Fruit maturity is a critical factor in the supply chain, consumer preference, and agriculture industry. Most classification methods on fruit maturity identify only two classes: ripe and unripe, but this paper estimates six maturity stages of papaya fruit. Deep learning architectures have gained respect and brought breakthroughs in unimodal processing. This paper suggests a novel non-destructive and multimodal classification using deep convolutional neural networks that estimate fruit maturity by feature concatenation of data acquired from two imaging modes: visible-light and hyperspectral imaging systems. Morphological changes in the sample fruits can be easily measured with RGB images, while spectral signatures that provide high sensitivity and high correlation with the internal properties of fruits can be extracted from hyperspectral images with wavelength range in between 400 nm and 900 nm—factors that must be considered when building a model. This study further modified the architectures: AlexNet, VGG16, VGG19, ResNet50, ResNeXt50, MobileNet, and MobileNetV2 to utilize multimodal data cubes composed of RGB and hyperspectral data for sensitivity analyses. These multimodal variants can achieve up to 0.90 F1 scores and 1.45% top-2 error rate for the classification of six stages. Overall, taking advantage of multimodal input coupled with powerful deep convolutional neural network models can classify fruit maturity even at refined levels of six stages. This indicates that multimodal deep learning architectures and multimodal imaging have great potential for real-time in-field fruit maturity estimation that can help estimate optimal harvest time and other in-field industrial applications.

Grading is a vital process during the postharvest of horticultural products as it dramatically affects consumer preference and satisfaction when goods reach the market. Manual grading is time-consuming, uneconomical, and potentially destructive. A non-invasive automated system for export-quality banana tiers was developed, which utilized RGB, hyperspectral imaging, and deep learning techniques. A real dataset of pre-classified banana tiers based on quality and size (Class 1 for export quality bananas, Class 2 for the local market, and Class 3 for defective fruits) was utilized using international standards. The multi-input model achieved an excellent overall accuracy of 98.45% using only a minimal number of samples compared to other methods in the literature. The model was able to incorporate both external and internal properties of the fruit. The size of the banana was used as a feature for grade classification as well as other morphological features using RGB imaging, while reflectance values that offer valuable information and have shown a high correlation with the internal features of fruits were obtained through hyperspectral imaging. This study highlighted the combined strengths of RGB and hyperspectral imaging in grading bananas, and this can serve as a paradigm for grading other horticultural crops. The fast-processing time of the multi-input model developed can be advantageous when it comes to actual farm postharvest processes.

Diabetes mellitus (DM) is a public problem closely associated with numerous oral complications, such as coated tongue, xerostomia, salivary dysfunction, etc. Tongue diagnosis plays an important role in clinical prognosis and treatment of diabetes in the traditional Chinese medicine (TCM). This study investigated discriminating tongue features to distinguish between type 2 DM and non-DM individuals through non-invasive TCM tongue diagnosis. The tongue features for 199 patients with type 2 DM, and 372 non-DM individuals, serving as control, are extracted by the automatic tongue diagnosis system (ATDS). A total of 9 tongue features, namely, tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissure, ecchymosis, teeth mark, and red dot. The demography, laboratory, physical examination, and tongue manifestation data between 2 groups were compared. Patients with type 2 DM possessed significantly larger covering area of yellow fur (58.5% vs 22.5%, P < .001), thick fur (50.8% vs 29.2%, P < .001), and bluish tongue (P < .001) than those of the control group. Also, a significantly higher portion (72.7% vs 55.2%, P < .05) of patients with long-term diabetics having yellow fur color than the short-term counterparts was observed. The high prevalence of thick fur, yellow fur color, and bluish tongue in patient with type 2 DM revealed that TCM tongue diagnosis can serve as a preliminary screening procedure in the early detection of type 2 DM in light of its simple and non-invasive nature, followed by other more accurate testing process. To the best of our knowledge, this is the first attempt in applying non-invasive TCM tongue diagnosis to the discrimination of type 2 DM patients and non-DM individuals.

Despite left ventricular (LV) dysfunction increases the risk of incidental acute ischemic stroke (AIS), the association between LV function and severity of neurological deficits after AIS remains unclear. Between November 2015 and October 1017, a total of 99 AIS patients were prospectively enrolled and categorized into two groups based on National Institute of Health Stroke Scale (NIHSS). The AIS patients with NIHSS <6 were allocated into Group 1 (n = 50) and those with NIHSS ≥6 were into Group 2 (n = 49). Echocardiography was performed within 5 days after AIS to assess chamber size, left ventricular ejection fraction (LVEF) and valvular regurgitation. Besides, two inflammatory biomarkers, neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR), were evaluated on admission. The results showed Group 2 had significantly higher value of NLR and PLR (all p-values < 0.01) but lower LVEF (p = 0.001) and frequency of mitral regurgitation (p = 0.021) than Group 1. The NIHSS and modified Rankin scale were significantly negatively correlated with LVEF, whereas both were significantly positively correlated with NLR and PLR (all p-values < 0.02). Multivariate analysis showed LVEF <65%, aging and inflammation were significantly associated with NIHSS ≥6 (all p-values < 0.01). In conclusion, the AIS patients with NIHSS ≥6 had lower LVEF but more clinically dominant mitral regurgitation and higher NLR and PLR compared to those with NIHSS <6.

This study, an important groundwork for clinical tongue diagnosis and future traditional Chinese medicine (TCM) research, tested the hypothesis that some tongue features vary significantly between different gender and age groups by utilizing an automatic tongue diagnosis system (ATDS). A cross-sectional study of 1487 participants from a community-based population was performed. Study subjects with ages ranging from 20 to 92 were categorized into 3 groups: <40, 40 to 64, and ≥65 years old, and the subjects were also stratified according to gender. Tongue images were collected at the end of each normal health examination routine to further derive the relevant tongue features of every participant by using the ATDS developed by our team. There were a total of nine tongue features that were identified: tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissure, ecchymosis, teeth mark, and red dot. The corresponding tongue features, demography, and physical/laboratory examination data were compared between different gender and age groups. Our study showed that, compared to females, males had enlarged tongue shape, thicker fur, more fissures and fewer teeth marks (all P < .001), and also had more red tongue color (P = .019), normal saliva (P = .001), more red dots (P = .005) and yellower fur (P = .014). In females, increasing age was associated with more enlarged tongue shape, thicker fur, yellower fur, more saliva, fissures and fewer teeth marks (all P < .001), more ecchymoses (P = .009), and more red tongue color (P = .023). These associations of age with more fissures, fewer teeth marks, fewer red dots (P < .001), median tongue shape (P = .029), and wet saliva (P = .014) were also evident in males, but other relationships were not clearly evident. Even though most of the common tongue features derived from a community-based population are consistent with TCM theory, yet some significantly gender- and age-dependent tongue characteristics were identified. These disparities in tongue features associated with gender or age shall be prudently taken into consideration in clinical tongue diagnosis and future TCM research.

This study tested the hypothesis that intrarenal arterial transfusion of oxidized low-density lipoprotein (ox-LDL) jeopardized the residual renal function and kidney architecture in rat chronic kidney disease ((CKD), i.e., induced by 5/6 nephrectomy) that was reversed by rosuvastatin. Cell culture was categorized into A1 (NRK-52E cells), A2 (NRK-52E + TGF-β), A3 (NRK-52E + TGF-β + ox-LDL) and A4 (NRK-52E + TGF-β + ox-LD). The result of in vitro study showed that cell viability (at 24, 48 and 72 h), NRK-52E ox-LDL-uptake, protein expressions of epithelial–mesenchymal–transition (EMT) markers (i.e., p-Smad2/snail/α-SMA/FSP1) and cell migratory and wound healing capacities were significantly progressively increased from A1 to A4 (all p < 0.001). SD rats were categorized into group 1 (sham-operated control), group 2 (CKD), group 3 (CKD + ox-LDL/0.2 mg/rat at day 14 after CKD induction) and group 4 (CKD + ox-LDL-treated as group 3+ rosuvastatin/10 mg/kg/day by days 20 to 42 after CKD induction) and kidneys were harvested at day 42. The circulatory levels of BUN and creatinine, ratio of urine-protein to urine-creatinine and the protein expressions of the above-mentioned EMT, apoptotic (cleaved-caspase3/cleaved-PARP/mitochondrial-Bax) and oxidative-stress (NOX-1/NOX-2/oxidized-protein) markers were lowest in group 1, highest in group 3 and significantly higher in group 4 than in group 2 (all p < 0.0001). Histopathological findings demonstrated that the kidney injury score, fibrotic area and kidney injury molecule-1 (KIM-1) displayed an identical pattern, whereas the cellular expression of podocyte components (ZO-1/synaptopodin) exhibited an opposite pattern of EMT markers (all p < 0.0001). In conclusion, ox-LDL damaged the residual renal function and kidney ultrastructure in CKD mainly through augmenting oxidative stress, EMT and fibrosis that was remarkably reversed by rosuvastatin.