learning-assisted ultra-fast bpMRI protocol offered similar sensitivity (91 percent vs. 94 percent) and negative predictive value (NPV) (95 percent vs. 96 percent) for csPCa detection as mpMRI.
“There was no significant difference in the diagnostic performance of correctly identifying csPCa between both protocols,” wrote lead study author Antonia-Maria Pausch, M.D., a fellow at the Institute for Diagnostic and Interventional Radiology at the University Hospital Zurich in Zurich, Switzerland, and colleagues.
The study authors pointed out that the more experienced reviewing radiologist’s assessments with ultra-fast bpMRI had 25 percent higher specificity, 17 percent higher positive predictive value (PPV) and 17 percent higher accuracy rates than the evaluations of the radiologist with three years of experience.
(Editor’s note: For related content, see “Can MRI-Based Deep Lrearning Improve Risk Stratification in PI-RADS 3 Cases?,” “Can Deep Learning Radiomics with bpMRI Bolster Accuracy for Prostate Cancer Diagnosis?” and “Emerging AI Platform Shows Promise for Prostate Cancer Detection on mpMRI.”)
Otherwise, the researchers noted 87 percent inter-reader agreement for ultra-fast bpMRI in comparison to 83 percent for mpMRI for csPCa. The study authors also higher PI-QUAL ratings and emphasized an 80 percent reduction in scan time with ultra-fast bpMRI.
“Deep-learning-assisted ultra-fast bpMRI protocols offer a promising alternative to conventional mpMRI for diagnosing csPCa in biopsy-naïve patients with comparable inter-reader agreement and diagnostic performance at superior image quality,” added Pausch and colleagues.
Reference
1. Pausch AM, Fillebock V, Elsner C, Rupp N, Eberli D, Hotker AM.Ultra-fast biparametric MRI in prostate cancer assessment: diagnostic performance and image quality compared to conventional multiparametric MRI. Presented at the European Congress of Radiology (ECR), February 26-March 2, 2025, Vienna, Austria. Available at https://www.myesr.org/congress/ . Accessed March 1, 2025.
Can Abbreviated Breast MRI Have an Impact in Assessing Post-Neoadjuvant Chemotherapy Response?
April 24th 2025New research presented at the Society for Breast Imaging (SBI) conference suggests that abbreviated MRI is comparable to full MRI in assessing pathologic complete response to neoadjuvant chemotherapy for breast cancer.
Clarius Mobile Health Unveils Anterior Knee Feature for Handheld Ultrasound
April 23rd 2025The T-Mode Anterior Knee feature reportedly offers a combination of automated segmentation and real-time conversion of grayscale ultrasound images into color-coded visuals that bolster understanding for novice ultrasound users.
What is the Best Use of AI in CT Lung Cancer Screening?
April 18th 2025In comparison to radiologist assessment, the use of AI to pre-screen patients with low-dose CT lung cancer screening provided a 12 percent reduction in mean interpretation time with a slight increase in specificity and a slight decrease in the recall rate, according to new research.
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.