Monte Carlo: A flexible and accurate technique for modeling light transport in food and agricultural products

Recent Advances in Light Penetration Depth for Postharvest Quality Evaluation of Fruits and Vegetables

Light penetration depth, as a characteristic parameter reflecting light attenuation and transmission in biological tissues, has been applied in nondestructive detection of fruits and vegetables. Recently, with emergence of new optical detection technologies, researchers have begun to explore methods evaluating optical properties of double-layer or even multilayer fruit and vegetable tissues due to the differences between peel and pulp in the chemical composition and physical properties, which has gradually promoted studies on light penetration depth. A series of demonstrated research on light penetration depth could ensure the accuracy of the optical information obtained from each layer of tissue, which is beneficial to enhance detection accuracy for quality assessment of fruits and vegetables. Therefore, the aim of this review is to give detailed outlines about the theory and principle of light penetration depth based on several emerging optical detection technologies and to focus primarily on its applications in the field of quality evaluation of fruits and vegetables, its future applicability in fruits and vegetables and the challenges it may face in the future.

Principles, developments, and applications of spatially resolved spectroscopy in agriculture: a review

Agriculture is the primary source of human survival, which provides the most basic living and survival conditions for human beings. As living standards continue to improve, people are also paying more attention to the quality and safety of agricultural products. Therefore, the detection of agricultural product quality is very necessary. In the past decades, the spectroscopy technique has been widely used because of its excellent results in agricultural quality detection. However, traditional spectral inspection methods cannot accurately describe the internal information of agricultural products. With the continuous research and development of optical properties, it has been found that the internal quality of an object can be better reflected by separating the properties of light, such as its absorption and scattering properties. In recent years, spatially resolved spectroscopy has been increasingly used in the field of agricultural product inspection due to its simple compositional structure, low-value cost, ease of operation, efficient detection speed, and outstanding ability to obtain information about agricultural products at different depths. It can also separate optical properties based on the transmission equation of optics, which allows for more accurate detection of the internal quality of agricultural products. This review focuses on the principles of spatially resolved spectroscopy, detection equipment, analytical methods, and specific applications in agricultural quality detection. Additionally, the optical properties methods and direct analysis methods of spatially resolved spectroscopy analysis methods are also reported in this paper.

Epidemiological Data Mining for Assisting with Foodborne Outbreak Investigation

Diseases caused by the consumption of food are a significant but avoidable public health issue, and identifying the source of contamination is a key step in an outbreak investigation to prevent foodborne illnesses. Historical foodborne outbreaks provide rich data on critical attributes such as outbreak factors, food vehicles, and etiologies, and an improved understanding of the relationships between these attributes could provide insights for developing effective food safety interventions. The purpose of this study was to identify hidden patterns underlying the relations between the critical attributes involved in historical foodborne outbreaks through data mining approaches. A statistical analysis was used to identify the associations between outbreak factors and food sources, and the factors that were strongly significant were selected as predictive factors for food vehicles. A multinomial prediction model was built based on factors selected for predicting "simple" foods (beef, dairy, and vegetables) as sources of outbreaks. In addition, the relations between the food vehicles and common etiologies were investigated through text mining approaches (support vector machines, logistic regression, random forest, and naïve Bayes). A support vector machine model was identified as the optimal model to predict etiologies from the occurrence of food vehicles. Association rules also indicated the specific food vehicles that have strong relations to the etiologies. Meanwhile, a food ingredient network describing the relationships between foods and ingredients was constructed and used with Monte Carlo simulation to predict possible ingredients from foods that cause an outbreak. The simulated results were confirmed with foods and ingredients that are already known to cause historical foodborne outbreaks. The method could provide insights into the prediction of the possible ingredient sources of contamination when given the name of a food. The results could provide insights into the early identification of food sources of contamination and assist in future outbreak investigations. The data-driven approach will provide a new perspective and strategies for discovering hidden knowledge from massive data.

Applications of optical property measurement for quality evaluation of agri-food products: a review

Spectroscopic techniques coupled with chemometric approaches have been widely used for quality evaluation of agricultural and food (agri-food) products due to the nondestructive, simple, fast, and easy characters. However, these techniques face the issues or challenges of relatively weak robustness, generalizability, and applicability in modeling and prediction because they measure the aggregate amount of light interaction with tissues, resulting in the combined effect of absorption and scattering of photons. Optical property measurement could separate absorption from scattering, providing new insights into more reliable prediction performance in quality evaluation, which is attracting increasing attention. In this review, a brief overview of the currently popular measurement techniques, in terms of light transfer principles and data analysis algorithms, is first presented. Then, the emphases are put on the recent advances of these techniques for measuring optical properties of agri-food products since 2000. Corresponding applications on qualitative and quantitative analyses of quality evaluation, as well as light transfer simulations within tissues, were reviewed. Furthermore, the leading groups working on optical property measurement worldwide are highlighted, which is the first summary to the best of our knowledge. Finally, challenges for optical property measurement are discussed, and some viewpoints on future research directions are also given.

Analysis of Light Penetration Depth in Apple Tissues by Depth-Resolved Spatial-Frequency Domain Imaging

Spatial-frequency domain imaging (SFDI) has been developed as an emerging modality for detecting early-stage bruises of fruits, such as apples, due to its unique advantage of a depth-resolved imaging feature. This paper presents theoretical and experimental analyses to determine the light penetration depth in apple tissues under spatially modulated illumination. Simulation and practical experiments were then carried out to explore the maximum light penetration depths in 'Golden Delicious' apples. Then, apple experiments for early-stage bruise detection using the estimated reduced scattering coefficient mapping were conducted to validate the results of light penetration depths. The results showed that the simulations produced comparable or a little larger light penetration depth in apple tissues (~2.2 mm) than the practical experiment (~1.8 mm or ~2.3 mm). Apple peel further decreased the light penetration depth due to the high absorption properties of pigment contents. Apple bruises located beneath the surface peel with the depth of about 0-1.2 mm could be effectively detected by the SFDI technique. This study, to our knowledge, made the first effort to investigate the light penetration depth in apple tissues by SFDI, which would provide useful information for enhanced detection of early-stage apple bruising by selecting the appropriate spatial frequency.

Real-time and accurate estimation ex vivo of four basic optical properties from thin tissue based on a cascade forward neural network

Double integrating sphere measurements obtained from thin ex vivo tissues provides more spectral information and hence allows full estimation of all basic optical properties (OPs) theoretically. However, the ill-conditioned nature of the OP determination increases excessively with the reduction in tissue thickness. Therefore, it is crucial to develop a model for thin ex vivo tissues that is robust to noise. Herein, we present a deep learning solution to precisely extract four basic OPs in real-time from thin ex vivo tissues, leveraging a dedicated cascade forward neural network (CFNN) for each OP with an additional introduced input of the refractive index of the cuvette holder. The results show that the CFNN-based model enables accurate and fast evaluation of OPs, as well as robustness to noise. Our proposed method overcomes the highly ill-conditioned restriction of OP evaluation and can distinguish the effects of slight changes in measurable quantities without any a priori knowledge.

Estimation of optical properties of turbid media using spatially resolved diffuse reflectance combined with LSTM-attention network

The accurate estimation of the optical properties of turbid media by using a spatially resolved (SR) technique remains a challenging task due to measurement errors in the acquired spatially resolved diffuse reflectance (SRDR) and challenges in inversion model implementation. In this study, what we believe to be a novel data-driven model based on a long short-term memory network and attention mechanism (LSTM-attention network) combined with SRDR is proposed for the accurate estimation of the optical properties of turbid media. The proposed LSTM-attention network divides the SRDR profile into multiple consecutive and partially overlaps sub-intervals by using the sliding window technique, and uses the divided sub-intervals as the input of the LSTM modules. It then introduces an attention mechanism to evaluate the output of each module automatically and form a score coefficient, finally obtaining an accurate estimation of the optical properties. The proposed LSTM-attention network is trained with Monte Carlo (MC) simulation data to overcome the difficulty in preparing training (reference) samples with known optical properties. Experimental results of the MC simulation data showed that the mean relative error (MRE) with 5.59% for the absorption coefficient [with the mean absolute error (MAE) of 0.04 cm^-1, coefficient of determination (R²) of 0.9982, and root mean square error (RMSE) of 0.058 cm^-1] and 1.18% for the reduced scattering coefficient (with an MAE of 0.208 cm^-1, R² of 0.9996, and RMSE of 0.237 cm^-1), which were significantly better than those of the three comparative models. The SRDR profiles of 36 liquid phantoms, collected using a hyperspectral imaging system that covered a wavelength range of 530-900 nm, were used to test the performance of the proposed model further. The results showed that the LSTM-attention model achieved the best performance (with the MRE of 14.89%, MAE of 0.022 cm^-1, R² of 0.9603, and RMSE of 0.026 cm^-1 for the absorption coefficient; and the MRE of 9.76%, MAE of 0.732 cm^-1, R² of 0.9701, and RMSE of 1.470 cm^-1for the reduced scattering coefficient). Therefore, SRDR combined with the LSTM-attention model provides an effective method for improving the estimation accuracy of the optical properties of turbid media.

Optical Property Mapping of Apples and the Relationship With Quality Properties

This paper reports on the measurement of optical property mapping of apples at the wavelengths of 460, 527, 630, and 710 nm using spatial-frequency domain imaging (SFDI) technique, for assessing the soluble solid content (SSC), firmness, and color parameters. A laboratory-based multispectral SFDI system was developed for acquiring SFDI of 140 "Golden Delicious" apples, from which absorption coefficient (μ _a ) and reduced scattering coefficient (μ _s ') mappings were quantitatively determined using the three-phase demodulation coupled with curve-fitting method. There was no noticeable spatial variation in the optical property mapping based on the resulting effect of different sizes of the region of interest (ROI) on the average optical properties. Support vector machine (SVM), multiple linear regression (MLR), and partial least square (PLS) models were developed based on μ _a , μ _s ' and their combinations (μ _a × μ _s ' and μ _eff ) for predicting apple qualities, among which SVM outperformed the best. Better prediction results for quality parameters based on the μ _a were observed than those based on the μ _s ', and the combinations further improved the prediction performance, compared to the individual μ _a or μ _s '. The best prediction models for SSC and firmness parameters [slope, flesh firmness (FF), and maximum force (Max.F)] were achieved based on the μ _a × μ _s ', whereas those for color parameters of b* and C* were based on the μ _eff , with the correlation coefficients of prediction as 0.66, 0.68, 0.73, 0.79, 0.86, and 0.86, respectively.

Tutorial on the Use of Deep Learning in Diffuse Optical Tomography

Diffuse optical tomography using deep learning is an emerging technology that has found impressive medical diagnostic applications. However, creating an optical imaging system that uses visible and near-infrared (NIR) light is not straightforward due to photon absorption and multi-scattering by tissues. The high distortion levels caused due to these effects make the image reconstruction incredibly challenging. To overcome these challenges, various techniques have been proposed in the past, with varying success. One of the most successful techniques is the application of deep learning algorithms in diffuse optical tomography. This article discusses the current state-of-the-art diffuse optical tomography systems and comprehensively reviews the deep learning algorithms used in image reconstruction. This article attempts to provide researchers with the necessary background and tools to implement deep learning methods to solve diffuse optical tomography.