A reasonable and balanced diet is essential for maintaining good health. With advancements in deep learning, an automated nutrition estimation method based on food images offers a promising solution for monitoring daily nutritional intake and promoting dietary health. While monocular image-based nutrition estimation is convenient, efficient and economical, the challenge of limited accuracy remains a significant concern. To tackle this issue, we proposed DPF-Nutrition, an end-to-end nutrition estimation method using monocular images. In DPF-Nutrition, we introduced a depth prediction module to generate depth maps, thereby improving the accuracy of food portion estimation. Additionally, we designed an RGB-D fusion module that combined monocular images with the predicted depth information, resulting in better performance for nutrition estimation. To the best of our knowledge, this was the pioneering effort that integrated depth prediction and RGB-D fusion techniques in food nutrition estimation. Comprehensive experiments performed on Nutrition5k evaluated the effectiveness and efficiency of DPF-Nutrition.

This study investigated the effects of ultrasound treatment on the quality of salted Culter alburnus fish. The results showed that with the increasing ultrasound power, the structural degradation of muscle fibers was intensified, and the conformation of myofibrillar protein was significantly changed. The high-power ultrasound treatment group (300 W) had relatively higher thiobarbiturate reactive substance content (0.37 mg malondialdehyde eq/kg) and peroxidation value (0.63 mmol/kg). A total of 66 volatile compounds were identified with obvious differences among groups. The 200 W ultrasound group exhibited fewer fishy substances (Hexanal, 1-Pentene-3-ol, and 1-Octane-3-ol). Compared with control group, ultrasound groups (200, 300 W) contained more umami taste-related amino peptides such as γ-Glu-Met, γ-Glu-Ala, and Asn-pro. In the ultrasound treatment group, L-isoleucine and L-methionine, which may be used as flavor precursors, were significantly down-regulated, while carbohydrates and its metabolites were up-regulated. Amino acid, carbohydrate, and FA (fatty acyls) metabolism products in salted fish were enriched by ultrasound treatment, and those products might ultimately be related to the taste and flavor of salted fish.

Tilapia (Oreochromis mossambicus) skin high value-added compounds have not been fully utilized in tilapia processing. Here, the protective effects of tilapia skin peptides (TSP) on primary ovarian failure (POF) and their underlying mechanisms in mice were investigated. Cyclophosphamide (CP) was injected intraperitoneally (ip) for 14 days (10 mg kg⁻¹ d⁻¹) to establish a mouse model of POF. At the same time, the mice were given intragastrically (ig) TSP for 30 days (250 mg kg⁻¹ d⁻¹, 500 mg kg⁻¹ d⁻¹, and 1000 mg kg⁻¹ d⁻¹, respectively). The ovarian index, estrous cycle, hormone level, changes in the number of follicles at various levels, and biochemical tests were carried out at the end of the experiment. The body weight and ovarian index of mice in the POF group were markedly lower than that of the control group. Treatment with TSP reversed these changes significantly. TSP administration significantly restored the estrous cycle disorder of the mice versus that of the POF group. The level changes of progesterone (P), estradiol (E2), follicle-stimulating hormone (FSH), and luteinizing hormone (LH) induced by CP were significantly reversed by TSP treatment. TSP inhibited oxidative stress in CP-induced mice by enhancing the total superoxide dismutase (T-SOD) activity and reducing malondialdehyde (MDA) levels in the ovaries. TSP improved the apoptosis of ovarian granulosa cells in CP-induced mice compared with the POF group. Furthermore, TSP regulated the Bcl-2/Bax/caspase-3 apoptosis pathway and enhanced the Nrf2/HO-1 signaling pathway. In conclusion, TSP could improve CP-induced POF via alleviating ovarian oxidative stress and granulosa cell apoptosis.

This present work investigated the influence of konjac glucomannan (KGM) enzymatic hydrolysates on the textural properties, microstructure, and water distribution of surimi gel from grass carp (Ctenopharyngodon idellus). The molecular weight (M_w) of KGM enzymatic hydrolyzed by β-dextranase degraded from 149.03 kDa to 36.84 kDa with increasing enzymatic time. In the microstructure of surimi gels, KGM enzymatic hydrolysates with higher M_w showed entangled rigid-chains, while KGM enzymatic hydrolysates with lower M_w (36.84 kDa) exhibited swelled fragments. The hardness of surimi gel with a decline in KGM M_w exhibited first increasing then decreasing trends, while the whiteness of surimi gel increased. When KGM M_w decreased, the immobile water percentage of total signals decreased from 96.7% to 93.6%, and mobile water increased from 3.03% to 6.37%. In particular, the surimi gel with the addition of K2 showed better gel strength and water distributions. KGM enzymatic hydrolysates are expected to be used as a low-calorie healthy gel enhancer in surimi processing.