A Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy.

Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.

Rapid Assessment of Fish Freshness for Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy and Fusion-Based Artificial Intelligence.

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.

Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses.

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

FootAssure: A multimodal, in-home wound detection device for diabetic peripheral neuropathy.

Currently, there is no single technology capable of assessing all the multitude of factors associated with peripheral complications of diabetic neuropathy. In this work, a multimodal wound detection system is proposed to help facilitate in-home examinations, utilizing a combination of thermal, multi-spectral 3D imaging modalities. The proposed system is capable of the 3D surface rendering of the foot and would overlay thermal, blood oxygenation, besides other skin health information to aid with foot health monitoring. Examples of biomarkers include pre-ulcer formation, blood circulation, temperature change, oxygenation, swelling, blisters/ulcer formation and healing, and toe health.

Handheld Multispectral Fluorescence Imaging System to Detect and Disinfect Surface Contamination.

Contamination inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle food. Food contamination must be prevented, and zero tolerance legal requirements and damage to the reputation of institutions or restaurants can be very costly. This paper introduces a new handheld fluorescence-based imaging system that can rapidly detect, disinfect, and document invisible organic residues and biofilms which may host pathogens. The contamination, sanitization inspection, and disinfection (CSI-D) system uses light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm, for the detection of organic residues, including saliva and respiratory droplets. The 275 nm light is also utilized to disinfect pathogens commonly found within the contaminated residues. Efficacy testing of the neutralizing effects of the ultraviolet light was conducted for Aspergillus fumigatus, Streptococcus pneumoniae, and the influenza A virus (a fungus, a bacterium, and a virus, respectively, each commonly found in saliva and respiratory droplets). After the exposure to UVC light from the CSI-D, all three pathogens experienced deactivation (> 99.99%) in under ten seconds. Up to five-log reductions have also been shown within 10 s of UVC irradiation from the CSI-D system.

Review of the potential of optical technologies for cancer diagnosis in neurosurgery: a step toward intraoperative neurophotonics.

Advances in image-guided therapy enable physicians to obtain real-time information on neurological disorders such as brain tumors to improve resection accuracy. Image guidance data include the location, size, shape, type, and extent of tumors. Recent technological advances in neurophotonic engineering have enabled the development of techniques for minimally invasive neurosurgery. Incorporation of these methods in intraoperative imaging decreases surgical procedure time and allows neurosurgeons to find remaining or hidden tumor or epileptic lesions. This facilitates more complete resection and improved topology information for postsurgical therapy (i.e., radiation). We review the clinical application of recent advances in neurophotonic technologies including Raman spectroscopy, thermal imaging, optical coherence tomography, and fluorescence spectroscopy, highlighting the importance of these technologies in live intraoperative tissue mapping during neurosurgery. While these technologies need further validation in larger clinical trials, they show remarkable promise in their ability to help surgeons to better visualize the areas of abnormality and enable safe and successful removal of malignancies.

Separating melanin from hemodynamics in nevi using multimode hyperspectral dermoscopy and spatial frequency domain spectroscopy.

Changes in the pattern and distribution of both melanocytes (pigment producing) and vasculature (hemoglobin containing) are important in distinguishing melanocytic proliferations. The ability to accurately measure melanin distribution at different depths and to distinguish it from hemoglobin is clearly important when assessing pigmented lesions (benign versus malignant). We have developed a multimode hyperspectral dermoscope (SkinSpect™) able to more accurately image both melanin and hemoglobin distribution in skin. SkinSpect uses both hyperspectral and polarization-sensitive measurements. SkinSpect's higher accuracy has been obtained by correcting for the effect of melanin absorption on hemoglobin absorption in measurements of melanocytic nevi. In vivo human skin pigmented nevi (N=20) were evaluated with the SkinSpect, and measured melanin and hemoglobin concentrations were compared with spatial frequency domain spectroscopy (SFDS) measurements. We confirm that both systems show low correlation of hemoglobin concentrations with regions containing different melanin concentrations (R=0.13 for SFDS, R=0.07 for SkinSpect).

Polarization-sensitive hyperspectral imaging in vivo: a multimode dermoscope for skin analysis.

Attempts to understand the changes in the structure and physiology of human skin abnormalities by non-invasive optical imaging are aided by spectroscopic methods that quantify, at the molecular level, variations in tissue oxygenation and melanin distribution. However, current commercial and research systems to map hemoglobin and melanin do not correlate well with pathology for pigmented lesions or darker skin. We developed a multimode dermoscope that combines polarization and hyperspectral imaging with an efficient analytical model to map the distribution of specific skin bio-molecules. This corrects for the melanin-hemoglobin misestimation common to other systems, without resorting to complex and computationally intensive tissue optical models. For this system's proof of concept, human skin measurements on melanocytic nevus, vitiligo, and venous occlusion conditions were performed in volunteers. The resulting molecular distribution maps matched physiological and anatomical expectations, confirming a technologic approach that can be applied to next generation dermoscopes and having biological plausibility that is likely to appeal to dermatologists.

Calibration standards for multicenter clinical trials of fluorescence spectroscopy for in vivo diagnosis.

In the context of clinical trials, calibration protocols for optical instruments that ensure measurement accuracy and the ability to carry out meaningful comparisons of data acquired from multiple instruments are required. A series of calibration standards and procedures are presented to assess technical feasibility of optical devices for cervical precancer detection. Measurements of positive and negative standards, and tissue are made with two generations of research grade spectrometers. Calibration accuracy, ability of standards to correct and account for changes in experimental conditions, and device components are analyzed. The relative frequency of measured calibration standards is investigated retrospectively using statistical analysis of trends in instrument performance. Fluorescence measurements of standards and tissue made with completely different spectrometers show good agreement in intensity and lineshape. Frequency of wavelength calibration standards is increased to every 2 h to compensate for thermal drifts in grating mount. Variations in illumination energy detected between standards and patient measurements require probe redesign to allow for simultaneous acquisition of illumination power with every patient measurement. The use of frequent and well-characterized standards enables meaningful comparison of data from multiple devices and unambiguous interpretation of experiments among the biomedical optics community.

Spectrally programmable light engine for in vitro or in vivo molecular imaging and spectroscopy.

A spectrally and temporally programmable light engine can create any spectral profile for hyperspectral, fluorescence, or principal-component imaging or with medical photonics devices employing spectroscopy, microscopy, and endoscopy. Multispectral imaging feasibility was demonstrated by capturing nine images at wavelengths from 450 to 650 mm (25-nm FWHM) with a CCD-camera-equipped bronchoscope coupled to the light engine. Selected wavelength regions were combined to produce a color endoscopy image.