Ultrasound placental image texture analysis using artificial intelligence to predict hypertension in pregnancy

Abstract Background The placental pathological changes in hypertensive disorders of pregnancy (HDP) starts early in pregnancy, the deep convolutional neural networks (CNN) can identify these changes before its clinical manifestation. Objective To compare the placental quantitative ultrasound image texture of women with HDP to those with the normal outcome. Methods The cases were enrolled in the first trimester of pregnancy, good quality images of the placenta were taken serially in the first, second, and third trimester of pregnancy. The women were followed till delivery, those with normal outcomes were controls, and those with HDP were cases. The images were processed and classified using validated deep learning tools. Results Total of 429 cases were fully followed till delivery, 58 of them had HDP (13.5%). In the first trimester, there was a significant difference in the placental length (p = .033), uterine artery PI (p = .019), biomarkers PAPP-A (p = .001) PlGF (p = .013) and placental image texture (p = .001) between the cases and controls. In the second trimester the uterine artery PI, serum PAPP-A (p = .010) and PlGF (p = .005) levels were significantly low among women who developed hypertension later on pregnancy. The image texture disparity between the two groups was highly significant (p < .001). The model “resnext 101_32x8d” had Cohen kappa score of 0.413 (moderate) and the accuracy score of 0.710 (good). In the first trimester the best sensitivity and specificity was observed for abnormal placental image texture (70.6% and 76.6%, respectively) followed by PlGF (64% and 50%, respectively), in the second trimester the abnormal image texture had the highest sensitivity and specificity (60.4% and 73.3%, respectively) followed by uterine artery PI (58.6% and 54.7%, respectively). Similarly in the third trimester, uterine artery PI had sensitivity and specificity of 60.3% and specificity of 50.7%, whereas the abnormal image texture had sensitivity and specificity of 83.5%. Conclusion Ultrasound placental analysis using artificial intelligence (UPAAI) is a promising technique, would open avenues for more research in this field.

[1]  Madhusudan Upadya,et al.  Hypertensive disorders in pregnancy , 2018, Indian journal of anaesthesia.

[2]  A. Singh,et al.  Use of first‐trimester placenta growth factor concentration to predict hypertensive disorders of pregnancy in a low‐risk Asian population , 2017, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[3]  S. Cicero,et al.  ASPRE trial: performance of screening for preterm pre‐eclampsia , 2017, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[4]  M. Oelze.  Emerging quantitative ultrasound applications: From diagnosing disease to monitoring of therapy , 2016 .

[5]  Ritu Singh,et al.  Role of maternal factors, PAPP-A, and Doppler in screening for early- and late-onset pregnancy hypertension in Asian population , 2016, Hypertension in pregnancy.

[6]  Ritu Singh,et al.  Early prediction of hypertension during pregnancy in a low‐resource setting , 2016, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[7]  Y. Teng,et al.  Pulsatility index in combination with biomarkers or mean arterial pressure for the prediction of pre-eclampsia: Systematic literature review and meta-analysis , 2015, Annals of medicine.

[8]  E. Gratacós,et al.  Correlation of quantitative texture analysis of cranial ultrasound with later neurobehavior in preterm infants. , 2014, Ultrasound in medicine & biology.

[9]  Jing Li,et al.  A Risk Prediction Model for the Assessment and Triage of Women with Hypertensive Disorders of Pregnancy in Low-Resourced Settings: The miniPIERS (Pre-eclampsia Integrated Estimate of RiSk) Multi-country Prospective Cohort Study , 2014, PLoS medicine.

[10]  M. McHugh.  Interrater reliability: the kappa statistic , 2012, Biochemia medica.

[11]  Ivan Amat-Roldan,et al.  Feasibility and Reproducibility of Fetal Lung Texture Analysis by Automatic Quantitative Ultrasound Analysis and Correlation with Gestational Age , 2012, Fetal Diagnosis and Therapy.

[12]  K. Joseph,et al.  Epidemiology of pre-eclampsia and the other hypertensive disorders of pregnancy. , 2011, Best practice & research. Clinical obstetrics & gynaecology.

[13]  J W Hunt,et al.  Monitoring structural changes in cells with high-frequency ultrasound signal statistics. , 2005, Ultrasound in medicine & biology.

[14]  Constantinos S. Pattichis,et al.  Texture-based classification of atherosclerotic carotid plaques , 2003, IEEE Transactions on Medical Imaging.

[15]  Ruey-Feng Chang,et al.  Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. , 2002, Ultrasound in medicine & biology.

[16]  D. Vince,et al.  Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images. , 2000, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[17]  S Swarnamani,et al.  Application of artificial neural networks for the classification of liver lesions by image texture parameters. , 1996, Ultrasound in medicine & biology.

[18]  J M Thijssen,et al.  Texture of B-mode echograms: 3-D simulations and experiments of the effects of diffraction and scatterer density. , 1985, Ultrasonic imaging.

[19]  R. Filly,et al.  Placental thickness. , 1985, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.