Automated, fast, robust brain extraction on contrast-enhanced T1-weighted MRI in presence of brain tumors: an optimized model based on multi-center datasets.

OBJECTIVES: Existing brain extraction models should be further optimized to provide more information for oncological analysis. We aimed to develop an nnU-Net-based deep learning model for automated brain extraction on contrast-enhanced T1-weighted (T1CE) images in presence of brain tumors. METHODS: This is a multi-center, retrospective study involving 920 patients. A total of 720 cases with four types of intracranial tumors from private institutions were collected and set as the training group and the internal test group. Mann-Whitney U test (U test) was used to investigate if the model performance was associated with pathological types and tumor characteristics. Then, the generalization of model was independently tested on public datasets consisting of 100 glioma and 100 vestibular schwannoma cases. RESULTS: In the internal test, the model achieved promising performance with median Dice similarity coefficient (DSC) of 0.989 (interquartile range (IQR), 0.988-0.991), and Hausdorff distance (HD) of 6.403 mm (IQR, 5.099-8.426 mm). U test suggested a slightly descending performance in meningioma and vestibular schwannoma group. The results of U test also suggested that there was a significant difference in peritumoral edema group, with median DSC of 0.990 (IQR, 0.989-0.991, p = 0.002), and median HD of 5.916 mm (IQR, 5.000-8.000 mm, p = 0.049). In the external test, our model also showed to be robust performance, with median DSC of 0.991 (IQR, 0.983-0.998) and HD of 8.972 mm (IQR, 6.164-13.710 mm). CONCLUSIONS: For automated processing of MRI neuroimaging data presence of brain tumors, the proposed model can perform brain extraction including important superficial structures for oncological analysis. CLINICAL RELEVANCE STATEMENT: The proposed model serves as a radiological tool for image preprocessing in tumor cases, focusing on superficial brain structures, which could streamline the workflow and enhance the efficiency of subsequent radiological assessments. KEY POINTS: • The nnU-Net-based model is capable of segmenting significant superficial structures in brain extraction. • The proposed model showed feasible performance, regardless of pathological types or tumor characteristics. • The model showed generalization in the public datasets.

Outcome of Sclerotherapy in a Preterm Infant with a Giant Fetal Neck Lymphatic Malformation: A Case Report.

Introduction: Lymphatic malformation (LM), most commonly present in the neck area, is benign vascular malformations of the lymphatic system. In an infant, however, LM poses a high risk of adverse outcomes. Case Presentation: We present a case with a giant fetal LM. Through ultrasonography, at 23+ weeks of gestation, a septate cystic mass 7.2×6.5×6.3 cm in size was found on the right side of the fetus's neck. After extensive counseling by the multidisciplinary team, the parents chose to continue the pregnancy. Severe fetal tracheal compression was observed at 29 weeks by magnetic resonance imaging (MRI). At 31 weeks and 5 days, owing to suspected fetal distress, an emergency cesarean section was performed and a male baby weighing 1720 g was delivered. The mass was 10×16×8 cm in size and ex utero intrapartum treatment (EXIT) was implemented. Due to progressive growth of the mass secondary to intralesional bleeding, an intralesional injection of bleomycin was administered three days later. This injection was repeated at the age of 1 month and 8 days. The baby was followed up and, by a year after his birth, LM had disappeared. The baby has since been in good health. Conclusion: Accurate prenatal diagnosis and regular monitoring of a fetus with LM may improve prognosis. It is essential to have a trained multidisciplinary team to evaluate the condition of the fetus and the neonate and to provide treatment based on the evaluation. Our experience with intralesional bleomycin injection for the treatment of a giant fetal neck LM in a preterm infant had a favorable outcome. Long-term follow-up by a multidisciplinary team is needed in such cases.

Combined Influences of Water Content and Coarse Grain Content on Shear Strength of Unsaturated Soil Mixture.

An interlayer existed between the ballast layer and subgrade in the conventional railway substructure. Considering that the shear strength τ of the interlayer soil was influenced by the changes in the ballast grain content and water content, this aspect was explored in the present study. Monotonic triaxial tests were fulfilled, which considered five coarse grain contents fv and three water contents of fine soil wf. The results showed that the growth in fv contributed to an increment in τ of the soil mixture under both saturation and unsaturation. Conversely, in previous studies, the growth of fv induced an increment in τ under saturation, but a decline in that under unsaturation. This was explained by the competing influences of fv and suction ψ: in previous studies, increasing fv induced a decline in the dry density of the fine soil fraction ρd-f, which contributed to a decline in ψ. When the negative influence of declining ψ outweighed the positive influence of the incrementing fv, the τ of the soil mixture decreased. Meanwhile, modelling of the τ-ψ relationship in the soil mixture with varying fv was performed. This proposed model was examined using the test results from both the present and previous studies, which shows its reasonably good performance.

Preoperative volume of the optic chiasm is an easily obtained predictor for visual recovery of pituitary adenoma patients following endoscopic endonasal transsphenoidal surgery: a cohort study.

BACKGROUND: Predicting the postoperative visual outcome of pituitary adenoma patients is important but remains challenging. This study aimed to identify a novel prognostic predictor which can be automatically obtained from routine MRI using a deep learning approach. MATERIALS AND METHODS: A total of 220 pituitary adenoma patients were prospectively enrolled and stratified into the recovery and nonrecovery groups according to the visual outcome at 6 months after endoscopic endonasal transsphenoidal surgery. The optic chiasm was manually segmented on preoperative coronal T2WI, and its morphometric parameters were measured, including suprasellar extension distance, chiasmal thickness, and chiasmal volume. Univariate and multivariate analyses were conducted on clinical and morphometric parameters to identify predictors for visual recovery. Additionally, a deep learning model for automated segmentation and volumetric measurement of optic chiasm was developed with nnU-Net architecture and evaluated in a multicenter data set covering 1026 pituitary adenoma patients from four institutions. RESULTS: Larger preoperative chiasmal volume was significantly associated with better visual outcomes ( P =0.001). Multivariate logistic regression suggested it could be taken as the independent predictor for visual recovery (odds ratio=2.838, P <0.001). The auto-segmentation model represented good performances and generalizability in internal (Dice=0.813) and three independent external test sets (Dice=0.786, 0.818, and 0.808, respectively). Moreover, the model achieved accurate volumetric evaluation of the optic chiasm with an intraclass correlation coefficient of more than 0.83 in both internal and external test sets. CONCLUSION: The preoperative volume of the optic chiasm could be utilized as the prognostic predictor for visual recovery of pituitary adenoma patients after surgery. Moreover, the proposed deep learning-based model allowed for automated segmentation and volumetric measurement of the optic chiasm on routine MRI.

Automated segmentation of craniopharyngioma on MR images using U-Net-based deep convolutional neural network.

OBJECTIVES: To develop a U-Net-based deep learning model for automated segmentation of craniopharyngioma. METHODS: A total number of 264 patients diagnosed with craniopharyngiomas were included in this research. Pre-treatment MRIs were collected, annotated, and used as ground truth to learn and evaluate the deep learning model. Thirty-eight patients from another institution were used for independently external testing. The proposed segmentation model was constructed based on a U-Net architecture. Dice similarity coefficients (DSCs), Hausdorff distance of 95% percentile (95HD), Jaccard value, true positive rate (TPR), and false positive rate (FPR) of each case were calculated. One-way ANOVA analysis was used to investigate if the model performance was associated with the radiological characteristics of tumors. RESULTS: The proposed model showed a good performance in segmentation with average DSCs of 0.840, Jaccard of 0.734, TPR of 0.820, FPR of 0.000, and 95HD of 3.669 mm. It performed feasibly in the independent external test set, with average DSCs of 0.816, Jaccard of 0.704, TPR of 0.765, FPR of 0.000, and 95HD of 4.201 mm. Also, one-way ANOVA suggested the performance was not statistically associated with radiological characteristics, including predominantly composition (p = 0.370), lobulated shape (p = 0.353), compressed or enclosed ICA (p = 0.809), and cavernous sinus invasion (p = 0.283). CONCLUSIONS: The proposed deep learning model shows promising results for the automated segmentation of craniopharyngioma. KEY POINTS: • The segmentation model based on U-Net showed good performance in segmentation of craniopharyngioma. • The proposed model showed good performance regardless of the radiological characteristics of craniopharyngioma. • The model achieved feasibility in the independent external dataset obtained from another center.

Prenatal diagnosis of generalized arterial calcification of infancy in the second trimester.

OBJECTIVES: Generalized arterial calcification of infancy (GACI) is a rare autosomal recessive disorder characterized by subintimal fibrous proliferation and deposition of calcium salts in the internal elastic lamina, leading to extensive arterial calcification and stenosis of large and medium-sized arteries. Prenatal diagnosis is usually made in the third trimester by detection of aortic and pulmonary calcification with associated nonimmune hydrops; earlier prenatal diagnosis is rare. This study was performed to examine the prenatal ultrasound and genetic features of fetuses with GACI. METHODS: We retrospectively reviewed the ultrasound findings, their progression in utero, and the clinical features in three fetuses with GACI ascertained using ultrasound in the second trimester. GACI was subsequently confirmed through pathological examination and/or molecular genetic testing. RESULTS: All three fetuses had hyperechogenic valves or annuli as the first detectable manifestation in the second trimester, followed by relatively rapid progression to arterial wall calcification. Three novel mutations of the ENPP1 gene associated with GACI were found in two of the cases (c.26dupG, c.1454A > G, and c.263C > G). CONCLUSIONS: GACI should be suspected when hyperechogenic cardiac valves, annuli, or arterial walls are noted after ruling out other causes of arterial calcification. Genetic testing is important for prenatal and future preimplantation genetic diagnosis.

Cases report: MRI findings of asymptomatically familial subependymal heterotopia with filamin A gene abnormality.

Subependymal heterotopia (SEH) is a rare neuronal migration disorder consisting of gray matter nodules along the lateral ventricular walls and is often associated with other brain malformations. Despite most SEH cases showing epilepsy during their lifetimes, very few patients with asymptomatically familial SEH tend to cause misdiagnosis or missed diagnosis. We present four familial SEH cases without any positive symptoms and medical history, including two fetuses, who were diagnosed by MRI and confirmed by genetic testing with mutation of filamin A. This report emphasizes the role of MRI in the recognition of SEH at an early age of gestation and in asymptomatically familial SEH. MRI provides a fast, repeatable, reliable, and cheap choice for detecting and screening familial SEH.

Can prenatal diagnosis of parachute mitral valve be achieved? A case report of fetal parachute mitral valve.

Parachute mitral valve (PMV) is a common form of congenital mitral stenosis and is difficult to diagnose prenatally. This report describes a fetal case of PMV with coarctation of the aorta that was diagnosed at 25 weeks' gestation by echocardiography and confirmed at autopsy. We describe the ultrasonographic features in this case and present a useful sign for making a prenatal diagnosis of PMV.

A CT-based radiomics nomogram for predicting early recurrence in patients with high-grade serous ovarian cancer.

PURPOSE: To develop and validate a radiomics nomogram for predicting early recurrence in high-grade serous ovarian cancer (HGSOC) patients. MATERIALS AND METHODS: From May 2008 to December 2019, 256 eligible HGSOC patients were enrolled and divided into training (n = 179) and test cohorts (n = 77) in a 7:3 ratio. A radiomics signature (Radscore) was selected by using recursive feature elimination based on a support vector machine (SVM-RFE) and building a radiomics model for recurrence prediction. Independent clinical risk factors were generated by univariable and multivariable Cox regression analyses. A combined model was developed based on the Radscore and independent clinical risk factors and presented as a radiomics nomogram. Its performance was assessed by AUC, Kaplan-Meier survival analysis and decision curve analysis. RESULTS: Seven radiomics features were selected. The radiomics model yielded AUCs of 0.715 (95% CI: 0.640, 0.790) and 0.717 (95% CI: 0.600, 0.834) in the training and test cohorts, respectively. The clinical model (FIGO stage and residual disease) yielded AUCs of 0.632 and 0.691 in the training and test cohorts, respectively. The combined model demonstrated AUCs of 0.749 (95% CI: 0.678, 0.821) and 0.769 (95% CI: 0.662, 0.877) in the training and test cohorts, respectively. In the combined model, PFS was significantly shorter in the high-risk group than in the low-risk group (P < 0.0001). CONCLUSIONS: The radiomics nomogram performed well for early individualized recurrence prediction in patients with HGSOC and can also be used to differentiate high-risk patients from low-risk patients.

Quantitative evaluation of fetal ventricular function by speckle tracking echocardiography.

METHODS: The study included 59 patients with normal fetal heart structure, blood flow, and heart rhythm (fetal abnormality-negative group) and 50 patients with abnormal fetal heart structure, blood flow, and/or heart rhythm (fetal abnormality-positive group). Automated Cardiac Motion Quantification (aCMQ) was performed in both groups to obtain left and right ventricular endocardial global longitudinal strain (GLSendo), mid-myocardial global longitudinal strain (GLSmid), and epicardial global longitudinal strain (GLSepi). Parameters between the two groups were compared and correlation analyses performed. A deformation analysis was performed by two trained observers, and reproducibility was assessed. RESULTS: The fetal left ventricular and right ventricular global longitudinal strain (LV-GLS and RV-GLS, respectively) decreased in a gradient from the endocardium to the epicardium. LV-GLS and RV-GLS of all myocardial layers were lower in the fetal abnormality-positive than -negative group (all P < 0.05). Correlation analysis showed that neither LV-GLS nor RV-GLS was significantly correlated with gestational age in the fetal abnormality-negative group (all P > 0.05), whereas left ventricular GLSendo, GLSmid, and GLSepi were negatively correlated with gestational age in the fetal abnormality-positive group (r = -.39 to -.44, all P < 0.05). Repeatability testing showed that the inter-observer and intra-observer intra-class correlation coefficients for LV-GLS and RV-GLS in each myocardial layer were >.75 (all P < 0.001). CONCLUSIONS: As a new speckle tracking echocardiography tool, aCMQ has feasibility and repeatability in evaluating myocardial deformation of the fetal ventricle. This technique might provide helpful information on ventricular myocardial deformation in fetal hearts with abnormal structure or rhythm for clinical guidance in pregnancy.

Accuracy of flow-void diameters on MR images in diagnosing uterine arteriovenous malformations in patients with pregnancy-related diseases.

To evaluate the "flow void" diameter in patients with pregnancy-related diseases with and without uterine AVMs and assess the diagnostic performance of unenhanced MRI for uterine AVMs. From May 2014 to April 2019, 79 patients with pregnancy-related diseases were included, including 36 with and 43 without uterine AVMs confirmed by DSA. On MRI, the diameter of the most prominent "flow void" (hereinafter referred to as fv-D) was measured and compared between patients with and without uterine AVMs. The diagnostic performance of fv-D was estimated with receiver operating characteristic curves. The "flow void" sign was observed in patients with and without uterine AVMs (P > 0.05). The fv-D was significantly larger in patients with uterine AVMs in the myometrium and parametrium than in patients without uterine AVMs (P < 0.0001). The fv-D achieved a reliable diagnostic performance in the myometrium (sensitivity 80.6%, specificity 60.5%, negative predictive value 78.8%, positive predictive value 63%, AUC 0.727, cut-off: > 1.33 mm) and parametrium (sensitivity 97.2%, specificity 67.4%, negative predictive value 96.7%, positive predictive value 71.4%, AUC 0.881, cut-off > 2.6 mm). On MRI, fv-D could diagnose uterine AVMs. The fv-D had a much higher diagnostic efficiency in the parametrium than in the myometrium. The parametrium fv-D greatly improved the diagnostic sensitivity and provides a more accurate, noninvasive method of investigating possible uterine AVMs.

Effect of prophylactic balloon occlusion of internal iliac artery in pregnancies complicated by placenta previa and accreta.

BACKGROUND: Placenta previa and accreta are serious obstetric conditions that are associated with a high risk of intraoperative massive hemorrhage, the prophylactic intravascular balloon occlusion technique is increasingly used in managing uncontrolled hemorrhage in cesarean section (CS). We aim to examine the clinical effectiveness of prophylactic balloon occlusion of the internal iliac artery (PBOIIA) during CS in improving maternal outcomes for patients with placenta previa and accreta. METHODS: A total of 420 women with placenta previa and accreta who underwent CS from January 2014 to December 2018 were included retrospectively. Patients were divided into balloon group in which patients had PBOIIA (n = 248) and the control group in which patients did not have PBOIIA (n = 172). Meanwhile, we performed a subgroup analysis in whether taking parallel transverse uterine incision (PTUI) surgery. Information on conditions of patients and newborns, perioperative blood indicators, surgical outcomes were collected. RESULTS: Median estimated blood loss (mEBL) was 2200 mL in the balloon group and 2150 mL in the control group respectively, there was no significant difference between two-groups comparison (P > 0.05), and the rate of patients with hysterectomy was also has no difference between the two groups (36.3% verus 35.5%, P > 0.05), while there is a significant difference between two groups in the amount of PRBCs transfused [3 (0-31.5) verus 3 (0-39), P <0.05], moreover, the proportion of PRBCS> 8 units in the balloon group is significantly lower than that in control group (11.29% verus 23.26%, P <0.05).. However, the total hospitalization costs (45,624.4 ± 11,061.9 verus 37,523.1 ± 14,662.2, CYN) and surgery costs (19,910.6 ± 2622.6 verus 11,850.5 ± 3146.1, CYN) in balloon group were significantly higher than those in control group (P < 0.05). Subgroup analysis showed PTUI surgery had no significant differences in EBL (P >0.05), but it could significantly decrease hysterectomy rates (P <0.05). CONCLUSIONS: PBOIIA has no significant effect on reducing intraoperative EBL and hysterectomy rate in patients with placenta previa and accreta. and although it could reduce the intraoperative PRBCs in patients with massive hemorrhage, it significantly increases the financial cost for patients. Therefore, PBOIIA should not be routinely recommended to patients with placenta previa and accreta.

The Development and Validation of a CT-Based Radiomics Nomogram to Preoperatively Predict Lymph Node Metastasis in High-Grade Serous Ovarian Cancer.

PURPOSE: To develop and validate a radiomics model for predicting preoperative lymph node (LN) metastasis in high-grade serous ovarian cancer (HGSOC). MATERIALS AND METHODS: From May 2008 to January 2018, a total of 256 eligible HGSOC patients who underwent tumor resection and LN dissection were divided into a training cohort (n=179) and a test cohort (n=77) in a 7:3 ratio. A Radiomics Model was developed based on a training cohort of 179 patients. A radiomics signature (defined as the Radscore) was selected by using the random forest method. Logistics regression was used as the classifier for modeling. An Integrated Model that incorporated the Radscore and CT_reported LN status (CT_LN_report) was developed and presented as a radiomics nomogram. Its performance was determined by the area under the curve (AUC), calibration, and decision curve. The radiomics nomogram was internally tested in an independent test cohort (n=77) and a CT-LN-report negative subgroup (n=179) using the formula derived from the training cohort. RESULTS: The AUC value of the CT_LN_report was 0.688 (95% CI: 0.626, 0.759) in the training cohort and 0.717 (95% CI: 0.630, 0.804) in the test cohort. The Radiomics Model yielded an AUC of 0.767 (95% CI: 0.696, 0.837) in the training cohort and 0.753 (95% CI: 0.640, 0.866) in the test. The radiomics nomogram demonstrated favorable calibration and discrimination in the training cohort (AUC=0.821), test cohort (AUC=0.843), and CT-LN-report negative subgroup (AUC=0.82), outperforming the Radiomics Model and CT_LN_report alone. CONCLUSIONS: The radiomics nomogram derived from portal phase CT images performed well in predicting LN metastasis in HGSOC and could be recommended as a new, convenient, and non-invasive method to aid in clinical decision-making.

Clinical characteristics of 50 children with azygos lobe: a retrospective study.

An azygos lobe is a rare anatomic variant of the lung which may be misdiagnosed as other pathological conditions. There is a dearth of information on the clinical characteristics of children with azygos lobe. This study aims to summarize the clinical features of children with azygos lobe, which may be helpful to improve recognition and clinical care of those patients. Clinical findings of the children with imaging findings of azygos lobe were collected and analyzed. In this study, 50 children with azygos lobe were included. A total of 28% cases were found to have azygos lobe incidentally. The remaining 72% cases were diagnosed when they presented with respiratory symptoms including cough (36%), fever (34%), wheezing (18%), dyspnea (14%), and cyanosis (8%). Congenital heart disease, Down syndrome, and other respiratory malformations were also found in a small proportion of these patients. Only 7 (14%) patients suffered from azygos lobe infection and were clinically cured after reasonable anti-infective treatment. Compared with the non-infected group, no valuable risk factors were found to be related to azygos lobe infection. All children who had azygos lobe infections responded to appropriate antibiotics therapy. There was no evidence that an azygos lobe was associated with recurrent infections.Conclusion: The clinical characteristics of children with azygos lobe are nonspecific and diagnosis relies on chest imaging. Some congenital abnormalities may be complicated with azygos lobe. It is reasonable to keep watch over those patients without symptoms. What is Known: • An azygos lobe is a congenital variation of the lung. • Azygos lobe can mimic various pathological conditions leading to misdiagnosis and inappropriate treatment in adults, which presents challenges during thoracic surgical interventions. What is New: • Azygos lobe in children may be complicated with other congenital abnormalities. • There is no evidence that azygos lobe is associated with recurrent infections. • After appropriate anti-infective treatment, those children with azygos lobe infections could be clinically cured.

Acute development of syringomyelia following TBM in a pediatric case.

BACKGROUND: Syringomyelia secondary to tuberculous meningitis (TBM) is rarely reported, and is usually a late complication. Acute development of syringomyelia following TBM is an exceedingly rare condition with only a few cases published in adults and no previous reports in children. CASE PRESENTATION: We present a case of syringomyelia as an acute complication of TBM in a 12-year-old boy despite appropriate chemotherapy. The patient developed spastic paraplegia of the lower limbs with fecal and urinary retention seventeen days after the initial symptoms of TBM. He was managed successfully with continued chemotherapy and high-dose intravenous immunoglobulin (IVIG). CONCLUSIONS: This case reminds us that syrinx formation may be responsible for early neurological deterioration in children being managed for TBM. IVIG may be considered as an effective treatment option for this situation.

Sacrococcygeal teratoma in one twin: a case report and literature review.

BACKGROUND: Sacrococcygeal teratoma is one of the most common congenital tumors in newborns and infancy. The incidence is 1 per 20,000-40,000 live births. Ultrasonography is an optimal method for prenatal screening and diagnosis of fetal sacrococcygeal teratoma. MRI can be used to assist in the diagnosis. However, sacrococcygeal teratoma in the twin pregnancy is rare. CASE PRESENTATION: We reported a case of one twin with sacrococcygeal teratoma in dichorionic-diamniotic twin pregnancy.One twin with sacrococcygeal teratoma was diagnosed at the second trimester by ultrasonic examination and another twin was normal. A regular and careful antenatal care was conducted by the multidisciplinary team. The parents refused to perform the fetal MRI and examine the chromosome of both twin.At 37 + 1 of gestation, planned cesarean section was performed. The healthy male co-twin (twin A) weighed 2880 g.The male twin with SCT (twin B) weighed 2900 g, complying with 6 × 3 × 3 cm cystic and solid mass in sacrococcygeal region. At four days of age twin B underwent excisional surgery of the sacrococcygeal teratoma and coccyx and discharged 7 days after surgery. The mother and both babies were followed up and are all in good health until now. CONCLUSION(S): Sacrococcygeal teratoma in twin pregnancy is rare. Early antenatal diagnosis is important. Once the sacrococcygeal teratoma is diagnosed, clinicians should be aware of the associated maternal and fetal complications. Expecting parents should be counseled by the multidisciplinary team about the management and prognosis of the STC twin and co-twin. Prompt surgical excision of the sacrococcygeal teratoma after birth should be suggested.

Twin pregnancy complicated with congenital Hemivertebra: report of two cases and literature review.

BACKGROUND: Hemivertebra deformity, involving one or multiple vertebral bodies, is one of the important causes of congenital scoliosis. Congenital fetal hemivertebrae could be diagnosed by ultrasonography and confirmed by fetal magnetic resonance imaging during pregnancy. However, reports of hemivertebrae in twins during the perinatal period are very rare. CASE PRESENTATION: We report two cases of congenital fetal hemivertebrae, each affecting one fetus in a dichorionic diamniotic (DCDA) twin pregnancy. We have also conducted a literature review of its prenatal screening, diagnosis, management, and outcomes. These two cases of congenital fetal hemivertebrae in one fetus of a DCDA twin were both initially found by ultrasonography and confirmed by fetal magnetic resonance imaging (MRI). One couple chose selective termination of the hemivertebrae fetus after they were extensively counseled by the multidisciplinary team regarding the treatment and prognosis of the hemivertebrae twin, and a healthy baby weighing 2320 g was delivered at the 37+ 1 gestational week. The other couple decided to continue the twin pregnancy and gave birth to two living newborns weighing 2580 g and 2060 g at 37+ 1 gestational weeks. These three babies were all in good health during follow-up. CONCLUSIONS: Based on our center's experience, comprehensive ultrasonography is necessary for early prenatal diagnosis of this condition. In addition, fetal MRI will confirm the diagnosis of hemivertebrae and provide parents with helpful information for their decision about the fate of the affected fetus.

Risk scoring system with MRI for intraoperative massive hemorrhage in placenta previa and accreta.

BACKGROUND: Placenta previa and accreta are serious obstetric conditions that are associated with a high risk of intraoperative massive hemorrhage. PURPOSE: To develop a scoring system for intraoperative massive hemorrhage combining MRI and clinical characteristics to predict the risk of massive hemorrhage in placenta previa and accreta STUDY TYPE: Retrospective cohort study. SUBJECTS: In all, 374 patients consisting of 259 patients with placenta previa and accreta after previous cesarean section (CS) for the derivation cohort and 115 patients for the validation cohort. FIELD STRENGTH/SEQUENCE: 1.5T single-shot fast spin-echo sequence. [Correction added on October 23, 2019, after first online publication: The field strength in the preceding sentence was corrected.] ASSESSMENT: Using the derivation cohort, clinical and MRI data were collected and multivariable logistic regressions analysis was conducted to develop a scoring system for prediction of intraoperative massive bleeding (blood loss volume > 2000 mL). Finally, the scoring system was validated on 115 patients. STATISTICAL TESTS: Student's t-test, Mann-Whitney U-test, X 2 statistics, multivariable analysis, and receiver operating characteristic (ROC) analysis. RESULTS: Ten indicators, including clinically maternal age (1 point), preoperative hemoglobin level (1 point), gravidity number (1 point), number of CS (1 point), and MRI T2 dark intraplacental bands (4 points), cervical canal length (3 points), placenta thickness on the uterine scar area (4 points), empty vascular shadow of the uterus (1 point), low signal discontinuity in the muscular layer of the posterior wall of the bladder (6 points) and attachment position of the placenta (1 point) were imputed. From the ROC analysis, a total score of 7 points was identified as the optimal cutoff value, allowing good differentiation of intraoperative massive bleeding in the derivation cohort (AUC, 0.863; 95% confidence interval [CI]: 0.811-0.916) and in the validation cohort (AUC, 0.933; 95% CI: 0.885-0.980). DATA CONCLUSION: The scoring system for intraoperative massive hemorrhage consists of MRI and clinical indicators, and using a cutoff value of 7 points for a high risk of massive bleeding, the developed scoring system could accurately assess the risk of intraoperative massive hemorrhage in patients with placenta previa and accreta. This scoring system can potentially reduce the incidence of intraoperative massive bleeding by identifying patients at high risk. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2020;51:947-958.

Radiomics-Based Machine Learning Technology Enables Better Differentiation Between Glioblastoma and Anaplastic Oligodendroglioma.

Purpose: The aim of this study was to test whether radiomics-based machine learning can enable the better differentiation between glioblastoma (GBM) and anaplastic oligodendroglioma (AO). Methods: This retrospective study involved 126 patients histologically diagnosed as GBM (n = 76) or AO (n = 50) in our institution from January 2015 to December 2018. A total number of 40 three-dimensional texture features were extracted from contrast-enhanced T1-weighted images using LIFEx package. Six diagnostic models were established with selection methods and classifiers. The optimal radiomics features were separately selected into three datasets with three feature selection methods [distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT)]. Then datasets were separately adopted into linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Specificity, sensitivity, accuracy, and area under curve (AUC) of each model were calculated to evaluate their diagnostic performances. Results: The diagnostic performance of machine learning models was superior to human readers. Both classifiers showed promising ability in discrimination with AUC more than 0.900 when combined with suitable feature selection method. For LDA-based models, the AUC of models were 0.986, 0.994, and 0.970 in the testing group, respectively. For the SVM-based models, the AUC of models were 0.923, 0.817, and 0.500 in the testing group, respectively. The over-fitting model was GBDT + SVM, suggesting that this model was too volatile that unsuitable for classification. Conclusion: This study indicates radiomics-based machine learning has the potential to be utilized in clinically discriminating GBM from AO.

Management of postpartum pulmonary embolism combined with retained placenta accreta: A case report.

RATIONALE: Retained placenta accreta is an increasing obstetric problem in recent years, and pulmonary embolism (PE) during pregnancy and the postpartum period is a vital condition, but lack of standard therapy guidelines. This report describes a case of postpartum PE combined with retained placenta accreta. PATIENT CONCERNS: A 27-year-old woman presenting with fever and dyspnea after delivery was admitted to our hospital with retained placenta accreta. DIAGNOSES: The patient was diagnosed with the infection, postpartum PE, and residual placenta. INTERVENTIONS: The antibiotics and low molecular weight heparin were initially started to cure the infection and control PE. Mifepristone was then used to promote the necrosis of residual placenta while long-term use of warfarin was served as continuous anticoagulant therapy. Hysteroscopic resection of retained placenta was not performed until thrombi had been almost disappeared after more than 2 months of anticoagulation therapy. OUTCOMES: The patient's menstruation returned to normal within several weeks after hysteroscopic resection and she completely recovered from PE after 3 months of anticoagulant therapy. LESSONS: Treatment of retained placenta accreta can be postponed when encountering complicated cases, such as postpartum PE. PE in perinatal stage can be managed referring to nonmaternal PE.