Non-ionizing measurement and quantification of bell-shaped chests in spinal muscular atrophy: a pilot study.

Background: Spinal Muscular Atrophy (SMA) is manifested by deformation of the chest wall, including a bell-shaped chest. We determined the ability of a novel non-ionizing, non-volitional method to measure and quantify bell-shaped chests in SMA. Methods: A 3D depth camera and a chest x-ray (CXR) were used to capture chest images in 14 SMA patients and 28 controls. Both methods measure the distance between two points, but measurements performed by 3D analysis allow for the consideration of the curve of a surface (geodesic measurements), whereas the CXR allows solely for the determination of the shortest path between two points, with no regard for the surface (Euclidean measurements). The ratio of the upper to lower chest distances was quantified to distinguish chest shape in imaging by both the 3D depth camera and the CXR, and the ratios were compared between healthy and SMA patients. Results: The mean 3D Euclidean ratio of distances measured by 3D imaging was 1.00 in the control group and 0.92 in the SMA group (p = 0.01), the latter indicative of a bell-shaped chest. This result repeated itself in the ratio of geodesic measurements (0.99 vs. 0.89, respectively, p = 0.03). Conclusion: The herein-described novel, noninvasive 3D method for measuring the upper and lower chest distances was shown to distinguish the bell-shaped chest configuration in patients with SMA from the chests of controls. This method bears several advantages over CXR and may be readily applicable in clinical settings that manage children with SMA.

3D surface topographic measurements for idiopathic scoliosis are highly correlative to patient self-image questionnaires.

PURPOSE: Adolescent idiopathic scoliosis (AIS) is a deformity of the spine that results in external asymmetry of the torso in the shoulder, waist, and rib hump. Several patient reported outcome measures (PROMS) including the Trunk Appearance Perception Scale (TAPS) and SRS-22r self-image domain are used to measure the patient's self-perception. The purpose of this study is to investigate the relationship between objective surface topographic measurements of the torso to subjective patient self-perception. METHODS: 131 AIS subjects and 37 controls participated in this study. All subjects completed TAPS and SRS-22r PROMS followed by whole body 3d surface topographic scanning. An automated analysis pipeline was used to compute 57 measurements. Multivariate linear models were developed to predict TAPS and SRS-22r self-image using each unique combination of 3 parameters and leave one out validation where the best combinations were selected. RESULTS: Back surface rotation, waist crease vertical asymmetry and rib prominence volume were most predictive of TAPS. The final predicted TAPS values from leave one out cross validation was correlated to ground truth TAPS scores with an R value of 0.65. Back surface rotation, silhouette centroid deviation, and shoulder normal asymmetry were most predictive of SRS-22r self-image with a correlation of R = 0.48. CONCLUSION: Surface topographic measurements of the torso are correlated to TAPS and SRS-22r self-image scores in AIS patients and controls, with TAPS exhibiting a stronger relationship, better reflecting the patient's external asymmetries.

Deep learning-based image analysis predicts PD-L1 status from H&E-stained histopathology images in breast cancer.

Programmed death ligand-1 (PD-L1) has been recently adopted for breast cancer as a predictive biomarker for immunotherapies. The cost, time, and variability of PD-L1 quantification by immunohistochemistry (IHC) are a challenge. In contrast, hematoxylin and eosin (H&E) is a robust staining used routinely for cancer diagnosis. Here, we show that PD-L1 expression can be predicted from H&E-stained images by employing state-of-the-art deep learning techniques. With the help of two expert pathologists and a designed annotation software, we construct a dataset to assess the feasibility of PD-L1 prediction from H&E in breast cancer. In a cohort of 3,376 patients, our system predicts the PD-L1 status in a high area under the curve (AUC) of 0.91 - 0.93. Our system is validated on two external datasets, including an independent clinical trial cohort, showing consistent prediction performance. Furthermore, the proposed system predicts which cases are prone to pathologists miss-interpretation, showing it can serve as a decision support and quality assurance system in clinical practice.

Can We Quantify Aging-Associated Postural Changes Using Photogrammetry? A Systematic Review.

BACKGROUND: Aging is widely known to be associated with changes in standing posture. Recent advancements in the field of computerized image processing have allowed for improved analyses of several health conditions using photographs. However, photogrammetry's potential for assessing aging-associated postural changes is yet unclear. Thus, the aim of this review is to evaluate the potential of photogrammetry in quantifying age-related postural changes. MATERIALS AND METHODS: We searched the databases PubMed Central, Scopus, Embase, and SciELO from the beginning of records to March 2021. Inclusion criteria were: (a) participants were older adults aged ≥60; (b) standing posture was assessed by photogrammetric means. PRISMA guidelines were followed. We used the Newcastle-Ottawa Scale to assess methodological quality. RESULTS: Of 946 articles reviewed, after screening and the removal of duplicates, 11 reports were found eligible for full-text assessment, of which 5 full studies met the inclusion criteria. Significant changes occurring with aging included deepening of thoracic kyphosis, flattening of lumbar lordosis, and increased sagittal inclination. CONCLUSIONS: These changes agree with commonly described aging-related postural changes. However, detailed quantification of these changes was not found; the photogrammetrical methods used were often unvalidated and did not adhere to known protocols. These methodological difficulties call for further studies using validated photogrammetrical methods and improved research methodologies.

Reliability of automated topographic measurements for spine deformity.

PURPOSE: This study introduces a novel surface-topographic scanning system capable of automatically generating a suite of objective measurements to characterize torso shape. RESEARCH QUESTION: what is the reliability of the proposed system for measurement of trunk alignment parameters in patients with adolescent idiopathic scoliosis (AIS) and controls? METHODS: Forty-six adolescents (26 with AIS and 20 controls) were recruited for a prospective reliability study. A series of angular, volumetric, and area measures were computed from topographic scans in each of three clinically relevant poses using a fully automated processing pipeline. Intraclass correlation coefficients (ICC(2,1)) were computed within (intra-) and between (inter-) raters. Measurements were also performed on a torso phantom. RESULTS: Topographic measurements computed on a phantom were highly accurate (mean RMS error 1.7%) compared with CT. For human subjects, intra- and inter-rater reliability were both high (average ICC > 0.90) with intrinsic (pose-independent) measurements having near-perfect reliability (average ICC > 0.98). CONCLUSION: The proposed system is a suitable tool for topographic analysis of AIS; topographic measurements offer an objective description of torso shape that may complement other imaging modalities. Further research is needed to compare topographic findings with gold standard imaging of spinal alignment, e.g., standing radiography. CONCLUSION: clinical parameters can be reliably measured in a fully automated system, paving the way for objective analysis of symmetry, body shape pre/post-surgery, and tracking of pathology without ionizing radiation.

Hamiltonian Operator for Spectral Shape Analysis.

Many shape analysis methods treat the geometry of an object as a metric space that can be captured by the Laplace-Beltrami operator. In this paper, we propose to adapt the classical Hamiltonian operator from quantum mechanics to the field of shape analysis. To this end, we study the addition of a potential function to the Laplacian as a generator for dual spaces in which shape processing is performed. We present general optimization approaches for solving variational problems involving the basis defined by the Hamiltonian using perturbation theory for its eigenvectors. The suggested operator is shown to produce better functional spaces to operate with, as demonstrated on different shape analysis tasks.

Intel® RealSense™ SR300 Coded Light Depth Camera.

Intel® RealSense™ SR300 is a depth camera capable of providing a VGA-size depth map at 60 fps and 0.125mm depth resolution. In addition, it outputs an infrared VGA-resolution image and a 1080p color texture image at 30 fps. SR300 form-factor enables it to be integrated into small consumer products and as a front facing camera in laptops and Ultrabooks™. The SR300 depth camera is based on a coded-light technology where triangulation between projected patterns and images captured by a dedicated sensor is used to produce the depth map. Each projected line is coded by a special temporal optical code, that enables a dense depth map reconstruction from its reflection. The solid mechanical assembly of the camera allows it to stay calibrated throughout temperature and pressure changes, drops, and hits. In addition, active dynamic control maintains a calibrated depth output. An extended API LibRS released with the camera allows developers to integrate the camera in various applications. Algorithms for 3D scanning, facial analysis, hand gesture recognition, and tracking are within reach for applications using the SR300. In this paper, we describe the underlying technology, hardware, and algorithms of the SR300, as well as its calibration procedure, and outline some use cases. We believe that this paper will provide a full case study of a mass-produced depth sensing product and technology.

Efficient Inter-Geodesic Distance Computation and Fast Classical Scaling.

Multidimensional scaling (MDS) is a dimensionality reduction tool used for information analysis, data visualization and manifold learning. Most MDS procedures embed data points in low-dimensional euclidean (flat) domains, such that distances between the points are as close as possible to given inter-point dissimilarities. We present an efficient solver for classical scaling, a specific MDS model, by extrapolating the information provided by distances measured from a subset of the points to the remainder. The computational and space complexities of the new MDS methods are thereby reduced from quadratic to quasi-linear in the number of data points. Incorporating both local and global information about the data allows us to construct a low-rank approximation of the inter-geodesic distances between the data points. As a by-product, the proposed method allows for efficient computation of geodesic distances.

Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer.

Importance: Immunohistochemistry (IHC) is the most widely used assay for identification of molecular biomarkers. However, IHC is time consuming and costly, depends on tissue-handling protocols, and relies on pathologists' subjective interpretation. Image analysis by machine learning is gaining ground for various applications in pathology but has not been proposed to replace chemical-based assays for molecular detection. Objective: To assess the prediction feasibility of molecular expression of biomarkers in cancer tissues, relying only on tissue architecture as seen in digitized hematoxylin-eosin (H&E)-stained specimens. Design, Setting, and Participants: This single-institution retrospective diagnostic study assessed the breast cancer tissue microarrays library of patients from Vancouver General Hospital, British Columbia, Canada. The study and analysis were conducted from July 1, 2015, through July 1, 2018. A machine learning method, termed morphological-based molecular profiling (MBMP), was developed. Logistic regression was used to explore correlations between histomorphology and biomarker expression, and a deep convolutional neural network was used to predict the biomarker expression in examined tissues. Main Outcomes and Measures: Positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristics curve measures of MBMP for assessment of molecular biomarkers. Results: The database consisted of 20 600 digitized, publicly available H&E-stained sections of 5356 patients with breast cancer from 2 cohorts. The median age at diagnosis was 61 years for cohort 1 (412 patients) and 62 years for cohort 2 (4944 patients), and the median follow-up was 12.0 years and 12.4 years, respectively. Tissue histomorphology was significantly correlated with the molecular expression of all 19 biomarkers assayed, including estrogen receptor (ER), progesterone receptor (PR), and ERBB2 (formerly HER2). Expression of ER was predicted for 105 of 207 validation patients in cohort 1 (50.7%) and 1059 of 2046 validation patients in cohort 2 (51.8%), with PPVs of 97% and 98%, respectively, NPVs of 68% and 76%, respectively, and accuracy of 91% and 92%, respectively, which were noninferior to traditional IHC (PPV, 91%-98%; NPV, 51%-78%; and accuracy, 81%-90%). Diagnostic accuracy improved given more data. Morphological analysis of patients with ER-negative/PR-positive status by IHC revealed resemblance to patients with ER-positive status (Bhattacharyya distance, 0.03) and not those with ER-negative/PR-negative status (Bhattacharyya distance, 0.25). This suggests a false-negative IHC finding and warrants antihormonal therapy for these patients. Conclusions and Relevance: For at least half of the patients in this study, MBMP appeared to predict biomarker expression with noninferiority to IHC. Results suggest that prediction accuracy is likely to improve as data used for training expand. Morphological-based molecular profiling could be used as a general approach for mass-scale molecular profiling based on digitized H&E-stained images, allowing quick, accurate, and inexpensive methods for simultaneous profiling of multiple biomarkers in cancer tissues.

3D analysis of child facial dimensions for design of medical devices in low-middle income countries (LMIC).

BACKGROUND: Facial anthropometric data are scarce in African children. However, such data may be useful for the design of medical devices for high disease burden settings. The aim of this study was to obtain 3D facial anthropometric data of Congolese children aged 0-5 years. METHODS & FINDINGS: The faces of 287 Congolese children were successfully scanned using a portable structured-light based 3D video camera, suitable for field work in low- income settings. The images were analyzed using facial analysis algorithms. Normal growth curves were generated for the following facial dimensions: distance between nares and distance from subnasion to upper lip. At birth, 1 year, and 5 years of age the median dimensions were: 13·92, 14·66, and 17.60 mm, respectively for distance between nares, and 10·16, 10.88, and 13·79 mm, respectively for distance from subnasion to upper lip. Modeled facial contours conveniently clustered into three average sizes which could be used as templates for the design of medical instruments. CONCLUSION: Capturing of 3D images of infants and young children in LMICs is feasible using portable cameras and computerized analysis. This method and these specific data on Congolese pediatric facial dimensions may assist in the design of appropriately sized medical devices (thermometers, face masks, pulse oximeters, etc.) for this population.

3D Reconstruction of Scoliotic Spines from Stereoradiography and Depth Imaging.

Spine shape can be reconstructed from stereoradiography, but often requires specialized infrastructure or fails to account for subject posture. In this paper a protocol is presented for stereo reconstructions that integrates surface recordings with radiography and naturally accounts for variations in patient posture. Low cost depth cameras are added to an existing radiographic system to capture patient pose. A statistical model of human body shape is learned from public datasets and registered to depth scans, providing 3D correspondence across images for stereo reconstruction of radiographic landmarks. A radiographic phantom was used to validate these methods in vitro with RMS 3D landmark reconstruction error of 2.0 mm. Surfaces were automatically and reliably registered, with SD 12 mm translation disparity and SD .5° rotation. The proposed method is suitable for 3D radiographic reconstructions and may be beneficial in compensating for involuntary patient motion.

Multi-Region Active Contours with a Single Level Set Function.

Segmenting an image into an arbitrary number of coherent regions is at the core of image understanding. Many formulations of the segmentation problem have been suggested over the past years. These formulations include, among others, axiomatic functionals, which are hard to implement and analyze, and graph-based alternatives, which impose a non-geometric metric on the problem. We propose a novel method for segmenting an image into an arbitrary number of regions using an axiomatic variational approach. The proposed method allows to incorporate various generic region appearance models, while avoiding metrication errors. In the suggested framework, the segmentation is performed by level set evolution. Yet, contrarily to most existing methods, here, multiple regions are represented by a single non-negative level set function. The level set function evolution is efficiently executed through the Voronoi Implicit Interface Method for multi-phase interface evolution. The proposed approach is shown to obtain accurate segmentation results for various natural 2D and 3D images, comparable to state-of-the-art image segmentation algorithms.

On convex relaxation of graph isomorphism.

We consider the problem of exact and inexact matching of weighted undirected graphs, in which a bijective correspondence is sought to minimize a quadratic weight disagreement. This computationally challenging problem is often relaxed as a convex quadratic program, in which the space of permutations is replaced by the space of doubly stochastic matrices. However, the applicability of such a relaxation is poorly understood. We define a broad class of friendly graphs characterized by an easily verifiable spectral property. We prove that for friendly graphs, the convex relaxation is guaranteed to find the exact isomorphism or certify its inexistence. This result is further extended to approximately isomorphic graphs, for which we develop an explicit bound on the amount of weight disagreement under which the relaxation is guaranteed to find the globally optimal approximate isomorphism. We also show that in many cases, the graph matching problem can be further harmlessly relaxed to a convex quadratic program with only n separable linear equality constraints, which is substantially more efficient than the standard relaxation involving n2 equality and n2 inequality constraints. Finally, we show that our results are still valid for unfriendly graphs if additional information in the form of seeds or attributes is allowed, with the latter satisfying an easy to verify spectral characteristic.

Design of aerosol face masks for children using computerized 3D face analysis.

BACKGROUND: Aerosol masks were originally developed for adults and downsized for children. Overall fit to minimize dead space and a tight seal are problematic, because children's faces undergo rapid and marked topographic and internal anthropometric changes in their first few months/years of life. Facial three-dimensional (3D) anthropometric data were used to design an optimized pediatric mask. METHODS: Children's faces (n=271, aged 1 month to 4 years) were scanned with 3D technology. Data for the distance from the bridge of the nose to the tip of the chin (H) and the width of the mouth opening (W) were used to categorize the scans into "small," "medium," and "large" "clusters." RESULTS: "Average" masks were developed from each cluster to provide an optimal seal with minimal dead space. The resulting computerized contour, W and H, were used to develop the SootherMask® that enables children, "suckling" on their own pacifier, to keep the mask on their face, mainly by means of subatmospheric pressure. The relatively wide and flexible rim of the mask accommodates variations in facial size within and between clusters. CONCLUSIONS: Unique pediatric face masks were developed based on anthropometric data obtained through computerized 3D face analysis. These masks follow facial contours and gently seal to the child's face, and thus may minimize aerosol leakage and dead space.

Spectral multidimensional scaling.

An important tool in information analysis is dimensionality reduction. There are various approaches for large data simplification by scaling its dimensions down that play a significant role in recognition and classification tasks. The efficiency of dimension reduction tools is measured in terms of memory and computational complexity, which are usually a function of the number of the given data points. Sparse local operators that involve substantially less than quadratic complexity at one end, and faithful multiscale models with quadratic cost at the other end, make the design of dimension reduction procedure a delicate balance between modeling accuracy and efficiency. Here, we combine the benefits of both and propose a low-dimensional multiscale modeling of the data, at a modest computational cost. The idea is to project the classical multidimensional scaling problem into the data spectral domain extracted from its Laplace-Beltrami operator. There, embedding into a small dimensional Euclidean space is accomplished while optimizing for a small number of coefficients. We provide a theoretical support and demonstrate that working in the natural eigenspace of the data, one could reduce the process complexity while maintaining the model fidelity. As examples, we efficiently canonize nonrigid shapes by embedding their intrinsic metric into , a method often used for matching and classifying almost isometric articulated objects. Finally, we demonstrate the method by exposing the style in which handwritten digits appear in a large collection of images. We also visualize clustering of digits by treating images as feature points that we map to a plane.

Graph isomorphisms and automorphisms via spectral signatures.

An isomorphism between two graphs is a connectivity preserving bijective mapping between their sets of vertices. Finding isomorphisms between graphs, or between a graph and itself (automorphisms), is of great importance in applied sciences. The inherent computational complexity of this problem is as yet unknown. Here, we introduce an efficient method to compute such mappings using heat kernels associated with the graph Laplacian. While the problem is combinatorial in nature, in practice we experience polynomial runtime in the number of vertices. As we demonstrate, the proposed method can handle a variety of graphs and is competitive with state-of-the-art packages on various important examples.

Are MSER features really interesting?

Detection and description of affine-invariant features is a cornerstone component in numerous computer vision applications. In this note, we analyze the notion of maximally stable extremal regions (MSERs) through the prism of the curvature scale space, and conclude that in its original definition, MSER prefers regular (round) regions. Arguing that interesting features in natural images usually have irregular shapes, we propose alternative definitions of MSER which are free of this bias, yet maintain their invariance properties.

On scene segmentation and histograms-based curve evolution.

We consider curve evolution based on comparing distributions of features, and its applications for scene segmentation. In the first part, we promote using cross-bin metrics such as the Earth Mover's Distance (EMD), instead of standard bin-wise metrics as the Bhattacharyya or Kullback-Leibler metrics. To derive flow equations for minimizing functionals involving the EMD, we employ a tractable expression for calculating EMD between one-dimensional distributions. We then apply the derived flows to various examples of single image segmentation, and to scene analysis using video data. In the latter, we consider the problem of segmenting a scene to spatial regions in which different activities occur. We use a nonparametric local representation of the regions by considering multiple one-dimensional histograms of normalized spatiotemporal derivatives. We then obtain semisupervised segmentation of regions using the flows derived in the first part of the paper. Our results are demonstrated on challenging surveillance scenes, and compare favorably with state-of-the-art results using parametric representations by dynamic systems or mixtures of them.

Low bit-rate compression of facial images.

An efficient approach for face compression is introduced. Restricting a family of images to frontal facial mug shots enables us to first geometrically deform a given face into a canonical form in which the same facial features are mapped to the same spatial locations. Next, we break the image into tiles and model each image tile in a compact manner. Modeling the tile content relies on clustering the same tile location at many training images. A tree of vector-quantization dictionaries is constructed per location, and lossy compression is achieved using bit-allocation according to the significance of a tile. Repeating this modeling/coding scheme over several scales, the resulting multiscale algorithm is demonstrated to compress facial images at very low bit rates while keeping high visual qualities, outperforming JPEG-2000 performance significantly.