Hand-held Camera Research Articles

A technique for decreasing reflection during cadaveric photography.

To create anatomical educational materials that can be viewed in three dimensions using stereo photographs and photogrammetry, multiple photographs must be taken from different directions. In this process, shadows and reflections from different positions in each photograph are undesirable for creating three-dimensional (3D) anatomy educational materials. Although a ring flash eliminates shadows, allowing light to enter from all directions, reflections cannot be eliminated. In particular, Thiel-embalmed cadavers, which are widely used in clinical anatomy, are highly wet and exhibit strong specular highlights. In this study, a straight polarization filter was attached to a handheld camera lens and ring flash, and shooting was performed using cross-polarization photography. Consequently, even in Thiel-embalmed cadavers, the details lost due to the effects of reflections and shadows can be recovered, and good results can be obtained when taking stereo photos or creating a 3D model using photogrammetry.

Handheld dermatoscope versus digital camera for hair counts in laser facial hair removal

ABSTRACT The lack of uniform and objective techniques to evaluate treatment efficacy in photo-epilation studies leads to contradictory results. Thus, there is an urgent need to explore commonly accepted assessment tools. One of the most common methods uses hair counts via digital photography. However, macrophotography may not be able to depict the vellus-like hair induced by photo-epilation. On the other hand, handheld dermatoscopy is practical, affordable and offers high-quality magnification. Hair counts from a handheld dermatoscope and a digital camera were compared in 73 women who underwent 6 sessions with the Alexandrite 755 nm laser. Significantly more hairs were counted using the dermatoscope than using the digital camera (76.9 ± 41.3 vs. 58.6 ± 31.4, p < .005), independently of hair thickness and hair density. The difference in hair counts between the two instruments was inversely related to hair thickness and directly related to hair density. The handheld dermatoscope may be a more effective tool than the widely used digital camera in evaluating the response to laser hair removal treatment.

Comparison of 2-Field and 5-Field Mydriatic Handheld Retinal Imaging in a Community-Based Diabetic Retinopathy Screening Program

Introduction: The purpose of this study was to compare 2-field (2F) and 5-field (5F) mydriatic handheld retinal imaging for the assessment of diabetic retinopathy (DR) severity in a community-based DR screening program (DRSP). Methods: This was a prospective, cross-sectional diagnostic study, evaluating images of 805 eyes from 407 consecutive patients with diabetes acquired from a community-based DRSP. Mydriatic standardized 5F imaging (macula, disc, superior, inferior, temporal) with handheld retinal camera was performed. 2F (disc, macula), and 5F images were independently assessed using the International DR classification at a centralized reading center. Simple (K) and weighted (Kw) kappa statistics were calculated for DR. Sensitivity and specificity for referable DR ([refDR] moderate nonproliferative DR [NPDR] or worse) and vision-threatening DR ([vtDR] severe NPDR or worse) for 2F compared to 5F imaging were calculated. Results: Distribution of DR severity by 2F/5F images (%): no DR 66.0/61.7, mild NPDR 10.7/14.4, moderate NPDR 7.9/8.1, severe NPDR 3.3/5.6, proliferative DR 5.6/4.6, ungradable 6.5/5.6. Exact agreement of DR grading between 2F and 5F was 81.7%, within 1-step 97.1% (K = 0.64, Kw = 0.78). Sensitivity/specificity for 2F compared 5F was refDR 0.80/0.97, vtDR 0.73/0.98. The ungradable images rate with 2F was 16.1% higher than with 5F (6.5 vs. 5.6%, p < 0.001). Conclusions: Mydriatic 2F and 5F handheld imaging have substantial agreement in assessing severity of DR. However, the use of mydriatic 2F handheld imaging only meets the minimum standards for sensitivity and specificity for refDR but not for vtDR. When using handheld cameras, the addition of peripheral fields in 5F imaging further refines the referral approach by decreasing ungradable rate and increasing sensitivity for vtDR.

Clinical validation of a smartphone-based retinal camera for diabetic retinopathy screening

AimsThis study aims to compare the performance of a handheld fundus camera (Eyer) and standard tabletop fundus cameras (Visucam 500, Visucam 540, and Canon CR-2) for diabetic retinopathy and diabetic macular edema screening.MethodsThis was a multicenter, cross-sectional study that included images from 327 individuals with diabetes. The participants underwent pharmacological mydriasis and fundus photography in two fields (macula and optic disk centered) with both strategies. All images were acquired by trained healthcare professionals, de-identified, and graded independently by two masked ophthalmologists, with a third senior ophthalmologist adjudicating in discordant cases. The International Classification of Diabetic Retinopathy was used for grading, and demographic data, diabetic retinopathy classification, artifacts, and image quality were compared between devices. The tabletop senior ophthalmologist adjudication label was used as the ground truth for comparative analysis. A univariate and stepwise multivariate logistic regression was performed to determine the relationship of each independent factor in referable diabetic retinopathy.ResultsThe mean age of participants was 57.03 years (SD 16.82, 9–90 years), and the mean duration of diabetes was 16.35 years (SD 9.69, 1–60 years). Age (P = .005), diabetes duration (P = .004), body mass index (P = .005), and hypertension (P < .001) were statistically different between referable and non-referable patients. Multivariate logistic regression analysis revealed a positive association between male sex (OR 1.687) and hypertension (OR 3.603) with referable diabetic retinopathy. The agreement between devices for diabetic retinopathy classification was 73.18%, with a weighted kappa of 0.808 (almost perfect). The agreement for macular edema was 88.48%, with a kappa of 0.809 (almost perfect). For referable diabetic retinopathy, the agreement was 85.88%, with a kappa of 0.716 (substantial), sensitivity of 0.906, and specificity of 0.808. As for image quality, 84.02% of tabletop fundus camera images were gradable and 85.31% of the Eyer images were gradable.ConclusionsOur study shows that the handheld retinal camera Eyer performed comparably to standard tabletop fundus cameras for diabetic retinopathy and macular edema screening. The high agreement with tabletop devices, portability, and low costs makes the handheld retinal camera a promising tool for increasing coverage of diabetic retinopathy screening programs, particularly in low-income countries. Early diagnosis and treatment have the potential to prevent avoidable blindness, and the present validation study brings evidence that supports its contribution to diabetic retinopathy early diagnosis and treatment.

NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields.

Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we present an efficient framework capable of fast reconstruction, compact modeling, and streamable rendering. First, we propose to decompose the 4D spatiotemporal space according to temporal characteristics. Points in the 4D space are associated with probabilities of belonging to three categories: static, deforming, and new areas. Each area is represented and regularized by a separate neural field. Second, we propose a hybrid representations based feature streaming scheme for efficiently modeling the neural fields. Our approach, coined NeRFPlayer, is evaluated on dynamic scenes captured by single hand-held cameras and multi-camera arrays, achieving comparable or superior rendering performance in terms of quality and speed comparable to recent state-of-the-art methods, achieving reconstruction in 10 seconds per frame and interactive rendering. Project website: https://bit.ly/nerfplayer.

A method supporting fault-tolerant optical text recognition from video sequences recorded with handheld cameras

In the paper a method supporting the optical character recognition from video sequences recorded with cameras without good stabilization is proposed. Due to the presence of various distortions, such as motion blur, shadows, lossy compression artifacts, auto-focusing errors, etc., the quality of individual video frames, e.g., recorded by a smartphone camera, differs noticeably, influencing the results of text recognition, causing the presence of additional errors that may be unacceptable even in fault-tolerant applications. Although the quality of individual video frames may be assessed using state-of-the-art no-reference image quality metrics, the obtained results, particularly using the relatively fast metrics, are poorly correlated with recognition results. Therefore, a novel hybrid approach to image quality assessment supporting fault-tolerant optical character recognition is proposed, making it possible to select automatically the video frames leading to the smallest number of errors. Since the data extraction is rarely perfect, the proposed method may be particularly useful in systems where users should identify the faults defined as a too high number of text recognition errors. The proposed method makes it possible to eliminate low quality fragments of video sequences from further analysis, reducing the overall computational burden. It may also be useful in industrial OCR applications based on offline video recording with memory constraints where the use of online OCR services is not possible.

UAV-based operational modal analysis method using improved homography-based perspective rectification method

In this paper, a new dynamic photogrammetry method using an unmanned aerial vehicle (UAV) is proposed and the UAV-based operational modal analysis method is established. The presented dynamic photogrammetry method can measure the dynamic displacements of structure using one or two cameras. However, it is difficult to use fixed cameras or handheld cameras to measure the dynamic responses for some outdoor structures, because it is hard to reach for measurement or maintenance sometimes. Therefore, UAV is an effective alternative and the homography-based perspective rectification method can be used to correct the UAV images. However, the presented methods use only four calibration points. Additionally, there is still obvious signal drift in the extracted dynamic responses. In this paper, a new time varying homography matrix, calculated using n calibration points, is proposed here for the first time to correct the perspective distortion for image at different time and the relative displacements are used to eliminate the influence of UAV in-plane motion. The influence analysis of UAV vibration and the method to eliminate the UAV vibration are the novelty of this paper. And then, the UAV-based operational modal analysis method is proposed. The proposed method is verified using a plane frame structure in laboratory. The results show that the proposed method can effectively eliminate the vibration of UAV and identify the structural modal parameters. Under the impulse excitation and white noise excitation, when the calibration points n is larger than 60, the relative errors of natural frequency and damping ratio are less than 0.4% and 5.45%, respectively. And the MAC values are all greater than 0.99. Meanwhile, the influence of the number of adopted calibration points on modal parameters identification is considered in the experiment and the advised value is given.

Automatic segmentation and quantified analysis of meibomian glands from infrared images.

An algorithm for automated segmentation of meibomian glands from infrared images obtained using a novel prototype infrared hand-held imager has been proposed in this study. Meibomian gland dysfunction (MGD) is quantified in terms of five clinically relevant metrics. A comparison of these metrics in patients with MGD has been presented against a sample of the normative healthy population. This is a prospective cross-sectional observational study. Patients presenting to the clinics were enrolled after written informed consent. The everted eyelids of 200 eyes of patients (of which 100 were healthy and 100 were diagnosed with MGD) were imaged using a prototype hand-held camera. The proposed algorithm was used to process the images using enhancement techniques and the glands were automatically segmented. A comparison of glands of normal eyes versus MGD-affected eyes is performed using five metrics presented in this study: (i) drop-out, (ii) length, (iii) width, (iv) the number of glands, and (v) the number of tortuous glands. The 95% confidence interval for the metrics did not show any overlap between the two groups. In MGD patients, the drop-out ratio was higher than normal. The length and number of glands were significantly lesser than normal. A number of tortuous glands were more in the MGD group. The metrics for MGD versus healthy and cut-off ranges were computed in the results. The prototype infrared hand-held meibographer and the proposed automatic algorithm for gland segmentation and quantification are effective aids in MGD diagnosis. We present a set of five metrics, which are clinically relevant for guiding clinicians in the diagnosis of MGD.

RareAnom: A Benchmark Video Dataset for Rare Type Anomalies

Existing video anomaly detection methods and datasets suffer from restricted anomaly categories containing single-source (CCTV) videos recorded in controlled environment, inadequate annotations, and lack of adequate supervision. To mitigate these problems, we introduce a new dataset (RareAnom) containing 17 rare types of real-world anomalies (2200 videos) recorded using multiple sources (e.g., CCTV, handheld cameras, dash-cams, and mobile phones) with rich temporal annotations. A new fully unsupervised anomaly detection and classification method has been proposed. It has three stages: training of a 3D Convolution Autoencoder using pseudo-labelled video segments, anomaly detection using latent features, and classification. Unlike the existing datasets, we have benchmarked RareAnom using three levels of supervision: fully, weakly, and unsupervised. It has been compared with UCF-Crime and XD-Violence datasets. The proposed anomaly detection and classification method beats the latest unsupervised methods by 4.49%, 8.66%, and 6.77% on RareAnom, UCF-Crime, and XD-violence datasets, respectively.

Day and night camera trap videos are effective for identifying individual wild Asian elephants.

Regular monitoring of wild animal populations through the collection of behavioral and demographic data is critical for the conservation of endangered species. Identifying individual Asian elephants (Elephas maximus), for example, can contribute to our understanding of their social dynamics and foraging behavior, as well as to human-elephant conflict mitigation strategies that account for the behavior of specific individuals involved in the conflict. Wild elephants can be distinguished using a variety of different morphological traits-e.g., variations in ear and tail morphology, body scars and tumors, and tusk presence, shape, and length-with previous studies identifying elephants via direct observation or photographs taken from vehicles. When elephants live in dense forests like in Thailand, remote sensing photography can be a productive approach to capturing anatomical and behavioral information about local elephant populations. While camera trapping has been used previously to identify elephants, here we present a detailed methodology for systematic, experimenter differentiation of individual elephants using data captured from remote sensing video camera traps. In this study, we used day and night video footage collected remotely in the Salakpra Wildlife Sanctuary in Thailand and identified 24 morphological characteristics that can be used to recognize individual elephants. A total of 34 camera traps were installed within the sanctuary as well as crop fields along its periphery, and 107 Asian elephants were identified: 72 adults, 11 sub-adults, 20 juveniles, and four infants. We predicted that camera traps would provide enough information such that classified morphological traits would aid in reliably identifying the adult individuals with a low probability of misidentification. The results indicated that there were low probabilities of misidentification between adult elephants in the population using camera traps, similar to probabilities obtained by other researchers using handheld cameras. This study suggests that the use of day and night video camera trapping can be an important tool for the long-term monitoring of wild Asian elephant behavior, especially in habitats where direct observations may be difficult.

Performance of Automated Machine Learning for Diabetic Retinopathy Image Classification from Multi-field Handheld Retinal Images

To create and validate code-free automated deep learning models (autoML) for diabetic retinopathy (DR) classification from handheld retinal images. Prospective development and validation of autoML models for DR image classification. 17,829 de-identified retinal images from 3,566 eyes with diabetes acquired using handheld retinal cameras in a community-based DR screening program. AutoML models were generated based on previously acquired 5-field (macula-centered, disc-centered, superior, inferior, temporal macula) handheld retinal images. Each individual image was labeled using the International DR and diabetic macular edema (DME) classification scale by four certified graders at a centralized reading center under oversight by a senior retina specialist. Images for model development were split 8-1-1 for training, optimization, and testing to detect referable DR [(refDR), defined as moderate nonproliferative DR or worse or any level of DME]. Internal validation was performed using a published image set from the same patient population (N=450 images from 225 eyes). External validation was performed using a publicly available retinal imaging dataset from the Asia Pacific Tele-Ophthalmology Society (N=3,662 images). Area under the precision-recall curve (AUPRC), sensitivity, specificity, positive predictive value, negative predictive value, (SN, SP, PPV, NPV, respectively) accuracy, and F1 scores. RefDR was present in 17.3%, 39.1% and 48.0% of the training set, internal and external validation sets respectively. The model's AUPRC was 0.995 with a precision and recall of 97% using a score threshold of 0.5. Internal validation showed SN, SP, PPV, NPV, accuracy and F1 scores were 0.96 (95% CI:0.884-0.99), 0.98 (95% CI:0.937-0.995), 0.96 (95% CI:0.884-0.99), 0.98 (95% CI:0.937-0.995), 0.97 and 0.96, respectively. External validation showed SN, SP, PPV, NPV, accuracy and F1 scores were 0.94 (95% CI:0.929-0.951), 0.97 (95% CI:0.957-0.974), 0.96 (95% CI:0.952-0.971), 0.95 (95% CI:0.935-0.956), 0.97 and 0.96, respectively. This study demonstrates the accuracy and feasibility of code-free autoML models for identifying refDR developed using handheld retinal imaging in a community-based screening program. Potentially, the use of autoML may increase access to machine learning models that may be adapted for specific programs that are guided by the clinical need to rapidly address disparities in healthcare delivery.

Health system adaptions to improve care for people living with non-communicable diseases during COVID-19 in low-middle income countries: A scoping review.

During the COVID-19 pandemic, access to health care for people living with non-communicable diseases (NCDs) has been significantly disrupted. Calls have been made to adapt health systems and innovate service delivery models to improve access to care. We identified and summarized the health systems adaptions and interventions implemented to improve NCD care and their potential impact on low- and middle-income countries (LMICs). We comprehensively searched Medline/PubMed, Embase, CINAHL, Global Health, PsycINFO, Global Literature on coronavirus disease, and Web of Science for relevant literature published between January 2020 and December 2021. While we targeted articles written in English, we also included papers published in French with abstracts written in English. After screening 1313 records, we included 14 papers from six countries. We identified four unique health systems adaptations/interventions for restoring, maintaining, and ensuring continuity of care for people living with NCDs: telemedicine or teleconsultation strategies, NCD medicine drop-off points, decentralization of hypertension follow-up services and provision of free medication to peripheral health centers, and diabetic retinopathy screening with a handheld smartphone-based retinal camera. We found that the adaptations/interventions enhanced continuity of NCD care during the pandemic and helped bring health care closer to patients using technology and easing access to medicines and routine visits. Telephonic aftercare services appear to have saved a significant amount of patients' time and funds. Hypertensive patients recorded better blood pressure controls over the follow-up period. Although the identified measures and interventions for adapting health systems resulted in potential improvements in access to NCD care and better clinical outcomes, further exploration is needed to establish the feasibility of these adaptations/interventions in different settings given the importance of context in their successful implementation. Insights from such implementation studies are critical for ongoing health systems strengthening efforts to mitigate the impact of COVID-19 and future global health security threats for people living with NCDs.

A Decade from the Costa Concordia Shipwreck: Lesson Learned on the Contribution of Infrared Thermography during the Maritime Salvage Operations

On 13 January 2012, the Italian vessel Costa Concordia wrecked on the shore of Giglio Island, about 15 km off the coast of southern Tuscany (Italy), causing the loss of 32 lives. It is considered one of the worst disasters in maritime history. Salvage operations started immediately after the wreck with the coordination of the Italian National Civil Protection Department and the technological support of several Research Centers, which were activated for the management of the consequent emergency phase. A multi-parametric and multiplatform monitoring system was promptly implemented, involving several advanced remote sensing techniques, among which was Infrared Thermography (IRT). In this framework, IRT monitoring was performed during a 35-day period (25 January–1 March 2012), using a terrestrial, hand-held thermal camera. Six different thermal images were acquired daily from the island’s coastline in three different positions, both in daylight and night times. The aim was to detect thermal anomalies connected to possible deformations of the vessel and oil spills. Between 3–4 February, IRT successfully revealed on oil spill drifting from the stern of the wreck towards the island harbor. Furthermore, the wreck’s thermal dilatation was also analyzed during a 24-day close-range monitoring, providing interesting insights for the interpretation of the deformation monitoring results. This paper presents the outcomes of these innovative and experimental monitoring activities, with the aim of testing the potential of IRT as a versatile and operative tool to be used in maritime and environmental disaster response.

Comparisons of handheld retinal imaging devices with ultrawide field images for determining diabetic retinopathy severity.

To compare diabetic retinopathy (DR) severity identified on handheld retinal imaging with ultrawide field (UWF) images. Mydriatic images of 225 eyes of 118 diabetic patients were prospectively imaged with the Aurora (AU) handheld retinal camera [5-field protocol (macula-centred, disc-centred, temporal, superior, inferior)] and compared with UWF images. Images were classified based on the international classification for DR. Sensitivity, specificity, kappa statistics (K/Kw) were calculated on an eye and person-level. Distribution of DR severity by AU/UWF images (%) by eye was no DR 41.3/36.0, mild non-proliferative DR (NPDR) 18.7/17.8, moderate 10.2/10.7, severe 16.4/15.1, proliferative DR (PDR) 13.3/20.4. Agreement between UWF and AU was exact in 64.4%, within 1-step 90.7%, k=0.55 (95% CI:0.45-0.65), and kw=0.79 (95% CI:0.73-0.85) by eye, and exact in 68%, within 1-step 92.9%, k=0.58 (95% CI:0.50-0.66), and kw=0.76 (95% CI:0.70-0.81) by person. Sensitivity/specificity for any DR, refDR, vtDR and PDR were as follows: 0.90/0.83, 0.90/0.97, 0.82/0.95 and 0.69/1.00 by person and 0.86/0.90, 0.84/0.98, 0.75/0.95 and 0.63/0.99 by eye. Handheld imaging missed 37% (17/46) eyes and 30.8% (8/26) persons with PDR. Only 3.9% (1/26) persons or 6.5% (3/46) eyes with PDR were missed if a referral threshold of moderate NPDR was used. Data from this study show that comparing UWF and handheld images, when PDR was the referral threshold for handheld devices, 37.0% of eyes or 30.8% of patients with PDR were missed. Due to the identification of neovascular lesions outside of the handheld fields, lower referral thresholds are needed if handheld devices are used.

Framework for Integrating Productive, Contributory, and Noncontributory Work with Safe and Unsafe Acts and Conditions.

It is common for companies that are in the process of implementing the Last Planner System (LPS) journey to attempt an increase in productive work and a reduction in waste, such as contributory and noncontributory work. Even though the LPS has proven to have a synergy with the health and safety requirements, companies with deficient health and safety management systems tend to classify work involving substandard acts or conditions as standard, and then pretend to benchmark against other companies that are indeed performing safe work. The following work introduces a framework to simultaneously register and analyze productive, contributory, and noncontributory work, with the substandard acts and conditions in a construction site, allowing for the measurement of production and health & safety indicators simultaneously. In the absence of technology that automatically captures these indicators, it is proposed that simultaneous measurements be made through direct inspections and photo and video recording by means of a handheld camera. The proposed continuous improvement framework follows the steps indicated below: (1) defining the productive, contributory, and noncontributory work with surveys performed on the most representative stakeholders of the industry; (2) proposing a new classification of production and safety work; (3) assessing the level of application of the LPS in the company; (4) measuring the indicators; (5) improving the use of the LPS and performing new measurements; (6) statistically linking deadly, serious, and minor accidents, standard and substandard acts, standard and substandard conditions, and productive, contributory, and noncontributory work. This framework was applied to a case study of a building project in Lima and the results were improved simultaneous indicators, especially the health and safety indicators. Automated classification of productive and nonproductive work using technology still represents a challenge.

Light Field View Synthesis Using the Focal Stack and All-in-Focus Image.

Light field reconstruction and synthesis algorithms are essential for improving the lower spatial resolution for hand-held plenoptic cameras. Previous light field synthesis algorithms produce blurred regions around depth discontinuities, especially for stereo-based algorithms, where no information is available to fill the occluded areas in the light field image. In this paper, we propose a light field synthesis algorithm that uses the focal stack images and the all-in-focus image to synthesize a 9 × 9 sub-aperture view light field image. Our approach uses depth from defocus to estimate a depth map. Then, we use the depth map and the all-in-focus image to synthesize the sub-aperture views, and their corresponding depth maps by mimicking the apparent shifting of the central image according to the depth values. We handle the occluded regions in the synthesized sub-aperture views by filling them with the information recovered from the focal stack images. We also show that, if the depth levels in the image are known, we can synthesize a high-accuracy light field image with just five focal stack images. The accuracy of our approach is compared with three state-of-the-art algorithms: one non-learning and two CNN-based approaches, and the results show that our algorithm outperforms all three in terms of PSNR and SSIM metrics.

ILabel: Revealing Objects in Neural Fields

A neural field trained with self-supervision to efficiently represent the geometry and colour of a 3D scene tends to automatically decompose it into coherent and accurate object-like regions, which can be revealed with sparse labelling interactions to produce a 3D semantic scene segmentation. Our real-time iLabel system takes input from a hand-held RGB-D camera, requires zero prior training data, and works in an ‘open set’ manner, with semantic classes defined on the fly by the user. iLabel's underlying model is a simple multilayer perceptron (MLP), trained from scratch to learn a neural representation of a single 3D scene. The model is updated continually and visualised in real-time, allowing the user to focus interactions to achieve extremely efficient semantic segmentation. A room-scale scene can be accurately labelled into 10+ semantic categories with around 100 clicks, taking less than 5 minutes. Quantitative labelling accuracy scales powerfully with the number of clicks, and rapidly surpasses standard pre-trained semantic segmentation methods. We also demonstrate a hierarchical labelling variant of iLabel and a ‘hands-free’ mode where the user only needs to supply label names for automatically-generated locations.

Hyperspectral imaging in systemic sclerosis-associated Raynaud phenomenon

Background/purposeLack of robust, feasible, and quantitative outcomes impedes Raynaud phenomenon (RP) clinical trials in systemic sclerosis (SSc) patients. Hyperspectral imaging (HSI) non-invasively measures oxygenated and deoxygenated hemoglobin (oxyHb and deoxyHb) concentrations and oxygen saturation (O2 sat) in the skin and depicts data as oxygenation heatmaps. This study explored the potential role of HSI in quantifying SSc-RP disease severity and activity.MethodsPatients with SSc-RP (n = 13) and healthy control participants (HC; n = 12) were prospectively recruited in the clinic setting. Using a hand-held camera, bilateral hand HSI (HyperMed™, Waltham, MA) was performed in a temperature-controlled room (22 °C). OxyHb, deoxyHb, and O2 sat values were calculated for 78-mm2 regions of interest for the ventral fingertips and palm (for normalization). Subjects underwent a cold provocation challenge (gloved hand submersion in 15 °C water bath for 1 min), and repeated HSI was performed at 0, 10, and 20 min. Patients completed two patient-reported outcome (PRO) instruments: the Raynaud Condition Score (RCS) and the Cochin Hand Function Scale (CHFS) for symptom burden assessment. Statistical analyses were performed using the Mann-Whitney U test and a mixed effects model (Stata, College Station, TX).ResultsNinety-two percent of participants were women in their 40s. For SSc-RP patients, 69% had limited cutaneous SSc, the mean ± SD SSc duration was 11 ± 5 years, and 38% had prior digital ulcers—none currently. Baseline deoxyHb was higher, and O2 sat was lower, in SSc patients versus HC (p < 0.05). SSc patients had a greater decline in oxyHb and O2 sat from baseline to time 0 (after cold challenge) with distinct rewarming oxyHb, O2 sat, and deoxyHb trajectories versus HCs (p < 0.01). There were no significant correlations between oxyHb, deoxyHb, and O2 sat level changes following cold challenge and RCS or CHFS scores.ConclusionHyperspectral imaging is a feasible approach for SSc-RP quantification in the clinic setting. The RCS and CHFS values did not correlate with HSI parameters. Our data suggest that HSI technology for the assessment of SSc-RP at baseline and in response to cold provocation is a potential quantitative measure for SSc-RP severity and activity, though longitudinal studies that assess sensitivity to change are needed.

An Intelligent Vision-Based Nutritional Assessment Method for Handheld Food Items

Dietary assessment has proven to be an important tool to evaluate the dietary intake of patients with diabetes and obesity. The traditional approach of accessing the dietary intake is to conduct a 24-hour dietary recall (24HR), a structured interview designed to obtain information on food categories and volume consumed by the participants. Due to the unconscious biases in this kind of self-reporting approach, many research studies have explored the use of vision-based approaches to provide accurate and objective assessments. Despite the promising results of food recognition by deep neural networks, there still exist several hurdles in deep learning-based food volume estimation ranging from domain shift between synthetic and raw 3D models, shape completion ambiguity and, most importantly, lack of large-scale paired training dataset. Therefore, this paper proposed an intelligent nutritional assessment approach via weakly-supervised point cloud completion. It aims to close the reality gap in 3D point cloud completion tasks and address the targeted challenges by proposing the Point Cloud Auxiliary Classifier GAN (PC-ACGAN), a novel and robust point cloud completion architecture that can be trained in a weakly-supervised manner. Then the volume can be easily estimated from the completed representation of the food. In addition to advantages with regard to efficiency, another major merit of our system is that it can be used to estimate the volume of handheld food items without requiring the constraints including placing the food items on a table or next to fiducial markers, which facilitate the implementation on both wearable and handheld cameras. Comprehensive experiments have been carried out on major benchmark datasets and self-constructed volume-annotated dataset respectively, in which the proposed PC-ACGAN demonstrates comparable results with several strong fully-supervised baseline methods and shows superior completion ability in handling food volume estimation.

Comparisons of Handheld Retinal Imaging with Optical Coherence Tomography for the Identification of Macular Pathology in Patients with Diabetes

Introduction: Handheld retinal imaging cameras are relatively inexpensive and highly portable devices that have the potential to significantly expand diabetic retinopathy (DR) screening, allowing a much broader population to be evaluated. However, it is essential to evaluate if these devices can accurately identify vision-threatening macular diseases if DR screening programs will rely on these instruments. Thus, the purpose of this study was to evaluate the detection of diabetic macular pathology using monoscopic macula-centered images using mydriatic handheld retinal imaging compared with spectral domain optical coherence tomography (SDOCT). Methods: Mydriatic 40°–60° macula-centered images taken with 3 handheld retinal imaging devices (Aurora [AU], SmartScope [SS], RetinaVue 700 [RV]) were compared with the Cirrus 6000 SDOCT taken during the same visit. Images were evaluated for the presence of diabetic macular edema (DME) on monoscopic fundus photographs adapted from Early Treatment Diabetic Retinopathy Study (ETDRS) definitions (no DME, noncenter-involved DME [non-ciDME], and center-involved DME [ciDME]). Sensitivity, specificity, positive predictive value, and negative predictive value were calculated for each device with SDOCT as gold standard. Results: Severity by ETDRS photos: no DR 33.3%, mild NPDR 20.4%, moderate 14.2%, severe 11.6%, proliferative 20.4%, and ungradable for DR 0%; no DME 83.1%, non-ciDME 4.9%, ciDME 12.0%, and ungradable for DME 0%. Gradable images by SDOCT (N = 217, 96.4%) showed no DME in 75.6%, non-ciDME in 9.8%, and ciDME in 11.1%. The ungradable rate for images (poor visualization in >50% of the macula) was AU: 0.9%, SS: 4.4%, and RV: 6.2%. For DME, sensitivity and specificity were similar across devices (0.5–0.64, 0.93–0.97). For nondiabetic macular pathology (ERM, pigment epithelial detachment, traction retinal detachment) across all devices, sensitivity was low to moderate (0.2–0.5) but highly specific (0.93–1.00). Conclusions: Compared to SDOCT, handheld macular imaging attained high specificity but low sensitivity in identifying macular pathology. This suggests the importance of SDOCT evaluation for patients suspected to have DME on fundus photography, leading to more appropriate referral refinement.