Share：
Share this content in WeChat
X
[Chinese][PDF]291
• Clinical Article •
MR radiomics nomogram for prenatal diagnosis of placenta accreta diseases and prediction of adverse clinical outcomes
ZUO Mengzhe  WANG Qin  CHU Qian  XU Mengqin  PAN Ting  ZHANG Chunlei 

Cite this article as: ZUO M Z, WANG Q, CHU Q, et al. MR radiomics nomogram for prenatal diagnosis of placenta accreta diseases and prediction of adverse clinical outcomes[J]. Chin J Magn Reson Imaging, 2025, 16(6): 100-109. DOI:10.12015/issn.1674-8034.2025.06.015.


[Abstract] Objective To explore the value of a nomogram constructed based on placental MR radiomics features, MR imaging sign scores, and clinical indicators in the prenatal diagnosis of placenta accreta spectrum disorder (PAS) and the risk assessment of adverse clinical outcomes.Materials and Methods A total of 167 pregnant women with clinically suspected PAS were prospectively included and underwent prenatal placental MR examination and delivered in the First People' Hospital of Kunshan. The clinical and imaging data of the patients were obtained, including 89 cases of PAS and 78 cases of non-PAS. They were stratified and randomly divided into a training set (119 cases) and a validation set (48 cases) in a ratio of 7∶3. The subjective signs of MR were analyzed and scored by referring to the scoring scale in previous studies. Radiomics features were extracted from two T2WI sequences of placental MR. The Least Absolute Shrinkage and Selection Operator was used for feature screening and constructing a radiomics model to predict PAS, generating a radiomics score (Radscore). Logistic regression analysis was applied to the clinical indicators, MR imaging sign scores, and Radscore of training set to establish different joint models for PAS prediction. Bootstrap methods were used for internal testing of all models, and the validation set was used for verification. The predictive performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC) and clinical decision curves. The optimal model was visualized as a nomogram, yielding a nomogram predicted value. The predictive value of the nomogram for PAS and adverse clinical outcomes was assessed.Results Among all models, the joint prediction model constructed based on abortion history, MR imaging sign scores, and Radscore demonstrated the highest diagnostic value for PAS. The training and validation sets achieved AUC values of 0.857 [95% confidence interval (CI): 0.791 to 0.923] and 0.848 (95% CI: 0.740 to 0.956), respectively, outperforming the MR imaging sign score, clinical model, clinical-MR sign model, and radiomics model. The differences in the training set were statistically significant (Z values were 2.764, 3.218, 2.470, and 2.213, respectively; all P values < 0.05), with higher clinical net benefits than other models. The nomogram predicted value generated by the model exhibited strong discriminative ability for placenta accreta vs. placenta increta (PI) and PI vs. placenta percreta, with AUCs of 0.837 (95% CI: 0.769 to 0.905) and 0.879 (95% CI: 0.807 to 0.951), respectively. It also showed high predictive value for adverse clinical outcomes (AUC: 0.822, 95% CI: 0.753 to 0.891).Conclusions The nomogram integrating placental MR radiomics features, MR imaging sign scores, and abortion history holds significant clinical value for prenatal diagnosis, subtype classification, and risk assessment of adverse outcomes in PAS.
[Keywords] placenta accreta spectrum disorders；magnetic resonance imaging；radiomics；nomogram；adverse clinical outcomes

ZUO Mengzhe1, 2   WANG Qin3   CHU Qian3   XU Mengqin1   PAN Ting1   ZHANG Chunlei2*  

1 Department of Radiology, The First People's Hospital of Kunshan, Kunshan 215300, China

2 Department of Radiology, Maternal and Child Health Care Hospital of Kunshan, Kunshan 215300, China

3 Department of Obstetrics, Maternal and Child Health Care Hospital of Kunshan, Kunshan 215300, China

Corresponding author: ZHANG C L, E-mail: 15862368856@163.com

Conflicts of interest   None.

Received  2025-02-28
Accepted  2025-06-05
DOI: 10.12015/issn.1674-8034.2025.06.015
Cite this article as: ZUO M Z, WANG Q, CHU Q, et al. MR radiomics nomogram for prenatal diagnosis of placenta accreta diseases and prediction of adverse clinical outcomes[J]. Chin J Magn Reson Imaging, 2025, 16(6): 100-109. DOI:10.12015/issn.1674-8034.2025.06.015.

[1]
JAUNIAUX E, BHIDE A, KENNEDY A, et al. FIGO consensus guidelines on placenta accreta spectrum disorders: Prenatal diagnosis and screening[J]. Int J Gynaecol Obstet, 2018, 140(3): 274-280. DOI: 10.1002/ijgo.12408.
[2]
HOBSON S R, KINGDOM J C, MURJI A, et al. No. 383-screening, diagnosis, and management of placenta accreta spectrum disorders[J]. J Obstet Gynaecol Can, 2019, 41(7): 1035-1049. DOI: 10.1016/j.jogc.2018.12.004.
[3]
SHAMSHIRSAZ A A, FOX K A, SALMANIAN B, et al. Maternal morbidity in patients with morbidly adherent placenta treated with and without a standardized multidisciplinary approach[J/OL]. Am J Obstet Gynecol, 2015, 212(2): 218.e1-218.e9 [2025-03-02]. https://pubmed.ncbi.nlm.nih.gov/25173187/. DOI: 10.1016/j.ajog.2014.08.019.
[4]
JHA P, PŌDER L, BOURGIOTI C, et al. Society of Abdominal Radiology (SAR) and European Society of Urogenital Radiology (ESUR) joint consensus statement for MR imaging of placenta accreta spectrum disorders[J]. Eur Radiol, 2020, 30(5): 2604-2615. DOI: 10.1007/s00330-019-06617-7.
[5]
ELLER A G, BENNETT M A, SHARSHINER M, et al. Maternal morbidity in cases of placenta accreta managed by a multidisciplinary care team compared with standard obstetric care[J]. Obstet Gynecol, 2011, 117(2Pt 1): 331-337. DOI: 10.1097/AOG.0b013e3182051db2.
[6]
CHEN S W, LI Q S, ZHANG J T, et al. Color Doppler ultrasound, magnetic resonance imaging and their combination in placenta increta[J]. Chin Journalof Ultrasound Med, 2010, 26(12): 1116-1118. DOI: 10.3969/j.issn.1002-0101.2010.12.023.
[7]
JAUNIAUX E, COLLINS S, BURTON G J. Placenta accreta spectrum: pathophysiology and evidence-based anatomy for prenatal ultrasound imaging[J]. Am J Obstet Gynecol, 2018, 218(1): 75-87. DOI: 10.1016/j.ajog.2017.05.067.
[8]
BOWMAN Z S, ELLER A G, KENNEDY A M, et al. Accuracy of ultrasound for the prediction of placenta accreta[J/OL]. Am J Obstet Gynecol, 2014, 211(2): 177.e1-177.e7 [2025-03-02]. https://pubmed.ncbi.nlm.nih.gov/24631709/. DOI: 10.1016/j.ajog.2014.03.029.
[9]
KAPOOR H, HANAOKA M, DAWKINS A, et al. Review of MRI imaging for placenta accreta spectrum: Pathophysiologic insights, imaging signs, and recent developments[J]. Placenta, 2021, 104: 31-39. DOI: 10.1016/j.placenta.2020.11.004.
[10]
DO Q N, LEWIS M A, XI Y, et al. MRI of the placenta accreta spectrum (PAS) disorder: radiomics analysis correlates with surgical and pathological outcome[J]. J Magn Reson Imaging, 2020, 51(3): 936-946. DOI: 10.1002/jmri.26883.
[11]
LIU Q Y, ZHOU W M, YAN Z M, et al. Development and validation of MRI-based scoring models for predicting placental invasiveness in high-risk women for placenta accreta spectrum[J]. Eur Radiol, 2024, 34(2): 957-969. DOI: 10.1007/s00330-023-10058-8.
[12]
ZHU X M, ZOU L, LIU P, et al. Clinical value of MRI-based scoring system in predicting placenta accreta spectrum disorders[J]. Chin J Magn Reson Imag, 2021, 12(11): 37-41. DOI: 10.12015/issn.1674-8034.2021.11.008.
[13]
BAO Y W, PANG Y, SUN Z Y, et al. Functional diagnosis of placenta accreta by intravoxel incoherent motion model diffusion-weighted imaging[J]. Eur Radiol, 2021, 31(2): 740-748. DOI: 10.1007/s00330-020-07200-1.
[14]
GUIOT J, VAIDYANATHAN A, DEPREZ L, et al. A review in radiomics: Making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-440. DOI: 10.1002/med.21846.
[15]
BARTELS H C, O'DOHERTY J, WOLSZTYNSKI E, et al. Correction: Radiomics-based prediction of FIGO grade for placenta accreta spectrum[J/OL]. Eur Radiol Exp, 2023, 7(1): 73 [2025-02-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10665277/. DOI: 10.1186/s41747-023-00397-y.
[16]
PENG L L, ZHANG X, LIU J, et al. MRI-radiomics-clinical-based nomogram for prenatal prediction of the placenta accreta spectrum disorders[J]. Eur Radiol, 2022, 32(11): 7532-7543. DOI: 10.1007/s00330-022-08821-4.
[17]
WU Q X, YAO K, LIU Z Y, et al. Radiomics analysis of placenta on T2WI facilitates prediction of postpartum haemorrhage: a multicentre study[J]. EBioMedicine, 2019, 50: 355-365. DOI: 10.1016/j.ebiom.2019.11.010.
[18]
WANG Y C, HUANG G, BA Z X, et al. A preliminary study on diagnostic model of placenta implantation based on magnetic resonance image feature machine learning[J]. Chin J Magn Reson Imag, 2023, 14(8): 94-99, 107. DOI: 10.12015/issn.1674-8034.2023.08.015.
[19]
SHAZLY S A, HORTU I, SHIH J C, et al. Prediction of clinical outcomes in women with placenta accreta spectrum using machine learning models: an international multicenter study[J]. J Matern Fetal Neonatal Med, 2022, 35(25): 6644-6653. DOI: 10.1080/14767058.2021.1918670.
[20]
AL-KHAN A, GUPTA V, ILLSLEY N P, et al. Maternal and fetal outcomes in placenta accreta after institution of team-managed care[J]. Reprod Sci, 2014, 21(6): 761-771. DOI: 10.1177/1933719113512528.
[21]
WANG X, ZHAO F M, LI Y Q, et al. Interpretation of society of abdominal radiology and European society of urogenital radiology joint consensus statement for MR imaging of placenta accreta spectrum disorders[J/OL]. Chin J Obstet Gynecol Pediatr Electron Ed, 2020, 16(2): 161-170 [2025-02-18]. https://zhfylcyxzz.cma-cmc.com.cn/CN/10.3877/cma.j.issn.1673-5250.2020.02.007. DOI: 10.3877/cma.j.issn.1673-5250.2020.02.007.
[22]
WEI W, WANG K, LIU Z Y, et al. Radiomic signature: a novel magnetic resonance imaging-based prognostic biomarker in patients with skull base chordoma[J]. Radiother Oncol, 2019, 141: 239-246. DOI: 10.1016/j.radonc.2019.10.002.
[23]
MA H, LIN J J, DAI L H, et al. The predictive value of MRI diagnostic rating scale for placenta previa with placenta implantation in clinical application[J]. J Clin Radiol, 2023, 42(1): 96-101. DOI: 10.13437/j.cnki.jcr.2023.01.029.
[24]
SRISAJJAKUL S, PRAPAISILP P, BANGCHOKDEE S. Magnetic resonance imaging of placenta accreta spectrum: a step-by-step approach[J]. Korean J Radiol, 2021, 22(2): 198-212. DOI: 10.3348/kjr.2020.0580.
[25]
FAMILIARI A, LIBERATI M, LIM P, et al. Diagnostic accuracy of magnetic resonance imaging in detecting the severity of abnormal invasive placenta: A systematic review and meta-analysis[J]. Acta Obstet Gynecol Scand, 2018, 97(5): 507-520. DOI: 10.1111/aogs.13258.
[26]
PATEL-LIPPMANN K K, PLANZ V B, PHILLIPS C H, et al. Placenta accreta spectrum disorders: update and pictorial review of the SAR-ESUR joint consensus statement for MRI[J/OL]. Radiographics, 2023, 43(5): e220090 [2025-02-18]. https://pubmed.ncbi.nlm.nih.gov/37079459. DOI: 10.1148/rg.220090.
[27]
MAHALINGAM H V, RANGASAMI R, PREMKUMAR J, et al. Placenta accreta scoring system (PASS)-assessment of a simplified clinico-radiological scoring system for antenatal diagnosis of placenta accreta[J/OL]. Egypt J Radiol Nucl Med, 2021, 52(1): 42 [2025-02-18]. https://ejrnm.springeropen.com/articles/10.1186/s43055-021-00427-y. DOI: 10.1186/s43055-021-00427-y.
[28]
XIA J F, HU Y R, HUANG Z H, et al. A novel MRI-based diagnostic model for predicting placenta accreta spectrum[J]. Magn Reson Imaging, 2024, 109: 34-41. DOI: 10.1016/j.mri.2024.02.014.
[29]
ROMEO V, RICCIARDI C, CUOCOLO R, et al. Machine learning analysis of MRI-derived texture features to predict placenta accreta spectrum in patients with placenta previa[J]. Magn Reson Imaging, 2019, 64: 71-76. DOI: 10.1016/j.mri.2019.05.017.
[30]
ZOU J L, HU Z Y, WANG X L, et al. Radiomics model based on MR T2WI for prenatal diagnosis and classification of placenta accreta spectrum disorders[J]. Chin J Magn Reson Imag, 2024, 15(1): 137-144. DOI: 10.12015/issn.1674-8034.2024.01.022.
[31]
REN H N, MORI N, MUGIKURA S, et al. Prediction of placenta accreta spectrum using texture analysis on coronal and sagittal T2-weighted imaging[J]. Abdom Radiol (NY), 2021, 46(11): 5344-5352. DOI: 10.1007/s00261-021-03226-1.
[32]
CHEN J H, CEN X Y, MO K. Study on the value of two fast imaging sequences of MR in the diagnosis of placenta previa with placenta implantation in the third trimester of pregnancy[J]. J Imag Res Med Appl, 2019, 3(19): 96-97.
[33]
PIZZI A D, TAVOLETTA A, NARCISO R, et al. Prenatal planning of placenta previa: diagnostic accuracy of a novel MRI-based prediction model for placenta accreta spectrum (PAS) and clinical outcome[J]. Abdom Radiol (NY), 2019, 44(5): 1873-1882. DOI: 10.1007/s00261-018-1882-8.
[34]
YAN X L, HUANG G, YAN P, et al. Nomogram of ultrasound scoring system combined with clinical features for predicting postpartum hemorrhage in patients with pernicious placenta previa[J]. Chin J Med Imag Technol, 2024, 40(3): 401-406. DOI: 10.13929/j.issn.1003-3289.2024.03.017.
[35]
BOURGIOTI C, ZAFEIROPOULOU K, FOTOPOULOS S, et al. MRI prognosticators for adverse maternal and neonatal clinical outcome in patients at high risk for placenta accreta spectrum (PAS) disorders[J]. J Magn Reson Imaging, 2019, 50(2): 602-618. DOI: 10.1002/jmri.26592.

PREV Predictive value of quantitative parameters from DCE-MRI histogram combined with ADC value for chemoradiotherapy efficacy in locally advanced cervical cancer
NEXT Study on the evaluation of cervical medullary compression and activity in craniovertebral junction malformation used dynamic flexion-extension cervical spine MRI
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn