Computer aided diagnosis of obesity based on thermal imaging using various convolutional neural networks

Clustering-Based Thermography for Detecting Multiple Substances Under Large-Scale Floating Covers

This study presents a novel approach for monitoring waste substrate digestion under high-density polyethylene (HDPE) geomembranes in sewage treatment plants. The method integrates infrared thermal imaging with a clustering algorithm to predict the distribution of various substrates beneath Traditional outdoor large-scale opaque geomembranes, using solar radiation as an excitation source. The technique leverages ambient weather conditions to assess the thermal responses of HDPE covers. Cooling constants are used to reconstruct thermal images, and clustering algorithms are explored to segment and identify different material states beneath the covers. Laboratory experiments have validated the algorithm's effectiveness in accurately classifying varied regions by analyzing transient temperature variations caused by natural excitations. This method provides critical insights into scum characteristics and biogas collection processes, thereby enhancing decision-making in sewage treatment management. The methodology under development is anticipated to undergo rigorous evaluation across various floating covers at a large-scale sewage treatment facility in Melbourne. Subsequent to field validation, the implementation of an on-site, continuous thermography monitoring system is envisioned to be further advanced.

Tongue image fusion and analysis of thermal and visible images in diabetes mellitus using machine learning techniques

The study aimed to achieve the following objectives: (1) to perform the fusion of thermal and visible tongue images with various fusion rules of discrete wavelet transform (DWT) to classify diabetes and normal subjects; (2) to obtain the statistical features in the required region of interest from the tongue image before and after fusion; (3) to distinguish the healthy and diabetes using fused tongue images based on deep and machine learning algorithms. The study participants comprised of 80 normal subjects and age- and sex-matched 80 diabetes patients. The biochemical tests such as fasting glucose, postprandial, Hba1c are taken for all the participants. The visible and thermal tongue images are acquired using digital single lens reference camera and thermal infrared cameras, respectively. The digital and thermal tongue images are fused based on the wavelet transform method. Then Gray level co-occurrence matrix features are extracted individually from the visible, thermal, and fused tongue images. The machine learning classifiers and deep learning networks such as VGG16 and ResNet50 was used to classify the normal and diabetes mellitus. Image quality metrics are implemented to compare the classifiers' performance before and after fusion. Support vector machine outperformed the machine learning classifiers, well after fusion with an accuracy of 88.12% compared to before the fusion process (Thermal-84.37%; Visible-63.1%). VGG16 produced the classification accuracy of 94.37% after fusion and attained 90.62% and 85% before fusion of individual thermal and visible tongue images, respectively. Therefore, this study results indicates that fused tongue images might be used as a non-contact elemental tool for pre-screening type II diabetes mellitus.

Convolutional Neural Network to Classify Infrared Thermal Images of Fractured Wrists in Pediatrics

Convolutional neural network (CNN) models were devised and evaluated to classify infrared thermal (IRT) images of pediatric wrist fractures. The images were recorded from 19 participants with a wrist fracture and 21 without a fracture (sprain). The injury diagnosis was by X-ray radiography. For each participant, 299 IRT images of their wrists were recorded. These generated 11,960 images (40 participants × 299 images). For each image, the wrist region of interest (ROI) was selected and fast Fourier transformed (FFT) to obtain a magnitude frequency spectrum. The spectrum was resized to 100 × 100 pixels from its center as this region represented the main frequency components. Image augmentations of rotation, translation and shearing were applied to the 11,960 magnitude frequency spectra to assist with the CNN generalization during training. The CNN had 34 layers associated with convolution, batch normalization, rectified linear unit, maximum pooling and SoftMax and classification. The ratio of images for the training and test was 70:30, respectively. The effects of augmentation and dropout on CNN performance were explored. Wrist fracture identification sensitivity and accuracy of 88% and 76%, respectively, were achieved. The CNN model was able to identify wrist fractures; however, a larger sample size would improve accuracy.

A review of the application of deep learning in obesity: From early prediction aid to advanced management assistance

BACKGROUND AND AIMS

Obesity is a chronic disease which can cause severe metabolic disorders. Machine learning (ML) techniques, especially deep learning (DL), have proven to be useful in obesity research. However, there is a dearth of systematic reviews of DL applications in obesity. This article aims to summarize the current trend of DL usage in obesity research.

METHODS

An extensive literature review was carried out across multiple databases, including PubMed, Embase, Web of Science, Scopus, and Medline, to collate relevant studies published from January 2018 to September 2023. The focus was on research detailing the application of DL in the context of obesity. We have distilled critical insights pertaining to the utilized learning models, encompassing aspects of their development, principal results, and foundational methodologies.

RESULTS

Our analysis culminated in the synthesis of new knowledge regarding the application of DL in the context of obesity. Finally, 40 research articles were included. The final collection of these research can be divided into three categories: obesity prediction (n = 16); obesity management (n = 13); and body fat estimation (n = 11).

CONCLUSIONS

This is the first review to examine DL applications in obesity. It reveals DL's superiority in obesity prediction over traditional ML methods, showing promise for multi-omics research. DL also innovates in obesity management through diet, fitness, and environmental analyses. Additionally, DL improves body fat estimation, offering affordable and precise monitoring tools. The study is registered with PROSPERO (ID: CRD42023475159).

Lightweight convolutional neural network (CNN) model for obesity early detection using thermal images

Objective

The presence of a lightweight convolutional neural network (CNN) model with a high-accuracy rate and low complexity can be useful in building an early obesity detection system, especially on mobile-based applications. The previous works of the CNN model for obesity detection were focused on the accuracy performances without considering the complexity size. In this study, we aim to build a new lightweight CNN model that can accurately classify normal and obese thermograms with low complexity sizes.

Methods

The DenseNet201 CNN architectures were modified by replacing the standard convolution layers with multiple depthwise and pointwise convolution layers from the MobileNet architectures. Then, the depth network of the dense block was reduced to determine which depths were the most comparable to obtain minimum validation losses. The proposed model then was compared with state-of-the-art DenseNet and MobileNet CNN models in terms of classification performances, and complexity size, which is measured in model size and computation cost.

Results

The results of the testing experiment show that the proposed model has achieved an accuracy of 81.54% with a model size of 1.44 megabyte (MB). This accuracy was comparable to that of DenseNet, which was 83.08%. However, DenseNet's model size was 71.77 MB. On the other hand, the proposed model's accuracy was higher than that of MobileNetV2, which was 79.23%, with a computation cost of 0.69 billion floating-point operations per second (GFLOPS), which approximated that of MobileNetV2, which was 0.59 GFLOPS.

Conclusions

The proposed model inherited the feature-extracting ability from the DenseNet201 architecture while keeping the lightweight complexity characteristic of the MobileNet architecture.

Applications of Artificial Intelligence to Obesity Research: Scoping Review of Methodologies

BACKGROUND

Obesity is a leading cause of preventable death worldwide. Artificial intelligence (AI), characterized by machine learning (ML) and deep learning (DL), has become an indispensable tool in obesity research.

OBJECTIVE

This scoping review aimed to provide researchers and practitioners with an overview of the AI applications to obesity research, familiarize them with popular ML and DL models, and facilitate the adoption of AI applications.

METHODS

We conducted a scoping review in PubMed and Web of Science on the applications of AI to measure, predict, and treat obesity. We summarized and categorized the AI methodologies used in the hope of identifying synergies, patterns, and trends to inform future investigations. We also provided a high-level, beginner-friendly introduction to the core methodologies to facilitate the dissemination and adoption of various AI techniques.

RESULTS

We identified 46 studies that used diverse ML and DL models to assess obesity-related outcomes. The studies found AI models helpful in detecting clinically meaningful patterns of obesity or relationships between specific covariates and weight outcomes. The majority (18/22, 82%) of the studies comparing AI models with conventional statistical approaches found that the AI models achieved higher prediction accuracy on test data. Some (5/46, 11%) of the studies comparing the performances of different AI models revealed mixed results, indicating the high contingency of model performance on the data set and task it was applied to. An accelerating trend of adopting state-of-the-art DL models over standard ML models was observed to address challenging computer vision and natural language processing tasks. We concisely introduced the popular ML and DL models and summarized their specific applications in the studies included in the review.

CONCLUSIONS

This study reviewed AI-related methodologies adopted in the obesity literature, particularly ML and DL models applied to tabular, image, and text data. The review also discussed emerging trends such as multimodal or multitask AI models, synthetic data generation, and human-in-the-loop that may witness increasing applications in obesity research.

Deep learning techniques for automated detection of autism spectrum disorder based on thermal imaging

Children with autism spectrum disorder have impairments in emotional processing which leads to the inability in recognizing facial expressions. Since emotion is a vital criterion for having fine socialisation, it is incredibly important for the autistic children to recognise emotions. In our study, we have chosen the facial skin temperature as a biomarker to measure emotions. To assess the facial skin temperature, the thermal imaging modality has been used in this study, since it has been recognised as a promising technique to evaluate emotional responses. The aim of this study was the following: (1) to compare the facial skin temperature of autistic and non-autistic children by using thermal imaging across various emotions; (2) to classify the thermal images obtained from the study using the customised convolutional neural network compared with the ResNet 50 network. Fifty autistic and fifty non-autistic participants were included for the study. Thermal imaging was used to obtain the temperature of specific facial regions such as the eyes, cheek, forehead and nose while we evoked emotions (Happiness, anger and sadness) in children using an audio-visual stimulus. Among the emotions considered, the emotion anger had the highest temperature difference between the autistic and non-autistic participants in the region's eyes (1.9%), cheek (2.38%) and nose (12.6%). The accuracy obtained by classifying the thermal images of the autistic and non-autistic children using Customised Neural Network and ResNet 50 Network was 96% and 90% respectively. This computer aided diagnostic tool can be a predictable and a steadfast method in the diagnosis of the autistic individuals.

Research on sports aided teaching and training decision system oriented to deep convolutional neural network

Aiming at the construction of the decision-making system for sports-assisted teaching and training, this article first gives a deep convolutional neural network model for sports-assisted teaching and training decision-making. Subsequently, In order to meet the needs of athletes to assist in physical exercise, a squat training robot is built using a self-developed modular flexible cable drive unit, and its control system is designed to assist athletes in squatting training in sports. First, the human squat training mechanism is analyzed, and the overall structure of the robot is determined; second, the robot force servo control strategy is designed, including the flexible cable traction force planning link, the lateral force compensation link and the establishment of a single flexible cable passive force controller; In order to verify the effect of robot training, a single flexible cable force control experiment and a man-machine squat training experiment were carried out. In the single flexible cable force control experiment, the suppression effect of excess force reached more than 50%. In the squat experiment under 200 N, the standard deviation of the system loading force is 7.52 N, and the dynamic accuracy is above 90.2%. Experimental results show that the robot has a reasonable configuration, small footprint, stable control system, high loading accuracy, and can assist in squat training in physical education.