Display options
Cite
Ghi T, Conversano F, Ramirez Zegarra R, et al. Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor. Ultrasound Obstet Gynecol. 2022;59(1):93-99doi: 10.1002/uog.23739.
Ghi, T., Conversano, F., Ramirez Zegarra, R., Pisani, P., Dall'Asta, A., Lanzone, A., Lau, W., Vimercati, A., Iliescu, D. G., Mappa, I., Rizzo, G., Casciaro, S. (2022). Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor. Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology, 59(1), 93-99. https://doi.org/10.1002/uog.23739
Ghi, T, et al. "Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor." Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology vol. 59,1 (2022): 93-99. doi: https://doi.org/10.1002/uog.23739
Ghi T, Conversano F, Ramirez Zegarra R, Pisani P, Dall'Asta A, Lanzone A, Lau W, Vimercati A, Iliescu DG, Mappa I, Rizzo G, Casciaro S. Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor. Ultrasound Obstet Gynecol. 2022 Jan;59(1):93-99. doi: 10.1002/uog.23739. PMID: 34309926.
Copy Download .nbib Format: NLM
Share it on

Ultrasound Obstet Gynecol. 2022 Jan;59(1):93-99. doi: 10.1002/uog.23739.

Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology

T Ghi, F Conversano, R Ramirez Zegarra, P Pisani, A Dall'Asta, A Lanzone, W Lau, A Vimercati, D G Iliescu, I Mappa, G Rizzo, S Casciaro,

Affiliations

  1. Department of Medicine and Surgery, Obstetrics and Gynecology Unit, University of Parma, Parma, Italy.
  2. National Research Council, Institute of Clinical Physiology, Lecce, Italy.
  3. Department of Obstetrics and Gynecology, St Joseph Krankenhaus, Berlin, Germany.
  4. Obstetrics and High-Risk Unit, Fondazione Policlinico A. Gemelli IRCCS, Rome, Italy.
  5. Department of Obstetrics and Gynecology, Kwong Wah Hospital, Kowloon, Hong Kong.
  6. Department of Obstetrics, Gynecology, Neonatology and Anesthesiology, University Hospital of Bari Consorziale Policlinico, Bari, Italy.
  7. University Emergency County Hospital, Craiova, Romania.
  8. University of Medicine and Pharmacy, Craiova, Romania.
  9. Division of Maternal and Fetal Medicine, Cristo Re Hospital, University of Rome Tor Vergata, Rome, Italy.
  10. Department of Obstetrics and Gynecology, The First I.M. Sechenov Moscow State Medical University, Moscow, Russia.

PMID: 34309926 DOI: 10.1002/uog.23739

Abstract

OBJECTIVES: To describe a newly developed machine-learning (ML) algorithm for the automatic recognition of fetal head position using transperineal ultrasound (TPU) during the second stage of labor and to describe its performance in differentiating between occiput anterior (OA) and non-OA positions.

METHODS: This was a prospective cohort study including singleton term (> 37 weeks of gestation) pregnancies in the second stage of labor, with a non-anomalous fetus in cephalic presentation. Transabdominal ultrasound was performed to determine whether the fetal head position was OA or non-OA. For each case, one sonographic image of the fetal head was then acquired in an axial plane using TPU and saved for later offline analysis. Using the transabdominal sonographic diagnosis as the gold standard, a ML algorithm based on a pattern-recognition feed-forward neural network was trained on the TPU images to discriminate between OA and non-OA positions. In the training phase, the model tuned its parameters to approximate the training data (i.e. the training dataset) such that it would identify correctly the fetal head position, by exploiting geometric, morphological and intensity-based features of the images. In the testing phase, the algorithm was blinded to the occiput position as determined by transabdominal ultrasound. Using the test dataset, the ability of the ML algorithm to differentiate OA from non-OA fetal positions was assessed in terms of diagnostic accuracy. The F

RESULTS: Over a period of 24 months (February 2018 to January 2020), at 15 maternity hospitals affiliated to the International Study group on Labor ANd Delivery Sonography (ISLANDS), we enrolled into the study 1219 women in the second stage of labor. On the basis of transabdominal ultrasound, they were classified as OA (n = 801 (65.7%)) or non-OA (n = 418 (34.3%)). From the entire cohort (OA and non-OA), approximately 70% (n = 824) of the patients were assigned randomly to the training dataset and the rest (n = 395) were used as the test dataset. The ML-based algorithm correctly classified the fetal occiput position in 90.4% (357/395) of the test dataset, including 224/246 with OA (91.1%) and 133/149 with non-OA (89.3%) fetal head position. Evaluation of the algorithm's performance gave an F

CONCLUSIONS: This newly developed ML-based algorithm for the automatic assessment of fetal head position using TPU can differentiate accurately, in most cases, between OA and non-OA positions in the second stage of labor. This algorithm has the potential to support not only obstetricians but also midwives and accoucheurs in the clinical use of TPU to determine fetal occiput position in the labor ward. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.

© 2021 International Society of Ultrasound in Obstetrics and Gynecology.

Keywords: artificial intelligence; fetal occiput position; intrapartum ultrasound; transperineal ultrasound

References

  1. Carseldine WJ, Phipps H, Zawada SF, Campbell NT, Ludlow JP, Krishnan SY, DE Vries BS. Does occiput posterior position in the second stage of labour increase the operative delivery rate? Aust N Z J Obstet Gynaecol 2013; 53: 265-270. - PubMed
  2. O'Mahony F, Hofmeyr GJ, Menon V. Choice of instruments for assisted vaginal delivery. Cochrane Database of Systematic Reviews 2010, Issue 11, CD005455. - PubMed
  3. Olagundoye V, MacKenzie IZ. The impact of a trial of instrumental delivery in theatre on neonatal outcome. BJOG 2007; 114: 603-608. - PubMed
  4. Gurol-Urganci I, Cromwell D, Edozien L, Mahmood T, Adams E, Richmond D, Templeton A, van der Meulen J. Third- and fourth-degree perineal tears among primiparous women in England between 2000 and 2012: time trends and risk factors. BJOG 2013; 120: 1516-1525. - PubMed
  5. Chadwick LM, Pemberton PJ, Kurinczuk JJ. Neonatal subgaleal haematoma: associated risk factors, complications and outcome. J Paediatr Child Health 1996; 32: 228-232. - PubMed
  6. Towner D, Castro MA, Eby-Wilkens E, Gilbert WM. Effect of mode of delivery in nulliparous women on neonatal intracranial injury. N Engl J Med 1999; 341: 1709-1714. - PubMed
  7. Walsch CA, Robson M, McAuliffe FM. Mode of delivery at term and adverse neonatal outcomes. Obstet Gynecol 2013; 121: 122-128. - PubMed
  8. Ghi T. Sonographic confirmation of fetal position before operative vaginal delivery should be recommended in clinical guidelines. Ultrasound Obstet Gynecol 2021; 57: 36-37. - PubMed
  9. Ramphul M, Ooi PV, Burke G, Kennelly MM, Said SA, Montgomery AA, Murphy DJ. Instrumental delivery and ultrasound: a multicentre randomised controlled trial of ultrasound assessment of the fetal head position versus standard care as an approach to prevent morbidity at instrumental delivery. BJOG 2014; 121: 1029-1038. - PubMed
  10. Ghi T, Dall'Asta A, Masturzo B, Tassis B, Martinelli M, Volpe N, Prefumo F, Rizzo G, Pilu G, Cariello L, Sabbioni L, Morselli-Labate AM, Todros T, Frusca T. Randomised Italian Sonography for occiput POSition Trial Ante vacuum (R.I.S.POS.T.A.). Ultrasound Obstet Gynecol 2018; 52: 699-705. - PubMed
  11. Eggebø TM, Hassan WA, Salvesen KÅ, Torkildsen EA, Østborg TB, Lees CC. Prediction of delivery mode by ultrasound-assessed fetal position in nulliparous women with prolonged first stage of labor. Ultrasound Obstet Gynecol 2015; 46: 606-610. - PubMed
  12. Murphy DJ, Strachan BK, Bahl R; Royal College of Obstetricians and Gynaecologists. Assisted Vaginal Birth: Green-top Guideline No. 26. BJOG 2020; 127: e70-e112. - PubMed
  13. Ghi T, Eggebø T, Lees C, Kalache K, Rozenberg P, Youssef A, Salomon LJ, Tutschek B. ISUOG Practice Guidelines: intrapartum ultrasound. Ultrasound Obstet Gynecol 2018; 52: 128-139. - PubMed
  14. Hobson S, Cassell K, Windrim R, Cargill Y. No. 381-Assisted Vaginal Birth. J Obstet Gynaecol Can 2019; 41: 870-882. - PubMed
  15. Deutsche Gesellschaft für Gynäkologie und Geburtshilfe e.V. (DGGG). S3-Leitlinien-Detailansicht. Die vaginale Geburt am Termin [Internet]. 2021. https://www.awmf.org/leitlinien/detail/ll/015-083.html - PubMed
  16. Youssef A, Ghi T, Pilu G. How to perform ultrasound in labor: assessment of fetal occiput position. Ultrasound Obstet Gynecol 2013; 41: 476-478. - PubMed
  17. Kreiser D, Schiff E, Lipitz S, Kayam Z, Avraham A, Achiron R. Determination of fetal occiput position by ultrasound during the second stage of labor. J Matern Fetal Med 2001; 10: 283-286. - PubMed
  18. Sherer DM, Miodovnik M, Bradley KS, Langer O. Intrapartum fetal head position I: comparison between transvaginal digital examination and transabdominal ultrasound assessment during the active stage of labor. Ultrasound Obstet Gynecol 2002; 19: 258-263. - PubMed
  19. Sherer DM, Miodovnik M, Bradley KS, Langer O. Intrapartum fetal head position II: comparison between transvaginal digital examination and transabdominal ultrasound assessment during the second stage of labor. Ultrasound Obstet Gynecol 2002; 19: 264-268. - PubMed
  20. Akmal S, Tsoi E, Kametas N, Howard R, Nicolaides KH. Intrapartum sonography to determine fetal head position. J Matern Fetal Neonatal Med 2002; 12: 172-177. - PubMed
  21. Souka AP, Haritos T, Basayiannis K, Noikokyri N, Antsaklis A. Intrapartum for the examination of the fetal head position in normal and obstructed labor. J Matern Fetal Neonatal Med 2003; 13: 59-63. - PubMed
  22. Akmal S, Kametas N, Tsoi E, Hargreaves C, Nicolaides KH. Comparison of transvaginal digital examination with intrapartum sonography to determine fetal occipital position before instrumental delivery. Ultrasound Obstet Gynecol 2003; 21: 437-440. - PubMed
  23. Akmal S, Tsoi E, Nicolaides KH. Intrapartum sonography to determine fetal occipital position: interobserver agreement. Ultrasound Obstet Gynecol 2004; 24: 421-424. - PubMed
  24. Chou MR, Kreiser D, Taslimi MM, Druzin ML, El-Sayed YY. Vaginal versus ultrasound examination of fetal occiput position during the second stage of labor. Am J Obstet Gynecol 2004; 191: 521-524. - PubMed
  25. Dupuis O, Ruimark S, Corinne D, Simone T, André D, René-Charles R. Fetal head position during the second stage of labor: comparison of digital vaginal examination and transabdominal ultrasonographic examination. Eur J Obstet Gynecol Reprod Biol 2005; 123: 193-197. - PubMed
  26. Zahalka N, Sadan O, Malinger G, Liberati M, Boaz M, Glezerman M, Rotmensch S. Comparison of transvaginal sonography with digital examination and transabdominal sonography for the determination of fetal head position in the second stage of labor. Am J Obstet Gynecol 2005; 193: 381-386. - PubMed
  27. Ramphul M, Murphy DJ. Establishing the accuracy and acceptability of abdominal ultrasound to define the fetal head position in the second stage of labour: a validation study. Eur J Obstet Gynecol Reprod Biol 2012; 164: 35-39. - PubMed
  28. Ramphul M, Ooi PV, Burke G, Kennelly MM, Said SAT, Montgomery AA, Murphy DJ. Instrumental delivery and ultrasound (IDUS): a multicentre randomised controlled trial of ultrasound assessment of the fetal head position versus standard care as an approach to prevent morbidity at instrumental delivery. BJOG 2014; 121: 1029-1038. - PubMed
  29. Ghi T, Bellussi F, Eggebø T, Tondi F, Pacella G, Salsi G, Cariello L, Piastra A, Youssef A, Pilu G, Rizzo N. Sonographic assessment of fetal occiput position during the second stage of labor: how reliable is the transperineal approach? J Matern Fetal Neonatal Med 2015; 28: 1985-1988. - PubMed
  30. Drukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol 2020; 56: 498-505. - PubMed
  31. Garcia-Canadilla P, Sanchez-Martinez S, Crispi F, Bijnens B. Machine Learning in Fetal Cardiology: What to Expect. Fetal Diagn Ther 2020; 47: 363-372. - PubMed
  32. Christiansen F, Epstein EL, Smedberg E, Åkerlund M, Smith K, Epstein E. Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment. Ultrasound Obstet Gynecol 2021; 57: 155-163. - PubMed
  33. Du Y, Fang Z, Jiao J, Xi G, Zhu C, Ren Y, Guo Y, Wang Y. Application of ultrasound-based radiomics technology in fetal-lung-texture analysis in pregnancies complicated by gestational diabetes and/or pre-eclampsia. Ultrasound Obstet Gynecol 2021; 57: 804-812. - PubMed
  34. Ambroise Grandjean G, Hossu G, Bertholdt C, Noble P, Morel O, Grangé G. Artificial intelligence assistance for fetal head biometry: Assessment of automated measurement software. Diagn Interv Imaging 2018; 99: 709-716. - PubMed
  35. Tolsgaard MG, Svendsen MBS, Thybo JK, Petersen OB, Sundberg KM, Christensen AN. Does artificial intelligence for classifying ultrasound imaging generalize between different populations and contexts? Ultrasound Obstet Gynecol 2021; 57: 342-343. - PubMed
  36. Tsur A, Batsry L, Toussia-Cohen S, Rosenstein MG, Barak O, Brezinov Y, Yoeli-Ullman R, Sivan E, Sirota M, Druzin ML, Stevenson DK, Blumenfeld YJ, Aran D. Development and validation of a machine-learning model for prediction of shoulder dystocia. Ultrasound Obstet Gynecol 2020; 56: 588-596. - PubMed
  37. Xie HN, Wang N, He M, Zhang LH, Cai HM, Xian JB, Lin MF, Zheng J, Yang YZ. Using deep-learning algorithms to classify fetal brain ultrasound images as normal or abnormal. Ultrasound Obstet Gynecol 2020; 56: 579-587. - PubMed
  38. Yadav S, Shukla S. Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. 2016 IEEE 6th International conference on advanced computing (IACC). DOI: 10.1109/IACC.2016.25. - PubMed
  39. Tharwat A. Classification assessment methods. Applied Computing and Informatics 2020; 17. DOI: 10.1016/j.aci.2018.08.003. - PubMed
  40. Ghi T, Farina A, Pedrazzi A, Rizzo N, Pelusi G, Pilu G. Diagnosis of station and rotation of the fetal head in the second stage of labor with intrapartum translabial ultrasound. Ultrasound Obstet Gynecol 2009; 33: 331-336. - PubMed
  41. Barbera AF, Pombar X, Perugino G, Lezotte DC, Hobbins JC. A new method to assess fetal head descent in labor with transperineal ultrasound. Ultrasound Obstet Gynecol 2009; 33: 313-319. - PubMed
  42. Eggebø TM, Gjessing LK, Heien C, Smedvig E, Økland I, Romundstad P, Salvesen KA. Prediction of labor and delivery by transperineal ultrasound in pregnancies with prelabor rupture of membranes at term. Ultrasound Obstet Gynecol 2006; 27: 387-391. - PubMed
  43. Angeli L, Conversano F, Dall'Asta A, Eggebø T, Volpe N, Marta S, Pisani P, Casciaro S, Di Paola M, Frusca T, Ghi T. Automatic measurement of head-perineum distance during intrapartum ultrasound: description of the technique and preliminary results. J Matern Fetal Neonatal Med 2020. DOI: 10.1080/14767058.2020.1799974. - PubMed
  44. Angeli L, Conversano F, Dall'Asta A, Volpe N, Simone M, Di Pasquo E, Pignatelli D, Schera GBL, Di Paola M, Ricciardi P, Ferretti A, Frusca T, Casciaro S, Ghi T. New technique for automatic sonographic measurement of change in head-perineum distance and angle of progression during active phase of second stage of labor. Ultrasound Obstet Gynecol 2020; 56: 597-602. - PubMed
  45. Youssef A, Salsi G, Montaguti E, Bellussi F, Pacella G, Azzarone C, Farina A, Rizzo N, Pilu G. Automated Measurement of the Angle of Progression in Labor: A Feasibility and Reliability Study. Fetal Diagn Ther 2017; 41: 293-299. - PubMed
  46. Conversano F, Peccarisi M, Pisani P, Di Paola M, De Marco T, Franchini R, Greco A, D'Ambrogio G, Casciaro S. Automatic ultrasound technique to measure angle of progression during labor. Ultrasound Obstet Gynecol 2017; 50: 766-775. - PubMed
  47. Montaguti E, Rizzo N, Pilu G, Youssef A. Automated 3D ultrasound measurement of the angle of progression in labor. J Matern Fetal Neonatal Med 2018; 31: 141-149. - PubMed

Publication Types