Agreement Between A 2-Dimensional Digital Image-Based 3-Compartment Body Composition Model and Dual Energy X-Ray Absorptiometry for The Estimation of Relative Adiposity.

The purpose of this study was to compare relative adiposity (%Fat) derived from a 2-dimensional image-based 3-component (3C) model (%Fat3C-IMAGE) and dual-energy X-ray absorptiometry (DXA) (%FatDXA) against a 5-component (5C) laboratory criterion (%Fat5C). 57 participants were included (63.2% male, 84.2% White/Caucasian, 22.5±4.7 yrs., 23.9±2.8 kg/m2). For each participant, body mass and standing height were measured to the nearest 0.1 kg and 0.1 cm, respectively. A digital image of each participant was taken using a 9.7 inch, 16g iPad Air 2 and analyzed using a commercially available application (version 1.1.2, made Health and Fitness, USA) for the estimation of body volume (BV) and inclusion in %Fat3C-IMAGE . %Fat3C-IMAGE and %Fat5C included measures of total body water derived from bioimpedance spectroscopy. The criterion %Fat5C included BV estimates derived from underwater weighing and bone mineral content measures via DXA. %FatDXA estimates were calculated from a whole-body DXA scan. A standardized mean effect size (ES) assessed the magnitude of differences between models with values of 0.2, 0.5, and 0.8 for small, moderate, and large differences, respectively. Data are presented as mean ± standard deviation. A strong correlation (r = 0.94, p <.001) and small mean difference (ES = 0.24, p <.001) was observed between %Fat3C-IMAGE (19.20±5.80) and %Fat5C (17.69±6.20) whereas a strong correlation (r = 0.87, p <.001) and moderate-large mean difference (ES = 0.70, p <.001) was observed between %FatDXA (22.01±6.81) and %Fat5C. Furthermore, %Fat3C-IMAGE (SEE = 2.20 %Fat, TE= 2.6) exhibited smaller SEE and TE than %FatDXA (SEE = 3.14 %Fat, TE = 5.5). The 3C image-based model performed slightly better in our sample of young adults than the DXA 3C model. Thus, the 2D image analysis program provides an accurate and non-invasive estimate of %Fat within a 3C model in young adults. Compared to DXA, the 3C image-based model allows for a more cost-effective and portable method of body composition assessment, potentially increasing accessibility to multi-component methods.

Non-contact detection method of pregnant sows backfat thickness based on two-dimensional images.

Since sow backfat thickness (BFT) is highly correlated with its service life and reproductive effectiveness, dynamic monitoring of BFT is a critical component of large-scale sow farm productivity. Existing contact measures of sow BFT have their problems including, high measurement intensity and sows' stress reaction, low biological safety, and difficulty in meeting the requirements for multiple measurements. This article presents a two-dimensional (2D) image-based approach for determining the BFT of pregnant sows when combined with the backfat growth rate (BGR). The 2D image features of sows extracted by convolutional neural networks (CNN) and the artificially defined phenotypic features of sows such as hip width, hip height, body length, hip height-width ratio, length-width ratio, and waist-hip ratio, were used respectively, combined with BGR, to construct a prediction model for sow BFT using support vector regression (SVR). Following testing and comparison, it was shown that using CNN to extract features from images could effectively replace artificially defined features, BGR contributed to the model's accuracy improvement. The CNN-BGR-SVR model performed the best, with R2 of 0.72 and mean absolute error of 1.21 mm, and root mean square error of 1.50 mm, and mean absolute percentage error of 7.57%. The results demonstrated that the CNN-BGR-SVR model based on 2D images was capable of detecting sow BFT, establishing a new reference for non-contact sow BFT detection technology.

Accuracy Report on a Handheld 3D Ultrasound Scanner Prototype Based on a Standard Ultrasound Machine and a Spatial Pose Reading Sensor.

The aim of this study was to develop and evaluate a 3D ultrasound scanning method. The main requirements were the freehand architecture of the scanner and high accuracy of the reconstructions. A quantitative evaluation of a freehand 3D ultrasound scanner prototype was performed, comparing the ultrasonographic reconstructions with the CAD (computer-aided design) model of the scanned object, to determine the accuracy of the result. For six consecutive scans, the 3D ultrasonographic reconstructions were scaled and aligned with the model. The mean distance between the 3D objects ranged between 0.019 and 0.05 mm and the standard deviation between 0.287 mm and 0.565 mm. Despite some inherent limitations of our study, the quantitative evaluation of the 3D ultrasonographic reconstructions showed comparable results to other studies performed on smaller areas of the scanned objects, demonstrating the future potential of the developed prototype.

Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification.

Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.

A Doorway Detection and Direction (3Ds) System for Social Robots via a Monocular Camera.

In this paper, we propose a novel algorithm to detect a door and its orientation in indoor settings from the view of a social robot equipped with only a monocular camera. The challenge is to achieve this goal with only a 2D image from a monocular camera. The proposed system is designed through the integration of several modules, each of which serves a special purpose. The detection of the door is addressed by training a convolutional neural network (CNN) model on a new dataset for Social Robot Indoor Navigation (SRIN). The direction of the door (from the robot's observation) is achieved by three other modules: Depth module, Pixel-Selection module, and Pixel2Angle module, respectively. We include simulation results and real-time experiments to demonstrate the performance of the algorithm. The outcome of this study could be beneficial in any robotic navigation system for indoor environments.

Extrinsic Factors as Component Positions to Bone and Intrinsic Factors Affecting Postoperative Rotational Limb Alignment in Total Knee Arthroplasty.

BACKGROUND: This study aimed to identify the factors affecting postoperative rotational limb alignment of the tibia relative to the femur. We hypothesized that not only component positions but also several intrinsic factors were associated with postoperative rotational limb alignment. METHODS: This study included 99 knees (90 women and 9 men) with a mean age of 77 ± 6 years. A three-dimensional (3D) assessment system was applied under weight-bearing conditions to biplanar long-leg radiographs using 3D-to-2D image registration technique. The evaluation parameters were (1) component position; (2) preoperative and postoperative coronal, sagittal, and rotational limb alignment; (3) preoperative bony deformity, including femoral torsion, condylar twist angle, and tibial torsion; and (4) preoperative and postoperative range of motion (ROM). RESULTS: In multiple linear regression analysis using a stepwise procedure, postoperative rotational limb alignment was associated with the following: (1) rotation of the component position (tibia: ß = 0.371, P < .0001; femur: ß = -0.327, P < .0001), (2) preoperative rotational limb alignment (ß = 0.253, P = .001), (3) postoperative flexion angle (ß = 0.195, P = .007), and (4) tibial torsion (ß = 0.193, P = .010). CONCLUSION: In addition to component positions, the intrinsic factors, such as preoperative rotational limb alignment, ROM, and tibial torsion, affected postoperative rotational limb alignment. On a premise of correct component positions, the intrinsic factors that can be controlled by surgeons should be taken care. In particular, ROM is necessary to be improved within the possible range to acquire better postoperative rotational limb alignment.

Optoelectronic memory using two-dimensional materials.

An atomically thin optoelectronic memory array for image sensing is demonstrated with layered CuIn7Se11 and extended to InSe and MoS2 atomic layers. Photogenerated charge carriers are trapped and subsequently retrieved from the potential well formed by gating a 2D material with Schottky barriers. The atomically thin layered optoelectronic memory can accumulate photon-generated charges during light exposure, and the charges can be read out later for data processing and permanent storage. An array of atomically thin image memory pixels was built to illustrate the potential of fabricating large-scale 2D material-based image sensors for image capture and storage.

Proteomic analysis of ligamentum flavum from patients with lumbar spinal stenosis.

Lumbar spinal stenosis (LSS) is a syndromic degenerative spinal disease and is characterized by spinal canal narrowing with subsequent neural compression causing gait disturbances. Although LSS is a major age-related musculoskeletal disease that causes large decreases in the daily living activities of the elderly, its molecular pathology has not been investigated using proteomics. Thus, we used several proteomic technologies to analyze the ligamentum flavum (LF) of individuals with LSS. Using comprehensive proteomics with strong cation exchange fractionation, we detected 1288 proteins in these LF samples. A GO analysis of the comprehensive proteome revealed that more than 30% of the identified proteins were extracellular. Next, we used 2D image converted analysis of LC/MS to compare LF obtained from individuals with LSS to that obtained from individuals with disc herniation (nondegenerative control). We detected 64 781 MS peaks and identified 1675 differentially expressed peptides derived from 286 proteins. We verified four differentially expressed proteins (fibronectin, serine protease HTRA1, tenascin, and asporin) by quantitative proteomics using SRM/MRM. The present proteomic study is the first to identify proteins from degenerated and hypertrophied LF in LSS, which will help in studying LSS.

Body composition estimates using a 2D image analysis system across different environmental conditions: An agreement study.

PURPOSE: This study examined the agreement between %Fat measurements using a smartphone-based application (IMAGE) across different environmental conditions. METHODS: A single reference image was obtained using an 8 MP smartphone camera under Ambient Light in front of a white background. Additional photos were obtained using a 0.7 MP, 5 MP, and 12 MP smartphone cameras; low-, moderate-, and bright-lighting conditions; and various color backgrounds including black, green, orange, and gray. RESULTS: %Fat measured using the 0.7 MP camera (27.8 ± 6.2 %Fat) was higher than the reference (26.8 ± 6.1 %Fat) (p < 0.001). The black (32.0 ± 12.0 %Fat), green (27.5 ± 6.3 %Fat), and gray (27.8 ± 6.3 %Fat) backgrounds yielded higher %Fat than the white (p = 0.03, 0.01, and 0.001). All camera, lighting, and background conditions were strongly correlated with the reference (all intraclass correlation coefficient [ICC] >0.98, all standard error of the estimate [SEE] <1.5 %Fat, all p < 0.001), except the black background which yielded poorer agreement with the white background (ICC = 0.69, SEE = 4.5%, p < 0.001). CONCLUSION: %Fat from IMAGE were strongly correlated across various environmental conditions.

Overlapping Shoeprint Detection by Edge Detection and Deep Learning.

In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional convolutional neural networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces and employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.

Non-stationary neural signal to image conversion framework for image-based deep learning algorithms.

This paper presents a time-efficient preprocessing framework that converts any given 1D physiological signal recordings into a 2D image representation for training image-based deep learning models. The non-stationary signal is rasterized into the 2D image using Bresenham's line algorithm with time complexity O(n). The robustness of the proposed approach is evaluated based on two publicly available datasets. This study classified three different neural spikes (multi-class) and EEG epileptic seizure and non-seizure (binary class) based on shapes using a modified 2D Convolution Neural Network (2D CNN). The multi-class dataset consists of artificially simulated neural recordings with different Signal-to-Noise Ratios (SNR). The 2D CNN architecture showed significant performance for all individual SNRs scores with (SNR/ACC): 0.5/99.69, 0.75/99.69, 1.0/99.49, 1.25/98.85, 1.5/97.43, 1.75/95.20 and 2.0/91.98. Additionally, the binary class dataset also achieved 97.52% accuracy by outperforming several others proposed algorithms. Likewise, this approach could be employed on other biomedical signals such as Electrocardiograph (EKG) and Electromyography (EMG).

Object identification in cerebral visual impairment characterized by gaze behavior and image saliency analysis.

Individuals with cerebral visual impairment (CVI) have difficulties identifying common objects, especially when presented as cartoons or abstract images. In this study, participants were shown a series of images of ten common objects, each from five possible categories ranging from abstract black & white line drawings to color photographs. Fifty individuals with CVI and 50 neurotypical controls verbally identified each object and success rates and reaction times were collected. Visual gaze behavior was recorded using an eye tracker to quantify the extent of visual search area explored and number of fixations. A receiver operating characteristic (ROC) analysis was also carried out to compare the degree of alignment between the distribution of individual eye gaze patterns and image saliency features computed by the graph-based visual saliency (GBVS) model. Compared to controls, CVI participants showed significantly lower success rates and longer reaction times when identifying objects. In the CVI group, success rate improved moving from abstract black & white images to color photographs, suggesting that object form (as defined by outlines and contours) and color are important cues for correct identification. Eye tracking data revealed that the CVI group showed significantly greater visual search areas and number of fixations per image, and the distribution of eye gaze patterns in the CVI group was less aligned with the high saliency features of the image compared to controls. These results have important implications in helping to understand the complex profile of visual perceptual difficulties associated with CVI.

Integration of statistical shape modeling and alternating interpolation-based model tracking technique for measuring knee kinematics in vivo using clinical interleaved bi-plane fluoroscopy.

Background: A 2D fluoroscopy/3D model-based registration with statistical shape modeling (SSM)-reconstructed subject-specific bone models will help reduce radiation exposure for 3D kinematic measurements of the knee using clinical alternating bi-plane fluoroscopy systems. The current study aimed to develop such an approach and evaluate in vivo its accuracy and identify the effects of the accuracy of SSM models on the kinematic measurements. Methods: An alternating interpolation-based model tracking (AIMT) approach with SSM-reconstructed subject-specific bone models was used for measuring 3D knee kinematics from dynamic alternating bi-plane fluoroscopy images. A two-phase optimization scheme was used to reconstruct subject-specific knee models from a CT-based SSM database of 60 knees using one, two, or three pairs of fluoroscopy images. Using the CT-reconstructed model as a benchmark, the performance of the AIMT with SSM-reconstructed models in measuring bone and joint kinematics during dynamic activity was evaluated in terms of mean target registration errors (mmTRE) for registered bone poses and the mean absolute differences (MAD) for each motion component of the joint poses. Results: The mmTRE of the femur and tibia for one image pair were significantly greater than those for two and three image pairs without significant differences between two and three image pairs. The MAD was 1.16 to 1.22° for rotations and 1.18 to 1.22 mm for translations using one image pair. The corresponding values for two and three image pairs were 0.75 to 0.89° and 0.75 to 0.79 mm; and 0.57 to 0.79° and 0.6 to 0.69 mm, respectively. The MAD values for one image pair were significantly greater than those for two and three image pairs without significant differences between two and three image pairs. Conclusions: An AIMT approach with SSM-reconstructed models was developed, enabling the registration of interleaved fluoroscopy images and SSM-reconstructed models from more than one asynchronous fluoroscopy image pair. This new approach had sub-millimeter and sub-degree measurement accuracy when using more than one image pair, comparable to the accuracy of CT-based methods. This approach will be helpful for future kinematic measurements of the knee with reduced radiation exposure using 3D fluoroscopy with clinically alternating bi-plane fluoroscopy systems.

'Smart' Buffalo Weight Estimation via Digital Technologies: Experiences from South Italy.

The present work aims at describing a viable "protocol" for unobtrusive direct/indirect monitoring of biometric parameters for the estimation of body conditions on Mediterranean Buffalo populations, using low-cost automated systems i.e., smart cameras endowed with depth perception capabilities.

Improving the Performance Properties of Eutectoid Steel Products by a Complex Effect.

This study focuses on the assessment of possible hypereutectoid steel carbide mesh crushing. It is used for tools production, including forming rolls of various diameters, with modification and cyclic heat treatment methods. For steel containing 1.79-1.83% C, we studied the effect of 0.35-1.15% Si on the possible crushing of the cementite mesh within crystallization by introducing modifiers Ti, V, N, as well as simultaneously modifying V with N and Ti with N. The obtained castings of Ø200 mm, 400 mm high were cut into discs, from which we made samples for tests on wear, determining mechanical properties, thermal resistance, and susceptibility to brittle fracture. The assessment was performed in the as-cast and after double and triple normalizing and annealing with drawback. With additional fans blowing, we changed the cooling rate from 25 °C/h to 100-150 °C/h. We performed the microstructure analyses using traditional metallographic, micro-X-ray spectral analyses, and also used the segmentation process based on 2D image markers. It was found that the as-cast modifying additives infusion is insufficient for carbide mesh crushing. It can be made by multi-stage normalizing with accelerated cool-down for products up to 600 mm in diameter to cycle temperatures above the steel transfer from a plastic to elastic state (above 450 °C).

3D-2D image registration in the presence of soft-tissue deformation in image-guided transbronchial interventions.

Purpose. Target localization in pulmonary interventions (e.g. transbronchial biopsy of a lung nodule) is challenged by deformable motion and may benefit from fluoroscopic overlay of the target to provide accurate guidance. We present and evaluate a 3D-2D image registration method for fluoroscopic overlay in the presence of tissue deformation using a multi-resolution/multi-scale (MRMS) framework with an objective function that drives registration primarily by soft-tissue image gradients.Methods. The MRMS method registers 3D cone-beam CT to 2D fluoroscopy without gating of respiratory phase by coarse-to-fine resampling and global-to-local rescaling about target regions-of-interest. A variation of the gradient orientation (GO) similarity metric (denotedGO') was developed to downweight bone gradients and drive registration via soft-tissue gradients. Performance was evaluated in terms of projection distance error at isocenter (PDEiso). Phantom studies determined nominal algorithm parameters and capture range. Preclinical studies used a freshly deceased, ventilated porcine specimen to evaluate performance in the presence of real tissue deformation and a broad range of 3D-2D image mismatch.Results. Nominal algorithm parameters were identified that provided robust performance over a broad range of motion (0-20 mm), including an adaptive parameter selection technique to accommodate unknown mismatch in respiratory phase. TheGO'metric yielded median PDEiso= 1.2 mm, compared to 6.2 mm for conventionalGO.Preclinical studies with real lung deformation demonstrated median PDEiso= 1.3 mm with MRMS +GO'registration, compared to 2.2 mm with a conventional transform. Runtime was 26 s and can be reduced to 2.5 s given a prior registration within ∼5 mm as initialization.Conclusions. MRMS registration via soft-tissue gradients achieved accurate fluoroscopic overlay in the presence of deformable lung motion. By driving registration via soft-tissue image gradients, the method avoided false local minima presented by bones and was robust to a wide range of motion magnitude.

Walking Speed Classification from Marker-Free Video Images in Two-Dimension Using Optimum Data and a Deep Learning Method.

Walking speed is considered a reliable assessment tool for any movement-related functional activities of an individual (i.e., patients and healthy controls) by caregivers and clinicians. Traditional video surveillance gait monitoring in clinics and aged care homes may employ modern artificial intelligence techniques to utilize walking speed as a screening indicator of various physical outcomes or accidents in individuals. Specifically, ratio-based body measurements of walking individuals are extracted from marker-free and two-dimensional video images to create a walk pattern suitable for walking speed classification using deep learning based artificial intelligence techniques. However, the development of successful and highly predictive deep learning architecture depends on the optimal use of extracted data because redundant data may overburden the deep learning architecture and hinder the classification performance. The aim of this study was to investigate the optimal combination of ratio-based body measurements needed for presenting potential information to define and predict a walk pattern in terms of speed with high classification accuracy using a deep learning-based walking speed classification model. To this end, the performance of different combinations of five ratio-based body measurements was evaluated through a correlation analysis and a deep learning-based walking speed classification test. The results show that a combination of three ratio-based body measurements can potentially define and predict a walk pattern in terms of speed with classification accuracies greater than 92% using a bidirectional long short-term memory deep learning method.

The effect of a known object in a static image of a burn to improve the burn size estimation.

INTRODUCTION: Currently information regarding burn size from referring departments to burn centres varies in accuracy. Inaccurate assessment of burn size can lead to over or under treatment. Photographs of injuries may improve accuracy of assessment. We aimed to assess the accuracy of measuring burn size on a static image by including a standard object in the image. METHODS: Simulated burn areas were drawn on different body parts of the model. Using an iPhone® model 5 s with an 8 megapixel camera we took photos of the marked area, and repeated them with the palm, a standard bank card and a penny in the picture. First the Du Bois formula, was used to calculate body surface area. Members of the Burns team were asked to view the photos (n = 30) and estimate the percentage of the simulated burn. RESULTS: We found an overall overestimation of burn size. Small areas of the forearm were better estimated and within 1.1% of the calculated surface area, however we found no improvement when using a standard object in these images. The back areas were most overestimated ranging from 0.9%-8.9% despite all being the same sized area. CONCLUSIONS: Static images tend to overestimate burn size despite the use of a standard object in the image.

Development of a fluoroscopically guided robotic assistant for instrument placement in pelvic trauma surgery.

Purpose: A method for fluoroscopic guidance of a robotic assistant is presented for instrument placement in pelvic trauma surgery. The solution uses fluoroscopic images acquired in standard clinical workflow and helps avoid repeat fluoroscopy commonly performed during implant guidance. Approach: Images acquired from a mobile C-arm are used to perform 3D-2D registration of both the patient (via patient CT) and the robot (via CAD model of a surgical instrument attached to its end effector, e.g; a drill guide), guiding the robot to target trajectories defined in the patient CT. The proposed approach avoids C-arm gantry motion, instead manipulating the robot to acquire disparate views of the instrument. Phantom and cadaver studies were performed to determine operating parameters and assess the accuracy of the proposed approach in aligning a standard drill guide instrument. Results: The proposed approach achieved average drill guide tip placement accuracy of 1.57 ± 0.47 mm and angular alignment of 0.35 ± 0.32 deg in phantom studies. The errors remained within 2 mm and 1 deg in cadaver experiments, comparable to the margins of errors provided by surgical trackers (but operating without the need for external tracking). Conclusions: By operating at a fixed fluoroscopic perspective and eliminating the need for encoded C-arm gantry movement, the proposed approach simplifies and expedites the registration of image-guided robotic assistants and can be used with simple, non-calibrated, non-encoded, and non-isocentric C-arm systems to accurately guide a robotic device in a manner that is compatible with the surgical workflow.

Data-Driven Deformable 3D-2D Registration for Guiding Neuroelectrode Placement in Deep Brain Stimulation.

Purpose: Deep brain stimulation is a neurosurgical procedure used in treatment of a growing spectrum of movement disorders. Inaccuracies in electrode placement, however, can result in poor symptom control or adverse effects and confound variability in clinical outcomes. A deformable 3D-2D registration method is presented for high-precision 3D guidance of neuroelectrodes. Methods: The approach employs a model-based, deformable algorithm for 3D-2D image registration. Variations in lead design are captured in a parametric 3D model based on a B-spline curve. The registration is solved through iterative optimization of 16 degrees-of-freedom that maximize image similarity between the 2 acquired radiographs and simulated forward projections of the neuroelectrode model. The approach was evaluated in phantom models with respect to pertinent imaging parameters, including view selection and imaging dose. Results: The results demonstrate an accuracy of (0.2 ± 0.2) mm in 3D localization of individual electrodes. The solution was observed to be robust to changes in pertinent imaging parameters, which demonstrate accurate localization with ≥20° view separation and at 1/10th the dose of a standard fluoroscopy frame. Conclusions: The presented approach provides the means for guiding neuroelectrode placement from 2 low-dose radiographic images in a manner that accommodates potential deformations at the target anatomical site. Future work will focus on improving runtime though learning-based initialization, application in reducing reconstruction metal artifacts for 3D verification of placement, and extensive evaluation in clinical data from an IRB study underway.