Showing papers by "Elisenda Eixarch published in 2020"

Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes

Abstract: The goal of this study was to evaluate the maturity of current Deep Learning classification techniques for their application in a real maternal-fetal clinical environment. A large dataset of routinely acquired maternal-fetal screening ultrasound images (which will be made publicly available) was collected from two different hospitals by several operators and ultrasound machines. All images were manually labeled by an expert maternal fetal clinician. Images were divided into 6 classes: four of the most widely used fetal anatomical planes (Abdomen, Brain, Femur and Thorax), the mother’s cervix (widely used for prematurity screening) and a general category to include any other less common image plane. Fetal brain images were further categorized into the 3 most common fetal brain planes (Trans-thalamic, Trans-cerebellum, Trans-ventricular) to judge fine grain categorization performance. The final dataset is comprised of over 12,400 images from 1,792 patients, making it the largest ultrasound dataset to date. We then evaluated a wide variety of state-of-the-art deep Convolutional Neural Networks on this dataset and analyzed results in depth, comparing the computational models to research technicians, which are the ones currently performing the task daily. Results indicate for the first time that computational models have similar performance compared to humans when classifying common planes in human fetal examination. However, the dataset leaves the door open on future research to further improve results, especially on fine-grained plane categorization.

Structural Brain Changes during the Neonatal Period in a Rabbit Model of Intrauterine Growth Restriction.

Abstract: BACKGROUND Intrauterine growth restriction (IUGR) is associated with abnormal neurodevelopment, but the associated structural brain changes are poorly documented. The aim of this study was to describe in an animal model the brain changes at the cellular level in the gray and white matter induced by IUGR during the neonatal period. METHODS The IUGR model was surgically induced in pregnant rabbits by ligating 40-50% of the uteroplacental vessels in 1 horn, whereas the uteroplacental vessels of the contralateral horn were not ligated. After 5 days, IUGR animals from the ligated horn and controls from the nonligated were delivered. On the day of delivery, perinatal data and placentas were collected. On postnatal day 1, functional changes were first evaluated, and thereafter, neuronal arborization in the frontal cortex and density of pre-oligodendrocytes, astrocytes, and microglia in the corpus callosum were evaluated. RESULTS Higher stillbirth in IUGR fetuses together with a reduced birth weight as compared to controls was evidenced. IUGR animals showed poorer functional results, an altered neuronal arborization pattern, and a decrease in the pre-oligodendrocytes, with no differences in microglia and astrocyte densities. CONCLUSIONS Overall, in the rabbit model used, IUGR is related to functional and brain changes evidenced already at birth, including changes in the neuronal arborization and abnormal oligodendrocyte maturation.

Ex-vivo mechanical sealing properties and toxicity of a bioadhesive patch as sealing system for fetal membrane iatrogenic defects

Abstract: Preterm prelabor rupture of membranes (PPROM) is the most frequent complication of fetal surgery. Strategies to seal the membrane defect created by fetoscopy aiming to reduce the occurrence of PPROM have been attempted with little success. The objective of this study was to evaluate the ex-vivo mechanical sealing properties and toxicity of four different bioadhesives integrated in semi-rigid patches for fetal membranes. We performed and ex-vivo study using term human fetal membranes to compare the four integrated patches composed of silicone or silicone-polyurethane combined with dopaminated-hyaluronic acid or hydroxypropyl methylcellulose (HPMC). For mechanical sealing properties, membranes were mounted in a multiaxial inflation device with saline, perforated and sealed with the 4 combinations. We measured bursting pressure and maximum pressure free of leakage (n = 8). For toxicity, an organ culture of membranes sealed with the patches was used to measure pyknotic index (PI) and lactate dehydrogenase (LDH) concentration (n = 5). All bioadhesives achieved appropriate bursting pressures, but only HPMC forms achieved high maximum pressures free of leakage. Concerning toxicity, bioadhesives showed low PI and LDH levels, suggesting no cell toxicity. We conclude that a semi-rigid patch coated with HPMC achieved ex-vivo sealing of iatrogenic defects in fetal membranes with no signs of cell toxicity. These results warrant further research addressing long-term adhesiveness and feasibility as a sealing system for fetoscopy.

Deep Q-CapsNet Reinforcement Learning Framework for Intrauterine Cavity Segmentation in TTTS Fetal Surgery Planning

Abstract: Fetoscopic laser photocoagulation is the most effective treatment for Twin-to-Twin Transfusion Syndrome, a condition affecting twin pregnancies in which there is a deregulation of blood circulation through the placenta, that can be fatal to both babies. For the purposes of surgical planning, we design the first automatic approach to detect and segment the intrauterine cavity from axial, sagittal and coronal MRI stacks. Our methodology relies on the ability of capsule networks to successfully capture the part-whole interdependency of objects in the scene, particularly for unique class instances ( i.e., intrauterine cavity). The presented deep Q-CapsNet reinforcement learning framework is built upon a context-adaptive detection policy to generate a bounding box of the womb. A capsule architecture is subsequently designed to segment (or refine) the whole intrauterine cavity. This network is coupled with a strided nnU-Net feature extractor, which encodes discriminative feature maps to construct strong primary capsules. The method is robustly evaluated with and without the localization stage using 13 performance measures, and directly compared with 15 state-of-the-art deep neural networks trained on 71 singleton and monochorionic twin pregnancies. An average Dice score above 0.91 is achieved for all ablations, revealing the potential of our approach to be used in clinical practice.

TTTS-STgan: Stacked Generative Adversarial Networks for TTTS Fetal Surgery Planning Based on 3D Ultrasound

Abstract: Twin-to-twin transfusion syndrome (TTTS) is characterized by an unbalanced blood transfer through placental abnormal vascular connections. Prenatal ultrasound (US) is the imaging technique to monitor monochorionic pregnancies and diagnose TTTS. Fetoscopic laser photocoagulation is an elective treatment to coagulate placental communications between both twins. To locate the anomalous connections ahead of surgery, preoperative planning is crucial. In this context, we propose a novel multi-task stacked generative adversarial framework to jointly learn synthetic fetal US generation, multi-class segmentation of the placenta, its inner acoustic shadows and peripheral vasculature, and placenta shadowing removal. Specifically, the designed architecture is able to learn anatomical relationships and global US image characteristics. In addition, we also extract for the first time the umbilical cord insertion on the placenta surface from 3D HD-flow US images. The database consisted of 70 US volumes including singleton, mono- and dichorionic twins at 17-37 gestational weeks. Our experiments show that 71.8% of the synthesized US slices were categorized as realistic by clinicians, and that the multi-class segmentation achieved Dice scores of 0.82 ± 0.13, 0.71 ± 0.09, and 0.72 ± 0.09, for placenta, acoustic shadows, and vasculature, respectively. Moreover, fetal surgeons classified 70.2% of our completed placenta shadows as satisfactory texture reconstructions. The umbilical cord was successfully detected on 85.45% of the volumes. The framework developed could be implemented in a TTTS fetal surgery planning software to improve the intrauterine scene understanding and facilitate the location of the optimum fetoscope entry point.

Maternal high-dose valacyclovir and its correlation with newborn blood viral load and outcome in congenital cytomegalovirus infection

Abstract: Currently, there is no validated treatment for fetal cytomegalovirus (CMV). Two studies suggest that high-dose maternal valacyclovir decreases fetal viral load and improves outcomes in moderately-s...

Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning

Abstract: Twin-to-twin transfusion syndrome (TTTS) is a serious condition that occurs in about 10–15% of monochorionic twin pregnancies. In most instances, the blood flow is unevenly distributed throughout the placenta anastomoses leading to the death of both fetuses if no surgical procedure is performed. Fetoscopic laser coagulation is the optimal therapy to considerably improve co-twin prognosis by clogging the abnormal anastomoses. Notwithstanding progress in recent years, TTTS surgery is highly risky. Computer-assisted planning of the intervention can thus improve the outcome. In this work, we implement a GPU-accelerated random walker (RW) algorithm to detect the placenta, both umbilical cord insertions and the placental vasculature from Doppler ultrasound (US). Placenta and background seeds are manually initialized in 10–20 slices (out of 245). Vessels are automatically initialized in the same slices by means of Otsu thresholding. The RW finds the boundaries of the placenta and reconstructs the vasculature. We evaluate our semiautomatic method in 5 monochorionic and 24 singleton pregnancies. Although satisfactory performance is achieved on placenta segmentation (Dice ≥ 84.0%), some vascular connections are still neglected due to the presence of US reverberation artifacts (Dice ≥ 56.9%). We also compared inter-user variability and obtained Dice coefficients of ≥ 76.8% and ≥ 97.42% for placenta and vasculature, respectively. After a 3-min manual initialization, our GPU approach speeds the computation 10.6 times compared to the CPU. Our semiautomatic method provides a near real-time user experience and requires short training without compromising the segmentation accuracy. A powerful approach is thus presented to rapidly plan the fetoscope insertion point ahead of TTTS surgery.