1
|
Pekar Zlotin M, Sharabi-Nov A, Meiri H, Revivo PE, Melcer Y, Maymon R, Jauniaux E. Clinical-sonographic scores for the screening of placenta accreta spectrum: a systematic review and meta-analysis. Am J Obstet Gynecol MFM 2024; 6:101369. [PMID: 38636601 DOI: 10.1016/j.ajogmf.2024.101369] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2023] [Revised: 03/14/2024] [Accepted: 04/01/2024] [Indexed: 04/20/2024]
Abstract
OBJECTIVE Clinical-sonographic scoring systems combining clinical features and ultrasound imaging markers have been proposed for the screening of placenta accreta spectrum, but their usefulness in different settings remains limited. This study aimed to assess and compare different clinical-sonographic score systems applied from mid-pregnancy for the prenatal evaluation of patients at risk of placenta accreta spectrum at birth. DATA SOURCES PubMed/MEDLINE, Google Scholar, and Embase were searched between October 1982 and October 2022 to identify eligible studies. STUDY ELIGIBILITY CRITERIA Observational studies providing data on the use of a combined clinical-ultrasound score system applied from mid-pregnancy for the prenatal evaluation of placenta accreta spectrum were included. METHODS Study characteristics were evaluated by 2 independent reviewers using a predesigned protocol registered on PROSPERO (CRD42022332486). Heterogeneity among studies was analyzed with Cochran's Q-test and I2 statistics. Statistical heterogeneity was quantified by estimating the variance between the studies using I2 statistics. The area under the receiver operating characteristic curve of each score and their summary receiver operating characteristic curves were calculated with sensitivity and specificity, and the integrated score of the summaries of the receiver operating characteristic curves of all sonographic markers was calculated. Forest plots were used to develop the meta-analysis of each sonographic marker and for the integrated sonographic score. RESULTS Of 1028 articles reviewed, 12 cohorts and 2 case-control studies including 1630 patients screened for placenta accreta spectrum by clinical-ultrasound scores met the eligibility criteria. A diagnosis of placenta accreta spectrum was reported in 602 (36.9%) cases, for which 547 (90.9%) intraoperative findings and/or histopathologic data were described. A wide variation was observed among the studies in reported sensitivities and specificities and in thresholds used for the identification of patients with a high probability of placenta accreta spectrum at birth. The summaries of the areas under the curve of the individual sonographic scores ranged from 0.85 (the lowest) for subplacental hypervascularity to 0.91 for placental location in the lower uterine segment, myometrial thinning, and placental lacunae and 0.95 for the loss of clear zone. Only 4 studies included placental bulging in their sonographic score system, and therefore no meta-analysis for this score was performed. The integrated summary of the areas under the curve was 0.83 (95% confidence interval, 79-0.86). Forest plot analysis revealed integrated sensitivities and specificities of 0.68 (95% confidence interval, 0.53-0.80) and 0.88 (95% confidence interval, 0.68-0.96), respectively. CONCLUSION Clinical-sonographic score systems can contribute to the prenatal screening of patients at risk of placenta accreta spectrum at birth. Although we included multiple sonographic studies conducted during the mid-pregnancy period, standardized evaluation should be performed not only with strict ultrasound criteria for the placental position, mid third trimester gestational age at examination, and sonographic markers associated with PAS. Numeric sensitivities, specificities, NPVs, PPV, LR-, and LR+ should be recorded prospectively to assess their accuracy in different set-ups and PTP should be verified at delivery. The variables recommended for most predictive screening are: loss of clear zone underneath the placental bed, placentation in the LUS, and placenta lacunae.
Collapse
Affiliation(s)
- Marina Pekar Zlotin
- Department of Obstetrics and Gynecology, The Yitzhak Shamir Medical Center, Be'er Ya'akov, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon); School of Medicine, Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon)
| | - Adi Sharabi-Nov
- Department of Statistics, Tel-Hai Academic College, Tel Hai, Israel (Dr Sharabi-Nov); Ziv Medical Center, Safed, Israel (Dr Sharabi-Nov)
| | - Hamutal Meiri
- PreTwin Screen Consortium, Tel Aviv, Israel (Drs Meiri and Melcer); TeleMarpe Ltd, Tel Aviv, Israel(Drs Meiri and Melcer)
| | - Perry Eliassi Revivo
- Department of Obstetrics and Gynecology, The Yitzhak Shamir Medical Center, Be'er Ya'akov, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon); School of Medicine, Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon)
| | - Yakkov Melcer
- PreTwin Screen Consortium, Tel Aviv, Israel (Drs Meiri and Melcer); TeleMarpe Ltd, Tel Aviv, Israel(Drs Meiri and Melcer)
| | - Ron Maymon
- Department of Obstetrics and Gynecology, The Yitzhak Shamir Medical Center, Be'er Ya'akov, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon); School of Medicine, Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel (Dr Pekar Zlotin, Dr Eliassi Revivo, and Dr Maymon).
| | - Eric Jauniaux
- EGA Institute for Women's Health, Faculty of Population Health Sciences, University College London, London, United Kingdom (Dr Jauniaux)
| |
Collapse
|
2
|
Adu-Bredu TK, Aryananda RA, Arkorful J, Matthewlynn S, Collins SL. Differentiating placenta accreta spectrum from scar dehiscence with underlying, non-adherent placenta: A systematic review of scoring systems and primary data analysis. Acta Obstet Gynecol Scand 2024. [PMID: 38819580 DOI: 10.1111/aogs.14886] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2024] [Revised: 05/14/2024] [Accepted: 05/14/2024] [Indexed: 06/01/2024]
Abstract
INTRODUCTION Accurate discrimination between placenta accreta spectrum (PAS) and scar dehiscence with underlying non-adherent placenta is challenging both on prenatal ultrasound and intraoperatively. This can lead to overdiagnosis of PAS and unnecessarily aggressive management of scar dehiscence which increases the risk of morbidity. Several scoring systems have been published which combine clinical and ultrasound information to help diagnose PAS in women at high risk. This research aims to provide insights into the reliability and utility of existing accreta scoring systems in differentiating these two closely related but different conditions to contribute to improved clinical decision making and patient outcomes. MATERIAL AND METHODS A literature search was performed in four electronic databases. The references of relevant articles were also assessed. The articles were then evaluated according to the predefined inclusion criteria. Primary data for testing each scoring system were obtained retrospectively from two hospitals with specialized PAS services. Each scoring system was used to evaluate the predicted outcome of each case. RESULTS The literature review yielded 15 articles. Of these, eight did not have a clearly described diagnostic criteria for accreta, hence were excluded. Of the remaining seven studies, one was excluded due to unorthodox diagnostic criteria and two were excluded as they differed from the other systems hindering comparison. Four scoring systems were therefore tested with the primary data. All the scoring systems demonstrated higher scores for high-grade PAS compared to scar dehiscence (p < 0.001) with an excellent Area Under the receiver operator characteristic Curve ranging from 0.82 (95% CI 0.71-0.92) to 0.87 (95% CI 0.79-0.96) in differentiating between these two conditions. However, no statistically significant differences were noted between the low-grade PAS and scar dehiscence on all scoring systems. CONCLUSIONS Most published scoring systems have no clearly defined diagnostic criteria. Scoring systems can differentiate between scar dehiscence with underlying non-adherent placenta from high-grade PAS with excellent diagnostic accuracy, but not for low-grade PAS. Hence, relying solely on these scoring systems may lead to errors in estimating the risk or extent of the condition which hinders preoperative planning.
Collapse
Affiliation(s)
- Theophilus K Adu-Bredu
- Nuffield Department of Women's and Reproductive Health, University of Oxford, Oxford, UK
| | - Rozi Aditya Aryananda
- Obstetrics and Gynecology Department, Maternal Fetal Medicine, Dr Soetomo Academic General Hospital, Universitas Airlangga, Surabaya, Indonesia
| | - Joseph Arkorful
- Department of Medical Imaging, University of Cape Coast, Cape Coast, Ghana
| | - Sam Matthewlynn
- Nuffield Department of Women's and Reproductive Health, University of Oxford, Oxford, UK
| | - Sally L Collins
- Nuffield Department of Women's and Reproductive Health, University of Oxford, Oxford, UK
| |
Collapse
|
3
|
Zhao H, Li X, Yang S, Liu T, Zhan J, Zou J, Lin C, Li Y, Du N, Xiao X. Risk factors of emergency cesarean section in pregnant women with severe placenta accreta spectrum: a retrospective cohort study. Front Med (Lausanne) 2023; 10:1195546. [PMID: 37502363 PMCID: PMC10370267 DOI: 10.3389/fmed.2023.1195546] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2023] [Accepted: 06/21/2023] [Indexed: 07/29/2023] Open
Abstract
Introduction Placenta accreta spectrum (PAS) may cause enormous and potentially life-threatening hemorrhage in the intrapartum and postpartum periods in emergency cesarean section. How to reduce the occurrence of emergency cesarean section in patients with severe PAS is the key to reducing the adverse outcomes of them. This study aimed to investigate the impact of emergency cesarean section on the perioperative outcomes of pregnant women with PAS and neonates, and also aimed to explore the risk factors of emergency cesarean section in pregnant women with PAS. Materials and methods A retrospective investigation was conducted among 163 pregnant women with severe PAS. Of these, 72 were subjected to emergency cesarean sections. Data on the perioperative characteristics of the mothers and neonates were collected. Multivariable linear regression analysis was used to detect associations between maternal and perioperative characteristics and volume of intraoperative bleeding. Binary logical regression was used to analyze the association between maternal preoperative characteristics and emergency cesarean section. Linear regression analysis is used to analyze the relationship between gestational age and emergency cesarean section. Results The risks of emergency cesarean section increase 98, 112, 124, and 62% when the pregnant women with PAS accompanied by GHD, ICP, more prior cesarean deliveries and more severe PAS type, respectively. Noteworthy, the risk of emergency cesarean section decreases 5% when pre-pregnancy BMI increases 1 kg/m2 (OR: 0.95; CI: 0.82, 0.98; p = 0.038). Moreover, there is no significant linear correlation between emergency cesarean section and gestational age. Conclusion GHD, ICP, multiple prior cesarean deliveries and severe PAS type may all increase the risk of emergency cesarean section for pregnant women with PAS, while high pre-pregnancy BMI may be a protective factor due to less activity level. For pregnant women with severe PAS accompanied by these high risk factors, more adequate maternal and fetal monitoring should be carried out in the third trimester to reduce the risk of emergency cesarean section.
Collapse
Affiliation(s)
- Hu Zhao
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| | - Xin Li
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Chengdu Women’s and Children’s Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Shuqi Yang
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| | - Tianjiao Liu
- Chengdu Women’s and Children’s Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Jun Zhan
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| | - Juan Zou
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| | - Changsheng Lin
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| | - Yalan Li
- The Fourth People’s Hospital of Chengdu, Psychosomatic Medical Center, Chengdu, China
| | - Na Du
- The Fourth People’s Hospital of Chengdu, Psychosomatic Medical Center, Chengdu, China
| | - Xue Xiao
- Department of Gynecology and Obstetrics, West China Second University Hospital, Sichuan University, Chengdu, China
- Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, West China Second Hospital, Sichuan University, Chengdu, China
| |
Collapse
|
4
|
Yang X, Zheng W, Yan J, Yang H. Comparison between placenta accreta scoring system, ultrasound staging, and clinical classification. Medicine (Baltimore) 2022; 101:e31622. [PMID: 36401394 PMCID: PMC9678602 DOI: 10.1097/md.0000000000031622] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/03/2022] Open
Abstract
Placenta accreta spectrum (PAS) is a series of disorders, which means that the placental trophoblast invades into the myometrium of the uterine wall. It is a serious obstetric complication which could be detected by ultrasound prenatally. In order to compare our placenta accreta scoring system with prenatal ultrasound staging system and International Federation of Gynecology and Obstetrics (FIGO) clinical classification, we did a retrospective study including 105 patients diagnosed with PAS disorders by operation or pathology at Peking University First Hospital, Beijing, China, between January, 2019 and December, 2020. Placenta accreta scoring system, prenatal ultrasound staging system and FIGO clinical classification were used on each patient. Basic information and clinical outcomes including gestational weeks, intraoperative hemorrhage, hysterectomy rate and blood transfusion were also counted. Both of placenta accreta scoring system, prenatal ultrasound staging system can give a rather clear prediction of placenta percreta, with their area under curve were 0.872 (95% confidential interval [CI]: 0.793-0.951) and 0.864 (95%CI: 0.779-0.949), P value were .000 compared with clinical classification. Beside for ultrasound staging system was designed for placenta previa patients, all those 3 criteria showed their relationships with preterm birth, hysterectomy rate and intraoperative bleeding. PAS scoring system also had the ability to predict a gestational week of delivery ≤34 weeks, intraoperative massive bleeding ≥2000 mL and hysterectomy at over 12 points. Our placenta accreta scoring system had good accordance with pre-operational ultrasound staging and FIGO clinical classification, with higher universality for patients without placenta previa.
Collapse
Affiliation(s)
- Xinrui Yang
- Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China
| | - Weiran Zheng
- Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China
| | - Jie Yan
- Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China
| | - Huixia Yang
- Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing, China
- * Correspondence: Huixia Yang, Department of Obstetrics and Gynecology, Peking University First Hospital, Beijing 100034, China (e-mail: )
| |
Collapse
|
5
|
Zhou Y, Song Z, Wang X, Zhang M, Chen X, Zhang D. Ultrasound-based nomogram for postpartum hemorrhage prediction in pernicious placenta previa. Front Physiol 2022; 13:982080. [PMID: 36072853 PMCID: PMC9441797 DOI: 10.3389/fphys.2022.982080] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2022] [Accepted: 07/26/2022] [Indexed: 12/01/2022] Open
Abstract
Background: Pernicious placenta previa (PPP) is one of the most dangerous complications in pregnancy after cesarean section, with high perinatal mortality. This study aimed to develop a nomogram to predict postpartum hemorrhage in patients with PPP. Methods: A total of 246 patients with confirmed PPP at Shengjing Hospital of China Medical University from January 2018 to December 2021 were included. Patients were divided into to two cohorts depending on a postpartum blood loss of > 1000 ml (n = 146) or ≤ 1000 ml (n = 100). Lasso regression analysis was performed on the risk factors screened by univariate analysis to screen out the final risk factors affecting postpartum hemorrhage. Based on the final risk factors, a Nomogram prediction model with excellent performance was constructed using Logistic regression. A nomogram was constructed with further screening of the selected risk factors of postpartum hemorrhage in PPP. A second nomogram based only on the total ultrasonic risk score was constructed. Decision curve analysis (DCA) was used to evaluate the clinical efficacy of the nomograms. Results: Older age, larger gestational age, larger neonatal birth weight, presence of gestational diabetes mellitus, larger amniotic fluid index, absence of gestational bleeding, and higher ultrasonic risk single score were selected to establish a nomogram for postpartum hemorrhage in PPP. The area under the curve of the nomogram constructed by Lasso regression analysis was higher than that of the ultrasonic total score alone (0.887 vs. 0.833). Additionally, DCA indicated better clinical efficacy in the former nomogram than in the later nomogram. Furthermore, internal verification of the nomogram constructed by Lasso regression analysis showed good agreement between predicted and actual values. Conclusion: A nomogram for postpartum hemorrhage in PPP was developed and validated to assist clinicians in evaluating postpartum hemorrhage. This nomogram was more accurate than using the ultrasonic score alone.
Collapse
Affiliation(s)
- Yangzi Zhou
- Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Zixuan Song
- Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, China
| | - Xiaoxue Wang
- Department of Health Management, Shengjing Hospital of China Medical University, Shenyang, China
| | - Mingjie Zhang
- Department of Surgery, Shengjing Hospital of China Medical University, Shenyang, China
| | - Xueting Chen
- Department of Health Management, Shengjing Hospital of China Medical University, Shenyang, China
| | - Dandan Zhang
- Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, China
- *Correspondence: Dandan Zhang,
| |
Collapse
|
6
|
Deep Learning Algorithm-Based Ultrasound Image Information in Diagnosis and Treatment of Pernicious Placenta Previa. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:3452176. [PMID: 35707039 PMCID: PMC9192257 DOI: 10.1155/2022/3452176] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 05/09/2022] [Accepted: 05/11/2022] [Indexed: 12/14/2022]
Abstract
This study was to explore the value of the deep dictionary learning algorithm in constructing a B ultrasound scoring system and exploring its application in the clinical diagnosis and treatment of pernicious placenta previa (PPP). 60 patients with PPP were divided into a low-risk group (severe, implantable) and high-risk group (adhesive, penetrating) according to their clinical characteristics, B ultrasound imaging characteristics, and postpartum pathological examination results. Under PPP ultrasonic image information using the deep learning algorithm, the B ultrasound image diagnostic scoring system was established to predict the depth of various types of placenta accreta. The results showed that the cut-off values of severe, implantable, adhesive, and penetrating types were <2.3, 2.3-6.5, 6.5-9, and ≥9 points, respectively; there were significant differences in the termination of pregnancy and neonatal birth weight between the two groups (P < 0.05); the positive predictive value, negative predictive value, and false positive rate of ultrasound images based on the deep dictionary learning algorithm for PPP were 95.33%, 94.89%, and 3.56%, respectively. Thus, the ultrasound image diagnostic scoring system based on the deep learning algorithm has an important predictive role for PPP, which can provide a more targeted diagnosis and treatment plan for patients in clinical practice and improve the prediction and treatment efficiency.
Collapse
|
7
|
Del Negro V, Aleksa N, Galli C, Ciminello E, Derme M, Vena F, Muzii L, Piccioni MG. Ultrasonographic Diagnosis of Placenta Accreta Spectrum (PAS) Disorder: Ideation of an Ultrasonographic Score and Correlation with Surgical and Neonatal Outcomes. Diagnostics (Basel) 2020; 11:diagnostics11010023. [PMID: 33375532 PMCID: PMC7824485 DOI: 10.3390/diagnostics11010023] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2020] [Revised: 12/22/2020] [Accepted: 12/22/2020] [Indexed: 12/02/2022] Open
Abstract
The objective of this study was to evaluate a novel ultrasonographic scoring system for the diagnosis of PAS and the prediction of maternal and neonatal outcomes. In this retrospective study, 138 patients with at least one previous caesarean section (CS) and placenta previa were included. They were divided into four groups ranging from Group 0 (Non PAS) to Group 3 (Placenta Percreta) according to the histological or surgical confirmation. Their ultrasound examinations during pregnancy were reviewed according to the nine different ultrasound signs reported by the European Working Group on Abnormally Invasive Placenta. For each parameter, 0 to 2 points were assigned. The sum of the points reflects the severity of PAS with a maximum score of 20. The scoring system revealed good performances in evaluation metrics, with an overall accuracy of 94%. In addition to this, patients’ characteristics and surgical and neonatal outcomes were analyzed with an evidence of higher incidence of complications in severe forms. Our study suggests that antenatal ultrasonographic diagnosis of PAS is feasible with sufficient level of accuracy. This will be important in identifying high-risk patients and implementing preventive strategy.
Collapse
Affiliation(s)
- Valentina Del Negro
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Natalia Aleksa
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Cecilia Galli
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Enrico Ciminello
- Department of Statistical Sciences, “Sapienza” University of Rome, 00185 Rome, Italy;
| | - Martina Derme
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Flaminia Vena
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Ludovico Muzii
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
| | - Maria Grazia Piccioni
- Department of Maternal and Child Health and Urological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.N.); (N.A.); (C.G.); (M.D.); (F.V.); (L.M.)
- Correspondence:
| |
Collapse
|
8
|
Liu J, Wu T, Peng Y, Luo R. Grade Prediction of Bleeding Volume in Cesarean Section of Patients With Pernicious Placenta Previa Based on Deep Learning. Front Bioeng Biotechnol 2020; 8:343. [PMID: 32426340 PMCID: PMC7203465 DOI: 10.3389/fbioe.2020.00343] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2020] [Accepted: 03/27/2020] [Indexed: 12/29/2022] Open
Abstract
In order to predict the amount of bleeding in the cesarean section of the patients with Pernicious Placenta Previa (PPP), this study proposed an automatic blood loss prediction method based on Magnetic Resonance Imaging (MRI) uterus image. Firstly, the DeepLab-V3 + network was used to segment the original MRI abdominal image to obtain the uterine region image. Then, the uterine region image and the corresponding blood loss data were trained by Visual Geometry Group Network-16 (VGGNet-16) network. The classification model of blood loss level was obtained. Using a dataset of 82 positive samples and 128 negative samples, the proposed method achieved accuracy, sensitivity and specificity of 75.61, 73.75, and 77.46% respectively. The experimental results showed that this method can not only automatically identify the uterine region of pregnant women, but also objectively determine the level of intraoperative bleeding. Therefore, this method has the potential to reduce the workload of the attending physician and improve the accuracy of experts' judgment on the level of bleeding during cesarean section, so as to select the corresponding hemostasis measures.
Collapse
Affiliation(s)
- Jun Liu
- Department of Information Engineering, Nanchang Hangkong University, Nanchang, China
| | - Tao Wu
- Department of Information Engineering, Nanchang Hangkong University, Nanchang, China
| | - Yun Peng
- NuVasive, San Diego, CA, United States
| | - Rongguang Luo
- Department of Medical Imaging and Interventional Radiology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| |
Collapse
|