Segmentation methods applied to MRI-derived radiomic analysis for the prediction of placenta accreta spectrum in patients with placenta previa.
Machine learning
Magnetic Resonance Imaging
Placenta Accreta Spectrum
Placenta previa
Radiomics
Segmentation
Journal
Abdominal radiology (New York)
ISSN: 2366-0058
Titre abrégé: Abdom Radiol (NY)
Pays: United States
ID NLM: 101674571
Informations de publication
Date de publication:
10 2023
10 2023
Historique:
received:
15
01
2023
accepted:
16
05
2023
revised:
15
05
2023
medline:
7
9
2023
pubmed:
13
7
2023
entrez:
13
7
2023
Statut:
ppublish
Résumé
To retrospectively evaluate the performance of different manual segmentation methods of placenta MR images for predicting Placenta Accreta Spectrum (PAS) disorders in patients with placenta previa (PP) using a Machine Learning (ML) Radiomics analysis. 64 patients (n=41 with PAS and n= 23 without PAS) with PP who underwent MRI examination for suspicion of PAS were retrospectively selected. All MRI examinations were acquired on a 1.5 T using T2-weighted (T2w) sequences on axial, sagittal and coronal planes. Ten different manual segmentation methods were performed on sagittal placental T2-weighted images obtaining five sets of 2D regions of interest (ROIs) and five sets of 3D volumes of interest (VOIs) from each patient. In detail, ROIs and VOIs were positioned on the following areas: placental tissue, retroplacental myometrium, cervix, placenta with underneath myometrium, placenta with underneath myometrium and cervix. For feature stability testing, the same process was repeated on 30 randomly selected placental MRI examinations by two additional radiologists, working independently and blinded to the original segmentation. Radiomic features were extracted from all available ROIs and VOIs. 100 iterations of 5-fold cross-validation with nested feature selection, based on recursive feature elimination, were subsequently run on each ROI/VOI to identify the best-performing method to classify instances correctly. Among the segmentation methods, the best performance in predicting PAS was obtained by the VOIs covering the retroplacental myometrium (Mean validation score: 0.761, standard deviation: 0.116). Our preliminary results show that the VOI including the retroplacental myometrium using T2w images seems to be the best method when segmenting images for the development of ML radiomics predictive models to identify PAS in patients with PP.
Identifiants
pubmed: 37439841
doi: 10.1007/s00261-023-03963-5
pii: 10.1007/s00261-023-03963-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3207-3215Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Références
R.M. Silver, K.D. Barbour, Placenta Accreta Spectrum, Obstet. Gynecol. Clin. North Am. 42 (2015) 381–402. https://doi.org/ https://doi.org/10.1016/j.ogc.2015.01.014 .
doi: 10.1016/j.ogc.2015.01.014
pubmed: 26002174
E. Jauniaux, F. Chantraine, R.M. Silver, J. Langhoff-Roos, FIGO consensus guidelines on placenta accreta spectrum disorders: Epidemiology, Int. J. Gynecol. Obstet. 140 (2018) 265–273. https://doi.org/ https://doi.org/10.1002/ijgo.12407 .
doi: 10.1002/ijgo.12407
E. Jauniaux, D. Ayres‐de‐Campos, J. Langhoff‐Roos, K.A. Fox, S. Collins, G. Duncombe, P. Klaritsch, F. Chantraine, J. Kingdom, L. Grønbeck, K. Rull, M. Tikkanen, L. Sentilhes, T. Asatiani, W. Leung, T. AIhaidari, D. Brennan, M. Seoud, A.M. Hussein, R. Jegasothy, K.N. Shah, D. Bomba‐Opon, C. Hubinont, P. Soma‐Pillay, N.T. Mandić, P. Lindqvist, B. Arnadottir, I. Hoesli, R. Cortez, FIGO classification for the clinical diagnosis of placenta accreta spectrum disorders, Int. J. Gynecol. Obstet. 146 (2019) 20–24, doi: https://doi.org/10.1002/ijgo.12761 .
J.L. Hecht, R. Baergen, L.M. Ernst, P.J. Katzman, S.M. Jacques, E. Jauniaux, T.Y. Khong, L.A. Metlay, L. Poder, F. Qureshi, J.T. Rabban, D.J. Roberts, S. Shainker, D.S. Heller, Classification and reporting guidelines for the pathology diagnosis of placenta accreta spectrum (PAS) disorders: recommendations from an expert panel, Mod. Pathol. (2020). https://doi.org/ https://doi.org/10.1038/s41379-020-0569-1 .
doi: 10.1038/s41379-020-0569-1
pubmed: 32741970
pmcid: 7395938
H. Imafuku, K. Tanimura, Y. Shi, A. Uchida, M. Deguchi, Y. Terai, Clinical factors associated with a placenta accreta spectrum, Placenta. (2021). https://doi.org/ https://doi.org/10.1016/j.placenta.2021.08.001 .
doi: 10.1016/j.placenta.2021.08.001
pubmed: 34375912
R.M. Silver, M.B. Landon, D.J. Rouse, K.J. Leveno, C.Y. Spong, E.A. Thom, A.H. Moawad, S.N. Caritis, M. Harper, R.J. Wapner, Y. Sorokin, M. Miodovnik, M. Carpenter, A.M. Peaceman, M.J. O’Sullivan, B. Sibai, O. Langer, J.M. Thorp, S.M. Ramin, B.M. Mercer, Maternal Morbidity Associated With Multiple Repeat Cesarean Deliveries, Obstet. Gynecol. 107 (2006) 1226–1232. https://doi.org/ https://doi.org/10.1097/01.AOG.0000219750.79480.84 .
doi: 10.1097/01.AOG.0000219750.79480.84
pubmed: 16738145
A. Mehrabadi, J.A. Hutcheon, S. Liu, S. Bartholomew, M.S. Kramer, R.M. Liston, K.S. Joseph, Contribution of Placenta Accreta to the Incidence of Postpartum Hemorrhage and Severe Postpartum Hemorrhage, Obstet. Gynecol. 125 (2015) 814–821. https://doi.org/ https://doi.org/10.1097/AOG.0000000000000722 .
doi: 10.1097/AOG.0000000000000722
pubmed: 25751202
L. Allen, E. Jauniaux, S. Hobson, J. Papillon-Smith, M.A. Belfort, FIGO consensus guidelines on placenta accreta spectrum disorders: Nonconservative surgical management, Int. J. Gynecol. Obstet. 140 (2018) 281–290. https://doi.org/ https://doi.org/10.1002/ijgo.12409 .
doi: 10.1002/ijgo.12409
V. Romeo, L. Sarno, A. Volpe, M.I. Ginocchio, R. Esposito, P.P. Mainenti, M. Petretta, R. Liuzzi, M. D’Armiento, P. Martinelli, A. Brunetti, S. Maurea, US and MR imaging findings to detect placental adhesion spectrum (PAS) in patients with placenta previa: a comparative systematic study, Abdom. Radiol. 44 (2019) 3398–3407. https://doi.org/ https://doi.org/10.1007/s00261-019-02185-y .
doi: 10.1007/s00261-019-02185-y
M. De Oliveira Carniello, L.G. Oliveira Brito, L.O. Sarian, J.R. Bennini, Diagnosis of placenta accreta spectrum in high‐risk women using ultrasonography or magnetic resonance imaging: systematic review and meta‐analysis, Ultrasound Obstet. Gynecol. 59 (2022) 428–436, doi: https://doi.org/10.1002/uog.24861 .
S. Hong, Y. Le, K.U. Lio, T. Zhang, Y. Zhang, N. Zhang, Performance comparison of ultrasonography and magnetic resonance imaging in their diagnostic accuracy of placenta accreta spectrum disorders: a systematic review and meta-analysis, Insights Imaging. 13 (2022) 1–13. https://doi.org/ https://doi.org/10.1186/S13244-022-01192-W/TABLES/2 .
doi: 10.1186/S13244-022-01192-W/TABLES/2
S. Maurea, V. Romeo, P.P. Mainenti, M.I. Ginocchio, G. Frauenfelder, F. Verde, R. Liuzzi, M. D’Armiento, L. Sarno, M. Morlando, M. Petretta, P. Martinelli, A. Brunetti, Diagnostic accuracy of magnetic resonance imaging in assessing placental adhesion disorder in patients with placenta previa: Correlation with histological findings, Eur. J. Radiol. 106 (2018) 77–84. https://doi.org/ https://doi.org/10.1016/j.ejrad.2018.07.014 .
doi: 10.1016/j.ejrad.2018.07.014
pubmed: 30150055
H. Kapoor, M. Hanaoka, A. Dawkins, A. Khurana, Review of MRI imaging for placenta accreta spectrum: Pathophysiologic insights, imaging signs, and recent developments, Placenta. 104 (2021) 31–39. https://doi.org/ https://doi.org/10.1016/j.placenta.2020.11.004 .
doi: 10.1016/j.placenta.2020.11.004
pubmed: 33238233
L. Alamo, A. Anaye, J. Rey, A. Denys, G. Bongartz, S. Terraz, S. Artemisia, R. Meuli, S. Schmidt, Detection of suspected placental invasion by MRI: Do the results depend on observer’ experience?, Eur. J. Radiol. 82 (2013) e51–e57. https://doi.org/ https://doi.org/10.1016/j.ejrad.2012.08.022 .
doi: 10.1016/j.ejrad.2012.08.022
pubmed: 23020968
C.L.A. Ghezzi, C.K. Silva, A.S. Casagrande, S.S. Westphalen, C.C. Salazar, J. Vettorazzi, Diagnostic performance of radiologists with different levels of experience in the interpretation of MRI of the placenta accreta spectrum disorder, Br. J. Radiol. (2021). https://doi.org/ https://doi.org/10.1259/bjr.20210827 .
doi: 10.1259/bjr.20210827
pubmed: 34538067
pmcid: 8631015
S. Maurea, F. Verde, P.P. Mainenti, L. Barbuto, F. Iacobellis, V. Romeo, R. Liuzzi, G. Raia, G. De Dominicis, C. Santangelo, L. Romano, A. Brunetti, Qualitative evaluation of MR images for assessing placenta accreta spectrum disorders in patients with placenta previa: A pilot validation study, Eur. J. Radiol. (2022). https://doi.org/ https://doi.org/10.1016/j.ejrad.2021.110078 .
doi: 10.1016/j.ejrad.2021.110078
pubmed: 36030661
P. Jha, L. Pōder, C. Bourgioti, N. Bharwani, S. Lewis, A. Kamath, S. Nougaret, P. Soyer, M. Weston, R.P. Castillo, A. Kido, R. Forstner, G. Masselli, Society of Abdominal Radiology (SAR) and European Society of Urogenital Radiology (ESUR) joint consensus statement for MR imaging of placenta accreta spectrum disorders., Eur. Radiol. 30 (2020) 2604–2615. https://doi.org/ https://doi.org/10.1007/s00330-019-06617-7 .
doi: 10.1007/s00330-019-06617-7
pubmed: 32040730
P. Lambin, R.T.H. Leijenaar, T.M. Deist, J. Peerlings, E.E.C. de Jong, J. van Timmeren, S. Sanduleanu, R.T.H.M. Larue, A.J.G. Even, A. Jochems, Y. van Wijk, H. Woodruff, J. van Soest, T. Lustberg, E. Roelofs, W. van Elmpt, A. Dekker, F.M. Mottaghy, J.E. Wildberger, S. Walsh, Radiomics: the bridge between medical imaging and personalized medicine, Nat. Rev. Clin. Oncol. 14 (2017) 749–762. https://doi.org/ https://doi.org/10.1038/nrclinonc.2017.141 .
doi: 10.1038/nrclinonc.2017.141
pubmed: 28975929
J. Guiot, A. Vaidyanathan, L. Deprez, F. Zerka, D. Danthine, A. Frix, P. Lambin, F. Bottari, N. Tsoutzidis, B. Miraglio, S. Walsh, W. Vos, R. Hustinx, M. Ferreira, P. Lovinfosse, R.T.H. Leijenaar, A review in radiomics: Making personalized medicine a reality via routine imaging, Med. Res. Rev. 42 (2022) 426–440. https://doi.org/ https://doi.org/10.1002/med.21846 .
doi: 10.1002/med.21846
pubmed: 34309893
V. Romeo, S. Maurea, The new era of advanced placental tissue characterization using MRI texture analysis: Clinical implications, EBioMedicine. 51 (2020) 102588. https://doi.org/10.1016/j.ebiom.2019.11.049 .
V. Romeo, C. Ricciardi, R. Cuocolo, A. Stanzione, F. Verde, L. Sarno, G. Improta, P.P. Mainenti, M. D’Armiento, A. Brunetti, S. Maurea, Machine learning analysis of MRI-derived texture features to predict placenta accreta spectrum in patients with placenta previa, Magn. Reson. Imaging. 64 (2019). https://doi.org/10.1016/j.mri.2019.05.017 .
H. Sun, H. Qu, L. Chen, W. Wang, Y. Liao, L. Zou, Z. Zhou, X. Wang, S. Zhou, Identification of suspicious invasive placentation based on clinical MRI data using textural features and automated machine learning., Eur. Radiol. 29 (2019) 6152–6162. https://doi.org/ https://doi.org/10.1007/s00330-019-06372-9 .
doi: 10.1007/s00330-019-06372-9
pubmed: 31444599
Q. Wu, K. Yao, Z. Liu, L. Li, X. Zhao, S. Wang, H. Shang, Y. Lin, Z. Wen, X. Zhang, J. Tian, M. Wang, Radiomics analysis of placenta on T2WI facilitates prediction of postpartum haemorrhage: A multicentre study, EBioMedicine. 50 (2019) 355–365. https://doi.org/ https://doi.org/10.1016/j.ebiom.2019.11.010 .
doi: 10.1016/j.ebiom.2019.11.010
pubmed: 31767539
pmcid: 6921361
A. Stanzione, R. Cuocolo, L. Ugga, F. Verde, V. Romeo, A. Brunetti, S. Maurea, Oncologic Imaging and Radiomics: A Walkthrough Review of Methodological Challenges, Cancers (Basel). 14 (2022) 4871. https://doi.org/ https://doi.org/10.3390/cancers14194871 .
doi: 10.3390/cancers14194871
pubmed: 36230793
pmcid: 9562166
C. Ricciardi, R. Cuocolo, F. Verde, G. Improta, A. Stanzione, V. Romeo, S. Maurea, M. D’Armiento, L. Sarno, M. Guida, M. Cesarelli, Resolution Resampling of Ultrasound Images in Placenta Previa Patients: Influence on Radiomics Data Reliability and Usefulness for Machine Learning, in: 2021: pp. 1011–1018. https://doi.org/10.1007/978-3-030-64610-3_113 .
A. Zwanenburg, M. Vallières, M.A. Abdalah, H.J.W.L. Aerts, V. Andrearczyk, A. Apte, S. Ashrafinia, S. Bakas, R.J. Beukinga, R. Boellaard, M. Bogowicz, L. Boldrini, I. Buvat, G.J.R. Cook, C. Davatzikos, A. Depeursinge, M.-C. Desseroit, N. Dinapoli, C.V. Dinh, S. Echegaray, I. El Naqa, A.Y. Fedorov, R. Gatta, R.J. Gillies, V. Goh, M. Götz, M. Guckenberger, S.M. Ha, M. Hatt, F. Isensee, P. Lambin, S. Leger, R.T.H. Leijenaar, J. Lenkowicz, F. Lippert, A. Losnegård, K.H. Maier-Hein, O. Morin, H. Müller, S. Napel, C. Nioche, F. Orlhac, S. Pati, E.A.G. Pfaehler, A. Rahmim, A.U.K. Rao, J. Scherer, M.M. Siddique, N.M. Sijtsema, J. Socarras Fernandez, E. Spezi, R.J.H.M. Steenbakkers, S. Tanadini-Lang, D. Thorwarth, E.G.C. Troost, T. Upadhaya, V. Valentini, L. V. van Dijk, J. van Griethuysen, F.H.P. van Velden, P. Whybra, C. Richter, S. Löck, The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping, Radiology. 295 (2020) 328–338. https://doi.org/10.1148/radiol.2020191145 .
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, A. Müller, J. Nothman, G. Louppe, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, É. Duchesnay, Scikit-learn: Machine Learning in Python, (2012).
B. Baeßler, K. Weiss, D. Pinto dos Santos, Robustness and Reproducibility of Radiomics in Magnetic Resonance Imaging, Invest. Radiol. 54 (2019) 221–228. https://doi.org/ https://doi.org/10.1097/RLI.0000000000000530 .
doi: 10.1097/RLI.0000000000000530
pubmed: 30433891
A. Stanzione, R. Galatola, R. Cuocolo, V. Romeo, F. Verde, P.P. Mainenti, A. Brunetti, S. Maurea, Radiomics in Cross-Sectional Adrenal Imaging: A Systematic Review and Quality Assessment Study, Diagnostics. 12 (2022) 578. https://doi.org/ https://doi.org/10.3390/diagnostics12030578 .
doi: 10.3390/diagnostics12030578
pubmed: 35328133
pmcid: 8947112
B. Kocak, E. Ates, E.S. Durmaz, M.B. Ulusan, O. Kilickesmez, Influence of segmentation margin on machine learning–based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas, Eur. Radiol. (2019). https://doi.org/ https://doi.org/10.1007/s00330-019-6003-8 .
doi: 10.1007/s00330-019-6003-8
pubmed: 31691122
X. Zhang, L. Zhong, B. Zhang, L. Zhang, H. Du, L. Lu, S. Zhang, W. Yang, Q. Feng, The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups, Cancer Imaging. 19 (2019) 89. https://doi.org/ https://doi.org/10.1186/s40644-019-0276-7 .
doi: 10.1186/s40644-019-0276-7
pubmed: 31864421
pmcid: 6925418
M. Pavic, M. Bogowicz, X. Würms, S. Glatz, T. Finazzi, O. Riesterer, J. Roesch, L. Rudofsky, M. Friess, P. Veit-Haibach, M. Huellner, I. Opitz, W. Weder, T. Frauenfelder, M. Guckenberger, S. Tanadini-Lang, Influence of inter-observer delineation variability on radiomics stability in different tumor sites, Acta Oncol. (Madr). 57 (2018) 1070–1074. https://doi.org/ https://doi.org/10.1080/0284186X.2018.1445283 .
doi: 10.1080/0284186X.2018.1445283
S. Gitto, R. Cuocolo, I. Emili, L. Tofanelli, V. Chianca, D. Albano, C. Messina, M. Imbriaco, L.M. Sconfienza, Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors, J. Digit. Imaging. 34 (2021) 820–832. https://doi.org/ https://doi.org/10.1007/s10278-021-00498-3 .
doi: 10.1007/s10278-021-00498-3
pubmed: 34405298
pmcid: 8455795
Q. Qiu, J. Duan, Z. Duan, X. Meng, C. Ma, J. Zhu, J. Lu, T. Liu, Y. Yin, Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: Impact of tumor segmentation variability, Quant. Imaging Med. Surg. (2019). https://doi.org/10.21037/qims.2019.03.02 .
B. Kocak, E.S. Durmaz, C. Erdim, E. Ates, O.K. Kaya, O. Kilickesmez, Radiomics of Renal Masses: Systematic Review of Reproducibility and Validation Strategies, Am. J. Roentgenol. 214 (2020) 129–136. https://doi.org/ https://doi.org/10.2214/AJR.19.21709 .
doi: 10.2214/AJR.19.21709
A. Stanzione, F. Verde, R. Cuocolo, V. Romeo, P. Paolo Mainenti, A. Brunetti, S. Maurea, Placenta Accreta Spectrum Disorders and Radiomics: Systematic review and quality appraisal, Eur. J. Radiol. 155 (2022) 110497. https://doi.org/10.1016/j.ejrad.2022.110497 .
B.D. Einerson, J. Comstock, R.M. Silver, D.W. Branch, P.J. Woodward, A. Kennedy, Placenta Accreta Spectrum Disorder, Obstet. Gynecol. 135 (2020) 1104–1111. https://doi.org/ https://doi.org/10.1097/AOG.0000000000003793 .
doi: 10.1097/AOG.0000000000003793
pubmed: 32282597
E. Jauniaux, D. Jurkovic, A.M. Hussein, G.J. Burton, New insights into the etiopathology of placenta accreta spectrum, Am. J. Obstet. Gynecol. 227 (2022) 384–391. https://doi.org/ https://doi.org/10.1016/j.ajog.2022.02.038 .
doi: 10.1016/j.ajog.2022.02.038
pubmed: 35248577
A.M. Hussein, R.A. Elbarmelgy, R.M. Elbarmelgy, M.M. Thabet, E. Jauniaux, Prospective evaluation of impact of <scp>post‐Cesarean</scp> section uterine scarring in perinatal diagnosis of placenta accreta spectrum disorder, Ultrasound Obstet. Gynecol. 59 (2022) 474–482. https://doi.org/ https://doi.org/10.1002/uog.23732 .
doi: 10.1002/uog.23732
pubmed: 34225385
pmcid: 9311077
E. Jauniaux, A.M. Hussein, N. Zosmer, R.M. Elbarmelgy, R.A. Elbarmelgy, H. Shaikh, G.J. Burton, A new methodologic approach for clinico-pathologic correlations in invasive placenta previa accreta, Am. J. Obstet. Gynecol. 222 (2020) 379.e1-379.e11. https://doi.org/ https://doi.org/10.1016/j.ajog.2019.11.1246 .
doi: 10.1016/j.ajog.2019.11.1246
E. Jauniaux, A.M. Hussein, R.M. Elbarmelgy, R.A. Elbarmelgy, G.J. Burton, Failure of placental detachment in accreta placentation is associated with excessive fibrinoid deposition at the utero-placental interface, Am. J. Obstet. Gynecol. (2022). https://doi.org/ https://doi.org/10.1016/j.ajog.2021.08.026 .
doi: 10.1016/j.ajog.2021.08.026
pubmed: 35931133