Biocellulose (BC) is pure extracellular cellulose produced by several species of micro-organisms that has numerous applications in the food, biomedical and paper industries. However, the existing biocellulose-producing bacterial strain with high yield was limited. The aim of this study was to isolate and identify the potential biocellulose-producing bacterial isolates from Malaysian acidic fruits. One hundred and ninety-three bacterial isolates were obtained from 19 local acidic fruits collected in Malaysia and screened for their ability to produce BC. A total of 15 potential bacterial isolates were then cultured in standard Hestrin-Schramm (HS) medium statically at 30°C for 2 weeks to determine the BC production. The most potent bacterial isolates were identified using 16S rRNA gene sequence analysis, morphological and biochemical characteristics. Three new and potent biocellulose-producing bacterial strains were isolated from soursop fruit and identified as Stenotrophomonas maltophilia WAUPM42, Pantoea vagans WAUPM45 and Beijerinckia fluminensis WAUPM53. Stenotrophomonas maltophilia WAUPM42 was the most potent biocellulose-producing bacterial strain that produced the highest amount of BC 0·58 g l(-1) in standard HS medium. Whereas, the isolates P. vagans WAUPM45 and B. fluminensis WAUPM53 showed 0·50 and 0·52 g l(-1) of BC production, respectively.
Bio-cellulose is the microbial extracellular cellulose that is produced by growing several microorganisms on agriculture by-products, and it is used in several food applications. This study aims to utilize sago by-product, coconut water, and the standard medium Hestrin-Schramm as the carbon sources in the culture medium for bio-cellulose production. The bacteria Beijerinkia fluminensis WAUPM53 and Gluconacetobacter xylinus 0416 were selected based on their bio-cellulose production activity. The structure was determined by Fourier transform infrared spectroscopy and scanning electron microscopy, while the toxicity safety was evaluated by brine shrimp lethality test. The results of Fourier transform infrared spectroscopy showed that the bio-cellulose produced by B. fluminensis cultivated in sago by-products was of high quality. The bio-cellulose production by B. fluminensis in the sago by-product medium was slightly higher than that in the coconut water medium and was comparable with the production in the Hestrin-Schramm medium. Brine shrimp lethality test confirmed that the bio-cellulose produced by B. fluminensis in the sago by-product medium has no toxicity, which is safe for applications in the food industry. This is the first study to determine the high potential of sago by-product to be used as a new carbon source for the bio-cellulose production.
Debates persist regarding the impact of Stain Normalization (SN) on recent breast cancer histopathological studies. While some studies propose no influence on classification outcomes, others argue for improvement. This study aims to assess the efficacy of SN in breast cancer histopathological classification, specifically focusing on Invasive Ductal Carcinoma (IDC) grading using Convolutional Neural Networks (CNNs). The null hypothesis asserts that SN has no effect on the accuracy of CNN-based IDC grading, while the alternative hypothesis suggests the contrary. We evaluated six SN techniques, with five templates selected as target images for the conventional SN techniques. We also utilized seven ImageNet pre-trained CNNs for IDC grading. The performance of models trained with and without SN was compared to discern the influence of SN on classification outcomes. The analysis unveiled a p-value of 0.11, indicating no statistically significant difference in Balanced Accuracy Scores between models trained with StainGAN-normalized images, achieving a score of 0.9196 (the best-performing SN technique), and models trained with non-normalized images, which scored 0.9308. As a result, we did not reject the null hypothesis, indicating that we found no evidence to support a significant discrepancy in effectiveness between stain-normalized and non-normalized datasets for IDC grading tasks. This study demonstrates that SN has a limited impact on IDC grading, challenging the assumption of performance enhancement through SN.
Computer-aided Invasive Ductal Carcinoma (IDC) grading classification systems based on deep learning have shown that deep learning may achieve reliable accuracy in IDC grade classification using histopathology images. However, there is a dearth of comprehensive performance comparisons of Convolutional Neural Network (CNN) designs on IDC in the literature. As such, we would like to conduct a comparison analysis of the performance of seven selected CNN models: EfficientNetB0, EfficientNetV2B0, EfficientNetV2B0-21k, ResNetV1-50, ResNetV2-50, MobileNetV1, and MobileNetV2 with transfer learning. To implement each pre-trained CNN architecture, we deployed the corresponded feature vector available from the TensorFlowHub, integrating it with dropout and dense layers to form a complete CNN model. Our findings indicated that the EfficientNetV2B0-21k (0.72B Floating-Point Operations and 7.1 M parameters) outperformed other CNN models in the IDC grading task. Nevertheless, we discovered that practically all selected CNN models perform well in the IDC grading task, with an average balanced accuracy of 0.936 ± 0.0189 on the cross-validation set and 0.9308 ± 0.0211on the test set.