In Vitro Assessment of the Neuro-Compatibility of Fe-20Mn as a Potential Bioresorbable Material for Craniofacial Surgery.

Background and Objectives: Spring-assisted surgery is a popular option for the treatment of non-syndromic craniosynostosis. The main drawback of this procedure is the need for a second surgery for spring removal, which could be avoided if a distractor material could be metabolised over time. Iron-Manganese alloys (FeMn) have a good trade-off between degradation rate and strength; however, their biocompatibility is still debated. Materials and Methods: In this study, the neuro-compatibility of Fe-20Mn (wt.%) was assessed using standard assays. PC-12 cells were exposed to Fe-20Mn (wt.%) and stainless steel via indirect contact. To examine the cytotoxicity, a Cell Tox Green assay was carried out after 1, 2, and 3 days of incubation. Following differentiation, a neurite morphological examination after 1 and 7 days of incubation time was carried out. The degradation response in modified Hank's solution at 1, 3, and 7 days was investigated, too. Results: The cytotoxicity assay showed a higher toxicity of Fe-20Mn than stainless steel at earlier time points; however, at the latest time point, no differences were found. Neurite morphology was similar for cells exposed to Fe-20Mn and stainless steel. Conclusions: In conclusion, the Fe-20Mn alloy shows promising neuro-compatibility. Future studies will focus on in vivo studies to confirm the cellular response to Fe-20Mn.

Understanding the Role of Surface Modification of Randomized Trabecular Titanium Structures in Bone Tissue Regeneration: An Experimental Study.

Background and Objectives: Three-dimensional (3D) metallic trabecular structures made by additive manufacturing (AM) technologies promote new bone formation and osteointegration. Surface modifications by chemical treatments can improve the osteoconductive properties of metallic structures. An in vivo study in sheep was conducted to assess the bone response to randomized trabecular titanium structures that underwent a surface modification by chemical treatment compared to the bone response to the untreated specimens. Material and Methods: Sixteen specimens with a randomized trabecular titanium structure were implanted in the spongious bone of the distal femur and proximal tibia and the cortical bone of the tibial diaphysis of two sheep. Of them, eight implants had undergone a chemical treatment (treated) and were compared to eight implants with the same structure but native surfaces (native). The sheep were sacrificed at 6 weeks. Surface features of the lattice structures (native and treated) were analyzed using a 3D non-contact profilometer. Compression tests of 18 lattice cubes were performed to investigate the mechanical properties of the two structures. Excellent biocompatibility for the trabecular structures was demonstrated in vitro using a cell mouse fibroblast culture. Histomorphometric analysis was performed to evaluate bone implant contact and bone ingrowth. Results: A compression test of lattice cubic specimens revealed a comparable maximum compressive strength value between the two tested groups (5099 N for native surfaces; 5558 N for treated surfaces; p > 0.05). Compared to native surfaces, a homogenous formation of micropores was observed on the surface of most trabeculae that increased the surface roughness of the treated specimens (4.3 versus 3.2 µm). The cellular viability of cells seeded on three-dimensional structure surfaces increased over time compared to that on plastic surfaces. The histomorphometric data revealed a similar behavior and response in spongious and cortical bone formation. The percentage of the implant surface in direct contact with the regenerated bone matrix (BIC) was not significantly different between the two groups either in the spongious bone (BIC: 27% for treated specimens versus 30% for native samples) or in the cortical bone (BIC: 75% for treated specimens versus 77% for native samples). Conclusions: The results of this study reveal rapid osseointegration and excellent biocompatibility for the trabecular structure regardless of surface treatment using AM technologies. The application of implant surfaces can be optimized to achieve a strong press-fit and stability, overcoming the demand for additional chemical surface treatments.

Three-dimensional cardiovascular imaging-genetics: a mass univariate framework.

Motivation: Left ventricular (LV) hypertrophy is a strong predictor of cardiovascular outcomes, but its genetic regulation remains largely unexplained. Conventional phenotyping relies on manual calculation of LV mass and wall thickness, but advanced cardiac image analysis presents an opportunity for high-throughput mapping of genotype-phenotype associations in three dimensions (3D). Results: High-resolution cardiac magnetic resonance images were automatically segmented in 1124 healthy volunteers to create a 3D shape model of the heart. Mass univariate regression was used to plot a 3D effect-size map for the association between wall thickness and a set of predictors at each vertex in the mesh. The vertices where a significant effect exists were determined by applying threshold-free cluster enhancement to boost areas of signal with spatial contiguity. Experiments on simulated phenotypic signals and SNP replication show that this approach offers a substantial gain in statistical power for cardiac genotype-phenotype associations while providing good control of the false discovery rate. This framework models the effects of genetic variation throughout the heart and can be automatically applied to large population cohorts. Availability and implementation: The proposed approach has been coded in an R package freely available at https://doi.org/10.5281/zenodo.834610 together with the clinical data used in this work. Contact: declan.oregan@imperial.ac.uk. Supplementary information: Supplementary data are available at Bioinformatics online.

CoCrMo alloys ions release behavior by TiNbN coating: an in vitro study.

The aim of the study was to show in vitro the greater inertness to the corrosion body fluid of TiNbN coating than the CoCrMo alloy substrate. The prosthetic component under study was a femoral component of total knee prosthesis in CoCrMo alloy coated in TiNbN with Physical Vapor Deposition technique immersed in static Hank's balanced salt solution (HBS) (pH = 6) for at least 34 months at a constant temperature of 37 °C. Another uncoated prosthetic component of CoCrMo alloy with the same type and size was left in static immersion in the same solution and for the same period of time. Scanning electron microscope (SEM) analysis was performed to investigate adhesion and proliferation at 24, 48, 72 h after seeding of 104 sub-confluents osteoblast-like cells (SaOS-2) cells on scaffold. The results of the study showed a reduction in the concentration of the metal ions released from the TiNbN-coated femoral component surface compared to the uncoated surface in the HBS solution. The overall reduction of the ions for the TiNbN-coated femoral component compared to the uncoated one was 80.1 ± 2%, 62.5% ± 8% and 48% ± 10% for Co, Cr, Mo, respectively (p < 0.01). SEM analysis confirmed the healthy state of the cells, the cellular adhesion and proliferation of SaOS-2 on the TiNbN-coated specimen. Although the results observed in vitro for the TiNbN coating are encouraging, clinical studies are certainly needed to be performed in order to understand how these positive findings can be translated in vivo and to determine the clinical benefit of TiNbN coating.

Phase Transformations in the CeO2-Sm2O3 System: A Multiscale Powder Diffraction Investigation.

The structure evolution in the CeO2-Sm2O3 system is revisited by combining high resolution synchrotron powder diffraction with pair distribution function (PDF) to inquire about local, mesoscopic, and average structure. The CeO2 fluorite structure undergoes two phase transformations by Sm doping, first to a cubic (C-type) and then to a monoclinic (B-type) phase. Whereas the C to B-phase separation occurs completely and on a long-range scale, no miscibility gap is detected between fluorite and C-type phases. The transformation rather occurs by growth of C-type nanodomains embedded in the fluorite matrix, without any long-range phase separation. A side effect of this mechanism is the ordering of the oxygen vacancies, which is detrimental for the application of doped ceria as an electrolyte in fuel cells. The results are discussed in the framework of other Y and Gd dopants, and the relationship between nanostructuring and the above equilibria is also investigated.

Effect of trabecular architectures on the mechanical response in osteoporotic and healthy human bone.

Research at the mesoscale bone trabeculae arrangement yields intriguing results that, due to their clinical resolution, can be applied in clinical field, contributing significantly to the diagnosis of bone-related diseases. While the literature offers quantitative morphometric parameters for a thorough characterization of the mesoscale bone network, there is a gap in understanding relationships among them, particularly in the context of various bone pathologies. This research aims to bridge these gaps by offering a quantitative evaluation of the interplay among morphometric parameters and mechanical response at mesoscale in osteoporotic and non-osteoporotic bones. Bone mechanical response, dependent on trabecular arrangement, is defined by apparent stiffness, computationally calculated using the Gibson-Ashby model. Key findings indicate that: (i) in addition to bone density, measured using X-ray absorptiometry, trabecular connectivity density, trabecular spacing and degree of anisotropy are crucial parameters for characterize osteoporosis state; (ii) apparent stiffness values exhibit strong correlations with bone density and connectivity density; (iii) connectivity density and degree of anisotropy result the best predictors of mechanical response. Despite the inherent heterogeneity in bone structure, suggesting the potential benefit of a larger sample size in the future, this approach presents a valuable method to enhance discrimination between osteoporotic and non-osteoporotic samples.

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy.

Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7 M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.

A biomechanical study of osseointegrated patient-matched additively manufactured implant for treatment of thumb amputees.

Thumb amputations leads to 50 % loss in hand functionality. To date, silicone vacuum prosthesis and autologous transplantation are the most adopted treatment solutions: nevertheless, vacuum prostheses lack in stability and cause skin issue and surgical treatment is not always accepted by patients. Osseointegrated implants were demonstrated to enhance stability, restore osseoperception and increase the time of prosthesis use. Thumb amputations present varying stump sizes: a standard size implant cannot address specificity of each patient, while a patient matched solution can meet surgeon requirements, by geometrical features of implant. The fixture presented in the current paper is the first additively manufactured patient matched osseointegrated implant for the treatment of thumb amputees. The current work aims to verify and validate a predictive finite element model (FEM) for mechanical strength of the presented fixture. FEM was demonstrated to correctly evaluate the mechanical strength of patient matched device. Minimum strength requirements were calculated in different core diameters: FEM were experimentally validated. Safety factor of 1.5 was guaranteed. Finally, considerations on performance of the prototype were carried out by means of insertion tests in Sawbones and axial pull-out force assessment. Cadaver tests to evaluate the entire procedure and production process are ongoing.

Bactericidal Activity of Silver-Doped Chitosan Coatings via Electrophoretic Deposition on Ti6Al4V Additively Manufactured Substrates.

Prosthetic reconstruction can serve as a feasible alternative, delivering both functional and aesthetic benefits to individuals with hand and finger injuries, frequent causes of emergency room visits. Implant-related infections pose significant challenges in arthroplasty and osteosynthesis procedures, contributing to surgical failures. As a potential solution to this challenge, this study developed a new class of silver (Ag)-doped chitosan (CS) coatings via electrophoretic deposition (EPD) on osseointegrated prostheses for infection therapy. These coatings were successfully applied to additively manufactured Ti6Al4V ELI samples. In the initial phase, the feasibility of the composite coating was assessed using the Thermogravimetric Analysis (TGA) and Attenuated Total Reflection (ATR) techniques. The optimized structures exhibited impressive water uptake in the range of 300-360%. Codeposition with an antibacterial agent proved effective, and scanning electron microscopy (SEM) was used to examine the coating morphology. Biologically, CS coatings demonstrated cytocompatibility when in direct contact with a fibroblast cell line (L929) after 72 h. When exposed to the Staphylococcus epidermidis strain (ATCC 12228), these coatings inhibited bacterial growth and biofilm formation within 24 h. These findings underscore the significant potential of this approach for various applications, including endoprostheses like hip implants, internal medical devices, and transcutaneous prostheses such as osseointegrated limb prosthetics for upper and lower extremities.

A novel AI device for real-time optical characterization of colorectal polyps.

Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conventional white light (WL) endoscopy video stream without virtual chromoendoscopy (blue light, BL). In this work, we evaluated the standalone performance of this computer-aided diagnosis device (CADx) on a prospectively acquired dataset of unaltered colonoscopy videos. An international group of endoscopists performed optical characterization of each polyp acquired in a prospective study, blinded to both histology and CADx result, by means of an online platform enabling careful video assessment. Colorectal polyps were categorized by reviewers, subdivided into 10 experts and 11 non-experts endoscopists, and by the CADx as either "adenoma" or "non-adenoma". A total of 513 polyps from 165 patients were assessed. CADx accuracy in WL was found comparable to the accuracy of expert endoscopists (CADxWL/Exp; OR 1.211 [0.766-1.915]) using histopathology as the reference standard. Moreover, CADx accuracy in WL was found superior to the accuracy of non-expert endoscopists (CADxWL/NonExp; OR 1.875 [1.191-2.953]), and CADx accuracy in BL was found comparable to it (CADxBL/CADxWL; OR 0.886 [0.612-1.282]). The proposed intelligent device shows the potential to support non-expert endoscopists in systematically reaching the performances of expert endoscopists in optical characterization.

Self-Supervised Learning for Few-Shot Medical Image Segmentation.

Fully-supervised deep learning segmentation models are inflexible when encountering new unseen semantic classes and their fine-tuning often requires significant amounts of annotated data. Few-shot semantic segmentation (FSS) aims to solve this inflexibility by learning to segment an arbitrary unseen semantically meaningful class by referring to only a few labeled examples, without involving fine-tuning. State-of-the-art FSS methods are typically designed for segmenting natural images and rely on abundant annotated data of training classes to learn image representations that generalize well to unseen testing classes. However, such a training mechanism is impractical in annotation-scarce medical imaging scenarios. To address this challenge, in this work, we propose a novel self-supervised FSS framework for medical images, named SSL-ALPNet, in order to bypass the requirement for annotations during training. The proposed method exploits superpixel-based pseudo-labels to provide supervision signals. In addition, we propose a simple yet effective adaptive local prototype pooling module which is plugged into the prototype networks to further boost segmentation accuracy. We demonstrate the general applicability of the proposed approach using three different tasks: organ segmentation of abdominal CT and MRI images respectively, and cardiac segmentation of MRI images. The proposed method yields higher Dice scores than conventional FSS methods which require manual annotations for training in our experiments.

Osseointegrated Metallic Implants for Finger Amputees: A Review of the Literature.

Digital trauma amputations and digital agenesis strongly affect the functionality and aesthetic appearance of the hand. Autologous reconstruction is the gold standard of treatment. Unfortunately, microsurgical options and transplantation procedures are not possible for patients who present contraindications or refuse to undergo transplantation from the toe (e.g. toe-to-thumb transplantation). To address these issues, osseointegrated finger prostheses are a promising alternative. The functional assessments registered during follow-up confirmed the promising outcomes of osseointegrated prostheses in the treatment of hand finger amputees. This review outlines (a) a detailed analysis of osseointegrated finger metallic components of the implants, (b) the surgical procedures suggested in the literature, and (c) the functional assessments and promising outcomes that demonstrate the potential of these medical osseointegrated devices in the treatment of finger amputees.

Heat Treatments for Stress Relieving AlSi9Cu3 Alloy Produced by Laser Powder Bed Fusion.

The present work explores the effect of a stress relieving heat treatment on the microstructure, tensile properties and residual stresses of the laser powder bed fused AlSi9Cu3 alloy. In fact, the rapid cooling rates together with subsequent heating/cooling cycles occurred during layer by layer additive manufacturing production make low temperature heat treatments desirable for promoting stress relaxation as well as limited grain growth: this combination can offer the opportunity of obtaining the best compromise between high strength, good elongation to failure and limited residual stresses. The microstructural features were analysed, revealing that the high cooling rate, induced by the process, caused a large supersaturation of the aluminum matrix and the refinement of the eutectic structure. Microhardness versus time curve, performed at 250 °C, allowed to identify a stabilization of the mechanical property at a duration of 25 h. The microstructure and the mechanical properties of the samples heat treated at 25 h and at 64 h, considered as a reference for the conventionally produced alloy, were compared with the ones of the as-built alloy. Finally, it was shown that a 59% reduction of the principal residual stresses could be achieved after the 25 h-long treatment and such evolution was correlated to the mechanical behaviour.

Phenotypic Expression and Outcomes in Individuals With Rare Genetic Variants of Hypertrophic Cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is caused by rare variants in sarcomere-encoding genes, but little is known about the clinical significance of these variants in the general population. OBJECTIVES: The goal of this study was to compare lifetime outcomes and cardiovascular phenotypes according to the presence of rare variants in sarcomere-encoding genes among middle-aged adults. METHODS: This study analyzed whole exome sequencing and cardiac magnetic resonance imaging in UK Biobank participants stratified according to sarcomere-encoding variant status. RESULTS: The prevalence of rare variants (allele frequency <0.00004) in HCM-associated sarcomere-encoding genes in 200,584 participants was 2.9% (n = 5,712; 1 in 35), and the prevalence of variants pathogenic or likely pathogenic for HCM (SARC-HCM-P/LP) was 0.25% (n = 493; 1 in 407). SARC-HCM-P/LP variants were associated with an increased risk of death or major adverse cardiac events compared with controls (hazard ratio: 1.69; 95% confidence interval [CI]: 1.38-2.07; P < 0.001), mainly due to heart failure endpoints (hazard ratio: 4.23; 95% CI: 3.07-5.83; P < 0.001). In 21,322 participants with both cardiac magnetic resonance imaging and whole exome sequencing, SARC-HCM-P/LP variants were associated with an asymmetric increase in left ventricular maximum wall thickness (10.9 ± 2.7 mm vs 9.4 ± 1.6 mm; P < 0.001), but hypertrophy (≥13 mm) was only present in 18.4% (n = 9 of 49; 95% CI: 9%-32%). SARC-HCM-P/LP variants were still associated with heart failure after adjustment for wall thickness (hazard ratio: 6.74; 95% CI: 2.43-18.7; P < 0.001). CONCLUSIONS: In this population of middle-aged adults, SARC-HCM-P/LP variants have low aggregate penetrance for overt HCM but are associated with an increased risk of adverse cardiovascular outcomes and an attenuated cardiomyopathic phenotype. Although absolute event rates are low, identification of these variants may enhance risk stratification beyond familial disease.

Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models.

Quantification of anatomical shape changes currently relies on scalar global indexes which are largely insensitive to regional or asymmetric modifications. Accurate assessment of pathology-driven anatomical remodeling is a crucial step for the diagnosis and treatment of many conditions. Deep learning approaches have recently achieved wide success in the analysis of medical images, but they lack interpretability in the feature extraction and decision processes. In this work, we propose a new interpretable deep learning model for shape analysis. In particular, we exploit deep generative networks to model a population of anatomical segmentations through a hierarchy of conditional latent variables. At the highest level of this hierarchy, a two-dimensional latent space is simultaneously optimised to discriminate distinct clinical conditions, enabling the direct visualisation of the classification space. Moreover, the anatomical variability encoded by this discriminative latent space can be visualised in the segmentation space thanks to the generative properties of the model, making the classification task transparent. This approach yielded high accuracy in the categorisation of healthy and remodelled left ventricles when tested on unseen segmentations from our own multi-centre dataset as well as in an external validation set, and on hippocampi from healthy controls and patients with Alzheimer's disease when tested on ADNI data. More importantly, it enabled the visualisation in three-dimensions of both global and regional anatomical features which better discriminate between the conditions under exam. The proposed approach scales effectively to large populations, facilitating high-throughput analysis of normal anatomy and pathology in large-scale studies of volumetric imaging.

Sex and regional differences in myocardial plasticity in aortic stenosis are revealed by 3D model machine learning.

AIMS: Left ventricular hypertrophy (LVH) in aortic stenosis (AS) varies widely before and after aortic valve replacement (AVR), and deeper phenotyping beyond traditional global measures may improve risk stratification. We hypothesized that machine learning derived 3D LV models may provide a more sensitive assessment of remodelling and sex-related differences in AS than conventional measurements. METHODS AND RESULTS: One hundred and sixteen patients with severe, symptomatic AS (54% male, 70 ± 10 years) underwent cardiovascular magnetic resonance pre-AVR and 1 year post-AVR. Computational analysis produced co-registered 3D models of wall thickness, which were compared with 40 propensity-matched healthy controls. Preoperative regional wall thickness and post-operative percentage wall thickness regression were analysed, stratified by sex. AS hypertrophy and regression post-AVR was non-uniform-greatest in the septum with more pronounced changes in males than females (wall thickness regression: -13 ± 3.6 vs. -6 ± 1.9%, respectively, P < 0.05). Even patients without LVH (16% with normal indexed LV mass, 79% female) had greater septal and inferior wall thickness compared with controls (8.8 ± 1.6 vs. 6.6 ± 1.2 mm, P < 0.05), which regressed post-AVR. These differences were not detectable by global measures of remodelling. Changes to clinical parameters post-AVR were also greater in males: N-terminal pro-brain natriuretic peptide (NT-proBNP) [-37 (interquartile range -88 to -2) vs. -1 (-24 to 11) ng/L, P = 0.008], and systolic blood pressure (12.9 ± 23 vs. 2.1 ± 17 mmHg, P = 0.009), with changes in NT-proBNP correlating with percentage LV mass regression in males only (ß 0.32, P = 0.02). CONCLUSION: In patients with severe AS, including those without overt LVH, LV remodelling is most plastic in the septum, and greater in males, both pre-AVR and post-AVR. Three-dimensional machine learning is more sensitive than conventional analysis to these changes, potentially enhancing risk stratification. CLINICAL TRIAL REGISTRATION: Regression of myocardial fibrosis after aortic valve replacement (RELIEF-AS); NCT02174471. https://clinicaltrials.gov/ct2/show/NCT02174471.

Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach.

Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localization tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artifacts (e.g., due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network's ability to infer landmarks, which are then used downstream in the pipeline to initialize atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution, and anatomically smooth bi-ventricular 3D models, despite the presence of artifacts in input CMR volumes.

Deep learning cardiac motion analysis for human survival prediction.

Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimising the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using a fully convolutional network trained on anatomical shape priors. This dense motion model formed the input to a supervised denoising autoencoder (4Dsurvival), which is a hybrid network consisting of an autoencoder that learns a task-specific latent code representation trained on observed outcome data, yielding a latent representation optimised for survival prediction. To handle right-censored survival outcomes, our network used a Cox partial likelihood loss function. In a study of 302 patients the predictive accuracy (quantified by Harrell's C-index) was significantly higher (p = .0012) for our model C=0.75 (95% CI: 0.70 - 0.79) than the human benchmark of C=0.59 (95% CI: 0.53 - 0.65). This work demonstrates how a complex computer vision task using high-dimensional medical image data can efficiently predict human survival.

Metabolic pathways associated with right ventricular adaptation to pulmonary hypertension: 3D analysis of cardiac magnetic resonance imaging.

AIMS: We sought to identify metabolic pathways associated with right ventricular (RV) adaptation to pulmonary hypertension (PH). We evaluated candidate metabolites, previously associated with survival in pulmonary arterial hypertension, and used automated image segmentation and parametric mapping to model their relationship to adverse patterns of remodelling and wall stress. METHODS AND RESULTS: In 312 PH subjects (47.1% female, mean age 60.8 ± 15.9 years), of which 182 (50.5% female, mean age 58.6 ± 16.8 years) had metabolomics, we modelled the relationship between the RV phenotype, haemodynamic state, and metabolite levels. Atlas-based segmentation and co-registration of cardiac magnetic resonance imaging was used to create a quantitative 3D model of RV geometry and function-including maps of regional wall stress. Increasing mean pulmonary artery pressure was associated with hypertrophy of the basal free wall (ß = 0.29) and reduced relative wall thickness (ß = -0.38), indicative of eccentric remodelling. Wall stress was an independent predictor of all-cause mortality (hazard ratio = 1.27, P = 0.04). Six metabolites were significantly associated with elevated wall stress (ß = 0.28-0.34) including increased levels of tRNA-specific modified nucleosides and fatty acid acylcarnitines, and decreased levels (ß = -0.40) of sulfated androgen. CONCLUSION: Using computational image phenotyping, we identify metabolic profiles, reporting on energy metabolism and cellular stress-response, which are associated with adaptive RV mechanisms to PH.

Fetal Skull Reconstruction via Deep Convolutional Autoencoders.

Ultrasound (US) imaging is arguably the most commonly used modality for fetal screening. Recently, 3DUS has been progressively adopted in modern obstetric practice, showing promising diagnosis capabilities, and alleviating many of the inherent limitations of traditional 2DUS, such as subjectivity and operator dependence. However, the involuntary movements of the fetus, and the difficulty for the operator to inspect the entire volume in real-time can hinder the acquisition of the entire region of interest. In this paper, we present two deep convolutional architectures for the reconstruction of the fetal skull in partially occluded 3DUS volumes: a TL deep convolutional network (TL-Net), and a conditional variational autoencoder (CVAE). The performance of the two networks was evaluated for occlusion rates up to 50%, both showing accurate results even when only 60% of the skull is included in the US volume (Dice coeff. $0.84\pm 0.04$ for CVAE and $0.83\pm 0.03$ for TL-Net). The reconstruction networks proposed here have the potential to optimize image acquisition protocols in obstetric sonography, reducing the acquisition time and providing comprehensive anatomical information even from partially occluded images.