Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

AI-based CT quantification reveals small airway loss and vascular simplification in rheumatoid arthritis-associated lung disease.

Clinical rheumatology·2026
Same author

3D deep-learning radiomics from MR-T2WI for predicting placenta accreta spectrum disorders: A multicenter study.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2026
Same author

Diagnostic value of lung ultrasound vs. quantitative computed tomography in connective tissue disease-associated interstitial lung disease: a preliminary study.

Clinical rheumatology·2026
Same author

Deep Learning and Attention Mechanism-based Prediction of Vaginal Invasion in Early-Stage Cervical Cancer

Current medical imaging·2025
Same author

Bioinformatics-based screening and experimental validation of biomarkers for the treatment of connective tissue-associated interstitial lung disease with liquorice and dried ginger soup.

Biomarkers : biochemical indicators of exposure, response, and susceptibility to chemicals·2025
Same author

Magnetic resonance imaging of focal organizing pneumonia: differential diagnosis with peripheral lung carcinoma.

Acta radiologica (Stockholm, Sweden : 1987)·2025

Related Experiment Video

Updated: Jul 17, 2026

Accurate and Simple Evaluation of Vascular Anastomoses in Monochorionic Placenta using Colored Dye
09:52

Accurate and Simple Evaluation of Vascular Anastomoses in Monochorionic Placenta using Colored Dye

Published on: September 5, 2011

The Efficacy of a Super-Resolution Reconstruction Radiomics Model Based on T2WI for Predicting Placenta Accreta

Yiwei Mou1, Changyi Guo2, Xirong Zhang1

  • 1Department of Medical Techniques, Shaanxi University of Chinese Medicine, Xianyang, 712000, China.

Current Medical Imaging
|July 16, 2026
PubMed
Summary

Super-resolution reconstruction (SRR) of T2-weighted MRI did not improve radiomics models for predicting placenta accreta spectrum (PAS) disorders. Enhanced image resolution did not add diagnostic value over conventional images for PAS prediction.

Keywords:
Deep learningMagnetic resonance imagingMulticenter studyPlacenta accreta spectrum disordersPredictive modelRadiomicsSuper-resolution reconstruction

More Related Videos

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks
09:33

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Published on: March 29, 2018

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators
09:51

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators

Published on: March 21, 2018

Related Experiment Videos

Last Updated: Jul 17, 2026

Accurate and Simple Evaluation of Vascular Anastomoses in Monochorionic Placenta using Colored Dye
09:52

Accurate and Simple Evaluation of Vascular Anastomoses in Monochorionic Placenta using Colored Dye

Published on: September 5, 2011

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks
09:33

Three-dimensional Rendering and Analysis of Immunolabeled, Clarified Human Placental Villous Vascular Networks

Published on: March 29, 2018

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators
09:51

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators

Published on: March 21, 2018

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence in Medicine

Background:

  • Placenta accreta spectrum (PAS) disorders pose significant risks to maternal and fetal health.
  • Accurate prediction of PAS is crucial for timely intervention and improved outcomes.

Purpose of the Study:

  • To evaluate if super-resolution reconstruction (SRR) of T2-weighted MRI enhances the diagnostic performance of radiomics models for PAS prediction.
  • To compare the efficacy of radiomics models using conventional versus super-resolution reconstructed images.

Main Methods:

  • Retrospective analysis of 603 suspected PAS cases across three centers.
  • Deep learning-based SRR generated 2× and 4× super-resolution T2-weighted images (T2WI).
  • Automated placenta segmentation using nnUNet, followed by radiomics feature extraction, selection (LASSO), and classifier development (KNN, AdaBoost, Gradient Boosting).

Main Results:

  • nnUNet segmentation achieved high Dice coefficients (0.863-0.883) on external validation sets.
  • The Gradient Boosting model on 4× SRR images showed the highest training AUC (0.874).
  • No statistically significant difference in diagnostic performance was found between conventional and SRR images across classifiers (P > 0.05); external validation AUCs were moderate (0.542-0.724).

Conclusions:

  • Super-resolution reconstruction (SRR) did not provide incremental diagnostic value for PAS prediction within the radiomics framework.
  • Radiomics models using SRR-enhanced T2WI were not superior to those using conventional images.
  • Routine SRR is not recommended for improving PAS prediction in this clinical context.