Texture analysis of magnetic resonance images of the human placenta throughout gestation: A feasibility study

As fetal gestational age increases, other modalities such as ultrasound have demonstrated increased levels of heterogeneity in the normal placenta. In this study, we introduce and apply ROI-based texture analysis to a retrospective fetal MRI database to characterize the second-order statistics of placenta and to evaluate the relationship between heterogeneity and gestational age. Positive correlations were observed for several Haralick texture metrics derived from fetal-brain specific T2-weighted and gravid uterus T1-weighted and T2-weighted images, confirming a quantitative increase in placental heterogeneity with gestational age. Our study shows the importance of identifying baseline MR textural changes at certain gestational ages from which placental diseased states may be compared. Specifically, when evaluating for placental invasion or insufficiency, findings should be evaluated in the context of the normal placental aging process, which occurs throughout gestation.

[1]  K. Thornburg,et al.  Placental programming of chronic diseases, cancer and lifespan: a review. , 2013, Placenta.

[2]  Moriah E Thomason,et al.  Fetal Magnetic Resonance Imaging at 3.0 T , 2011, Topics in magnetic resonance imaging : TMRI.

[3]  Thomas R. Knösche,et al.  White matter integrity, fiber count, and other fallacies: The do's and don'ts of diffusion MRI , 2013, NeuroImage.

[4]  K. Hopper,et al.  A reevaluation of placental grading and its clinical significance. , 1984, Journal of ultrasound in medicine.

[5]  J. W. Emerson,et al.  Estimated Placental Volume and Gestational Age , 2017, American Journal of Perinatology.

[6]  Marco Rovaris,et al.  DTI Parameter Optimisation for Acquisition at 1.5T: SNR Analysis and Clinical Application , 2010, Comput. Intell. Neurosci..

[7]  Derek K. Jones,et al.  “Squashing peanuts and smashing pumpkins”: How noise distorts diffusion‐weighted MR data , 2004, Magnetic resonance in medicine.

[8]  G. Parker,et al.  Magnetic resonance imaging relaxation time measurements of the placenta at 1.5 T. , 2011, Placenta.

[9]  R L Berkowitz,et al.  The ultrasonic changes in the maturing placenta and their relation to fetal pulmonic maturity. , 1979, American journal of obstetrics and gynecology.

[10]  A. Zwanenburg,et al.  EP-1677: Multicentre initiative for standardisation of image biomarkers , 2017 .

[11]  Christakis Constantinides Assessment of Cellular and Organ Function and Dysfunction using Direct and Derived MRI Methodologies , 2016 .

[12]  Martin O. Leach,et al.  Rapid development of image analysis research tools: Bridging the gap between researcher and clinician with pyOsiriX , 2016, Comput. Biol. Medicine.

[13]  J. Leyendecker,et al.  Placental evaluation with magnetic resonance. , 2013, Radiologic clinics of North America.

[14]  Ann M. Johnson,et al.  Comparison Between 1.5-T and 3-T MRI for Fetal Imaging: Is There an Advantage to Imaging With a Higher Field Strength? , 2016, AJR. American journal of roentgenology.

[15]  A. Sørensen,et al.  Placental magnetic resonance imaging T2* measurements in normal pregnancies and in those complicated by fetal growth restriction , 2015, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[16]  Andrés Larroza,et al.  Texture Analysis in Magnetic Resonance Imaging: Review and Considerations for Future Applications , 2016 .

[17]  C. Limperopoulos,et al.  In vivo placental MRI shape and textural features predict fetal growth restriction and postnatal outcome , 2018, Journal of magnetic resonance imaging : JMRI.

[18]  Tone F. Bathen,et al.  T2-weighted MRI-derived textural features reflect prostate cancer aggressiveness: preliminary results , 2017, European Radiology.

[19]  C. Pattichis,et al.  Brain MR image normalization in texture analysis of multiple sclerosis , 2009 .

[20]  A Messerschmidt,et al.  Placental pathologies in fetal MRI with pathohistological correlation. , 2009, Placenta.

[21]  H. Hricak,et al.  Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores , 2015, European Radiology.

[22]  D. Twickler,et al.  Ultrasound predictors of placental invasion: the Placenta Accreta Index. , 2015, American journal of obstetrics and gynecology.

[23]  Valeria Vinci,et al.  MRI and DWI: feasibility of DWI and ADC maps in the evaluation of placental changes during gestation , 2010, Prenatal diagnosis.

[24]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[25]  Scott Lakin Jones,et al.  To Be Human , 2011 .

[26]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[27]  C. Catalano,et al.  Diffusion and perfusion quantified by Magnetic Resonance Imaging are markers of human placenta development in normal pregnancy. , 2017, Placenta.

[28]  Oscar Acosta,et al.  Haralick textural features on T2‐weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer , 2017, Journal of magnetic resonance imaging : JMRI.

[29]  D. Twickler,et al.  MR imaging quantitative analysis of fetal chiari II malformations and associated open neural tube defects: Balanced SSFP versus half‐fourier RARE and interobserver reliability , 2013, Journal of magnetic resonance imaging : JMRI.

[30]  C. Baker,et al.  First- and second-order information in natural images: a filter-based approach to image statistics. , 2004, Journal of the Optical Society of America. A, Optics, image science, and vision.

[31]  F. Cendes,et al.  Texture analysis of medical images. , 2004, Clinical radiology.

[32]  A. Guttmacher,et al.  The Human Placenta Project: placental structure, development, and function in real time. , 2014, Placenta.

[33]  Luis Pedro Coelho,et al.  Mahotas: Open source software for scriptable computer vision , 2012, ArXiv.

[34]  C. Liang,et al.  Malignancy characterization of hepatocellular carcinomas based on texture analysis of contrast‐enhanced MR images , 2017, Journal of magnetic resonance imaging : JMRI.

[35]  Jorge Delgado,et al.  Fetal magnetic resonance imaging: jumping from 1.5 to 3 tesla (preliminary experience) , 2014, Pediatric Radiology.

[36]  Tai-Lang Jong,et al.  Evaluation of placental maturity by the sonographic textures , 2011, Archives of Gynecology and Obstetrics.

[37]  G. Rattá,et al.  Automatic Quantitative MRI Texture Analysis in Small-for-Gestational-Age Fetuses Discriminates Abnormal Neonatal Neurobehavior , 2013, PloS one.

[38]  Diane M Twickler,et al.  Fetal central nervous system ventricle and cisterna magna measurements by magnetic resonance imaging. , 2001, American journal of obstetrics and gynecology.

[39]  D. Twickler,et al.  Placenta Accreta and Vaginal Bleeding According to Gestational Age at Delivery , 2015, Obstetrics and gynecology.

[40]  Henry Rusinek,et al.  Textural differences in apparent diffusion coefficient between low- and high-stage clear cell renal cell carcinoma. , 2014, AJR. American journal of roentgenology.