Statistical models for meal-level estimation of mass and energy intake using features derived from video observation and a chewing sensor

Research Progress on Improving the Efficiency of CDT by Exacerbating Tumor Acidification

In recent years, chemodynamic therapy (CDT) has received extensive attention as a novel means of cancer treatment. The CDT agents can exert Fenton and Fenton-like reactions in the acidic tumor microenvironment (TME), converting hydrogen peroxide (H₂O₂) into highly toxic hydroxyl radicals (·OH). However, the pH of TME, as an essential factor in the Fenton reaction, does not catalyze the reaction effectively, hindering its efficiency, which poses a significant challenge for the future clinical application of CDT. Therefore, this paper reviews various strategies to enhance the antitumor properties of nanomaterials by modulating tumor acidity. Ultimately, the performance of CDT can be further improved by inducing strong oxidative stress to produce sufficient ·OH. In this paper, the various acidification pathways and proton pumps with potential acidification functions are mainly discussed, such as catalytic enzymes, exogenous acids, CAIX, MCT, NHE, NBCn1, etc. The problems, opportunities, and challenges of CDT in the cancer field are also discussed, thereby providing new insights for the design of nanomaterials and laying the foundation for their future clinical applications.

FOODCAM: A Novel Structured Light-Stereo Imaging System for Food Portion Size Estimation

Imaging-based methods of food portion size estimation (FPSE) promise higher accuracies compared to traditional methods. Many FPSE methods require dimensional cues (fiducial markers, finger-references, object-references) in the scene of interest and/or manual human input (wireframes, virtual models). This paper proposes a novel passive, standalone, multispectral, motion-activated, structured light-supplemented, stereo camera for food intake monitoring (FOODCAM) and an associated methodology for FPSE that does not need a dimensional reference given a fixed setup. The proposed device integrated a switchable band (visible/infrared) stereo camera with a structured light emitter. The volume estimation methodology focused on the 3-D reconstruction of food items based on the stereo image pairs captured by the device. The FOODCAM device and the methodology were validated using five food models with complex shapes (banana, brownie, chickpeas, French fries, and popcorn). Results showed that the FOODCAM was able to estimate food portion sizes with an average accuracy of 94.4%, which suggests that the FOODCAM can potentially be used as an instrument in diet and eating behavior studies.

Detection of Food Intake Sensor's Wear Compliance in Free-Living

Objective detection of periods of wear and non-wear is critical for human studies that rely on information from wearable sensors, such as food intake sensors. In this paper, we present a novel method of compliance detection on the example of the Automatic Ingestion Monitor v2 (AIM-2) sensor, containing a tri-axial accelerometer, a still camera, and a chewing sensor. The method was developed and validated using data from a study of 30 participants aged 18-39, each wearing the AIM-2 for two days (a day in pseudo-free-living and a day in free-living). Four types of wear compliance were analyzed: 'normal-wear', 'non-compliant-wear', 'non-wear-carried', and 'non-wear-stationary'. The ground truth of those four types of compliance was obtained by reviewing the images of the egocentric camera. The features for compliance detection were the standard deviation of acceleration, average pitch, and roll angles, and mean square error of two consecutive images. These were used to train three random forest classifiers 1) accelerometer-based, 2) image-based, and 3) combined accelerometer and image-based. Satisfactory wear compliance measurement accuracy was obtained using the combined classifier (89.24%) on leave one subject out cross-validation. The average duration of compliant wear in the study was 9h with a standard deviation of 2h or 70.96% of total on-time. This method can be used to calculate the wear and non-wear time of AIM-2, and potentially be extended to other devices. The study also included assessments of sensor burden and privacy concerns. The survey results suggest recommendations that may be used to increase wear compliance.

A Dual-Padded, Protrusion-Incorporated, Ring-Type Sensor for the Measurement of Food Mass and Intake

Dietary monitoring is vital in healthcare because knowing food mass and intake (FMI) plays an essential role in revitalizing a person’s health and physical condition. In this study, we report the development of a highly sensitive ring-type biosensor for the detection of FMI for dietary monitoring. To identify lightweight food on a spoon, we enhance the sensing system’s sensitivity with three components: (1) a first-class lever mechanism, (2) a dual pad sensor, and (3) a force focusing structure using a ring surface having protrusions. As a result, we confirmed that, as the food arm’s length increases, the force detected at the sensor is amplified by the first-class lever mechanism. Moreover, we obtained 1.88 and 1.71 times amplification using the dual pad sensor and the force focusing structure, respectively. Furthermore, the ring-type biosensor showed significant potential as a diagnostic indicator because the ring sensor signal was linearly proportional to the food mass delivered in a spoon, with R² = 0.988, and an average F₁ score of 0.973. Therefore, we believe that this approach is potentially beneficial for developing a dietary monitoring platform to support the prevention of obesity, which causes several adult diseases, and to keep the FMI data collection process automated in a quantitative, network-controlled manner.

Automatic Count of Bites and Chews From Videos of Eating Episodes

Methods for measuring of eating behavior (known as meal microstructure) often rely on manual annotation of bites, chews, and swallows on meal videos or wearable sensor signals. The manual annotation may be time consuming and erroneous, while wearable sensors may not capture every aspect of eating (e.g. chews only). The aim of this study is to develop a method to detect and count bites and chews automatically from meal videos. The method was developed on a dataset of 28 volunteers consuming unrestricted meals in the laboratory under video observation. First, the faces in the video (regions of interest, ROI) were detected using Faster R-CNN. Second, a pre-trained AlexNet was trained on the detected faces to classify images as a bite/no bite image. Third, the affine optical flow was applied in consecutively detected faces to find the rotational movement of the pixels in the ROIs. The number of chews in a meal video was counted by converting the 2-D images to a 1-D optical flow parameter and finding peaks. The developed bite and chew count algorithm was applied to 84 meal videos collected from 28 volunteers. A mean accuracy (±STD) of 85.4% (±6.3%) with respect to manual annotation was obtained for the number of bites and 88.9% (±7.4%) for the number of chews. The proposed method for an automatic bite and chew counting shows promising results that can be used as an alternative solution to manual annotation.