A major obstacle in applying machine learning for medical fields is the disparity between the data distribution of the training images and the data encountered in clinics. This phenomenon can be explained by inconsistent acquisition techniques and large variations across the patient spectrum. The result is poor translation of the trained models to the clinic, which limits their implementation in medical practice. Patient-specific trained networks could provide a potential solution. Although patient-specific approaches are usually infeasible because of the expenses associated with on-the-fly labeling, the use of generative adversarial networks enables this approach. This study proposes a patient-specific approach based on generative adversarial networks. In the presented training pipeline, the user trains a patient-specific segmentation network with extremely limited data which is supplemented with artificial samples generated by generative adversarial models. This approach is demonstrated in endoscopic video data captured during fetoscopic laser coagulation, a procedure used for treating twin-to-twin transfusion syndrome by ablating the placental blood vessels. Compared to a standard deep learning segmentation approach, the pipeline was able to achieve an intersection over union score of 0.60 using only 20 annotated images compared to 100 images using a standard approach. Furthermore, training with 20 annotated images without the use of the pipeline achieves an intersection over union score of 0.30, which, therefore, corresponds to a 100% increase in performance when incorporating the pipeline. A pipeline using GANs was used to generate artificial data which supplements the real data, this allows patient-specific training of a segmentation network. We show that artificial images generated using GANs significantly improve performance in vessel segmentation and that training patient-specific models can be a viable solution to bring automated vessel segmentation to the clinic.

BACKGROUND: Our objective was to investigate the association between the presence of placental anastomoses and intertwin differences in renin-angiotensin-aldosterone activation in monochorionic twins using amniotic fluid aldosterone (AF-ALD) levels. In addition, this study also examined the association between AF-ALD and the ALD levels in the umbilical cord blood (UCB-ALD) in monochorionic twins.
METHODS: This prospective study included monochorionic diamniotic (MD) twin pregnancies that were not complicated by twin-to-twin transfusion syndrome (TTTS) at delivery. Amniotic fluid and umbilical cord vein blood samples were collected from each twin at delivery, and the ALD levels were measured subsequently. The MD twins were divided into two groups: those with placental anastomoses and those without anastomoses owing to fetoscopic laser surgery. The differences in the AF-ALD levels between the larger and smaller twins were analyzed.
RESULTS: The AF-ALD levels showed a strong and significant positive correlation with UCB-ALD levels in 131 MD twins (r = 0.804, p < 0.001). Intertwin differences were examined in 41 and 28 pairs of MD twins with and without placental anastomoses, respectively. The AF-ALD levels in the smaller twins were significantly higher than those in the larger twins among the pairs of MD twins with placental anastomoses (p = 0.003); however, no statistically significant intertwin differences were observed among the twins without placental anastomoses (p > 0.05).
CONCLUSIONS: The AF-ALD levels reflect the UCB-ALD levels in MD twins. The presence of placental anastomoses led to intertwin discordance in the ALD levels in MD twins even uncomplicated with TTTS. It was considered that monochorionic twins have this clinical background, and it leads to the development of TTTS.

OBJECTIVE: To describe fetal brain Magnetic Resonance Imaging (MRI) findings in a large series of monochorionic (MC) pregnancies complicated by Twin Anemia-Polycythemia Sequence (TAPS) prenatally diagnosed, so to characterize the potential intracranial complications associated with this condition, their frequency and potential treatment options.
METHODS: This is a retrospective study of MC twin pregnancies complicated by TAPS and undergone fetal MRI in a single institution from 2006 to 2023. MRI control was performed and post-natal ultrasound (US) or MRI were available.
RESULTS: 1250 MC pregnancies were evaluated in our institution. 50 pregnancies (4%) were diagnosed with TAPS, 29 underwent a fetal brain MRI. 13/29 pregnancies (44.8%) demonstrated brain findings at MRI in at least a twin. Neuroradiological findings were detected in 14/57 twins (24.6%). We detected four main categories of findings: hemorrhagic lesions, T2-weighted white-matter hyperintensities (WMH), brain edema-swelling and venous congestion. Nineteen findings were present in the anemic and three in the polycythemic twins, with a statistically significant ratio between the two groups (p-value = 0.01). Intrauterine MRI follow-up demonstrated the sequalae of hemorrhagic lesions. A complete regression of brain swelling, veins prominence and T2-WMHs was demonstrated after treatment. Postnatal imaging confirmed prenatal features.
CONCLUSIONS: Our work demonstrates that TAPS-related MRI anomalies consisted in edematous/hemorrhagic lesions that occur mostly in anemic rather than in polycythemic twins. Fetoscopic laser surgery could have a potential decongestant role. Therefore, prenatal MRI may help in counselling and management in TAPS pregnancies, especially for the planning of therapy and the monitoring of its efficacy.

Twin reversed arterial perfusion (TRAP) sequence is a rare complication of monochorionic twinning whereby a donor twin perfuses an acardiac twin via aberrant vascular anastomoses. The resulting paradoxical retrograde blood flow supplying the acardiac twin is oxygen-poor, leading to some of the most severe malformations encountered in humans. Though the first descriptions of acardiac twins date back to at least the 16th century, the pathophysiologic processes which underpin the development of TRAP sequence are still being elucidated. Theories on the pathogenesis of TRAP sequence include deficiencies intrinsic to the embryo and primary abnormalities of the placental vasculature. Autopsy studies continue to provide clues to the underlying pathogenesis of TRAP sequence, and the characterization of the spectrum of manifestations that can be observed in acardiac twins. Herein, we present the clinical, autopsy, and molecular findings in a unique case of TRAP sequence. Novel findings include a primitive cloaca-like structure and chromosomal aberrations involving 6q11.1 and 15q25.1.

BACKGROUND: We aimed to investigate the incidence, prenatal factors and outcomes of twin-to-twin transfusion (TTTS) with right ventricular outflow tract obstruction (RVOTO).
METHODS: A systematic search was conducted to identify relevant studies published until February 2023 in English using the databases PubMed, Scopus and Web of Science. Studies reporting on pregnancies with TTTS and RVOTO were included. The random-effect model pooled the mean differences or odds ratios (OR) and the corresponding 95% confidence intervals. Heterogeneity was assessed using the I2 value.
RESULTS: A total of 17 studies encompassing 4332 TTTS pregnancies, of which 225 cases had RVOTO, were included. Incidence of RVOTO at time of TTTS diagnosis was 6%. In all, 134/197 (68%) had functional pulmonary stenosis and 62/197 (32%) had functional pulmonary atresia. Of these, 27% resolved following laser and 55% persisted after birth. Of those persisting, 27% required cardiac valve procedures. Prenatal associations were TTTS stage III (53% vs 39% in no-RVOTO), stage IV TTTS (28% in RVOTO vs 12% in no-RVOTO) and ductus venosus reversed a-wave (60% in RVOTO vs 19% in no-RVOTO). Gestational age at laser and gestational age at delivery were comparable between groups. Survival outcomes were also comparable between groups, including fetal demise of 26%, neonatal death of 12% and 6-month survival of 82% in RVOTO group. Findings were similar when subgroup analysis was done for studies including head-to-head analysis.
CONCLUSIONS: RVOT occurs in about 6% of the recipient twins with TTTS, especially in stages III and IV and those with reversed ductus venosus a-wave. The findings from this systematic review support the need for a thorough cardiac assessment of pregnancies complicated by TTTS, both before and after laser, to maximize perinatal outcome, and the importance of early diagnosis of TTTS and timely management.

Endoscopes navigate within the human body to observe anatomical structures with minimal invasiveness. A major shortcoming of their use is their narrow field-of-view during navigation in large, hollow anatomical regions. Mosaics of endoscopic images can provide surgeons with a map of the tool\'s environment. This would facilitate procedures, improve their efficiency, and potentially generate better patient outcomes. The emergence of magnetically steered endoscopes opens the way to safer procedures and creates an opportunity to provide robotic assistance both in the generation of the mosaic map and in navigation within this map. This paper proposes methods to autonomously navigate magnetic endoscopes to 1) generate endoscopic image mosaics and 2) use these mosaics as user interfaces to navigate throughout the explored area. These are the first strategies, which allow autonomous magnetic navigation in large, hollow organs during minimally invasive surgeries. The feasibility of these methods is demonstrated experimentally both in vitro and ex vivo in the context of the treatment of twin-to-twin transfusion syndrome. This minimally invasive procedure is performed in utero and necessitates coagulating shared vessels of twin fetuses on the placenta. A mosaic of the vasculature in combination with autonomous navigation has the potential to significantly facilitate this challenging surgery.

BACKGROUND: Our objective was to investigate outcomes in twin-to-twin transfusion syndrome (TTTS) treated with fetoscopic laser surgery (FLS) at <18 weeks vs ≥18 weeks, and to conduct subgroup analysis of TTTS with FLS at <16 weeks vs 16-18 weeks.
METHODS: PubMed, Scopus and Web of Science were searched systematically from inception until May 2023. Primary outcome was survival, and secondary outcomes included preterm premature rupture of membranes (PPROM), preterm birth and gestational age (GA) at delivery.
RESULTS: Nine studies encompassing 1691 TTTS pregnancies were included. TTTS stage III was significantly more common in TTTS pregnancies treated with FLS at <18 weeks (odds ratio [OR] 2.84, 95% confidence interval [CI] 1.24-6.54), and procedure duration was shorter at <18 weeks (MD -5.27 minutes, 95% CI -9.19 to -1.34). GA at delivery was significantly earlier in TTTS pregnancies treated with FLS at <18 weeks (MD -3.12 weeks, 95% CI -6.11 to -0.13). There were no significant differences in outcomes, including PPROM, PPROM at <7 days post-FLS, preterm birth at <28 and <32 weeks, delivery at <7 days post-FLS, and survival outcomes, including fetal demise, live birth and neonatal survival. Similarly, TTTS stage III was more common in TTTS with FLS at <16 weeks than at 16-18 weeks (OR 2.95, 95% CI 1.62-5.35), with no significant differences in the aforementioned outcomes.
CONCLUSIONS: In early TTTS treated with FLS, outcomes were comparable between those treated at <18 weeks compared with ≥18 weeks except for GA at delivery, which was 3 weeks earlier. In the subset treated at <16 weeks vs 16-18 weeks, the procedure was feasible without an increased risk of very early preterm birth or perinatal mortality.

BACKGROUND: Preterm prelabor rupture of membranes (PPROM) remains a major complication of fetal laser surgery in the treatment of twin-to-twin transfusion syndrome (TTTS). The aim of the study was to determine the impact of cannula size on pregnancy outcomes, with a particular focus on PPROM.
METHODS: The protocol was developed and registered in the PROSPERO database under registration number CRD42022333630. The PubMed, Web of Science, and EMBASE databases were searched electronically on May 18, 2022, and updated on March 2, 2023, utilizing a combination of the relevant MeSH terms, keywords, and word variants for \"TTTS\" and \"laser\". Randomized controlled trials, prospective and retrospective cohorts, case-control studies, and case reports/series with more than five participants were considered eligible for inclusion. Studies reporting the cannula diameter and PPROM rate after laser surgery in the treatment of monochorionic pregnancies affected by TTTS between 16- and 26 weeks\' gestation were included. Data was extracted independently, and when appropriate, a random-effects meta-analysis was undertaken to calculate pooled estimates and their confidence intervals. Heterogeneity in the effect estimates of the individual studies was calculated using the I2 statistic. The primary outcome was PPROM rate. Secondary outcomes were survival rate, preterm birth, and incomplete surgery. The quality of the included studies was assessed using a modified quality in prognosis study tool.
RESULTS: We included a total of 22 studies, consisting of 3426 patients. Only one study was scored as low quality, seven as moderate quality, and the remaining 14 as high quality. The mean PPROM rate after laser surgery treating TTTS was 22.9%, ranging from 11.6% for 9 French (Fr) to 54.0% for 12 Fr. Subsequent meta-regression for the clinically relevant PPROM rate before 34 weeks of gestation, showed increased PPROM rates for increased cannula size (p-value 0.01).
CONCLUSIONS: This systematic review confirmed PPROM as a frequent complication of fetal laser surgery, with a mean PPROM rate of 22.9%. A larger cannula diameter relates to a significant higher PPROM risk for PPROM before 34 weeks gestation. Hence, the ideal balance between optimal visualization requiring larger port diameters and shorter operation time and more complete procedures that benefit from larger diameters is crucial to reduce iatrogenic PPROM rates.

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon\'s side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.

OBJECTIVE: In twin-to-twin transfusion syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the two fetuses. In the current practice, TTTS is treated surgically by closing abnormal anastomoses using laser ablation. This surgery is minimally invasive and relies on fetoscopy. Limited field of view makes anastomosis identification a challenging task for the surgeon.
METHODS: To tackle this challenge, we propose a learning-based framework for in vivo fetoscopy frame registration for field-of-view expansion. The novelties of this framework rely on a learning-based keypoint proposal network and an encoding strategy to filter (i) irrelevant keypoints based on fetoscopic semantic image segmentation and (ii) inconsistent homographies.
RESULTS: We validate our framework on a dataset of six intraoperative sequences from six TTTS surgeries from six different women against the most recent state-of-the-art algorithm, which relies on the segmentation of placenta vessels.
CONCLUSIONS: The proposed framework achieves higher performance compared to the state of the art, paving the way for robust mosaicking to provide surgeons with context awareness during TTTS surgery.