Icon Legend

This session is not in your schedule.

This session is in your schedule. Click again to remove it.

Presentation Icons

Additional registration fee required

Faculty have requested this content not be shared outside of the session

CME Credit Offered

Abstract Award

Recording available 2/16-5/2

AIUM Credit

Foundation Awardee

Poster Icons

Abstract Award

Foundation Awardee

Poster Session 4

Category: Ultrasound/Imaging

Poster Session 4

(1219) MR radiomics and surgical outcomes in pregnant patients at increased risk for Placenta Accreta Spectrum

Thursday, February 12, 2026

3:30 PM - 5:00 PM

Submitting Author and Presenting Author(s)

Quyen N. Do, PhD (she/her/hers)

Assistant Professor
UT Southwestern Medical Center
Dallas, Texas, United States

Coauthor(s)

YX

Yin Xi, PhD

UT Southwestern Medical Center
UT Southwestern Medical Center, Texas, United States
ML

Matthew A. Lewis, PhD

UT Southwestern Medical Center
UT Southwestern Medical Center, Texas, United States
DO

David M. Owen, MD, PhD

UT Southwestern Medical Center
UT Southwestern Medical Center, Texas, United States
Alesha M. White, MD (she/her/hers)

Maternal Fetal Medicine Fellow
University of Texas Southwestern Medical Center
Grand Prairie, Texas, United States
NU

Naseem Uddin, MD

UT Southwestern Medical Center
UT Southwestern Medical Center, Texas, United States
BF

Baowei Fei, PhD

Professor
The University of Texas at Dallas
The University of Texas at Dallas, Texas, United States
Catherine Y. Spong, MD

Professor and Chair
University of Texas Southwestern Medical Center
Dallas, Texas, United States
Christina L. Herrera, MD

Assistant Professor
University of Texas Southwestern Medical Center
Dallas, Texas, United States

Objective:
To evaluate if placental radiomic features in pregnancies with increased risk of Placenta Accreta Spectrum (PAS) correlates with surgical outcome.

Study Design:
We conducted a prospective MRI study of pregnancies with increased risk for PAS. Inclusion criteria consisted of first trimester ultrasound findings indicating low uterine segment implantation and a history of cesarean delivery. Eligible participants underwent MRI at two time points: 16w0d-19w6d (Visit 1) and 24w0d-27w6d (Visit 2). Volumetric placental regions of interest (ROIs) were manually delineated on T2W and apparent diffusion coefficient (ADC) images. Radiomic features, including first order and texture features, were extracted from the segmented placenta in accordance with the Image Biomarker Standardization Initiative (IBSI) guidelines using the PyRadiomics package. Medical records were reviewed to determine surgical outcomes, and patients were grouped according to the outcome of hysterectomy. Patient demographics were compared between the two outcome groups using T-tests and Fisher’s Exact test. Univariate receiver operating characteristic (ROC) curve analysis was performed for each radiomic feature to evaluate their predictive power for surgical outcomes. Statistical significance was determined using false discovery rate (FDR)-adjusted p-values, with an adjusted p-value < 0.05 considered significant.

Results:
Of 49 patients meeting inclusion criteria, 18 required cesarean hysterectomy (Table 1). Seventeen radiomic features from T2W and ADC images were significantly associated with hysterectomy after FDR correction, with the calculated placenta location in the uterus the most predictive (Table 2). Number of prior cesarean delivery, estimated blood loss, and pathologic PAS grading were significantly different between the two groups.

Conclusion:
Radiomic features effectively predict surgical outcome in women at risk of PAS. These findings underscore the potential of MR-based radiomics as a non-invasive tool for risk stratification and preoperative planning in PAS.