Construction of multi-scale feature fusion segmentation model of MRI knee images based on dual attention mechanism weighted aggregation.

BACKGROUND: Early diagnosis of knee osteoarthritis is an important area of research in the field of clinical medicine. Due to the complexity in the MRI imaging sequences and the diverse structure of cartilage, there are many challenges in the segmentation of knee bone and cartilage. Relevant studies have conducted semantic fusion processing through splicing or summing forms, which results in reduced resolution and the accumulation of redundant information. OBJECTIVE: This study was envisaged to construct an MRI image segmentation model to improve the diagnostic efficiency and accuracy of different grade knee osteoarthritis by adopting the Dual Attention and Multi-scale Feature Fusion Segmentation network (DA-MFFSnet). METHODS: The feature information of different scales was fused through the Multi-scale Attention Downsample module to extract more accurate feature information, and the Global Attention Upsample module weighted lower-level feature information to reduce the loss of key information. RESULTS: The collected MRI knee images were screened and labeled, and the study results showed that the segmentation effect of DA-MFFSNet model was closer to that of the manually labeled images. The mean intersection over union, the dice similarity coefficient and the volumetric overlap error was 92.74%, 91.08% and 7.44%, respectively, and the accuracy of the differential diagnosis of knee osteoarthritis was 84.42%. CONCLUSIONS: The model exhibited better stability and classification effect. Our results indicated that the Dual Attention and Multi-scale Feature Fusion Segmentation model can improve the segmentation effect of MRI knee images in mild and medium knee osteoarthritis, thereby offering an important clinical value and improving the accuracy of the clinical diagnosis.

Effect of plasmin on casein hydrolysis and textural properties of rennet-induced model cheeses.

Plasmin plays an important role in casein hydrolysis during cheese ripening, which may influence the properties of the casein network and the texture of the final product. In view of this, the relation between plasmin-induced casein hydrolysis and textural changes of cheese during ripening was investigated in this study. Four batches of model cheese with different concentrations of added plasmin (0, 0.4, 0.6 and 1.0 µL/g milk) were prepared, and were stored for 12 weeks at 16 °C. During this period, plasmin activity, casein hydrolysis, textural properties and other compositional characteristics (pH, dry matter) were determined. Our results show that the addition of plasmin had significant effect on both the degree and the pattern of proteolysis. As a result, cheeses with different plasmin content showed different textural properties. With increased plasmin concentration, Young's modulus, hardness, resilience and cohesion decreased, while brittleness increased. All textural properties showed linear relations with the degree of casein hydrolysis, and logarithmic relations with the percentage of intact casein fractions. At the beginning of ripening, only slight changes in textural properties were found, although a substantial part (40-60 %) of the casein fractions was already been broken down. When ripening progressed, ongoing proteolysis significantly weakened the protein network and consequently led to noticeable textural changes. Model cheeses became softer, more brittle and less elastic. The knowledge gained from this study provide new insights in the changes of different textural parameters of model cheese. This will help to optimize the existing products and create new ones.

[Value of diffusion-weighted MRI in differentiation between benign and malignant polypoid gallbladder lesions].

OBJECTIVE: To evaluate the efficiency of diffusion-weighted MRI in differentiating between benign and malignant polypoid gallbladder lesions. METHODS: The study population consisted of 10 benign (5 polyps, 3 adenomyomatosis and 2 adenomas) and 13 malignant (all adenocarcinomas) polypoid gallbladder lesions treated in hospital from November 2007 to May 2014. DWI was evaluated by two observers. Qualitatively, the signal intensity of the lesions on DWI was visually evaluated and categorized as iso, high, or very high signal.Quantitatively, the ADC values of the lesions were measured from ADC maps. Statistical analysis was performed using a two-tailed Fisher's exact test and the Mann-Whitney test, respectively. The cut-off values were determined by receiver operating characteristic analysis. RESULTS: Qualitative analysis revealed a statistical difference (P=0.036). In the 10 benign lesions, three were categorized as iso, 5 as high, and 2 as very high signal.Four of the 13 malignant lesions were categorized as high, and the remaining 9 were categorized as very high signal. The mean ADC value of the malignant lesions [(1.13±0.28)×10(-3) mm2/s] was significantly lower than that of benign lesions [(2.22±0.42)×10(-3) mm2/s, P<0.01]. The cut-off value between cancer and the benign lesions was 1.5×10(-3) mm2/s, the sensitivity, specificity, and accuracy were 92%, 100% and 96%, respectively. CONCLUSION: Diffusion-weighted MRI may be useful in differentiating between benign and malignant polypoid gallbladder lesions.