Radiomics model based on MR T2WI for prenatal diagnosis and classification of placenta accreta spectrum disorders

Share this content in WeChat

• Clinical Article •

ZOU Jinli HU Zhenyuan WANG Xinlian WANG Keyang WEI Wei XIE Lizhi LIANG Yuting

Cite this article as: 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 Imaging, 2024, 15(1): 137-144. DOI:10.12015/issn.1674-8034.2024.01.022.

Abstract

[Abstract] Objective To investigate the application value of radiomics model based on MR T2WI for prenatal predicting placenta accreta spectrum disorders (PAS) and determining the subtype of PAS.Materials and Methods The data of 193 pregnant women with singleton pregnancies who were hospitalized for delivery in Beijing Obstetrics and Gynecology Hospital from January 2018 to January 2023 were retrospectively analyzed, including 134 cases of PAS and 59 cases of non-PAS. All pregnant women were randomly divided into training set and test set in a 2∶1 ratio based on the total number of patients with the same subtype. The radiomics features were extracted from T2WI sequence, Pearson correlation coefficient and least absolute shrinkage and selection operator (LASSO) regression were used for feature screening, and the radiomics models for predicting PAS were constructed. Then, a radiomics scoring system for clinical application is constructed and trained to evaluate the subtypes of PAS, and univariate analysis and multivariate analysis are used to further analyze other potential clinical risk factors, including age, gestational age, previous gravidity, previous parity, the history of cesarean section, placental problems (placenta previa), and the history of uterine-related operations. Establish a nomogram based on the selection of clinical major risk factors. The receiver operating characteristic (ROC) curve was drawn to evaluate the predictive performance of the model, and DeLong test was used to compare the predictive efficiency of these models, the calibration curve is used to evaluate the degree of calibration of the prediction model, and the decision curve is used to evaluate the clinical value of the prediction model.Results 806 radiomics features were extracted from T2WI sequence, 147 radiomics features were retained after Pearson correlation analysis, and 10 radiomics features were screened out after LASSO regression processing, and a radiomics model that is applied to scoring was established. The area under the curve (AUC) value of the radiomics model in the training set was 0.933 (95% CI: 0.888-0.978), the accuracy was 88.37%, the sensitivity was 88.78%, the specificity was 87.10%, the positive predictive value (PPV) was 95.60%, and the negative predictive value (NPV) was 71.05%; the AUC value in the test set was 0.914 (95% CI: 0.835-0.993), the accuracy was 89.06%, the sensitivity was 90.91%, the specificity was 85.00%, the PPV was 90.00%, and the NPV was 80.95%. The calibration curve and decision curve showed that the model had high performance and potential clinical application value. The radiomics scoring model has a strong ability to identify placenta percreta, the accuracy of training set and test set reached 82.95% and 89.06%, the sensitivity and NPV reached 100.00% in training set and test set, and the specificity reached 81.35% and 88.33%, respectively. In addition, this study successfully constructed a clinical-radiomics model and draws a nomogram for visualizing PAS in patients. In the training set, the AUC of the clinical-imaging model was 0.969 (95% CI: 0.946-0.993), in the test set, the AUC value was 0.976 (95% CI: 0.947-1.000). DeLong test results showed that there were significant differences in the performance of the two models (P＜0.05), and the clinical-imaging model had better performance.Conclusions The clinical-radiomics model based on the clinical major risk factors and radiomics scoring system has a good performance, and can be used as a method to predict the presence of PAS before delivery. And the radiomics scoring system has a good ability to distinguish the subtype of PAS, especially the placenta percreta.

[Keywords] placental diseases；placenta accreta spectrum disorders；prenatal diagnosis；radiomics；magnetic resonance imaging

Contributor Information

ZOU Jinli¹ HU Zhenyuan² WANG Xinlian¹ WANG Keyang¹ WEI Wei² XIE Lizhi³ LIANG Yuting^1*

¹ Department of Radiology, Beijing Obstetrics and Gynecology Hospital, Capital Medical University/Beijing Maternal and Child Health Care Hospital, Beijing 100006, China

² School of Electronics and information, Xi'an Polytechnic University, Xi'an 710048, China

³ Beijing Magnetic Resonance Products Department, GE Medical Systems Trade & Development (Shanghai) Co., Ltd., Beijing 100176, China

Corresponding author: LIANG Y T, E-mail: liangyuting@ccmu.edu.cn

Conflicts of interest None.

Publication Information

Received 2023-07-24

Accepted 2023-12-08

DOI: 10.12015/issn.1674-8034.2024.01.022

Text

References

[1]

BROWN L A, MENENDEZ-BOBSEINE M. Placenta accreta spectrum[J]. J Midwifery Women's Heath, 2021, 66(2): 265-269. DOI: 10.1111/jmwh.13182.

[2]

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.

[3]

JAUNIAUX E, CHANTRAINE F, SILVER R M, et al. FIGO consensus guidelines on placenta accreta spectrum disorders: Epidemiology[J]. Int J Gynaecol Obstet, 2018, 140(3): 265-273. DOI: 10.1002/ijgo.12407.

[4]

JAUNIAUX E, AYRES-DE-CAMPOS D, LANGHOFF-ROOS J, et al. FIGO classification for the clinical diagnosis of placenta accreta spectrum disorders[J]. Int J Gynaecol Obstet, 2019, 146(1): 20-24. DOI: 10.1002/ijgo.12761.

[5]

ZHANG H J, DOU R C, YANG H X, et al. Maternal and neonatal outcomes of placenta increta and percreta from a multicenter study in China[J]. J Matern Fetal Neonatal Med, 2019, 32(16): 2622-2627. DOI: 10.1080/14767058.2018.1442429.

[6]

MARCELLIN L, DELORME P, BONNET M P, et al. Placenta percreta is associated with more frequent severe maternal morbidity than placenta accreta[J/OL]. Am J Obstet Gynecol, 2018, 219(2): 193.e1-193.e9 [2023-03-11]. https://linkinghub.elsevier.com/retrieve/pii/S0002-9378(18)30380-6. DOI: 10.1016/j.ajog.2018.04.049.

[7]

SILVER R M. Abnormal placentation: placenta previa, Vasa previa, and placenta accreta[J]. Obstet Gynecol, 2015, 126(3): 654-668. DOI: 10.1097/AOG.0000000000001005.

[8]

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.

[9]

EINERSON B D, GILNER J B, ZUCKERWISE L C. Placenta accreta spectrum[J]. Obstet Gynecol, 2023, 142(1): 31-50. DOI: 10.1097/AOG.0000000000005229.

[10]

MATSUO K, YOUSSEFZADEH A C, MANDELBAUM R S, et al. Hospital surgical volume-outcome relationship in Caesarean hysterectomy for placenta accreta spectrum[J]. BJOG, 2022, 129(6): 986-993. DOI: 10.1111/1471-0528.16993.

[11]

FRATELLI N, PREFUMO F, MAGGI C, et al. Third-trimester ultrasound for antenatal diagnosis of placenta accreta spectrum in women with placenta previa: results from the ADoPAD study[J]. Ultrasound Obstet Gynecol, 2022, 60(3): 381-389. DOI: 10.1002/uog.24889.

[12]

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 [2023-03-11]. https://d.wanfangdata.com.cn/periodical/zhfylcyxzz202002007. DOI: 10.3877/cma.j.issn.1673-5250.2020.02.007.

[13]

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.

[14]

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.

[15]

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.

[16]

XUAN R R, LI T, WANG Y T, et al. Prenatal prediction and typing of placental invasion using MRI deep and radiomic features[J/OL]. Biomed Eng Online, 2021, 20(1): 56 [2023-01-07]. https://doi.org/10.1186/s12938-021-00893-5. DOI: 10.1186/s12938-021-00893-5.

[17]

ZHAO Y Y, WANG Y, CHEN L. Perioperative management of placenta accreta[J]. Chin J Obstet Gynecol, 2018, 53(11): 787-789. DOI: 10.3760/cma.j.issn.0529-567x.2018.11.014.

[18]

SCHWICKERT A, VAN BEEKHUIZEN H J, BERTHOLDT C, et al. Association of peripartum management and high maternal blood loss at cesarean delivery for placenta accreta spectrum (PAS): a multinational database study[J]. Acta Obstet Gynecol Scand, 2021, 100(Suppl 1): 29-40. DOI: 10.1111/aogs.14103.

[19]

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.

[20]

WANG F, XIA Y W, CHAI X F, et al. Analysis process and clinical application of radiomics[J]. Chin J Anat Clin, 2021, 26(2): 236-241. DOI: 10.3760/cma.j.cn101202-20200701-00200.

[21]

GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.

[22]

ZHU H, YIN X, WANG H J, et al. A computerized diagnostic model for automatically evaluating placenta accrete spectrum disorders based on the combined MR radiomics-clinical signatures[J/OL]. Sci Rep, 2022, 12(1): 10130 [2023-02-19]. https://www.nature.com/articles/s41598-022-14454-w. DOI: 10.1038/s41598-022-14454-w.

[23]

CHEN E, MAR W A, HOROWITZ J M, et al. Texture analysis of placental MRI: can it aid in the prenatal diagnosis of placenta accreta spectrum?[J]. Abdom Radiol, 2019, 44(9): 3175-3184. DOI: 10.1007/s00261-019-02104-1.

[24]

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.

[25]

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.

[26]

SILVER R M, BRANCH D W. Placenta accreta spectrum[J]. N Engl J Med, 2018, 378(16): 1529-1536. DOI: 10.1056/NEJMcp1709324.

[27]

HESSAMI K, SALMANIAN B, EINERSON B D, et al. Clinical correlates of placenta accreta spectrum disorder depending on the presence or absence of placenta previa: a systematic review and meta-analysis[J]. Obstet Gynecol, 2022, 140(4): 599-606. DOI: 10.1097/AOG.0000000000004923.

[28]

BHIDE A. Routine screening for placenta accreta spectrum[J/OL]. Best Pract Res Clin Obstet Gynaecol, 2023, 90: 102392 [2023-07-23]. https://pubmed.ncbi.nlm.nih.gov/37541113/. DOI: 10.1016/j.bpobgyn.2023.102392.

[29]

ZHENG W R, YANG X R, YAN J, et al. Review on placenta accreta spectrum based on international guidelines[J]. Chin J Perinat Med, 2020, 23(12): 843-848. DOI: 10.3760/cma.j.cn113903-20200726-00700.

[30]

CELLINA M, PIROVANO M, CIOCCA M, et al. Radiomic analysis of the optic nerve at the first episode of acute optic neuritis: an indicator of optic nerve pathology and a predictor of visual recovery?[J]. Radiol Med, 2021, 126(5): 698-706. DOI: 10.1007/s11547-020-01318-4.

[31]

KOLOSSVÁRY M, GERSTENBLITH G, BLUEMKE D A, et al. Contribution of risk factors to the development of coronary atherosclerosis as confirmed via coronary CT angiography: a longitudinal radiomics-based study[J]. Radiology, 2021, 299(1): 97-106. DOI: 10.1148/radiol.2021203179.

[32]

SUAREZ-IBARROLA R, HEIN S, REIS G, et al. Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer[J]. World J Urol, 2020, 38(10): 2329-2347. DOI: 10.1007/s00345-019-03000-5.

[33]

DO Q N, LEWIS M A, MADHURANTHAKAM A J, et al. Texture analysis of magnetic resonance images of the human placenta throughout gestation: a feasibility study[J/OL]. PLoS One, 2019, 14(1): e0211060 [2022-11-09]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0211060. DOI: 10.1371/journal.pone.0211060.

[34]

SUN H Q, QU H B, CHEN L, et al. Identification of suspicious invasive placentation based on clinical MRI data using textural features and automated machine learning[J]. Eur Radiol, 2019, 29(11): 6152-6162. DOI: 10.1007/s00330-019-06372-9.

[35]

NAM D, CHAPIRO J, PARADIS V, et al. Artificial intelligence in liver diseases: improving diagnostics, prognostics and response prediction[J/OL]. JHEP Rep, 2022, 4(4): 100443 [2023-02-19]. https://www.jhep-reports.eu/article/S2589-5559(22)00015-5/fulltext. DOI: 10.1016/j.jhepr.2022.100443.

[36]

NAZARI M, SHIRI I, ZAIDI H. Radiomics-based machine learning model to predict risk of death within 5-years in clear cell renal cell carcinoma patients[J]. Comput Biol Med, 2021, 129: 104135 [2022-11-09]. http://www.elsevier.com/locate/compbiomed. DOI: 10.1016/j.compbiomed.2020.104135.

[37]

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.

PREV The value of APT imaging in evaluating the therapeutic efficacy of concurrent chemoradiotherapy for cervical cancer

NEXT Quantitative assessment of skeletal muscle fat content in type 2 diabetic patients by magnetic resonance multi-echo DIXON technique

LINK

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