Deep learning-based monocular placental pose estimation: towards collaborative robotics in fetoscopy.

PURPOSE: Twin-to-twin transfusion syndrome (TTTS) is a placental defect occurring in monochorionic twin pregnancies. It is associated with high risks of fetal loss and perinatal death. Fetoscopic elective laser ablation (ELA) of placental anastomoses has been established as the most effective therapy for TTTS. Current tools and techniques face limitations in case of more complex ELA cases. Visualization of the entire placental surface and vascular equator; maintaining an adequate distance and a close to perpendicular angle between laser fiber and placental surface are central for the effectiveness of laser ablation and procedural success. Robot-assisted technology could address these challenges, offer enhanced dexterity and ultimately improve the safety and effectiveness of the therapeutic procedures. METHODS: This work proposes a 'minimal' robotic TTTS approach whereby rather than deploying a massive and expensive robotic system, a compact instrument is 'robotised' and endowed with 'robotic' skills so that operators can quickly and efficiently use it. The work reports on automatic placental pose estimation in fetoscopic images. This estimator forms a key building block of a proposed shared-control approach for semi-autonomous fetoscopy. A convolutional neural network (CNN) is trained to predict the relative orientation of the placental surface from a single monocular fetoscope camera image. To overcome the absence of real-life ground-truth placenta pose data, similar to other works in literature (Handa et al. in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016; Gaidon et al. in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016; Vercauteren et al. in: Proceedings of the IEEE, 2019) the network is trained with data generated in a simulated environment and an in-silico phantom model. A limited set of coarsely manually labeled samples from real interventions are added to the training dataset to improve domain adaptation. RESULTS: The trained network shows promising results on unseen samples from synthetic, phantom and in vivo patient data. The performance of the network for collaborative control purposes was evaluated in a virtual reality simulator in which the virtual flexible distal tip was autonomously controlled by the neural network. CONCLUSION: Improved alignment was established compared to manual operation for this setting, demonstrating the feasibility to incorporate a CNN-based estimator in a real-time shared control scheme for fetoscopic applications.

Cirurgias intrauterinas: alternativa de intervenção para as cardiopatias congênitas / Intrauterine surgeries: intervetion alternative for congenital cardiopathies

As cardiopatias congênitas são anormalidades estruturais ou funcionais do sistema cardiovascular, advindas desde o nascimento, mesmo que diagnosticadas posteriormente. Entre as malformações congênitas, as cardiopatias são as principais causas de mortalidade infantil nos Estados Unidos e em outros países desenvolvidos. Com o intuito de reduzir os efeitos progressivos dessas patologias, a intervenção intrauterina tem se destacado como opção terapêutica diante de resultados iniciais satisfatórios. O presente artigo teve por objetivo demonstrar a evolução da cirurgia intrauterina para correção cardíaca, a partir da avaliação dos benefícios ao feto e visando a riscos mínimos e aceitáveis para a mãe. Foi realizada uma pesquisa na base de dados Publisher Medline (PubMed), Scientific Electronic Library Online (SciELO) e Biblioteca Virtual da Saúde (BVS), incluindo artigos publicados entre 2008 e 2018; além da pesquisa efetuada no Manual de Medicina Fetal da SOGIMIG ­ 2018. Os critérios de elegibilidade são amplos. São necessários equipe multidisciplinar, equipamentos sofisticados e aperfeiçoamento da técnica, dessa forma dificulta-se a realização das cirurgias. Entretanto, diante dos resultados já demonstrados, a cirurgia intrauterina apresenta-se como alternativa terapêutica promissora.(AU)

The congenital cardiopathies are structural or functional abnormalities of the cardiovascular system, originated from birth, even when previously diagnosed. Among the congenic malformations, the cardiopathies are the main causes of infant mortality in the United States and in other developed countries. In order to reduce the progressive effects of these pathologies, intrauterine intervention has been highlighted as a therapeutic option in contempt of satisfactory initial results. This article has as goal to demonstrate the evolution of the intrauterine surgery for cardiac correction, based on the evaluation of the benefits to the fetus and aiming at minimum and acceptable risks to the mother. A research was made based on the Publisher Medline (PubMed) data base, Scientific Electronic Library Online (SciELO) and Biblioteca Virtual da Saúde (BVS), including published articles between 2008 and 2018. Beyond the research made on The fetal medicine manual from SOGIMIG ­ 2018. The eligibility criteria are broad. It is necessary a multidisciplinary team, sophisticated equipments and technique improvement, therefore interfering in the performance of surgeries. However, in contempt of the already demonstrated results the intrauterine surgery presents itself as a therapeutic promising alternative.(AU)

Evaluation of a new balloon for fetal endoscopic tracheal occlusion in the nonhuman primate model.

OBJECTIVE: We developed a new balloon called "Smart-TO," which allows noninvasive and easy unplugging, thanks to a magnetic valve actuated by the magnetic fringe field of a magnetic resonance imaging (MRI) scanner. The objective of this feasibility study was to evaluate the operation of this new balloon in a nonhuman primate model. METHODS: Four pregnant rhesus monkeys underwent fetal endoscopic tracheal occlusion using the "Smart-TO" balloon. The pregnant monkeys were simply carried around the perimeter of an MRI scanner a few days later. Study outcomes were feasibility of fetal tracheal occlusion using the "Smart-TO" balloon, persistence of the balloon in the fetal trachea, and deflation of the balloon when subjected to the magnetic fringe field of an MRI. RESULTS: At the time of the unplug procedure, in all cases, the balloon was still in a correct position, and its shape did not change based on their ultrasound appearance. After bringing the pregnant monkeys into the fringe field of the MRI scanner, the balloon deflated in all cases. CONCLUSION: The balloon we developed allows noninvasive, easily triggered, and externally controlled reversal occlusion, based on the nonhuman primate model. Further tests evaluating occlusiveness and potential adverse effects are necessary.

Long tail balloon as a new approach for fetoscopic tracheal occlusion for a treatment of severe congenital diaphragmatic hernia.

Severe congenital diaphragmatic hernia (CDH) remains a significant challenge for neonatal specialists. In order to reduce complications during extraction of the surgical balloon after fetoscopic tracheal occlusion (FETO) CDH, we have developed a FETO with a 'long tail balloon' of 2.5 mL volume. Here we describe two successful uses of the device with observed/expected total fetal lung volume (o/e TFLV) of 15% and with o/e TFLV of 24% and 'liver up'. The o/e TFLV increased to 134% in first case and to 47% in second fetus. The balloon was successfully extracted at 34 weeks' gestation by pulling the long tail suture during second fetoscopy. In the second case the fetus pulled out the balloon from trachea itself by traction onto the balloon's long tail. Both neonates were operated on for their CDH with a good outcome. This work showed the feasibility of this long tail balloon for FETO to reduce the technical difficulty of the balloon extraction and the possibility that fetuses are able to extract the balloon by itself by pulling the balloons' long tail. Further development of long tail balloon for FETO could facilitate its extraction thereby reducing neonatal complications.

Minimally Invasive Surgical Device for Precise Application of Bioadhesives to Prevent iPPROM.

INTRODUCTION: The benefits of endoscopic fetal surgery are deteriorated by the high risk of iatrogenic preterm prelabor rupture of fetal membranes (iPPROM). While previous studies have reported good sealing candidates to prevent membrane rupture, the delivery of these materials to the location of membrane puncture remains unsolved. MATERIALS AND METHODS: We describe an approach to apply sealing materials onto the amnion through the fetoscopy port. We developed a device composed of an umbrella-shaped polyester coated nitinol mesh and an applicator. The spontaneously unfolding umbrella is pushed through the port, pulled against the amnion, and glued onto the amnion defect site. We tested the adhesion strength of multiple glues and tested the feasibility and reproducibility of this fetal membrane sealing approach in an ex vivo model. RESULTS: The umbrella unfolded and was well positioned in all tests (n = 18). When applied via the fetoscopy port, umbrellas were successfully glued onto the fetal membrane, and all of them completely covered the defect (n = 5). The mean time needed for the whole procedure was 3 min. DISCUSSION: This study is a proof of concept presenting a potential future solution for the precise local application of bioadhesives for the prevention of iPPROM.

Tracheal Diameter and Respiratory Outcome in Infants with Congenital Diaphragmatic Hernia Treated by Fetal Endoscopic Tracheal Occlusion.

AIM: To evaluate tracheal diameters and their clinical impact in patients with congenital diaphragmatic hernia (CDH) after fetal endoscopic tracheal occlusion (FETO). METHODS: Patients born with CDH between January 2012 and August 2016 were divided into two groups: noFETO and FETO. Tracheal diameters at three levels (T1, carina, and maximum tracheal dilation) on chest X-ray at 1, 3, 6, 12, 24, and 36 months of follow-up, requirements of invasive and noninvasive respiratory support, the incidence of respiratory infections, and results of pulmonary function tests (PFT) were compared. RESULTS: A total of 71 patients with CDH were born in the study period, and there were 34/41 survivors in the no-FETO group (82.9%) and 13/30 in the FETO group (43.3%). The maximum tracheal diameter was significantly greater in the FETO group at all ages. No differences were observed in the diameters at T1 and the carina, in the requirements of invasive and noninvasive respiratory support, and in the incidence respiratory infections. At the PFT (6-12 months), the FETO group presented higher respiratory rates (46.1 ± 6.2 vs. 36.5 ± 10.6, p = 0.02). No differences in PFT results were found between the groups after the 1st year of life. CONCLUSIONS: The FETO procedure leads to persistent tracheomegaly. However, the tracheomegaly does not seem to have a significant clinical impact.

Impact of cannula size on recurrent twin-twin transfusion syndrome and twin anemia-polycythemia sequence after fetoscopic laser surgery.

OBJECTIVE: The optimal outcome after fetoscopic laser surgery (FLS) for twin-twin transfusion syndrome (TTTS) depends on the successful ablation of all placental anastomoses. The objective of this study was to determine the incidence of and risk factors for recurrent TTTS (rTTTS) or twin anemia-polycythemia sequence (TAPS) after FLS, focusing on the impact of cannula diameter. METHODS: This was a secondary analysis of data collected prospectively at two centers from 666 consecutive patients undergoing FLS for TTTS. The main outcomes were rTTTS and TAPS following FLS. Variables assessed included gestational age at intervention, stage of disease, recipient maximum vertical pocket, anterior placenta, number of anastomoses ablated, cannula diameter/operative scopes and use of the Solomon technique. Cannula diameter and corresponding scopes used were as follows: 8 Fr and 1.3 mm/0°; 9 Fr and 2.7 mm/0°; 10 Fr and 3 mm/0°; or 12 Fr and 3.3-3.7 mm/30-70°. Cannula diameter was used as a surrogate for scopes during analysis. Multivariate logistic regression analysis was performed to identify risk factors associated with rTTTS or TAPS after FLS; 'center' was considered an independent variable to account for variations in practice. In a nested cohort of pregnancies in which both fetuses survived, placental dye injection was performed in 315 placentae. Multivariate logistic regression analysis was performed to evaluate variables associated with the presence of residual anastomoses. RESULTS: rTTTS or TAPS occurred in 61 (9%) cases following FLS (rTTTS in eight (1%) and TAPS in 53 (8%)). Factors associated significantly with the risk of rTTTS/TAPS on multivariate analysis were cannula diameter (when an 8-Fr, 9-Fr, 10-Fr or 12-Fr cannula was used, there was rTTTS/TAPS in 24%, 13%, 2% or 0.8% of cases, respectively (P < 0.001)) and use of the Solomon technique (rTTTS/TAPS occurred in 4.2% of those in which it was used vs 18.1% in those in which it was not (P < 0.001)). Only use of the Solomon technique was associated significantly with no residual anastomoses found after delivery. CONCLUSIONS: Following FLS for TTTS, a lower incidence of rTTTS/TAPS was seen when the Solomon technique was used, as well as when a 10-Fr or 12-Fr cannula was used. A lower complication rate may be due to the use of a scope with better optics during placental mapping. Copyright © 2017 ISUOG. Published by John Wiley & Sons Ltd.

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration.

We have developed a calibration target for use with fluid-immersed endoscopes within the context of the GIFT-Surg (Guided Instrumentation for Fetal Therapy and Surgery) project. One of the aims of this project is to engineer novel, real-time image processing methods for intra-operative use in the treatment of congenital birth defects, such as spina bifida and the twin-to-twin transfusion syndrome. The developed target allows for the sterility-preserving optical distortion calibration of endoscopes within a few minutes. Good optical distortion calibration and compensation are important for mitigating undesirable effects like radial distortions, which not only hamper accurate imaging using existing endoscopic technology during fetal surgery, but also make acquired images less suitable for potentially very useful image computing applications, like real-time mosaicing. In this paper proposes a novel fabrication method to create an affordable, sterilizable calibration target suitable for use in a clinical setup. This method involves etching a calibration pattern by laser cutting a sandblasted stainless steel sheet. This target was validated using the camera calibration module provided by OpenCV, a state-of-the-art software library popular in the computer vision community.

Procedure-Related Complications and Survival Following Fetoscopic Endotracheal Occlusion (FETO) for Severe Congenital Diaphragmatic Hernia: Systematic Review and Meta-Analysis in the FETO Era.

Introduction This study aims to assess the procedure-related complications and survival following fetoscopic endotracheal occlusion (FETO) for severe congenital diaphragmatic hernia. Materials and Methods A systematic review and meta-analysis of PubMed and Scopus database searching for FETO procedure in severe CDH (lung-to-head ratio [LHR] < 1.0 and/or observed/expected LHR < 0.26 and > 1/3 liver herniation) were performed. The relative risk was assessed and 95% confidence interval (CI) calculated. Procedure complications and survival were compared between FETO and randomized controlled trial (RCT) as well as observational case-control studies. Results A total of 4,807 records were retrieved based on the title and abstracts, and 18 studies were eligible for statistical analysis (1 RCT and 17 observational case-control studies). Relative risk (95% CI) comparing FETO and controls for premature rupture of membrane, preterm birth < 32 weeks, preterm birth < 37 weeks, survival at 30 days, and survival at 6 months were 1.7 (0.8-2.4), 7.3 (0.4-134), 1.8 (0.8-3.9), 5.8 (1.5-22.9), and 10.5 (1.5-74.7), respectively. Mean difference (95% CI) for gestational age at delivery comparing FETO and controls was 1.8 (-3.1 to -0.5). All these outcomes showed a low level of evidence. Conclusion FETO procedure increased the neonatal survival at 30 days and 6 months; however, it presented a higher rate of premature rupture of membrane, preterm birth < 37 weeks, and decreased the gestational age at delivery by 2 weeks. Nonetheless, the level of evidence is low for all these outcomes. We suggested a large international multicenter RCT to prove the real benefits of FETO.

Use of the GlideScope video laryngoscope for intubation during ex utero intrapartum treatment in a fetus with a giant cyst of the 4th branchial cleft: A case report.

INTRODUCTION: In fetuses who are predicted to be at risk of catastrophic airway obstruction at delivery, the ex utero intrapartum treatment (EXIT) procedure is useful for securing the fetal airway while maintaining fetal oxygenation via placental circulation. Factors, including poor posture of the fetus and physician, narrow visual field, and issues of contamination in the aseptic surgical field, make fetal intubation during the EXIT procedure difficult. Herein, we report our experience of the usefulness of the GlideScope video laryngoscope (GVL) for intubation during the EXIT procedure. SYMPTOMS AND CLINICAL FINDINGS: A 28-year-old woman presented with a fetus having a cystic neck mass diagnosed on prenatal ultrasound at 25 weeks of gestation. We planned the EXIT procedure in conjunction with cesarean delivery at 38 weeks of gestation, as the mass enlarged to 4.9 cm × 3.2 cm, protruded externally at the neck, and subsequently resulted in polyhydramnios. THERAPEUTIC INTERVENTION AND OUTCOMES: After induction of anesthesia using intravenous thiopental (300 mg), adequate uterine relaxation was achieved with sevoflurane (2.0-3.0 vol%) combined with continuous intravenous infusion of nitroglycerin (0.5-1.0 µg/kg/min) for maintaining uteroplacental circulation. After hysterotomy, the head and right upper limb of the fetus were partially delivered, and fetal heart tones were monitored with a sterile Doppler probe. After oropharyngeal suctioning to improve the visual field, the fetus was intubated successfully using a sterile GVL by an anesthesiologist, and the passage of the endotracheal tube beyond the vocal cords was confirmed on the screen of the GVL system. Immediately after the fetal airway was definitely secured, the fetus was fully delivered with umbilical cord clamping. After delivery, nitroglycerine administration was ceased and sevoflurane administration was reduced to 0.5 minimum alveolar concentration. Additionally, oxytocin (10 units) and carbetocin (100 µg) were administered for recovery of uterine contraction. Cesarean delivery was successfully performed without any problems, and the neonate successfully underwent surgery for removal of the neck mass under general anesthesia on the 7th day after delivery. The neonate is developing normally. CONCLUSION: The GVL approach may be a useful noninvasive approach for establishing a clear fetal airway during the EXIT procedure.

Different effectiveness of closed embryo culture system with time-lapse imaging (EmbryoScope(TM)) in comparison to standard manual embryology in good and poor prognosis patients: a prospectively randomized pilot study.

BACKGROUND: Previously manual human embryology in many in vitro fertilization (IVF) centers is rapidly being replaced by closed embryo incubation systems with time-lapse imaging. Whether such systems perform comparably to manual embryology in different IVF patient populations has, however, never before been investigated. We, therefore, prospectively compared embryo quality following closed system culture with time-lapse photography (EmbryoScope™) and standard embryology. We performed a two-part prospectively randomized study in IVF (clinical trial # NCT92256309). Part A involved 31 infertile poor prognosis patients prospectively randomized to EmbryoScope™ and standard embryology. Part B involved embryos from 17 egg donor-recipient cycles resulting in large egg/embryo numbers, thus permitting prospectively alternative embryo assignments to EmbryoScope™ and standard embryology. We then compared pregnancy rates and embryo quality on day-3 after fertilization and embryologist time utilized per processed embryo. RESULTS: Part A revealed in poor prognosis patients no differences in day-3 embryo scores, implantation and clinical pregnancy rates between EmbryoScope™ and standard embryology. The EmbryoScope™, however, more than doubled embryology staff time (P < 0.0001). In Part B, embryos grown in the EmbyoScope™ demonstrated significantly poorer day-3 quality (depending on embryo parameter between P = 0.005 and P = 0.01). Suspicion that conical culture dishes of the EmbryoScope™ (EmbryoSlide™) may be the cause was disproven when standard culture dishes demonstrated no outcome difference in standard incubation. CONCLUSIONS: Though due to small patient numbers preliminary, this study raises concerns about the mostly uncontrolled introduction of closed incubation systems with time lapse imaging into routine clinical embryology. Appropriately designed and powered prospectively randomized studies appear urgently needed in well-defined patient populations before the uncontrolled utilization of these instruments further expands. TRIAL REGISTRATION: NCT02246309 Registered September 18, 2014.

The Impact of Entry Technique and Access Diameter on Prelabour Rupture of Membranes Following Primary Fetoscopic Laser Treatment for Twin-Twin Transfusion Syndrome.

OBJECTIVE: To evaluate the impact of entry method and access diameter at fetoscopic surgery for twin-twin transfusion syndrome in twin pregnancies with at least one survivor. The outcomes evaluated were prelabour rupture of membranes (PROM) and birth <4 weeks, preterm birth (PTB) <28 weeks, and latency to birth. METHODS: A retrospective analysis of prospectively collected data of consecutive laser procedures from 6 centers was performed. Three entry methods (sheath + trocar; cannula + trocar; cannula + Seldinger) and 6 access diameters (2.3, 3.0, 3.3, 3.5, 3.8, 4.0 mm) were used. Exclusion criteria were subsequent invasive interventions, termination of pregnancy or double fetal death after laser. Multivariate analysis was performed to determine risk factors for the study outcomes. RESULTS: Six hundred seventy three fetoscopic laser cases were analyzed. The use of different entry methods and access diameters did not affect PROM or birth <4 weeks, or latency from laser to birth. Access diameter was associated with PTB <28 weeks. Cervical length was associated with PROM and birth <4 weeks, and latency from laser to birth. CONCLUSION: Instrument choice at fetoscopic laser procedures did not affect outcomes <4 weeks. Access diameter may affect the likelihood for PTB <28 weeks. Cervical length is critically associated with obstetrical outcomes following laser surgery.

Neurodevelopmental outcome at 2 years in twin-twin transfusion syndrome survivors randomized for the Solomon trial.

BACKGROUND: The preferred treatment for twin-twin transfusion syndrome is fetoscopic laser coagulation of inter-twin vascular anastomoses on the monochorionic placenta. Severe postoperative complications can occur when inter-twin vascular anastomoses remain patent including twin-anemia polycythemia sequence or recurrent twin-twin transfusion syndrome. To minimize the occurrence of residual anastomoses, a modified laser surgery technique, the Solomon technique, was developed in which the entire vascular equator is coagulated. In the Solomon randomized controlled trial (NTR1245), the Solomon technique was associated with a significant reduction in twin-anemia polycythemia sequence and recurrence of twin-twin transfusion syndrome when compared with the standard laser surgery technique. Although a significant improvement in perinatal outcome was shown after the Solomon technique, the clinical importance should also be ascertained with long-term follow-up evaluation of the surviving children. OBJECTIVE: The purpose of this study was to compare the long-term neurodevelopmental outcome in surviving children with twin-twin transfusion syndrome who were included in the Solomon randomized trial and treated with either the Solomon technique or standard laser surgery technique. STUDY DESIGN: Routine standardized follow-up evaluation in survivors, at least 2 years after the estimated date of delivery, was performed at 2 of the 5 centers that participated in the Solomon trial: Buzzi Hospital Milan (Italy) and Leiden University Medical Center (The Netherlands). The primary outcome of this follow-up study was survival without long-term neurodevelopmental impairment at age 2 years. Neurodevelopmental impairment was defined as cerebral palsy, cognitive and/or motor development score of <85, bilateral blindness, or deafness. Cognitive and motor development was evaluated with the use of Bayley-III. All analyses per fetus, neonate, or child were conducted with the generalized estimated equation module to account for the effect that observations between co-twins are not independent. RESULTS: The primary outcome (survival without neurodevelopmental impairment) was detected in 95 of 141 cases (67%) in the Solomon group and in 99 of 146 cases (68%) in the standard group (P = .92). Neurodevelopmental impairment in long-term survivors who were included for follow-up evaluation was detected in 12 of 107 cases (11%) in the Solomon and in 10 of 109 cases (9%) in the standard group (P = .61). Neurodevelopmental impairment was due to cerebral palsy in 1 case (1%; spastic unilateral) in the Solomon group and in 2 cases (2%; spastic unilateral and spastic bilateral) in the standard group (P = .58). Cognitive development <85 cases was detected in 2 of 105 children (2%) in the Solomon group and in 6 of 106 children (6%) in the standard group (P = .23). Motor development <85 occurred in 8 of 103 children (8%) in the Solomon group and 3 of 104 children (3%) in the standard group (P = .23). CONCLUSION: We found no difference in survival without neurodevelopmental impairment between the Solomon and standard laser techniques. In view of the reduction of short-term complications and the absence of increased adverse long-term effects, these data support the use of the Solomon technique in the treatment of twin-twin transfusion syndrome.

Design of a flexible fetoscopy manipulation system for congenital diaphragmatic hernia.

Recent advancements in fetal surgery have proven that tracheal occlusion in fetuses with congenital diaphragmatic hernia is an effective way to prevent the occurrence of pulmonary hypoplasia. A novel flexible fetoscope with a parallel mechanism structure of a thumbstick to carry on the fetal tracheal balloon occlusion by the targeting and manipulation of the fetal endoscope at a high standard of quick response and dexterity is proposed in this paper. This design is compared with a commercial rigid fetoscope in terms of operation timing and reduced stress to the fetus at neck level. Experiments using a phantom have demonstrated that the flexible fetoscope has a better dexterity and is able to perform stable tracheoscopy and balloon inflation at different levels of the trachea, with the help of a fiberoptic camera.

Ultrasound image-based endoscope localization for minimally invasive fetoscopic surgery.

The purpose of this work is to introduce an ultrasound image-based intraoperative scheme for rigid endoscope localization during minimally invasive fetoscopic surgery. Positional information of surgical instruments with respect to anatomical features is important for the development of computer-aided surgery applications. While most surgical navigation systems use optical tracking systems with satisfactory accuracy, there are several operation limitations in such systems. We propose an elegant framework for intraoperative instrument localization that does not require any external tracking system but uses an ultrasound imaging system and a computation scheme based on constrained kinematics of minimally invasive fetoscopic surgery. Our proposed algorithm simultaneously estimates endoscope and port positions in an online sequential fashion with standard deviation of 1.28 mm for port estimation. Robustness of the port estimation algorithm against external disturbance was demonstrated by intentionally introducing artificial errors to measurement data. The estimation converges within eight iterations under disturbance magnitude of 30 mm.