Challenges in multi-centric generalization: phase and step recognition in Roux-en-Y gastric bypass surgery.

PURPOSE: Most studies on surgical activity recognition utilizing artificial intelligence (AI) have focused mainly on recognizing one type of activity from small and mono-centric surgical video datasets. It remains speculative whether those models would generalize to other centers. METHODS: In this work, we introduce a large multi-centric multi-activity dataset consisting of 140 surgical videos (MultiBypass140) of laparoscopic Roux-en-Y gastric bypass (LRYGB) surgeries performed at two medical centers, i.e., the University Hospital of Strasbourg, France (StrasBypass70) and Inselspital, Bern University Hospital, Switzerland (BernBypass70). The dataset has been fully annotated with phases and steps by two board-certified surgeons. Furthermore, we assess the generalizability and benchmark different deep learning models for the task of phase and step recognition in 7 experimental studies: (1) Training and evaluation on BernBypass70; (2) Training and evaluation on StrasBypass70; (3) Training and evaluation on the joint MultiBypass140 dataset; (4) Training on BernBypass70, evaluation on StrasBypass70; (5) Training on StrasBypass70, evaluation on BernBypass70; Training on MultiBypass140, (6) evaluation on BernBypass70 and (7) evaluation on StrasBypass70. RESULTS: The model's performance is markedly influenced by the training data. The worst results were obtained in experiments (4) and (5) confirming the limited generalization capabilities of models trained on mono-centric data. The use of multi-centric training data, experiments (6) and (7), improves the generalization capabilities of the models, bringing them beyond the level of independent mono-centric training and validation (experiments (1) and (2)). CONCLUSION: MultiBypass140 shows considerable variation in surgical technique and workflow of LRYGB procedures between centers. Therefore, generalization experiments demonstrate a remarkable difference in model performance. These results highlight the importance of multi-centric datasets for AI model generalization to account for variance in surgical technique and workflows. The dataset and code are publicly available at https://github.com/CAMMA-public/MultiBypass140.

Descemet Membrane Endothelial Keratoplasty as Treatment for Late-Onset Interface Fluid Syndrome After Laser In Situ Keratomileusis.

PURPOSE: We herein present Descemet membrane endothelial keratoplasty (DMEK) as an effective surgical means of treatment for the management of interface fluid syndrome (IFS) in a series of cases with distant history of laser in situ keratomileusis (LASIK). METHODS: Three cases from a single institution were included. All patients had documented IFS in the setting of history of LASIK. All 3 patients underwent DMEK for the treatment of IFS. Visual acuity, clinical findings, pachymetry, endothelial cell count, and anterior segment optical coherence tomography were recorded. RESULTS: We describe 3 cases of late-onset IFS that developed in eyes many years after LASIK (ranging from 15 to 31 years). All 3 patients had clinically significant corneal edema and evidence of poor endothelial function at the time of IFS diagnosis. DMEK was subsequently performed in each case. All 3 eyes showed resolution of corneal edema and improvement in best-corrected visual acuity after DMEK. CONCLUSIONS: DMEK can provide successful visual and anatomical recovery in patients who have had previous LASIK and experience late-onset IFS due to endothelial cell dysfunction.

Minimal data requirement for realistic endoscopic image generation with Stable Diffusion.

PURPOSE: Computer-assisted surgical systems provide support information to the surgeon, which can improve the execution and overall outcome of the procedure. These systems are based on deep learning models that are trained on complex and challenging-to-annotate data. Generating synthetic data can overcome these limitations, but it is necessary to reduce the domain gap between real and synthetic data. METHODS: We propose a method for image-to-image translation based on a Stable Diffusion model, which generates realistic images starting from synthetic data. Compared to previous works, the proposed method is better suited for clinical application as it requires a much smaller amount of input data and allows finer control over the generation of details by introducing different variants of supporting control networks. RESULTS: The proposed method is applied in the context of laparoscopic cholecystectomy, using synthetic and real data from public datasets. It achieves a mean Intersection over Union of 69.76%, significantly improving the baseline results (69.76 vs. 42.21%). CONCLUSIONS: The proposed method for translating synthetic images into images with realistic characteristics will enable the training of deep learning methods that can generalize optimally to real-world contexts, thereby improving computer-assisted intervention guidance systems.

Leber Hereditary Optic Neuropathy Gene Therapy: Longitudinal Relationships Among Visual Function and Anatomical Measures.

PURPOSE: To assess longitudinal relationships among visual function and anatomical measures of gene therapy in G11778A Leber hereditary optic neuropathy (LHON). DESIGN: Phase 1 clinical trial. METHODS: This was a single-institution study of patients with G11778A LHON. Patients with chronic bilateral visual loss >12 months (group 1, n = 11), acute bilateral visual loss <12 months (group 2, n = 9), or unilateral visual loss (group 3, n = 8) were administered unilateral intravitreal AAV2(Y444,500,730F)-P1ND4v2 injection with low, medium, high, and higher doses to worse eye for groups 1 and 2 and better eye for group 3. Oucome measures were best-corrected visual acuity (BCVA), visual field mean deviation (VF MD), steady-state pattern electroretinogram (SS-PERG), optical coherence tomography (OCT) retinal nerve fiber layer (RNFL) thickness and ganglion cell+inner plexiform layer (GCIPL) thickness, and National Eye Institute Visual Function Questionnaire (NEI-VFQ-25) scores. Mean follow-up was 33.6 months (range = 18-36 months). RESULTS: Baseline SS-PERG amplitude was much reduced in both eyes of all groups including asymptomatic eyes of group 3, and showed no appreciable changes irrespective of disease stage and treatment. Significant and progressive GCIPL and RNFL thinning occurred in all eyes; BCVA and VF MD fluctuated in treated and fellow eyes, with some eyes having modest improvement that may be related to natural history or to gene therapy. Mean NEI-VFQ-25 scores declined in group 3 subjects (P = .023), CONCLUSION: Asymptomatic eyes in LHON patients with unilateral visual loss may be beyond the window of effective neuroprotection given reduced GCIPL and SS-PERG. Randomization of patients to an untreated control group would help to assess treatment effect by accounting for variable natural history. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

Mitochondrially Targeted Gene Therapy Rescues Visual Loss in a Mouse Model of Leber's Hereditary Optic Neuropathy.

Leber's hereditary optic neuropathy (LHON) is a common mitochondrial genetic disease, causing irreversible blindness in young individuals. Current treatments are inadequate, and there is no definitive cure. This study evaluates the effectiveness of delivering wildtype human NADH ubiquinone oxidoreductase subunit 4 (hND4) gene using mito-targeted AAV(MTSAAV) to rescue LHOH mice. We observed a declining pattern in electroretinograms amplitudes as mice aged across all groups (p < 0.001), with significant differences among groups (p = 0.023; Control vs. LHON, p = 0.008; Control vs. Rescue, p = 0.228). Inner retinal thickness and intraocular pressure did not change significantly with age or groups. Compared to LHON mice, those rescued with wildtype hND4 exhibited improved retinal visual acuity (0.29 ± 0.1 cy/deg vs. 0.15 ± 0.1 cy/deg) and increased functional hyperemia response (effect of flicker, p < 0.001, effect of Group, p = 0.004; Interaction Flicker × Group, p < 0.001). Postmortem analysis shows a marked reduction in retinal ganglion cell density in the LHON group compared to the other groups (Effect of Group, p < 0.001, Control vs. LHON, p < 0.001, Control vs. Rescue, p = 0.106). These results suggest that MTSAAV-delivered wildtype hND4 gene rescues, at least in part, visual impairment in an LHON mouse model and has the therapeutic potential to treat this disease.

Intraoperative estimation of liver boundary conditions from multiple partial surfaces.

PURPOSE: A computer-assisted surgical system must provide up-to-date and accurate information of the patient's anatomy during the procedure to improve clinical outcome. It is therefore essential to consider the tissue deformations, and a patient-specific biomechanical model (PBM) is usually adopted. The predictive capability of the PBM is highly influenced by proper definition of attachments to the surrounding anatomy, which are difficult to estimate preoperatively. METHODS: We propose to predict the location of attachments using a deep neural network fed with multiple partial views of the intraoperative deformed organ surface directly encoded as point clouds. Compared to previous works, providing a sequence of deformed views as input allows the network to consider the temporal evolution of deformations and to handle the intrinsic ambiguity of estimating attachments from a single view. RESULTS: The method is applied to computer-assisted hepatic surgery and tested on both a synthetic and in vivo human open-surgery scenario. The network is trained on a patient-specific synthetic dataset in less than 5 h and produces a more accurate intraoperative estimation of attachments than applying the ones generally used in liver surgery (i.e., fixing vena cava or falciform ligament). The obtained results show 26% more accurate predictions than other solution previously proposed. CONCLUSIONS: Trained with patient-specific simulated data, the proposed network estimates the attachments in a fast and accurate manner also considering the temporal evolution of the deformations, improving patient-specific intraoperative guidance in computer-assisted surgical systems.

Weakly Supervised Temporal Convolutional Networks for Fine-Grained Surgical Activity Recognition.

Automatic recognition of fine-grained surgical activities, called steps, is a challenging but crucial task for intelligent intra-operative computer assistance. The development of current vision-based activity recognition methods relies heavily on a high volume of manually annotated data. This data is difficult and time-consuming to generate and requires domain-specific knowledge. In this work, we propose to use coarser and easier-to-annotate activity labels, namely phases, as weak supervision to learn step recognition with fewer step annotated videos. We introduce a step-phase dependency loss to exploit the weak supervision signal. We then employ a Single-Stage Temporal Convolutional Network (SS-TCN) with a ResNet-50 backbone, trained in an end-to-end fashion from weakly annotated videos, for temporal activity segmentation and recognition. We extensively evaluate and show the effectiveness of the proposed method on a large video dataset consisting of 40 laparoscopic gastric bypass procedures and the public benchmark CATARACTS containing 50 cataract surgeries.

TRandAugment: temporal random augmentation strategy for surgical activity recognition from videos.

PURPOSE: Automatic recognition of surgical activities from intraoperative surgical videos is crucial for developing intelligent support systems for computer-assisted interventions. Current state-of-the-art recognition methods are based on deep learning where data augmentation has shown the potential to improve the generalization of these methods. This has spurred work on automated and simplified augmentation strategies for image classification and object detection on datasets of still images. Extending such augmentation methods to videos is not straightforward, as the temporal dimension needs to be considered. Furthermore, surgical videos pose additional challenges as they are composed of multiple, interconnected, and long-duration activities. METHODS: This work proposes a new simplified augmentation method, called TRandAugment, specifically designed for long surgical videos, that treats each video as an assemble of temporal segments and applies consistent but random transformations to each segment. The proposed augmentation method is used to train an end-to-end spatiotemporal model consisting of a CNN (ResNet50) followed by a TCN. RESULTS: The effectiveness of the proposed method is demonstrated on two surgical video datasets, namely Bypass40 and CATARACTS, and two tasks, surgical phase and step recognition. TRandAugment adds a performance boost of 1-6% over previous state-of-the-art methods, that uses manually designed augmentations. CONCLUSION: This work presents a simplified and automated augmentation method for long surgical videos. The proposed method has been validated on different datasets and tasks indicating the importance of devising temporal augmentation methods for long surgical videos.

Broad transcriptomic dysregulation occurs across the cerebral cortex in ASD.

Neuropsychiatric disorders classically lack defining brain pathologies, but recent work has demonstrated dysregulation at the molecular level, characterized by transcriptomic and epigenetic alterations1-3. In autism spectrum disorder (ASD), this molecular pathology involves the upregulation of microglial, astrocyte and neural-immune genes, the downregulation of synaptic genes, and attenuation of gene-expression gradients in cortex1,2,4-6. However, whether these changes are limited to cortical association regions or are more widespread remains unknown. To address this issue, we performed RNA-sequencing analysis of 725 brain samples spanning 11 cortical areas from 112 post-mortem samples from individuals with ASD and neurotypical controls. We find widespread transcriptomic changes across the cortex in ASD, exhibiting an anterior-to-posterior gradient, with the greatest differences in primary visual cortex, coincident with an attenuation of the typical transcriptomic differences between cortical regions. Single-nucleus RNA-sequencing and methylation profiling demonstrate that this robust molecular signature reflects changes in cell-type-specific gene expression, particularly affecting excitatory neurons and glia. Both rare and common ASD-associated genetic variation converge within a downregulated co-expression module involving synaptic signalling, and common variation alone is enriched within a module of upregulated protein chaperone genes. These results highlight widespread molecular changes across the cerebral cortex in ASD, extending beyond association cortex to broadly involve primary sensory regions.

Gene therapy restores mitochondrial function and protects retinal ganglion cells in optic neuropathy induced by a mito-targeted mutant ND1 gene.

Therapies for genetic disorders caused by mutated mitochondrial DNA are an unmet need, in large part due barriers in delivering DNA to the organelle and the absence of relevant animal models. We injected into mouse eyes a mitochondrially targeted Adeno-Associated-Virus (MTS-AAV) to deliver the mutant human NADH ubiquinone oxidoreductase subunit I (hND1/m.3460 G > A) responsible for Leber's hereditary optic neuropathy, the most common primary mitochondrial genetic disease. We show that the expression of the mutant hND1 delivered to retinal ganglion cells (RGC) layer colocalizes with the mitochondrial marker PORIN and the assembly of the expressed hND1 protein into host respiration complex I. The hND1-injected eyes exhibit hallmarks of the human disease with progressive loss of RGC function and number, as well as optic nerve degeneration. We also show that gene therapy in the hND1 eyes by means of an injection of a second MTS-AAV vector carrying wild-type human ND1 restores mitochondrial respiratory complex I activity, the rate of ATP synthesis and protects RGCs and their axons from dysfunction and degeneration. These results prove that MTS-AAV is a highly efficient gene delivery approach with the ability to create mito-animal models and has the therapeutic potential to treat mitochondrial genetic diseases.

The Relationship Between Stage of Leber's Hereditary Optic Neuropathy and Pattern Electroretinogram Latency.

Purpose: The purpose of this study was to compare the baseline steady-state pattern electroretinogram (SS-PERG) of patients with G11778A Leber hereditary optic neuropathy (LHON) with different stages of visual acuity (VA) loss before allotopic gene therapy (GT). Methods: Patients (n = 28) were enrolled into groups (GT I: chronic bilateral VA ≤35 Early Treatment Diabetic Retinopathy Study [ETDRS]; GT II: acute bilateral VA ≤35 ETDRS; GT III: acute unilateral, VA ≤35 ETDRS, and better eye VA ≥70 ETDRS) and tested with SS-PERG together with 210 age-matched normal controls (NCs). SS-PERG amplitude (nV) and latency (ms) of each eye were averaged for groups GT I, GT II, and NC. Symptomatic eyes (GT III-S) and asymptomatic eyes (GT III-A) of group GT III were included separately and accounted for by using generalized estimating equation (GEE) methods. Results: Compared to NC, SS-PERG amplitudes were reduced similarly by approximately 50% (P < 0.001) among all GT groups (NC > GT I, GT II, GT III-S, and GT III-A). SS-PERG latencies were shorter by ≥3.5 ms in all LHON groups and differed by disease stage (G III-A < NC, P = 0.002; GT III-S < GT III-A, P = 0.01; GT II < GT III-S, P = 0.03; GT I < NC, P < 0.001, but not different from other GT groups, all P > 0.1). Conclusions: Although SS-PERG amplitude reduction did not distinguish between disease stages, SS-PERG latency shortening occurred in asymptomatic eyes and symptomatic eyes and distinguished between disease stages. Translational Relevance: SS-PERG latency shortening is consistent with primary damage of smaller/slower axons and sparing of larger/faster axons and may provide an objective staging of LHON, which may be helpful to determine efficacy in LHON trials.

Distortion and instability compensation with deep learning for rotational scanning endoscopic optical coherence tomography.

Optical Coherence Tomography (OCT) is increasingly used in endoluminal procedures since it provides high-speed and high resolution imaging. Distortion and instability of images obtained with a proximal scanning endoscopic OCT system are significant due to the motor rotation irregularity, the friction between the rotating probe and outer sheath and synchronization issues. On-line compensation of artefacts is essential to ensure image quality suitable for real-time assistance during diagnosis or minimally invasive treatment. In this paper, we propose a new online correction method to tackle both B-scan distortion, video stream shaking and drift problem of endoscopic OCT linked to A-line level image shifting. The proposed computational approach for OCT scanning video correction integrates a Convolutional Neural Network (CNN) to improve the estimation of azimuthal shifting of each A-line. To suppress the accumulative error of integral estimation we also introduce another CNN branch to estimate a dynamic overall orientation angle. We train the network with semi-synthetic OCT videos by intentionally adding rotational distortion into real OCT scanning images. The results show that networks trained on this semi-synthetic data generalize to stabilize real OCT videos, and the algorithm efficacy is demonstrated on both ex vivo and in vivo data, where strong scanning artifacts are successfully corrected.

An Electrical Bioimpedance Scanning System for Subsurface Tissue Detection in Robot Assisted Minimally Invasive Surgery.

In Robot Assisted Minimally Invasive Surgery, discriminating critical subsurface structures is essential to make the surgical procedure safer and more efficient. In this paper, a novel robot assisted electrical bio-impedance scanning (RAEIS) system is developed and validated using a series of experiments. The proposed system constructs a tri-polar sensing configuration for tissue homogeneity inspection. Specifically, two robotic forceps are used as electrodes for applying electric current and measuring reciprocal voltages relative to a ground electrode which is placed distal from the measuring site. Compared to existing electrical bioimpedance sensing technology, the proposed system is able to use miniaturized electrodes to measure a site flexibly with enhanced subsurfacial detection capability. This paper presents the concept, the modeling of the sensing method, the hardware design, and the system calibration. Subsequently, a series of experiments are conducted for system evaluation including finite element simulation, saline solution bath experiments and experiments based on ex vivo animal tissues. The experimental results demonstrate that the proposed system can measure the resistivity of the material with high accuracy, and detect a subsurface non-homogeneous object with 100% success rate. The proposed parameters estimation algorithm is able to approximate the resistivity and the depth of the subsurface object effectively with one fast scanning.

Neural recovery after cortical injury: Effects of MSC derived extracellular vesicles on motor circuit remodeling in rhesus monkeys.

Reorganization of motor circuits in the cortex and corticospinal tract are thought to underlie functional recovery after cortical injury, but the mechanisms of neural plasticity that could be therapeutic targets remain unclear. Recent work from our group have shown that systemic treatment with mesenchymal stem cell derived (MSCd) extracellular vesicles (EVs) administered after cortical damage to the primary motor cortex (M1) of rhesus monkeys resulted in a robust recovery of fine motor function and reduced chronic inflammation. Here, we used immunohistochemistry for cfos, an activity-dependent intermediate early gene, to label task-related neurons in the surviving primary motor and premotor cortices, and markers of axonal and synaptic plasticity in the spinal cord. Compared to vehicle, EV treatment was associated with a greater density of cfos+ pyramidal neurons in the deep layers of M1, greater density of cfos+ inhibitory interneurons in premotor areas, and lower density of synapses on MAP2+ lower motor neurons in the cervical spinal cord. These data suggest that the anti-inflammatory effects of EVs may reduce injury-related upper motor neuron damage and hyperexcitability, as well as aberrant compensatory re-organization in the cervical spinal cord to improve motor function.

Robot-Assisted Electrical Impedance Scanning system for 2D Electrical Impedance Tomography tissue inspection.

The electrical impedance tomography (EIT) technology is an important medical imaging approach to show the electrical characteristics and the homogeneity of a tissue region noninvasively. Recently, this technology has been introduced to the Robot Assisted Minimally Invasive Surgery (RAMIS) for assisting the detection of surgical margin with relevant clinical benefits. Nevertheless, most EIT technologies are based on a fixed multiple-electrodes probe which limits the sensing flexibility and capability significantly. In this study, we present a method for acquiring the EIT measurements during a RAMIS procedure using two already existing robotic forceps as electrodes. The robot controls the forceps tips to a series of predefined positions for injecting excitation current and measuring electric potentials. Given the relative positions of electrodes and the measured electric potentials, the spatial distribution of electrical conductivity in a section view can be reconstructed. Realistic experiments are designed and conducted to simulate two tasks: subsurface abnormal tissue detection and surgical margin localization. According to the reconstructed images, the system is demonstrated to display the location of the abnormal tissue and the contrast of the tissues' conductivity with an accuracy suitable for clinical applications.

Retinal microvascular and neuronal function in patients with multiple sclerosis: 2-year follow-up.

OBJECTIVE: To determine the longitudinal changes in retinal microstructure, microvasculature, microcirculation, and axonal and neuronal functions in patients with relapsing-remitting multiple sclerosis (RRMS) over the time course of about two years. METHODS: A total of 30 patients (60 eyes) with RRMS were followed for a period of 27 ± 6 months and evaluated with a battery of clinical tests including low contrast letter acuity (LCLA), intraretinal layer thicknesses by optical coherence tomography (OCT), ganglion cell function by steady-state pattern electroretinography (PERG), axonal function by polarization-sensitive OCT, volumetric vessel density (VVD) by OCT angiography, and retinal tissue perfusion (RTP) by retinal function imager. RESULTS: Axonal function measured as retinal nerve fiber layer birefringence in the temporal quadrant and vessel density in the deep vascular plexus were significantly decreased at 2-year follow-up (P < 0.05). Subgroup analyses showed that the increased retinal blood flow volume occurred in patients with no evidence of disease activity (NEDA), and with stable or improved visual function (P < 0.05). There was no significant difference in the expanded disability state scale, LCLA, RTP, VVD, or PERG measures between the two visits (P > 0.05). CONCLUSION: To our best knowledge, this is the first 2-year prospective comprehensive study with a detailed assessment of retinal microstructure and neuronal functions in patients with RRMS. The recovery of retinal microcirculation occurred in patients with NEDA, and stable or improved visual function, suggesting these measurements as potential imaging biomarkers for monitoring disease progression.

[Early discharge and postpartum home visit during the COVID-19 pandemic at the HULP (Madrid).] / Alta precoz y visita domiciliaria puerperal durante la pandemia por la COVID-19 en el Hospital Universitario La Paz (Madrid).

OBJECTIVE: The COVID-19 pandemic caused that the Health Department of the Autonomous Region of Madrid redirected the Obstetrics, Gynecology and Neonatology emergency care. On March 24th 2020, the HULP launched a program of postpartum early discharge and home visit. The objective of this work was to detect if the care strategy "Voluntary early discharge and home visit by the midwife (2nd year EIR)" applied by the HULP during the COVID-19 pandemic had any adverse effect on the woman and/or the newborn. METHODS: Cross-sectional observational descriptive study using convenience sampling among women included in the early discharge-home visit program from March 24th to May 5th 2020. 222 medical records and telephone surveys to postpartum women who complied with the inclusion criteria were analyzed. The statistical analysis was performed using SAS 9.4. RESULTS: The average of inpatient time was 25 hours and 15 minutes. 8.6% of newborns were sent back to the HULP, and 2.2% were readmitted for hyperbilirubinemia. 2.3% of parents took their infants to the Emergency Care Unit, but only 0.46% needed readmission. 0.4% of postpartum women were readmitted. At the discharge, 84.2% of newborns exclusively breastfed. After one week of the birth, 73.4% of infants were exclusively breastfeeding, 18% were mixed breastfeeding, and 8.6% were bottle feeding. 89.6% of women believed early discharge was appropriate. Home visit was described as "very satisfactory" in 83.3% of cases, and the care provided, in 88.7% of cases. CONCLUSIONS: With the early discharge-home visit program, continuity of care is provided, health problems were detected and resolved and high maternal satisfaction levels were obtained.

OBJETIVO: La pandemia por la COVID-19 motivó que la Consejería de Sanidad de la Comunidad de Madrid reorganizara la atención urgente de Obstetricia-Ginecología y Neonatología. El 24/03/2020 se inicia en el Hospital Universitario La Paz (HULP) un programa de alta precoz posparto y visita domiciliaria. El objetivo de este estudio fue detectar si la estrategia de "alta precoz voluntaria y visita domiciliaria por la residente de matrona" aplicada por el HULP durante la pandemia por la COVID-19 tuvo algún efecto adverso en puérpera y/o recién nacido (RN). METODOS: Estudio observacional descriptivo transversal, con muestreo de conveniencia en mujeres incluidas en el programa de alta precoz voluntaria-visita domiciliaria entre 24/03/2020 y 5/05/2020. Se analizaron 222 historias clínicas y cuestionarios telefónicos de puérperas que cumplieron los criterios de selección. El análisis estadístico se realizó con el programa SAS-9.4. RESULTADOS: La media de estancia hospitalaria fue de 25h 15min. Derivaron al HULP a 8,6% neonatos, ingresando un 2,2% por hiperbilirrubinemia. El 2,3% de padres con sus neonatos acudieron a urgencias, ingresando el 0,46%. El 0,4% de puérperas precisó reingreso. Al alta, el 84,2% de RN tomaban lactancia materna exclusiva (LME). A la semana, el 73,4% de RN estaban con LME, el 18% con lactancia mixta y el 8,6% con lactancia artificial. El 89,6% consideró adecuada el alta precoz. Percibieron como "muy satisfactoria" la visita domiciliaria un 83,3%, y la atención profesional recibida un 88,7%. CONCLUSIONES: Con el alta precoz-visita domiciliaria se ofrece continuidad de cuidados, detectando y resolviendo problemas, manteniendo un alto grado de satisfacción materna.

Longitudinal Study of Retinal Structure, Vascular, and Neuronal Function in Patients With Relapsing-Remitting Multiple Sclerosis: 1-Year Follow-Up.

Objective: The purpose of this study was to quantify retinal structural, vascular, and functional changes in patients with relapsing-remitting multiple sclerosis (RRMS) over 1 year. Methods: Eighty-eight eyes of 44 patients with RRMS underwent assessments of low contrast letter acuity (LCLA), retinal ganglion cell function detected by the steady-state pattern electroretinogram (PERG), axonal microstructural integrity measured as birefringence, intraretinal layer thicknesses by ultra-high-resolution optical coherence tomography (OCT), volumetric vessel density (VVD) by OCT angiography, and retinal tissue perfusion (RTP) by the Retinal Function Imager (RFI). All measurements were performed at baseline and 1-year follow-up. The impacts of disease activities and a history of optic neuritis (ON) were analyzed. Results: Compared to baseline, there were no significant differences in all variables (P > 0.05), except for the axonal birefringence and RTP. The birefringence's of the retinal fiber layer at the temporal and superior quadrants was significantly decreased (P < 0.05), whereas RTP was significantly increased (P < 0.05). In the subgroup with ON, significantly longer PERG latency and decreased VVD were observed at follow-up (P < 0.05). In patients with improved LCLA, significantly increased RTP and decreased VVD (P < 0.05) were also observed. Conclusions: This is the first longitudinal study that assessed the RTP and VVD, along with other retinal structural and functional parameters in MS. The recovery of retinal vascular function occurred with the improved LCLA, suggesting that these measurements may be associated with disease progression. Translational Relevance: The retinal microvascular changes could be potential biomarkers for monitoring therapeutic efficacy in MS.

Multi-task temporal convolutional networks for joint recognition of surgical phases and steps in gastric bypass procedures.

PURPOSE: Automatic segmentation and classification of surgical activity is crucial for providing advanced support in computer-assisted interventions and autonomous functionalities in robot-assisted surgeries. Prior works have focused on recognizing either coarse activities, such as phases, or fine-grained activities, such as gestures. This work aims at jointly recognizing two complementary levels of granularity directly from videos, namely phases and steps. METHODS: We introduce two correlated surgical activities, phases and steps, for the laparoscopic gastric bypass procedure. We propose a multi-task multi-stage temporal convolutional network (MTMS-TCN) along with a multi-task convolutional neural network (CNN) training setup to jointly predict the phases and steps and benefit from their complementarity to better evaluate the execution of the procedure. We evaluate the proposed method on a large video dataset consisting of 40 surgical procedures (Bypass40). RESULTS: We present experimental results from several baseline models for both phase and step recognition on the Bypass40. The proposed MTMS-TCN method outperforms single-task methods in both phase and step recognition by 1-2% in accuracy, precision and recall. Furthermore, for step recognition, MTMS-TCN achieves a superior performance of 3-6% compared to LSTM-based models on all metrics. CONCLUSION: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on a gastric bypass dataset with multi-level annotations. The proposed method shows that the joint modeling of phases and steps is beneficial to improve the overall recognition of each type of activity.