Longitudinal MRI in the context of in utero surgery for open spina bifida: A descriptive study.

INTRODUCTION: Fetal surgery for open spina bifida (OSB) requires comprehensive preoperative assessment using imaging for appropriate patient selection and to evaluate postoperative efficacy and complications. We explored patient access and conduct of fetal magnetic resonance imaging (MRI) for prenatal assessment of OSB patients eligible for fetal surgery. We compared imaging acquisition and reporting to the International Society of Ultrasound in Obstetrics and Gynecology MRI performance guidelines. MATERIAL AND METHODS: We surveyed access to fetal MRI for OSB in referring fetal medicine units (FMUs) in the UK and Ireland, and two NHS England specialist commissioned fetal surgery centers (FSCs) at University College London Hospital, and University Hospitals KU Leuven Belgium. To study MRI acquisition protocols, we retrospectively analyzed fetal MRI images before and after fetal surgery for OSB. RESULTS: MRI for fetal OSB was accessible with appropriate specialists available to supervise, perform, and report scans. The average time to arrange a fetal MRI appointment from request was 4 ± 3 days (range, 0-10), the average scan time available was 37 ± 16 min (range, 20-80 min), with 15 ± 11 min (range, 0-30 min) extra time to repeat sequences as required. Specific MRI acquisition protocols, and MRI reporting templates were available in only 32% and 18% of units, respectively. Satisfactory T2-weighted (T2W) brain imaging acquired in three orthogonal planes was achieved preoperatively in all centers, and 6 weeks postoperatively in 96% of FSCs and 78% of referring FMUs. However, for T2W spine image acquisition referring FMUs were less able to provide three orthogonal planes presurgery (98% FSC vs. 50% FMU, p < 0.001), and 6 weeks post-surgery (100% FSC vs. 48% FMU, p < 0.001). Other standard imaging recommendations such as T1-weighted (T1W), gradient echo (GE) or echoplanar fetal brain and spine imaging in one or two orthogonal planes were more likely available in FSCs compared to FMUs pre- and post-surgery (p < 0.001). CONCLUSIONS: There was timely access to supervised MRI for OSB fetal surgery assessment. However, the provision of images of the fetal brain and spine in sufficient orthogonal planes, which are required for determining eligibility and to determine the reversal of hindbrain herniation after fetal surgery, were less frequently acquired. Our evidence suggests the need for specific guidance in relation to fetal MRI for OSB. We propose an example guidance for MRI acquisition and reporting.

Duration of fetoscopic spina bifida repair does not affect the central nervous system in fetal lambs.

BACKGROUND: Prenatal spina bifida aperta repair improves neurologic outcomes yet comes with a significant risk of prematurity and uterine scar-related complications. To reduce such complications, different fetoscopic techniques, for example, with varying numbers of ports, are being explored. This has an effect on the duration of the procedure, potentially affecting central nervous system development. Both the condition and anesthesia can affect the central nervous system, particularly the hippocampus, a region crucial for prospective and episodic memory. Previous animal studies have shown the potential influence of anesthesia, premature delivery, and maternal surgery during pregnancy on this area. OBJECTIVE: This study aimed to compare the effects of 2- vs 3-port fetoscopic spina bifida aperta repair in the fetal lamb model using neuron count of the hippocampus as the primary outcome. STUDY DESIGN: Based on the hippocampal neuron count from previous lamb experiments, we calculated that we required 5 animals per group to achieve a statistical power of ≥ 80%. A spina bifida aperta defect was developed in fetal lambs at 75 days of gestation (term: 145 days). At 100 days, fetuses underwent either a 2-port or 3-port fetoscopic repair. At 143 days, all surviving fetuses were delivered by cesarean delivery, anesthetized, and transcardially perfused with a mixture of formaldehyde and gadolinium. Next, they underwent neonatal brain and spine magnetic resonance imaging after which these organs were harvested for histology. Hippocampus, frontal cortex, caudate nucleus, and cerebellum samples were immunostained to identify neurons, astrocytes, microglia, and markers associated with cell proliferation, myelination, and synapses. The degree of hindbrain herniation and the ventricular diameter were measured on magnetic resonance images and volumes of relevant brain and medulla areas were segmented. RESULTS: Both treatment groups included 5 fetuses and 9 unoperated littermates served as normal controls. The durations for both skin-to-skin (341±31 vs 287±40 minutes; P=.04) and fetal surgery (183±30 vs 128±22; P=.01) were longer for the 2-port approach than for the 3-port approach. There was no significant difference in neuron density in the hippocampus, frontal cortex, and cerebellum. In the caudate nucleus, the neuron count was higher in the 2-port group (965±156 vs 767±92 neurons/mm2; P=.04). There were neither differences in proliferation, astrogliosis, synaptophysin, or myelin. The tip of the cerebellar vermis was closer to the foramen magnum in animals undergoing the 2-port approach than in animals undergoing the 3-port approach (-0.72±0.67 vs -2.47±0.91 mm; P=.009). There was no significant difference in the ratio of the hippocampus, caudate nucleus, or cerebellar volume to body weight. For the spine, no difference was noted in spine volume-to-body weight ratio for the lower (L1-L2), middle (L3-L4), and higher (L5-L6) levels. Compared with controls, in repaired animals, the cerebellar vermis tip laid closer to the foramen magnum, parietal ventricles were enlarged, and medulla volumes were reduced. CONCLUSION: In the experimental spina bifida fetal lamb model, a 2-port repair took 40% longer than a 3-port repair. However, there was no indication of any relevant morphologic differences in the fetal brain.

Pre- and postnatal brain magnetic resonance imaging in congenital cytomegalovirus infection: a case report and a review of the literature.

BACKGROUND: Congenital cytomegalovirus infection (cCMV) is the most common known viral cause of neurodevelopmental delay in children. The risk of severe cerebral abnormalities and neurological sequelae is greatest when the infection occurs during the first trimester of pregnancy. Pre- and postnatal imaging can provide additional information and may help in the prediction of early neurological outcome. CASE PRESENTATION: This report presents the case of a newborn with cCMV infection with diffuse parenchymal calcifications, white matter (WM) abnormalities and cerebellar hypoplasia on postnatal brain imaging after magnetic resonance imaging (MRI) and neurosonogram (NSG) at 30 weeks showing lenticulostriate vasculopathy, bilateral temporal cysts and normal gyration pattern according to the gestational age (GA). No calcifications were seen on prenatal imaging. CONCLUSION: cCMV infection can still evolve into severe brain damage after 30 weeks of GA. For this reason, a two-weekly follow-up by fetal NSG with a repeat in utero MRI (iuMRI) in the late third trimester is recommended in cases with signs of active infection.

Uterine hemangioma in pregnancy: A case report and review of the literature.

INTRODUCTION: Uterine hemangioma is a rare benign vascular tumor which can cause bleeding problems in various age groups. Current knowledge on this rare condition in pregnancy is limited. We report on a recent case of uterine hemangioma in a pregnancy that was already diagnosed during her first trimester. We also provide a literature review to summarize the characteristics and outcomes of uterine hemangioma cases in pregnant women. MATERIAL AND METHODS: A systematic search was done of all published literature up to February 2021 using PubMed and Scopus databases. The selection process was registered using the online tool Rayyan QCRI. All data was described in a narrative format. The protocol was prospectively registered on PROSPERO (CRD42021237519). RESULTS: Fifteen case reports were included. In most cases, the diagnosis was established by antenatal ultrasound. More than half of the women developed a postpartum hemorrhage, necessitating a hysterectomy for bleeding control in half of the cases, although the risk for both seemed lower in those women in whom the hemangioma was diagnosed before delivery. One case of maternal mortality and two cases of fetal death were reported. There was one case of neonatal respiratory morbidity, although the neonatal data were not routinely reported upon. CONCLUSION: Current knowledge on uterine hemangioma in pregnancy is limited, but it seems to hold substantial risks for both pregnant women and their unborn child. We recommend routine screening for this condition at the standard mid-trimester anomaly scan. Pregnant women with uterine hemangioma should ideally be cared for in centers of expertise. An international registry will help to build a better understanding of this rare pathology.

Antenatal management of congenital diaphragmatic hernia: What's next ?

Congenital diaphragmatic hernia can be diagnosed in the prenatal period and its severity can be measured by fetal imaging. There is now level I evidence that, in selected cases, Fetoscopic Endoluminal Tracheal Occlusion with a balloon increases survival to discharge from the neonatal unit as well as the risk for prematurity. Both effects are dependent on the time point of tracheal occlusion. Fetoscopic Endoluminal Tracheal Occlusion may also lead to iatrogenic death when the balloon cannot be timely retrieved. The implementation of the findings from our clinical studies, may also vary based on local conditions. These may be different in terms of available skill set, access to fetal therapy, as well as outcome based on local neonatal management. We encourage prior benchmarking of local outcomes with optimal postnatal management, based on large enough numbers and using identical criteria as in the recent trials. We propose to work further on prenatal prediction methods, and the improvement of fetal intervention. In this manuscript, we describe a research agenda from a fetal medicine perspective. This research should be in parallel with innovation in neonatal and pediatric (surgical) management of this condition.

MRI Characteristics of Pediatric Renal Tumors: A SIOP-RTSG Radiology Panel Delphi Study.

BACKGROUND: The SIOP-Renal Tumor Study Group (RTSG) does not advocate invasive procedures to determine histology before the start of therapy. This may induce misdiagnosis-based treatment initiation, but only for a relatively small percentage of approximately 10% of non-Wilms tumors (non-WTs). MRI could be useful for reducing misdiagnosis, but there is no global consensus on differentiating characteristics. PURPOSE: To identify MRI characteristics that may be used for discrimination of newly diagnosed pediatric renal tumors. STUDY TYPE: Consensus process using a Delphi method. POPULATION: Not applicable. FIELD STRENGTH/SEQUENCE: Abdominal MRI including T1- and T2-weighted imaging, contrast-enhanced MRI, and diffusion-weighted imaging at 1.5 or 3 T. ASSESSMENT: Twenty-three radiologists from the SIOP-RTSG radiology panel with ≥5 years of experience in MRI of pediatric renal tumors and/or who had assessed ≥50 MRI scans of pediatric renal tumors in the past 5 years identified potentially discriminatory characteristics in the first questionnaire. These characteristics were scored in the subsequent second round, consisting of 5-point Likert scales, ranking- and multiple choice questions. STATISTICAL TESTS: The cut-off value for consensus and agreement among the majority was ≥75% and ≥60%, respectively, with a median of ≥4 on the Likert scale. RESULTS: Consensus on specific characteristics mainly concerned the discrimination between WTs and non-WTs, and WTs and nephrogenic rest(s) (NR)/nephroblastomatosis. The presence of bilateral lesions (75.0%) and NR/nephroblastomatosis (65.0%) were MRI characteristics indicated as specific for the diagnosis of a WT, and 91.3% of the participants agreed that MRI is useful to distinguish NR/nephroblastomatosis from WT. Furthermore, all participants agreed that age influenced their prediction in the discrimination of pediatric renal tumors. DATA CONCLUSION: Although the discrimination of pediatric renal tumors based on MRI remains challenging, this study identified some specific characteristics for tumor subtypes, based on the shared opinion of experts. These results may guide future validation studies and innovative efforts. LEVEL OF EVIDENCE: 3 Technical Efficacy Stage: 3.

What brain abnormalities can magnetic resonance imaging detect in foetal and early neonatal spina bifida: a systematic review.

PURPOSE: Open spina bifida (OSB) encompasses a wide spectrum of intracranial abnormalities. With foetal surgery as a new treatment option, robust intracranial imaging is important for comprehensive preoperative evaluation and prognostication. We aimed to determine the incidence of infratentorial and supratentorial findings detected by magnetic resonance imaging (MRI) alone and MRI compared to ultrasound. METHODS: Two systematic reviews comparing MRI to ultrasound and MRI alone were conducted on MEDLINE, EMBASE, and Cochrane databases identifying studies of foetal OSB from 2000 to 2020. Intracranial imaging findings were analysed at ≤ 26 or > 26 weeks gestation and neonates (≤ 28 days). Data was independently extracted by two reviewers and meta-analysis was performed where possible. RESULTS: Thirty-six studies reported brain abnormalities detected by MRI alone in patients who previously had an ultrasound. Callosal dysgenesis was identified in 4/29 cases (2 foetuses ≤ 26 weeks, 1 foetus under any gestation, and 1 neonate ≤ 28 days) (15.1%, CI:5.7-34.3%). Heterotopia was identified in 7/40 foetuses ≤ 26 weeks (19.8%, CI:7.7-42.2%), 9/36 foetuses > 26 weeks (25.3%, CI:13.7-41.9%), and 64/250 neonates ≤ 28 days (26.9%, CI:15.3-42.8%). Additional abnormalities included aberrant cortical folding and other Chiari II malformation findings such as lower cervicomedullary kink level, tectal beaking, and hypoplastic tentorium. Eight studies compared MRI directly to ultrasound, but due to reporting inconsistencies, it was not possible to meta-analyse. CONCLUSION: MRI is able to detect anomalies hitherto underestimated in foetal OSB which may be important for case selection. In view of increasing prenatal OSB surgery, further studies are required to assess developmental consequences of these findings.

Super-resolution Reconstruction MRI Application in Fetal Neck Masses and Congenital High Airway Obstruction Syndrome.

OBJECTIVE: Reliable airway patency diagnosis in fetal tracheolaryngeal obstruction is crucial to select and plan ex utero intrapartum treatment (EXIT) surgery. We compared the clinical utility of magnetic resonance imaging (MRI) super-resolution reconstruction (SRR) of the trachea, which can mitigate unpredictable fetal motion effects, with standard 2-dimensional (2D) MRI for airway patency diagnosis and assessment of fetal neck mass anatomy. STUDY DESIGN: A single-center case series of 7 consecutive singleton pregnancies with complex upper airway obstruction (2013-2019). SETTING: A tertiary fetal medicine unit performing EXIT surgery. METHODS: MRI SRR of the trachea was performed involving rigid motion correction of acquired 2D MRI slices combined with robust outlier detection to reconstruct an isotropic high-resolution volume. SRR, 2D MRI, and paired data were blindly assessed by 3 radiologists in 3 experimental rounds. RESULTS: Airway patency was correctly diagnosed in 4 of 7 cases (57%) with 2D MRI as compared with 2 of 7 cases (29%) with SRR alone or paired 2D MRI and SRR. Radiologists were more confident (P = .026) in airway patency diagnosis when using 2D MRI than SRR. Anatomic clarity was higher with SRR (P = .027) or paired data (P = .041) in comparison with 2D MRI alone. Radiologists detected further anatomic details by using paired images versus 2D MRI alone (P < .001). Cognitive load, as assessed by the NASA Task Load Index, was increased with paired or SRR data in comparison with 2D MRI. CONCLUSION: The addition of SRR to 2D MRI does not increase fetal airway patency diagnostic accuracy but does provide improved anatomic information, which may benefit surgical planning of EXIT procedures.

Cortical spectral matching and shape and volume analysis of the fetal brain pre- and post-fetal surgery for spina bifida: a retrospective study.

PURPOSE: A retrospective study was performed to study the effect of fetal surgery on brain development measured by MRI in fetuses with myelomeningocele (MMC). METHODS: MRI scans of 12 MMC fetuses before and after surgery were compared to 24 age-matched controls without central nervous system abnormalities. An automated super-resolution reconstruction technique generated isotropic brain volumes to mitigate 2D MRI fetal motion artefact. Unmyelinated white matter, cerebellum and ventricles were automatically segmented, and cerebral volume, shape and cortical folding were thereafter quantified. Biometric measures were calculated for cerebellar herniation level (CHL), clivus-supraocciput angle (CSO), transverse cerebellar diameter (TCD) and ventricular width (VW). Shape index (SI), a mathematical marker of gyrification, was derived. We compared cerebral volume, surface area and SI before and after MMC fetal surgery versus controls. We additionally identified any relationship between these outcomes and biometric measurements. RESULTS: MMC ventricular volume/week (mm3/week) increased after fetal surgery (median: 3699, interquartile range (IQR): 1651-5395) compared to controls (median: 648, IQR: 371-896); P = 0.015. The MMC SI is higher pre-operatively in all cerebral lobes in comparison to that in controls. Change in SI/week in MMC fetuses was higher in the left temporal lobe (median: 0.039, IQR: 0.021-0.054), left parietal lobe (median: 0.032, IQR: 0.023-0.039) and right occipital lobe (median: 0.027, IQR: 0.019-0.040) versus controls (P = 0.002 to 0.005). Ventricular volume (mm3) and VW (mm) (r = 0.64), cerebellar volume and TCD (r = 0.56) were moderately correlated. CONCLUSIONS: Following fetal myelomeningocele repair, brain volume, shape and SI were significantly different from normal in most cerebral layers. Morphological brain changes after fetal surgery are not limited to hindbrain herniation reversal. These findings may have neurocognitive outcome implications and require further evaluation.

The prevalence of brain lesions after in utero surgery for twin-to-twin transfusion syndrome on third-trimester MRI: a retrospective cohort study.

OBJECTIVE: Due to the increased risk of antenatal brain lesions, we offer a third-trimester magnetic resonance imaging (MRI) scan to all patients who underwent an in utero intervention for twin-twin transfusion syndrome (TTTS). However, the usefulness of such a policy has not been demonstrated yet. Therefore, we determined the prevalence of antenatal brain lesions detected on third-trimester MRI and the proportion of lesions detected exclusively on MRI. MATERIALS AND METHODS: We conducted a retrospective cohort study of monochorionic diamniotic twin pregnancies complicated by TTTS that underwent laser coagulation of the vascular anastomoses or fetal reduction by umbilical cord occlusion between 2010 and 2017. We reviewed the third-trimester MRI findings and compared those with the prenatal ultrasonography. RESULTS: Of the 141 patients treated with laser coagulation and 17 managed by cord occlusion, 112/141 (79%) and 15/17 (88%) patients reached 28 weeks. Of those, 69/112 (62%) and 11/15 (73%) underwent an MRI between 28 and 32 weeks. After laser coagulation, MRI detected an antenatal brain lesion in 6 of 69 pregnancies (9%) or in 6 of 125 fetuses (5%). In 4 cases (67%), the lesion was detected only on MRI. In the 11 patients treated with cord occlusion, no brain lesions were diagnosed. CONCLUSION: The prevalence of brain lesions detected by third-trimester MRI is higher compared to prenatal ultrasonography alone, making MRI a useful adjunct to detect antenatal brain lesions in twin pregnancies after in utero treatment for TTTS. KEY POINTS: • In utero interventions for twin-to-twin transfusion syndrome (TTTS) do not prevent the occurrence of antenatal brain lesions. • Fetal magnetic resonance imaging (MRI) has high accuracy in detecting anomalies of cortical development and can be a useful adjunct to ultrasonography in diagnosing certain brain abnormalities. • After laser coagulation of the anastomoses for TTTS, third-trimester MRI diagnosed a brain lesion that was not detected earlier on ultrasound scan in 6% of pregnancies.

An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI.

High-resolution volume reconstruction from multiple motion-corrupted stacks of 2D slices plays an increasing role for fetal brain Magnetic Resonance Imaging (MRI) studies. Currently existing reconstruction methods are time-consuming and often require user interactions to localize and extract the brain from several stacks of 2D slices. We propose a fully automatic framework for fetal brain reconstruction that consists of four stages: 1) fetal brain localization based on a coarse segmentation by a Convolutional Neural Network (CNN), 2) fine segmentation by another CNN trained with a multi-scale loss function, 3) novel, single-parameter outlier-robust super-resolution reconstruction, and 4) fast and automatic high-resolution visualization in standard anatomical space suitable for pathological brains. We validated our framework with images from fetuses with normal brains and with variable degrees of ventriculomegaly associated with open spina bifida, a congenital malformation affecting also the brain. Experiments show that each step of our proposed pipeline outperforms state-of-the-art methods in both segmentation and reconstruction comparisons including expert-reader quality assessments. The reconstruction results of our proposed method compare favorably with those obtained by manual, labor-intensive brain segmentation, which unlocks the potential use of automatic fetal brain reconstruction studies in clinical practice.

Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks.

Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks at both pixel level and structure level. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions.

Validation of the Fetal Lamb Model of Spina Bifida.

A randomized trial demonstrated that fetal spina bifida (SB) repair is safe and effective yet invasive. New less invasive techniques are proposed but are not supported by adequate experimental studies. A validated animal model is needed to bridge the translational gap to the clinic and should mimic the human condition. Introducing a standardized method, we comprehensively and reliably characterize the SB phenotype in two lamb surgical models with and without myelotomy as compared to normal lambs. Hindbrain herniation measured on brain magnetic resonance imaging (MRI) was the primary outcome. Secondary outcomes included gross examination with cerebrospinal fluid (CSF) leakage test, neurological examination with locomotor assessment, whole-body MRI, motor and somatosensory evoked potentials; brain, spinal cord, hindlimb muscles, bladder and rectum histology and/or immunohistochemistry. We show that the myelotomy model best phenocopies the anatomy, etiopathophysiology and symptomatology of non-cystic SB. This encompasses hindbrain herniation, ventriculomegaly, posterior fossa anomalies, loss of brain neurons; lumbar CSF leakage, hindlimb somatosensory-motor deficit with absence of motor and somatosensory evoked potentials due to loss of spinal cord neurons, astroglial cells and myelin; urinary incontinence. This model obtains the highest validity score for SB animal models and is adequate to assess the efficacy of novel fetal therapies.

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation.

Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning.

Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

GIFT-Cloud: A data sharing and collaboration platform for medical imaging research.

OBJECTIVES: Clinical imaging data are essential for developing research software for computer-aided diagnosis, treatment planning and image-guided surgery, yet existing systems are poorly suited for data sharing between healthcare and academia: research systems rarely provide an integrated approach for data exchange with clinicians; hospital systems are focused towards clinical patient care with limited access for external researchers; and safe haven environments are not well suited to algorithm development. We have established GIFT-Cloud, a data and medical image sharing platform, to meet the needs of GIFT-Surg, an international research collaboration that is developing novel imaging methods for fetal surgery. GIFT-Cloud also has general applicability to other areas of imaging research. METHODS: GIFT-Cloud builds upon well-established cross-platform technologies. The Server provides secure anonymised data storage, direct web-based data access and a REST API for integrating external software. The Uploader provides automated on-site anonymisation, encryption and data upload. Gateways provide a seamless process for uploading medical data from clinical systems to the research server. RESULTS: GIFT-Cloud has been implemented in a multi-centre study for fetal medicine research. We present a case study of placental segmentation for pre-operative surgical planning, showing how GIFT-Cloud underpins the research and integrates with the clinical workflow. CONCLUSIONS: GIFT-Cloud simplifies the transfer of imaging data from clinical to research institutions, facilitating the development and validation of medical research software and the sharing of results back to the clinical partners. GIFT-Cloud supports collaboration between multiple healthcare and research institutions while satisfying the demands of patient confidentiality, data security and data ownership.

Parenchymal Volumetric Assessment as a Predictive Tool to Determine Renal Function Benefit of Nephron-Sparing Surgery Compared with Radical Nephrectomy.

PURPOSE: To develop a preoperative prediction model using a computer-assisted volumetric assessment of potential spared parenchyma to estimate the probability of chronic kidney disease (CKD, estimated glomerular filtration rate [eGFR] <60 mL/min/1.73 m(2)) 6 months from extirpative renal surgery (nephron-sparing surgery [NSS] or radical nephrectomy [RN]). PATIENTS AND METHODS: Retrospective analysis of patients who underwent NSS or RN at our institution from January 2000 to June 2013 with a compatible CT scan 6-month renal function follow-up was performed. Primary outcome was defined as the accuracy of 6-month postoperative eGFR compared with actual postoperative eGFR based on root mean square error (RMSE). Models were constructed using renal volumes and externally validated. A clinical tool was developed on the best model after a given surgical procedure using area under the curve (AUC). RESULTS: We identified 130 (51 radical, 79 partial) patients with a median age of 58 years (interquartile range [IQR] 48-67) and preoperative eGFR of 82.1 (IQR 65.9-104.3); postoperative CKD (eGFR <60) developed in 42% (55/130). We performed various linear regression models to predict postoperative eGFR. The Quadratic model was the highest performing model, which relied only on preoperative GFR and the volumetric data for a RMSE of 15.3 on external validation corresponding to a clinical tool with an AUC of 0.89. CONCLUSION: Volumetric-based assessment provides information to predict postoperative eGFR. A tool based on this equation may assist surgical counseling regarding renal functional outcomes before renal tumor surgical procedures.

Tumour-related imaging parameters predicting the percentage of preserved normal renal parenchyma following nephron sparing surgery: a retrospective study.

OBJECTIVES: To examine pre-operative imaging parameters that predict the residual amount of healthy renal parenchyma after nephron sparing surgery (NSS) for renal tumours, as this can help stratify patients towards the optimal surgical choice. METHODS: Ninety-eight patients with the diagnosis of a solitary unilateral renal tumour and with pre- and post-operative imaging were included in this retrospective study. Imaging, patient and surgical parameters were acquired and their correlation to the percentage decrease of healthy renal parenchyma following surgery was statistically examined to find the most significant predictor of nephron sparing. RESULTS: Loss of healthy renal parenchyma was highest in patients with renal sinus tumour involvement (P = 0.003) and anterior tumours (P = 0.006), but not significantly correlated with medial/lateral location (P = 0.940) or exophytic/endophytic tumour growth (P = 0.244). The correlation of tumour size with the percentage of parenchymal sparing did not quite reach statistical significance (P = 0.053), but involvement of the urinary collecting system (P = 0.008) was a very good predictor of complications. Loss of healthy renal parenchyma was higher in patients with high-grade surgical complications (P = 0.001). CONCLUSIONS: Several pre-operative parameters correlate to percentage nephron sparing after NSS. Anterior tumour location and renal sinus involvement proved to be the best predictors of loss of healthy renal parenchyma.