METHODS: In our paper, we propose a real-time, lightweight liver segmentation model named G-MBRMD. Specifically, we employ a Transformer-based complex model as the teacher and a convolution-based lightweight model as the student. By introducing proposed multi-head mapping and boundary reconstruction strategies during the knowledge distillation process, Our method effectively guides the student model to gradually comprehend and master the global boundary processing capabilities of the complex teacher model, significantly enhancing the student model's segmentation performance without adding any computational complexity.
RESULTS: On the LITS dataset, we conducted rigorous comparative and ablation experiments, four key metrics were used for evaluation, including model size, inference speed, Dice coefficient, and HD95. Compared to other methods, our proposed model achieved an average Dice coefficient of 90.14±16.78%, with only 0.6 MB memory and 0.095 s inference speed for a single image on a standard CPU. Importantly, this approach improved the average Dice coefficient of the baseline student model by 1.64% without increasing computational complexity.
CONCLUSION: The results demonstrate that our method successfully realizes the unification of segmentation precision and lightness, and greatly enhances its potential for widespread application in practical settings.
METHODS: We carried out a systematic search of all available RCTs up to June 2019 in the following electronic databases: PubMed, Scopus, Web of Science and Google Scholar. Pooled weight mean difference (WMD) of the included studies was estimated using random-effects model.
RESULTS: A total of 27 articles were included in this meta-analysis, with walnuts dosage ranging from 15 to 108 g/d for 2 wk to 2 y. Overall, interventions with walnut intake did not alter waist circumference (WC) (WMD: -0.193 cm, 95 % CI: -1.03, 0.64, p = 0.651), body weight (BW) (0.083 kg, 95 % CI: -0.032, 0.198, p = 0.159), body mass index (BMI) (WMD: -0.40 kg/m,295 % CI: -0.244, 0.164, p = 0.703), and fat mass (FM) (WMD: 0.28 %, 95 % CI: -0.49, 1.06, p = 0.476). Following dose-response evaluation, reduced BW (Coef.= -1.62, p = 0.001), BMI (Coef.= -1.24, p = 0.041) and WC (Coef.= -5.39, p = 0.038) were significantly observed through walnut intake up to 35 g/day. However, the number of studies can be limited as to the individual analysis of the measures through the dose-response fashion.
CONCLUSIONS: Overall, results from this meta-analysis suggest that interventions with walnut intake does not alter BW, BMI, FM, and WC. To date, there is no discernible evidence to support walnut intake for improving anthropometric indicators of weight loss.