Dietary Assessment with Multimodal ChatGPT: A Systematic Analysis.

Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, prior AI methodologies tackle dietary assessment in a fragmented landscape (e.g., merely recognizing food types or estimating portion size), and encounter challenges in their ability to generalize across a diverse range of food categories, dietary behaviors, and cultural contexts. Recently, the emergence of multimodal foundation models, such as GPT-4V, has exhibited transformative potential across a wide range of tasks (e.g., scene understanding and image captioning) in various research domains. These models have demonstrated remarkable generalist intelligence and accuracy, owing to their large-scale pre-training on broad datasets and substantially scaled model size. In this study, we explore the application of GPT-4V powering multimodal ChatGPT for dietary assessment, along with prompt engineering and passive monitoring techniques. We evaluated the proposed pipeline using a self-collected, semi free-living dietary intake dataset comprising 16 real-life eating episodes, captured through wearable cameras. Our findings reveal that GPT-4V excels in food detection under challenging conditions without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further facilitating the process of dietary assessment.

Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring.

Camera-based passive dietary intake monitoring is able to continuously capture the eating episodes of a subject, recording rich visual information, such as the type and volume of food being consumed, as well as the eating behaviors of the subject. However, there currently is no method that is able to incorporate these visual clues and provide a comprehensive context of dietary intake from passive recording (e.g., is the subject sharing food with others, what food the subject is eating, and how much food is left in the bowl). On the other hand, privacy is a major concern while egocentric wearable cameras are used for capturing. In this article, we propose a privacy-preserved secure solution (i.e., egocentric image captioning) for dietary assessment with passive monitoring, which unifies food recognition, volume estimation, and scene understanding. By converting images into rich text descriptions, nutritionists can assess individual dietary intake based on the captions instead of the original images, reducing the risk of privacy leakage from images. To this end, an egocentric dietary image captioning dataset has been built, which consists of in-the-wild images captured by head-worn and chest-worn cameras in field studies in Ghana. A novel transformer-based architecture is designed to caption egocentric dietary images. Comprehensive experiments have been conducted to evaluate the effectiveness and to justify the design of the proposed architecture for egocentric dietary image captioning. To the best of our knowledge, this is the first work that applies image captioning for dietary intake assessment in real-life settings.

Large AI Models in Health Informatics: Applications, Challenges, and the Future.

Large AI models, or foundation models, are models recently emerging with massive scales both parameter-wise and data-wise, the magnitudes of which can reach beyond billions. Once pretrained, large AI models demonstrate impressive performance in various downstream tasks. A prime example is ChatGPT, whose capability has compelled people's imagination about the far-reaching influence that large AI models can have and their potential to transform different domains of our lives. In health informatics, the advent of large AI models has brought new paradigms for the design of methodologies. The scale of multi-modal data in the biomedical and health domain has been ever-expanding especially since the community embraced the era of deep learning, which provides the ground to develop, validate, and advance large AI models for breakthroughs in health-related areas. This article presents a comprehensive review of large AI models, from background to their applications. We identify seven key sectors in which large AI models are applicable and might have substantial influence, including: 1) bioinformatics; 2) medical diagnosis; 3) medical imaging; 4) medical informatics; 5) medical education; 6) public health; and 7) medical robotics. We examine their challenges, followed by a critical discussion about potential future directions and pitfalls of large AI models in transforming the field of health informatics.

Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation.

Medical image analysis plays an important role in clinical diagnosis. In this paper, we examine the recent Segment Anything Model (SAM) on medical images, and report both quantitative and qualitative zero-shot segmentation results on nine medical image segmentation benchmarks, covering various imaging modalities, such as optical coherence tomography (OCT), magnetic resonance imaging (MRI), and computed tomography (CT), as well as different applications including dermatology, ophthalmology, and radiology. Those benchmarks are representative and commonly used in model development. Our experimental results indicate that while SAM presents remarkable segmentation performance on images from the general domain, its zero-shot segmentation ability remains restricted for out-of-distribution images, e.g., medical images. In addition, SAM exhibits inconsistent zero-shot segmentation performance across different unseen medical domains. For certain structured targets, e.g., blood vessels, the zero-shot segmentation of SAM completely failed. In contrast, a simple fine-tuning of it with a small amount of data could lead to remarkable improvement of the segmentation quality, showing the great potential and feasibility of using fine-tuned SAM to achieve accurate medical image segmentation for a precision diagnostics. Our study indicates the versatility of generalist vision foundation models on medical imaging, and their great potential to achieve desired performance through fine-turning and eventually address the challenges associated with accessing large and diverse medical datasets in support of clinical diagnostics.

Counting Bites and Recognizing Consumed Food from Videos for Passive Dietary Monitoring.

Assessing dietary intake in epidemiological studies are predominantly based on self-reports, which are subjective, inefficient, and also prone to error. Technological approaches are therefore emerging to provide objective dietary assessments. Using only egocentric dietary intake videos, this work aims to provide accurate estimation on individual dietary intake through recognizing consumed food items and counting the number of bites taken. This is different from previous studies that rely on inertial sensing to count bites, and also previous studies that only recognize visible food items but not consumed ones. As a subject may not consume all food items visible in a meal, recognizing those consumed food items is more valuable. A new dataset that has 1,022 dietary intake video clips was constructed to validate our concept of bite counting and consumed food item recognition from egocentric videos. 12 subjects participated and 52 meals were captured. A total of 66 unique food items, including food ingredients and drinks, were labelled in the dataset along with a total of 2,039 labelled bites. Deep neural networks were used to perform bite counting and food item recognition in an end-to-end manner. Experiments have shown that counting bites directly from video clips can reach 74.15% top-1 accuracy (classifying between 0-4 bites in 20-second clips), and a MSE value of 0.312 (when using regression). Our experiments on video-based food recognition also show that recognizing consumed food items is indeed harder than recognizing visible ones, with a drop of 25% in F1 score.

Food Volume Estimation Based on Deep Learning View Synthesis from a Single Depth Map.

An objective dietary assessment system can help users to understand their dietary behavior and enable targeted interventions to address underlying health problems. To accurately quantify dietary intake, measurement of the portion size or food volume is required. For volume estimation, previous research studies mostly focused on using model-based or stereo-based approaches which rely on manual intervention or require users to capture multiple frames from different viewing angles which can be tedious. In this paper, a view synthesis approach based on deep learning is proposed to reconstruct 3D point clouds of food items and estimate the volume from a single depth image. A distinct neural network is designed to use a depth image from one viewing angle to predict another depth image captured from the corresponding opposite viewing angle. The whole 3D point cloud map is then reconstructed by fusing the initial data points with the synthesized points of the object items through the proposed point cloud completion and Iterative Closest Point (ICP) algorithms. Furthermore, a database with depth images of food object items captured from different viewing angles is constructed with image rendering and used to validate the proposed neural network. The methodology is then evaluated by comparing the volume estimated by the synthesized 3D point cloud with the ground truth volume of the object items.

Motion artifact reduction in photoplethysmogram signals based on Periodic Component Factorization.

Continuous blood pressure measurement based on pulse transit time (PTT) is a deeply research topic over recent decades. Advanced algorithms have been proposed by scholars to give satisfactory estimation in stationary position. Nevertheless, pulse transit time (PTT) is shown to be strongly affected by hand movement and the estimation of blood pressure is no longer accurate under strenuous exercise. Because of this, a novel algorithm called Periodic Component Factorization (PCF), which is an extension of Independent Component Analysis (ICA), for better removal of motion artifact (MA) from photoplethysmography (PPG) signals is proposed in this paper. Compared to FastICA algorithm based on nongaussianity such as kurtosis and skewness, PCF is able to extract dependent source components from noisy signals when the PPG signal shows quasi-periodicity or periodicity. This newly proposed algorithm undoubtedly shows its practicality and effectiveness in removing motion artifact of PPG signals.

Continuous systolic and diastolic blood pressure estimation utilizing long short-term memory network.

A novel blood pressure estimation method based on long short-term memory neural network, one of the recurrent neural networks being commonly used nowadays, is proposed in this paper for better chronic diseases monitoring. Along with the neural network, a newly proposed ambulatory blood pressure (ABP) processing technique called Two-stage Zero-order Holding (TZH) algorithm has also been presented in the paper. The proposed methodology has the advantages over traditional blood pressure estimation algorithms which are based on Pulse Transit time (PTT). The paper addresses the effectiveness of the algorithm by computing the Root-Mean-Squared Errors (RMSE) between the BP estimated and the ground truth. Our algorithm shows precise systolic blood pressure and diastolic blood pressure estimation with the average RMSE values in 2.751 mmHg and 1.604 mmHg respectively across the sample used. Experimental results suggest that BP estimation based on LSTM has great potential to be embedded into monitoring system for better accuracy and generalization.

Double sensor complementary placement method to reduce motion artifacts in PPG using fast independent component analysis.

A novel sensor placement method for better removal of motion artifacts (MA) from photoplethysmography (PPG) signal using Fast Independent Component Analysis (ICA) is proposed in this paper. The method enhances the determination of pulse transit time (PTT) of PPG signals. The design makes use of double reflectance mode based PPG probes, which are placed complementary to each other and on the two sides of a single finger. Furthermore, a novel indicator denoted as Separating Factor is proposed as well. It helps evaluating the performance of ICA with different sensors configuration. This paper then addresses the effectiveness of FastICA in motion artifacts reduction by using the novel method and normal sensors placement method to capture PPG. Results indicate that better independent source separation can be achieved and morphology of PPG signal is perfectly restored when using the method proposed in this paper.

[Aviation physiology]. / Flugphysiologie.

Aviation physiology should be known at least in parts by the physicians advising air travellers. Due to reducing atmospheric pressure at altitude gas volume in body cavities expands (Boyle's law). This might not be a problem during ascend since air can disappear easily through natural ways. However, air must return to body cavities during descend and a person with a cold may suffer from painful barotitis. Hypoxia is mostly due to a reduced pO2 in high altitude (Daltons's Law). This may be prevented by an aircraft cabin or supplemented oxygen. Decompression sickness is very rare in aviation but divers should comply to a dive free interval before flying.

Dinuclear Paddle-Wheel Copper(II) Carboxylates in the Catalytic Oxidation of Carboxylic Acids. Unusual Polymeric Chains Found in the Single-Crystal X-ray Structures of [Tetrakis(&mgr;-1-phenylcyclopropane-1-carboxylato-O,O')bis(ethanol-O)dicopper(II)] and catena-Poly[[bis(&mgr;-diphenylacetato-O:O')dicopper](&mgr;(3)-diphenylacetato-1-O:2-O':1'-O')(&mgr;(3)-diphenylacetato-1-O:2-O':2'-O')].

The X-ray structures and spectroscopic and magnetic properties of [tetrakis(&mgr;-1-phenylcyclopropane-1-carboxylato-O,O')bis(ethanol-O)dicopper(II)], 1, and catena-poly[[bis(&mgr;-diphenylacetato-O:O')dicopper](&mgr;(3)-diphenylacetato-1-O:2-O':1'-O')(&mgr;(3)-diphenylacetato-1-O:2-O':2'-O')], 2, two extended-chain copper(II) carboxylates with dinuclear paddle-wheel subunits, are reported. 1 crystallizes in the triclinic space group P&onemacr;, with a = 6.8873(3) Å, b = 11.7367(6) Å, c = 13.7899(7) Å, alpha = 107.076(4) degrees, beta = 93.545(4) degrees, gamma = 103.967(4) degrees, Z = 1. The Cu.Cu distance is 2.6009(4) Å, and the Cu.carboxylate O distances are in the range 1.937(2)-1.962(2) Å. The ethanol at the apex forms an unsymmetrical bifurcated H bond to two carboxylate oxygens of another dinuclear unit with O.O distances 2.980(3) and 3.108(3) Å, thereby extending the structure along the a-axis. The magnetic structure consists of isolated antiferromagnetically coupled dinuclear copper units, with a -2J value of 242 cm(-)(1), in concurrence with the EPR parameters, viz., g(x)() = 2.03(1), g(y)() = 2.07(1), g(z)() = 2.35(1), A( parallel) = 0.064(2) cm(-)(1), D = 0.316(15) cm(-)(1), E = 0.005(1) cm(-)(1). The -2J value is the smallest value measured for dinuclear copper carboxylates with oxygen-donor ligands at the axial position and no electron-withdrawing carboxylate R groups. 2 crystallizes in the monoclinic space group P2(1)/c, with a = 15.953(2) Å, b = 5.385(6) Å, c = 28.322(10) Å, beta = 120.22(3) degrees, Z = 2. The compound contains tetrakis(diphenylacetato)dicopper(II) units, forming a polymeric structure along the b-axis by axial coordination of a carboxylate oxygen to copper of a subsequent dinuclear unit, at 2.323(11) Å. The intradimer Cu.Cu distance is 2.594(4) Å; the interdimer Cu.Cu distance is 3.425(5) Å. The -2J value of 321 cm(-)(1) was interpreted as originated from isolated antiferromagnetically coupled dinuclear copper units. The EPR parameters are g(x)() = 2.07(1), g(y)() = 2.02(1), g(z)() = 2.33(1), D = 0.347(10) cm(-)(1), E = 0.0034(5) cm(-)(1). The dinuclear subunits are likely candidates for the catalytically active Cu species in copper(II)-catalyzed oxidation of carboxylic acids.

The communicating branch of the lateral plantar nerve: a descriptive anatomic study.

Since the communicating branch of the lateral plantar nerve has been implicated as a factor in the etiology of Morton's neuroma, a painful perineurofibrosis of a common plantar digital nerve, this project was designed to investigate the anatomy of this communicating branch. Both feet of 40 embalmed human cadavers were dissected to show the frequency of occurrence and anatomical variation of the communicating branch. The communicating branch was present in 66.2% of the feet we studied with no large gender-based differences. Branches occurred bilaterally in 52.5% of cadavers, while 27.5% had branches unilaterally. The occurrence of this branch does not correlate well with the likelihood of development of Morton's neuroma. Differences in diameter of the communicating branch ranged from less than 0.5 mm to as large as the common plantar digital nerves themselves, about 2 mm. The presence or absence of the communicating branch made no qualitative difference in the diameters of the common plantar digital nerves. There were 60.4% of the communicating branches in this study that had a typically-described orientation, arising more proximally in the foot from the fourth common plantar digital nerve, while 39.6% of the branches had a reversed orientation, arising more proximally from the third common plantar digital nerve. These reversed branches had a more oblique orientation when compared to the classic branches. Other anatomical variations were noted, including accessory branches that attached to deeper structures in the foot. These data form a basis for further research into the etiology of Morton's neuroma and improved surgical techniques for correcting this condition.