Geometric Metrics Research Articles

Deep learning for automatic target volume segmentation in radiation therapy: a review.

Deep learning, a new branch of machine learning algorithm, has emerged as a fast growing trend in medical imaging and become the state-of-the-art method in various clinical applications such as Radiology, Histo-pathology and Radiation Oncology. Specifically in radiation oncology, deep learning has shown its power in performing automatic segmentation tasks in radiation therapy for Organs-At-Risks (OAR), given its potential in improving the efficiency of OAR contouring and reducing the inter- and intra-observer variabilities. The similar interests were shared for target volume segmentation, an essential step of radiation therapy treatment planning, where the gross tumor volume is defined and microscopic spread is encompassed. The deep learning-based automatic segmentation method has recently been expanded into target volume automatic segmentation. In this paper, the authors summarized the major deep learning architectures of supervised learning fashion related to target volume segmentation, reviewed the mechanism of each infrastructure, surveyed the use of these models in various imaging domains (including Computational Tomography with and without contrast, Magnetic Resonant Imaging and Positron Emission Tomography) and multiple clinical sites, and compared the performance of different models using standard geometric evaluation metrics. The paper concluded with a discussion of open challenges and potential paths of future research in target volume automatic segmentation and how it may benefit the clinical practice.

Comparing Deep Learning Based Prostate Delineation With Manual Contouring From Multiple Experts

Accurate contouring of the target is very important in radiation therapy treatment planning. Unlike most other cancers where the radiation target occupies a small area of an organ, prostate cancer treatment involves the irradiation of the entire prostate. This study evaluates the quality of prostate contours generated from a deep learning segmentation (DLSEG) model.A total of 23 prostate cancer patients who did not underwent prostatectomy was randomly selected. The original contours used clinically was carefully quality checked and revised when necessary by one expert radiation oncologist (RO) and regarded as the ground truth (GT). Two additional ROs were invited to perform manual contouring of the prostate from scratch. Auto contours (labelled as AI) generated by a research version of DLSEG was then compared with those from manual delineations. A paired t-test was employed for statistical comparison. A comparative geometric analysis of the manual and automatic delineations was performed to quantify the multi-observer delineation variability, including dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD).Using GT contour as reference, the contours from three additional RO achieved an average of 0.81 ± 0.04 for DSC, 0.60 ± 0.16cm and 0.21 ± 0.05cm for HD95 and MSD, respectively. In contrast, AI contours achieved an average of 0.83 ± 0.05 for DSC, 0.60 ± 0.18cm and 0.21 ± 0.07 cm for HD95 and MSD, respectively. No statistical difference was found for the delineation accuracy between the three observers (P > 0.05). AI contours were considered to have similar performance to the three human experts with all geometric metrics (P > 0.05).The DLSEG model for prostate contouring tested demonstrates similar performance in terms of accuracy compared with expert ROs.

Deep Learning-Based Automatic Delineation of Target Volumes and Organs at Risk of Breast Cancer for On-Line Dosimetric Evaluation

In this study, we developed a deep learning model to achieve automatic multi-target delineation on planning CT (pCT) and daily Cone-Beam CT (CBCT). To improve the image quality of the CBCT for accurate target delineation and dose calculation, we introduce an unsupervised learning model to generate the artifact-free synthetic CT (sCT) from the CBCT. The geometric and dosimetric impact of the model on planning CT (pCT) and synthetic CT (sCT) was evaluated for breast cancer adaptive radiation therapy.We retrospectively analyzed 1127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT for patient setup acquired utilizing breath-hold guided by optical surface monitoring system was used to generate sCT with the generative adversarial network. Organs at risk (OARs) and target volumes including tumor bed (TB) and clinical target volume (CTV) for breast cancer were delineated automatically with 3D U-Net model on pCT and sCT. The automatic delineation was compared with manually delineated contours to evaluate the performance with geometric metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff Distance (HD95). The treatment plan which was transferred to the sCT from the pCT was generated with the same planning parameters as the original pCT-based plan. The dosimetric evaluation was performed by a quick dose recalculation on sCT relying on gamma analysis and the dose-volume histogram (DVH) parameters. The automatically delineating CTV on sCT which was rigidly registered to pCT was compared with manually delineating CTV on pCT to obtain DSC-CTV. The relationship between the ∆D95, ∆V95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.The range of the DSC and HD95 were 0.73-0.97, 2.22-9.36mm for pCT, 0.63-0.95, 2.30-19.57mm for sCT from institution A, 0.70-0.97, 2.10-11.43mm for pCT from institution B respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78HU. The mean gamma pass rate (3%/3 mm criterion) by comparing the dose on sCT with that on original pCT was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2Gy of D95. The mean ∆V95 of CTV was less than 6%. The mean ∆V95 of TB was more than 8%. The mean ∆D90/∆D95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer was bigger than that in right breast cancer.This study demonstrates that highly accurate multi-target delineation and dose calculation are achievable using the daily CBCT image via deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations to decide whether to re-plan during breast cancer radiotherapy.

A framework for automated and streamlined kV cone beam computed tomography image quality assurance: a multi-institutional study

The purpose of this study was to develop and evaluate a framework to support automated standardized testing and analysis of Cone Beam Computed Tomography (CBCT) image quality QA across multiple institutions. A survey was conducted among the participating institutions to understand the variability of the CBCT QA practices. A commercial, automated software platform was validated by seven institutions participating in a consortium dedicated to automated quality assurance. The CBCT image analysis framework was used to compare periodic QA results among 23 linear accelerators (linacs) from seven institutions. The CBCT image quality metrics (geometric distortion, spatial resolution, contrast, HU constancy, uniformity and noise) data are plotted as a function of means with the upper and lower control limits compared to the linac acceptance criteria and AAPM recommendations. For example, mean geometric distortion and HU constancy metrics were found to be 0.13 mm (TG142 recommendation: ≤2 mm) and 13.4 respectively (manufacturer acceptance specification: ≤±50).Image upload and analysis process was fully automated using a MATLAB-based platform. This analysis enabled a quantitative, longitudinal assessment of the performance of quality metrics which were also compared across 23 linacs. For key CBCT parameters such as uniformity, contrast, and HU constancy, all seven institutions used stricter goals than what would be recommended based on the analysis of the upper and lower control limits. These institutional goals were also found to be stricter than that found in AAPM published guidance. This work provides a reference that could be used to machine-specific optimized tolerance of CBCT image maintenance via control charts to monitor performance we well as the sensitivity of different tests in support of a broader quality assurance program. To ensure the daily image quality needed for patient care, the optimized statistical QA metrics recommended to using along with risk-based QA.

Clustering-based rule generation methods for fuzzy classifier using Autonomous Data Partitioning algorithm

In this paper, clustering-based rule generation methods for fuzzy classifier using non-parametric Autonomous Data Partitioning algorithm have been proposed. ADP-algorithm is used to determine the number of clusters for use in various k-means-like clustering algorithms. Proposed method contributes to solving the problem of determining optimal number of clusters/rules. The efficiency of fuzzy classifiers with rules constructed by the specified algorithms has been tested on data sets from the KEEL repository. Experimental results show that proposed method outperforms baseline algorithm (the extremums rulebase generation algorithm) both in terms of classification accuracy and geometric mean metrics.

The predictive value of segmentation metrics on dosimetry in organs at risk of the brain

BackgroundFully automatic medical image segmentation has been a long pursuit in radiotherapy (RT). Recent developments involving deep learning show promising results yielding consistent and time efficient contours. In order to train and validate these systems, several geometric based metrics, such as Dice Similarity Coefficient (DSC), Hausdorff, and other related metrics are currently the standard in automated medical image segmentation challenges. However, the relevance of these metrics in RT is questionable. The quality of automated segmentation results needs to reflect clinical relevant treatment outcomes, such as dosimetry and related tumor control and toxicity. In this study, we present results investigating the correlation between popular geometric segmentation metrics and dose parameters for Organs-At-Risk (OAR) in brain tumor patients, and investigate properties that might be predictive for dose changes in brain radiotherapy. MethodsA retrospective database of glioblastoma multiforme patients was stratified for planning difficulty, from which 12 cases were selected and reference sets of OARs and radiation targets were defined. In order to assess the relation between segmentation quality -as measured by standard segmentation assessment metrics- and quality of RT plans, clinically realistic, yet alternative contours for each OAR of the selected cases were obtained through three methods: (i) Manual contours by two additional human raters. (ii) Realistic manual manipulations of reference contours. (iii) Through deep learning based segmentation results. On the reference structure set a reference plan was generated that was re-optimized for each corresponding alternative contour set. The correlation between segmentation metrics, and dosimetric changes was obtained and analyzed for each OAR, by means of the mean dose and maximum dose to 1% of the volume (Dmax 1%). Furthermore, we conducted specific experiments to investigate the dosimetric effect of alternative OAR contours with respect to the proximity to the target, size, particular shape and relative location to the target. ResultsWe found a low correlation between the DSC, reflecting the alternative OAR contours, and dosimetric changes. The Pearson correlation coefficient between the mean OAR dose effect and the Dice was -0.11. For Dmax 1%, we found a correlation of -0.13. Similar low correlations were found for 22 other segmentation metrics. The organ based analysis showed that there is a better correlation for the larger OARs (i.e. brainstem and eyes) as for the smaller OARs (i.e. optic nerves and chiasm). Furthermore, we found that proximity to the target does not make contour variations more susceptible to the dose effect. However, the direction of the contour variation with respect to the relative location of the target seems to have a strong correlation with the dose effect. ConclusionsThis study shows a low correlation between segmentation metrics and dosimetric changes for OARs in brain tumor patients. Results suggest that the current metrics for image segmentation in RT, as well as deep learning systems employing such metrics, need to be revisited towards clinically oriented metrics that better reflect how segmentation quality affects dose distribution and related tumor control and toxicity.

Metaball skinning of synthetic astroglial morphologies into realistic mesh models for visual analytics and in silico simulations.

MotivationAstrocytes, the most abundant glial cells in the mammalian brain, have an instrumental role in developing neuronal circuits. They contribute to the physical structuring of the brain, modulating synaptic activity and maintaining the blood–brain barrier in addition to other significant aspects that impact brain function. Biophysically, detailed astrocytic models are key to unraveling their functional mechanisms via molecular simulations at microscopic scales. Detailed, and complete, biological reconstructions of astrocytic cells are sparse. Nonetheless, data-driven digital reconstruction of astroglial morphologies that are statistically identical to biological counterparts are becoming available. We use those synthetic morphologies to generate astrocytic meshes with realistic geometries, making it possible to perform these simulations.ResultsWe present an unconditionally robust method capable of reconstructing high fidelity polygonal meshes of astroglial cells from algorithmically-synthesized morphologies. Our method uses implicit surfaces, or metaballs, to skin the different structural components of astrocytes and then blend them in a seamless fashion. We also provide an end-to-end pipeline to produce optimized two- and three-dimensional meshes for visual analytics and simulations, respectively. The performance of our pipeline has been assessed with a group of 5000 astroglial morphologies and the geometric metrics of the resulting meshes are evaluated. The usability of the meshes is then demonstrated with different use cases.Availability and implementationOur metaball skinning algorithm is implemented in Blender 2.82 relying on its Python API (Application Programming Interface). To make it accessible to computational biologists and neuroscientists, the implementation has been integrated into NeuroMorphoVis, an open source and domain specific package that is primarily designed for neuronal morphology visualization and meshing.Supplementary informationSupplementary data are available at Bioinformatics online.

The Effect of TiN-, TiCN-, TiAlN-, and TiSiN Coated Tools on the Surface Defects and Geometric Tolerances of Holes in Multi-Spindle Drilling of Al2024 Alloy

The integrity of machined holes depends on many parameters, some of which are related to the cutting tool (geometry, coating, material). Other influential parameters are related to the machining process variables (spindle speed, feed rate, workpiece material), all of which can affect the quality of the hole and drilling induced damage on its surface. This study investigates the effect of uncoated tools and four types of tool coatings (TiN-, TiCN-, TiAlN-, and TiSiN) on the hole quality and its microstructure. The study analyzed several hole geometrical metrics, namely hole size, circularity, cylindricity, and perpendicularity of an Al2024 aluminum alloy using a multi-spindle drilling process that utilizes three drills capable of creating multiple holes simultaneously. The results showed that the uncoated carbide drill gave a high-hole quality at low spindle speed. Regarding the coated drills, TiCN coated drills produced holes with the least deviation, circularity, cylindricity and perpendicularity at high spindle speeds. TiSiN–carbide coated drills produced the most oversized holes and noticeable damage and deformations on their surface following TiAlN and TiN. The common surface damage found on the inner hole surface was smearing, feed marks, and metal debris adhesion. The ANOVA results revealed that the tool type had the highest percentage contribution that mainly affected the hole quality.

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer

PurposeTo investigate the dosimetric impact of deep learning-based auto-segmentation of organs at risk (OARs) on nasopharyngeal and rectal cancer.Methods and materialsTwenty patients, including ten nasopharyngeal carcinoma (NPC) patients and ten rectal cancer patients, who received radiotherapy in our department were enrolled in this study. Two deep learning-based auto-segmentation systems, including an in-house developed system (FD) and a commercial product (UIH), were used to generate two auto-segmented OARs sets (OAR_FD and OAR_UIH). Treatment plans based on auto-segmented OARs and following our clinical requirements were generated for each patient on each OARs sets (Plan_FD and Plan_UIH). Geometric metrics (Hausdorff distance (HD), mean distance to agreement (MDA), the Dice similarity coefficient (DICE) and the Jaccard index) were calculated for geometric evaluation. The dosimetric impact was evaluated by comparing Plan_FD and Plan_UIH to original clinically approved plans (Plan_Manual) with dose-volume metrics and 3D gamma analysis. Spearman’s correlation analysis was performed to investigate the correlation between dosimetric difference and geometric metrics.ResultsFD and UIH could provide similar geometric performance in parotids, temporal lobes, lens, and eyes (DICE, p > 0.05). OAR_FD had better geometric performance in the optic nerves, oral cavity, larynx, and femoral heads (DICE, p < 0.05). OAR_UIH had better geometric performance in the bladder (DICE, p < 0.05). In dosimetric analysis, both Plan_FD and Plan_UIH had nonsignificant dosimetric differences compared to Plan_Manual for most PTV and OARs dose-volume metrics. The only significant dosimetric difference was the max dose of the left temporal lobe for Plan_FD vs. Plan_Manual (p = 0.05). Only one significant correlation was found between the mean dose of the femoral head and its HD index (R = 0.4, p = 0.01), there is no OARs showed strong correlation between its dosimetric difference and all of four geometric metrics.ConclusionsDeep learning-based OARs auto-segmentation for NPC and rectal cancer has a nonsignificant impact on most PTV and OARs dose-volume metrics. Correlations between the auto-segmentation geometric metric and dosimetric difference were not observed for most OARs.

Effect of surface geometry on laser powder bed fusion defects

Laser Powder Bed Fusion (L-PBF) is an additive manufacturing (AM) technology which has enabled the fabrication of highly complex structures and components. A major challenge in producing these high complexity structures is predicting where defects are likely to occur, and how severe those defects will be. In this study build geometry is linked to manufacturability, using quantifiable AM defects and metrics. This was achieved by fabricating a variety of unsupported, thin-walled samples with different curvatures using Al-10Si-Mg alloy. A combination of X-Ray computed tomographic (XCT) and digital stereomicroscopy were used to capturing positional data about the total geometric error, surface quality and roughness metrics (Ra and Rz). This dataset was used to create empirical model which predicts geometric error based on the local curvature, orientation and thickness of the computer-aided-design (CAD) geometry. Local inclination angle was observed to have the strongest effect on manufacturability, heavily impacting the geometric error and surface quality metrics. Sample shape defined by curvature was observed to be a secondary factor, which became important in areas of low inclination angle. The empirical model was applied in a case study of a cellular structure, the double gyroid, which successfully identified problematic regions of the structure. The approach of linking fundamental geometry features to defects shown in this study provides additional guidance in design for AM, with potential applications in topology optimisation, optimising part orientation to reduce support, and for design of other intricate components such as the internal conduits of heat exchange devices, where supports are not feasible to use.

Cross-calibration of MODIS and VIIRS long near infrared bands for ocean color science and applications

Generation of consistent multi-sensor datasets is critical to the assessment of long-term global changes using satellite-borne instruments. Recent research suggests, however, that a fundamental assumption in satellite ocean color data processing concerning the calibration of the long near infrared band (i.e., 865 nm for MODIS) may introduce sensor-specific biases in space and/or time, which may also contribute to cross-sensor inconsistency in the derived reflectance data products. As such, it is necessary to assess the calibration of this band across sensors – performed here for MODIS/Aqua and VIIRS/SNPP using ‘simultaneous same view’ matchups (SSV; similar to simultaneous nadir overpass, but allowing for non-nadir measurements). Towards that end, we assess geometric, temporal, and spatial homogeneity metrics to identify SSVs, and develop a band-shifting approach applicable within standard satellite data processing routines to resolve expected spectral differences in the radiometry. We find top-of-atmosphere (TOA) radiance data from VIIRS/SNPP long near infrared band to be approximately 3% higher than the corresponding MODIS/A data. With the expectation that cross-calibrating the NIRL should improve cross-sensor continuity of downstream geophysical products (e.g., chlorophyll-a), we reprocessed VIIRS data using updated calibration coefficients. While we noticed many minor improvements in cross-sensor continuity in such data products, large-scale geographic and temporal biases between these two datasets still remain. These discontinuities may be the result of disparate errors in polarization correction or atmospheric correction, both of which are modulated by radiant path geometry.

On the Detection of Structural Aesthetic Defects of Android Mobile User Interfaces with a Metrics-based Tool

Smartphone users are striving for easy-to-learn and use mobile apps user interfaces. Accomplishing these qualities demands an iterative evaluation of the Mobile User Interface (MUI). Several studies stress the value of providing a MUI with a pleasing look and feel to engaging end-users. The MUI, therefore, needs to be free from all kinds of structural aesthetic defects. Such defects are indicators of poor design decisions interfering with the consistency of a MUI and making it more difficult to use. To this end, we are proposing a tool (Aesthetic Defects DEtection Tool (ADDET)) to determine the structural aesthetic dimension of MUIs. Automating this process is useful to designers in evaluating the quality of their designs. Our approach is composed of two modules. (1) Metrics assessment is based on the static analysis of a tree-structured layout of the MUI. We used 15 geometric metrics (also known as structural or aesthetic metrics) to check various structural properties before a defect is triggered. (2) Defects detection: The manual combination of metrics and defects are time-consuming and user-dependent when determining a detection rule. Thus, we perceive the process of identification of defects as an optimization problem. We aim to automatically combine the metrics related to a particular defect and optimize the accuracy of the rules created by assigning a weight, representing the metric importance in detecting a defect. We conducted a quantitative and qualitative analysis to evaluate the accuracy of the proposed tool in computing metrics and detecting defects. The findings affirm the tool’s reliability when assessing a MUI’s structural design problems with 71% accuracy.

FAWA: Fast Adversarial Watermark Attack

Recently, adversarial attacks have shown to lead the state-of-the-art deep neural networks (DNNs) to misclassification. However, most adversarial attacks are generated according to whether they are perceptual to human visual system, measured by geometric metrics such as the l2-norm, which ignores the common watermarks in cyber-physical systems. In this paper, we propose a fast adversarial watermark attack (FAWA) method based on fast differential evolution technique, which optimally superimposes a watermark on an image to fool DNNs. We also attempt to explain the reason why the attack is successful and propose two hypotheses on the vulnerability of DNN classifiers and the influence of the watermark attack on higher-layer features extraction respectively. In addition, we propose two countermeasure methods against FAWA based on random rotation and median filtering respectively. Experimental results show that our method achieves 41.3% success rate in fooling VGG-16 and have good transferability. Our approach is also shown to be effective in deceiving deep learning as a service (DLaaS) systems as well as the physical world. The proposed FAWA, hypotheses, and the countermeasure methods, provide a timely help for DNN designers to gain some knowledge of model vulnerability while designing DNN classifiers and related DLaaS applications.

Feature-preserving 3D mesh simplification for urban buildings

The goal of urban building mesh simplification is to generate a compact representation of a building from a given mesh. Local smoothness and sharp contours of urban buildings are important features for converting unstructured data into solid models, which should be preserved during the simplification. In this paper, we present a general method to filter and simplify 3D building mesh models, capable of preserving piecewise planar structures and sharp features. Given a building mesh model, a mesh filtering technique is firstly designed to yield piecewise planar regions and extract crease contours. The planar regions are used to constrain the simplification of the mesh. Mesh decimation is achieved through a series of edge collapse operations, which uses regional structural constraints and local geometric error metrics to handle planar and non-planar areas respectively. The proposed method preserves the mesh structure with meaningful levels of detail while reducing the number of faces. The effectiveness of this method is evaluated on various building models generated from different observation scales, and the performance is validated by extensive comparisons to state-of-the-art techniques.

An anchor-based graph method for detecting and classifying indoor objects from cluttered 3D point clouds

Most of the existing 3D indoor object classification methods have shown impressive achievements on the assumption that all objects are oriented in the upward direction with respect to the ground. To release this assumption, great effort has been made to handle arbitrarily oriented objects in terrestrial laser scanning (TLS) point clouds. As one of the most promising solutions, anchor-based graphs can be used to classify freely oriented objects. However, this approach suffers from missing anchor detection since valid detection relies heavily on the completeness of an anchor’s point clouds and is sensitive to missing data. This paper presents an anchor-based graph method to detect and classify arbitrarily oriented indoor objects. The anchors of each object are extracted by the structurally adjacent relationship among parts instead of the parts’ geometric metrics. In the case of adjacency, an anchor can be correctly extracted even with missing parts since the adjacency between an anchor and other parts is retained irrespective of the area extent of the considered parts. The best graph matching is achieved by finding the optimal corresponding node-pairs in a super-graph with fully connecting nodes based on maximum likelihood. The performances of the proposed method are evaluated with three indicators (object precision, object recall and object F1-score) in seven datasets. The experimental tests demonstrate the effectiveness of dealing with TLS point clouds, RGBD point clouds and Panorama RGBD point clouds, resulting in performance scores of approximately 0.8 for object precision and recall and over 0.9 for chair precision and table recall.

Deep pyramid local attention neural network for cardiac structure segmentation in two-dimensional echocardiography.

Automatic semantic segmentation in 2D echocardiography is vital in clinical practice for assessing various cardiac functions and improving the diagnosis of cardiac diseases. However, two distinct problems have persisted in automatic segmentation in 2D echocardiography, namely the lack of an effective feature enhancement approach for contextual feature capture and lack of label coherence in category prediction for individual pixels. Therefore, in this study, we propose a deep learning model, called deep pyramid local attention neural network (PLANet), to improve the segmentation performance of automatic methods in 2D echocardiography. Specifically, we propose a pyramid local attention module to enhance features by capturing supporting information within compact and sparse neighboring contexts. We also propose a label coherence learning mechanism to promote prediction consistency for pixels and their neighbors by guiding the learning with explicit supervision signals. The proposed PLANet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and sub-EchoNet-Dynamic, which are two large-scale and public 2D echocardiography datasets. The experimental results show that PLANet performs better than traditional and deep learning-based segmentation methods on geometrical and clinical metrics. Moreover, PLANet can complete the segmentation of heart structures in 2D echocardiography in real time, indicating a potential to assist cardiologists accurately and efficiently.

Rough or Noisy? Metrics for Noise Estimation in SfM Reconstructions.

Structure from Motion (SfM) can produce highly detailed 3D reconstructions, but distinguishing real surface roughness from reconstruction noise and geometric inaccuracies has always been a difficult problem to solve. Existing SfM commercial solutions achieve noise removal by a combination of aggressive global smoothing and the reconstructed texture for smaller details, which is a subpar solution when the results are used for surface inspection. Other noise estimation and removal algorithms do not take advantage of all the additional data connected with SfM. We propose a number of geometrical and statistical metrics for noise assessment, based on both the reconstructed object and the capturing camera setup. We test the correlation of each of the metrics to the presence of noise on reconstructed surfaces and demonstrate that classical supervised learning methods, trained with these metrics can be used to distinguish between noise and roughness with an accuracy above 85%, with an additional 5–6% performance coming from the capturing setup metrics. Our proposed solution can easily be integrated into existing SfM workflows as it does not require more image data or additional sensors. Finally, as part of the testing we create an image dataset for SfM from a number of objects with varying shapes and sizes, which are available online together with ground truth annotations.

LISA: Heliocentric formation design for the laser interferometer space antenna mission

The LISA (Laser Interferometer Space Antenna) mission has been selected by the European Space Agency’s Science Programme Committee as the third large-class mission of the Cosmic Vision Programme, addressing the science theme of the Gravitational Universe. With a planned launch date in 2034, LISA will be the first ever space-borne Gravitational Wave observatory, relying on laser interferometry between three spacecraft orbiting the Sun in a triangular formation. Airbus is currently leading an industrial Phase A system study on behalf of the European Space Agency. The paper will address the astrodynamics challenges associated with the LISA constellation design, driven by tight requirements on the geometric quality metrics of the near equilateral formation.

Mapping topological characteristics of dynamical systems into neural networks: A reservoir computing approach.

Significant advances have recently been made in modeling chaotic systems with the reservoir computing approach, especially for prediction. We find that although state prediction of the trained reservoir computer will gradually deviate from the actual trajectory of the original system, the associated geometric features remain invariant. Specifically, we show that the typical geometric metrics including the correlation dimension, the multiscale entropy, and the memory effect are nearly identical between the trained reservoir computer and its learned chaotic systems. We further demonstrate this fact on a broad range of chaotic systems ranging from discrete and continuous chaotic systems to hyperchaotic systems. Our findings suggest that the successfully reservoir computer may be topologically conjugate to an observed dynamical system.

Nation-Scale Mapping of Coastal Aquaculture Ponds with Sentinel-1 SAR Data Using Google Earth Engine

Global rapid expansion of the coastal aquaculture industry has made great contributions to enhance food security, but has also caused a series of ecological and environmental issues. Sustainable management of coastal areas requires the explicit and efficient mapping of the spatial distribution of aquaculture ponds. In this study, a Google Earth Engine (GEE) application was developed for mapping coastal aquaculture ponds at a national scale with a novel classification scheme using Sentinel-1 time series data. Relevant indices used in the classification mainly include the water index, texture, and geometric metrics derived from radar backscatter, which were then used to segment and classify aquaculture ponds. Using this approach, we classified aquaculture ponds for the full extent of the coastal area in Vietnam with an overall accuracy of 90.16% (based on independent sample evaluation). The approach, enabling wall-to-wall mapping and area estimation, is essential to the efficient monitoring and management of aquaculture ponds. The classification results showed that aquaculture ponds are widely distributed in Vietnam’s coastal area and are concentrated in the Mekong River Delta and Red River delta (85.14% of the total area), which are facing the increasing collective risk of climate change (e.g., sea level rise and salinity intrusion). Further investigation of the classification results also provides significant insights into the stability and deliverability of the approach. The water index derived from annual median radar backscatter intensity was determined to be efficient at mapping water bodies, likely due to its strong response to water bodies regardless of weather. The geometric metrics considering the spatial variation of radar backscatter patterns were effective at distinguishing aquaculture ponds from other water bodies. The primary use of GEE in this approach makes it replicable and transferable by other users. Our approach lays a solid foundation for intelligent monitoring and management of coastal ecosystems.