Back to all papers

Comparing prostate diffusion weighted images reconstructed with a commercial deep-learning product to a deep learning phase corrected model at 1.5 T.

November 23, 2025pubmed logopapers

Authors

Cochran RL,Bradley WR,Dhami RS,Milshteyn E,Pohl M,Ghosh S,Nakrour N,Lan P,Wang X,Guidon A,Harisinghani MG

Affiliations (11)

  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].
  • GE HealthCare, Boston, MA, United States. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States; Department of Radiology, Medical University of Graz, Graz, Austria. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].
  • GE HealthCare, Menlo Park, CA, United States. Electronic address: [email protected].
  • GE HealthCare, Houston, TX, United States. Electronic address: [email protected].
  • GE HealthCare, Boston, MA, United States. Electronic address: [email protected].
  • Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; Harvard Medical School, Cambridge, MA, United States. Electronic address: [email protected].

Abstract

To determine whether a new deep learning (DL) based phase corrected (DLPC) reconstruction model can enhance image quality of diffusion weighted images of the prostate acquired at 1.5 T compared to a commercially available DL based product. A retrospective study of 30 consecutive patients undergoing conventional multiparametric MRI (mpMRI) of the prostate on a single 1.5 T scanner was performed. Diffusion image datasets reconstructed with a commercially available DL product and a new DLPC model were assessed. Qualitative image assessment was performed by three board certified radiologists using a 5-point Likert scale across four features and inter-rater agreement was estimated using Gwet's AC2 statistic. Quantitative image comparison was performed by assessing SNR of acquired intermediate b-value (b = 1000 s/mm<sup>2</sup>) diffusion images. The Wilcoxon matched-pairs signed rank test was used to assess differences between techniques. Image noise was assessed using the edge function. Median patient age was 70 years (interquartile range: 66.0-75.3). All radiologists perceived less noise and better image quality for all DLPC image sets compared to commercial DL images (p < 0.05). Significantly higher SNR was observed for the acquired intermediate b-value diffusion images reconstructed with DLPC (median SNR: 49.4 vs 27.5; p < 0.001), and mean ADC values did not significantly differ between DLPC and DL images (p = 0.63). Edge analyses demonstrated significantly reduced noise for DLPC images (p < 0.001). DLPC image reconstruction of diffusion weighted prostate image datasets reduces image noise and improves SNR over a commercial DL product at 1.5 T.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.