Prevalence and influencing factors for artifact development in breast MRI-derived maximum intensity projections

Kapsner, Lorenz A; Balbach, Eva L; Laun, Frederik B; Baumann, Lukas; Ohlmeyer, Sabine; Uder, Michael; Bickelhaupt, Sebastian; Wenkel, Evelyn

doi:10.1177/02841851231198349

Cited by 1 publication

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within this period, female patients with a clinically indicated breast MRI performed with a full diagnostic protocol including CE sequences at the Institute of Radiology of the University Hospital Erlangen (UHE) were included in this study. The study sample is partially overlapping with previously reported cohorts in which (a) the automated detection of MRI artifacts on breast CE-MIPs by applying DL methods 19 and (b) a DL-based image quality assessment in high b-value diffusion-weighted breast MRI 20 were evaluated, as well as (c) an investigation of the prevalence of MRI-artifacts in breast CE-MIPs 21 . Details on the MRI protocols are given in supplement S1 .…”

Section: Methodsmentioning

confidence: 99%

Lesion-conditioning of synthetic MRI-derived subtraction-MIPs of the breast using a latent diffusion model

Kapsner,

Folle,

Hadler

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

The purpose of this feasibility study is to investigate if latent diffusion models (LDMs) are capable to generate contrast enhanced (CE) MRI-derived subtraction maximum intensity projections (MIPs) of the breast, which are conditioned by lesions. We trained an LDM with n = 2832 CE-MIPs of breast MRI examinations of n = 1966 patients (median age: 50 years) acquired between the years 2015 and 2020. The LDM was subsequently conditioned with n = 756 segmented lesions from n = 407 examinations, indicating their location and BI-RADS scores. By applying the LDM, synthetic images were generated from the segmentations of an independent validation dataset. Lesions, anatomical correctness, and realistic impression of synthetic and real MIP images were further assessed in a multi-rater study with five independent raters, each evaluating n = 204 MIPs (50% real/50% synthetic images). The detection of synthetic MIPs by the raters was akin to random guessing with an AUC of 0.58. Interrater reliability of the lesion assessment was high both for real (Kendall’s W = 0.77) and synthetic images (W = 0.85). A higher AUC was observed for the detection of suspicious lesions (BI-RADS $$\ge $$ ≥ 4) in synthetic MIPs (0.88 vs. 0.77; p = 0.051). Our results show that LDMs can generate lesion-conditioned MRI-derived CE subtraction MIPs of the breast, however, they also indicate that the LDM tended to generate rather typical or ‘textbook representations’ of lesions.

show abstract

Section: Methodsmentioning

confidence: 99%