In the current work, the characterization of novel chitosan/silica nanoparticle/nisin films with the addition of nisin as an antimicrobial technique for blueberry preservation during storage is investigated. Chitosan/Silica Nanoparticle/N (CH-SN-N) films presented a stable suspension as the surface loads (45.9 mV) and the distribution was considered broad (0.62). The result shows that the pH value was increased gradually with the addition of nisin to 4.12, while the turbidity was the highest at 0.39. The content of the insoluble matter and contact angle were the highest for the Chitosan/Silica Nanoparticle (CH-SN) film at 5.68%. The use of nano-materials in chitosan films decreased the material ductility, reduced the tensile strength and elongation-at-break of the membrane. The coated blueberries with Chitosan/Silica Nanoparticle/N films reported the lowest microbial contamination counts at 2.82 log CFU/g followed by Chitosan/Silica Nanoparticle at 3.73 and 3.58 log CFU/g for the aerobic bacteria, molds, and yeasts population, respectively. It was observed that (CH) film extracted 94 regions with an average size of 449.10, at the same time (CH-SN) film extracted 169 regions with an average size of 130.53. The (CH-SN-N) film presented the best result at 5.19%. It could be observed that the size of the total region of the fruit for the (CH) case was the smallest (1663 pixels), which implied that the fruit lost moisture content. As a conclusion, (CH-SN-N) film is recommended for blueberry preservation to prolong the shelf-life during storage.

No abstract

Current cancer diagnosis procedure requires expert knowledge and is time-consuming, which raises the need to build an accurate diagnosis support system for lymphoma identification and classification. Many studies have shown promising results using Machine Learning and, recently, Deep Learning to detect malignancy in cancer cells. However, the diversity and complexity of the morphological structure of lymphoma make it a challenging classification problem. In literature, many attempts were made to classify up to four simple types of lymphoma. This paper presents an approach using a reliable model capable of diagnosing seven different categories of rare and aggressive lymphoma. These Lymphoma types are Classical Hodgkin Lymphoma, Nodular Lymphoma Predominant, Burkitt Lymphoma, Follicular Lymphoma, Mantle Lymphoma, Large B-Cell Lymphoma, and T-Cell Lymphoma. Our proposed approach uses Residual Neural Networks, ResNet50, with a Transfer Learning for lymphoma's detection and classification. The model used results are validated according to the performance evaluation metrics: Accuracy, precision, recall, F-score, and kappa score for the seven multi-classes. Our algorithms are tested, and the results are validated on 323 images of 224 × 224 pixels resolution. The results are promising and show that our used model can classify and predict the correct lymphoma subtype with an accuracy of 91.6%.

No abstract

No abstract