Search

Brain tumors are one of the leading diseases imposing a huge morbidity rate across the world every year. Classifying brain tumors accurately plays a crucial role in clinical diagnosis and improves the overall healthcare process. ML techniques have shown promise in accurately classifying brain tumors based on medical imaging data such as MRI scans. These techniques aid in detecting and planning treatment early, improving patient outcomes. However, medical image datasets are frequently affected by a significant class imbalance, especially when benign tumors outnumber malignant tumors in number. This study presents an explainable ensemble-based pipeline for brain tumor classification that integrates a Dual-GAN mechanism with feature extraction techniques, specifically designed for highly imbalanced data. This Dual-GAN mechanism facilitates the generation of synthetic minority class samples, addressing the class imbalance issue without compromising the original quality of the data. Additionally, the integration of different feature extraction methods facilitates capturing precise and informative features. This study proposes a novel deep ensemble feature extraction (DeepEFE) framework that surpasses other benchmark ML and deep learning models with an accuracy of 98.15%. This study focuses on achieving high classification accuracy while prioritizing stable performance. By incorporating Grad-CAM, it enhances the transparency and interpretability of the overall classification process. This research identifies the most relevant and contributing parts of the input images toward accurate outcomes enhancing the reliability of the proposed pipeline. The significantly improved Precision, Sensitivity and F1-Score demonstrate the effectiveness of the proposed mechanism in handling class imbalance and improving the overall accuracy. Furthermore, the integration of explainability enhances the transparency of the classification process to establish a reliable model for brain tumor classification, encouraging their adoption in clinical practice promoting trust in decision-making processes. [ABSTRACT FROM AUTHOR]

Fermentation of pulses as a clean processing technique has been reported to have a favorable impact on the functional and nutritional quality of the starting materials. Compared to commonly fermented pulses such as peas and chickpeas, limited information is available on the effect of fermentation on lentils, especially when using a high protein isolate (>80% protein) as compared to seeds or flours. Therefore, in the present work, lentil protein isolate was used as a feedstock for submerged fermentation with Aspergillus niger, Aspergillus oryzae, or Lactobacillus plantarum. After 48 h, the samples showed increased protein content with enhanced solubility and oil‐holding capacity. Controlled fermentation, as opposed to spontaneous fermentation, maintained the high foaming capacity; however, all fermented samples had lower foam and emulsion stabilizing properties and reduced water‐holding capacity compared to the control. The fermented proteins were also less digestible, possibly due to an increase in phenolics and saponins. New volatile compounds were identified in fermented samples that show promise for improved sensory attributes. Significant differences were observed in specific quality attributes depending on the microbial strain used. Further research is required to better understand the fermentative metabolism of microbial communities when provided high‐protein lentil ingredients as growth substrates. Practical Application: Fermented lentil protein isolate has promising flavor profiles that may improve its sensory properties for food application. [ABSTRACT FROM AUTHOR]

The integration of Multi-Objective Optimization (MOO) and Multi-Criteria Decision-Making (MCDM) has gathered significant attention across various scientific research domains to facilitate integrated sustainability assessment. Recently, there has been a growing interest in hybrid approaches that combine MCDM with MOO, aiming to enhance the efficacy of the final decisions. However, a critical gap exists in terms of providing clear methodological guidance, particularly when dealing with data uncertainties. To address this gap, this systematic review is designed to develop a generic decision tree that serves as a practical roadmap for practitioners seeking to perform MOO and MCDM in an integrated fashion, with a specific focus on accounting for uncertainties. The systematic review identified the recent studies that conducted both MOO and MCDM in an integrated way. It is important to note that this review does not aim to identify the superior MOO or MCDM methods, but rather it delves into the strategies for integrating these two common methodologies. The prevalent MOO methods used in the reviewed articles were evolution-based metaheuristic methods. TOPSIS and PROMETHEE II are the prevalent MCDM ranking methods. The integration of MOO and MCDM methods can occur either a priori, a posteriori, or through a combination of both, each offering distinct advantages and drawbacks. The developed decision tree illustrated all three paths and integrated uncertainty considerations in each path. Finally, a real-world case study for the pulse fractionation process in Canada is used as a basis for demonstrating the various pathways presented in the decision tree and their application in identifying the optimized processing pathways for sustainably obtaining pulse protein. This study will help practitioners in different research domains use MOO and MCDM methods in an integrated way to identify the most sustainable and optimized system. [ABSTRACT FROM AUTHOR]

Background and Objectives: Fermentation has been increasingly used as a "clean" processing technique to modify proteins. The goal of this research was to assess the use of solid‐state fermentation (SSF) by Aspergillus oryzae on pea (pea protein isolate [PPI]) and navy bean protein isolates (NBPI) for different time periods (0–48 or 0−72 h, respectively) and its impact on their nutrition and volatile profile. Findings: The SSF process resulted in higher total phenolic content and lower protein digestibility, and consequently, the protein quality was reduced for both pulses. The quantity of the volatile compounds initially present in the samples did not change substantially after SSF; however, many new compounds were identified in fermented PPI, which have been reported to have pleasant sensory properties. Conclusions: The protein quality of PPI or NBPI was not improved by A. oryzae SSF; however, the results suggest the potential for using SSF to positively modify the volatile profile of PPI. Significance and Novelty: The findings of this research strengthened our knowledge base of fermented pulse ingredients with the use of protein isolates and navy beans, narrowing the somewhat limited gap for fermentation application to high protein substrates. [ABSTRACT FROM AUTHOR]

Dry pea (Pisum sativum) seeds are valuable sources of plant protein, dietary fiber, and starch, but their uses in food products are restricted to some extent due to several off‐flavor compounds. Saponins are glycosylated triterpenoids and are a major source of bitter, astringent, and metallic off‐flavors in pea products. β‐amyrin synthase (BAS) is the entry point enzyme for saponin biosynthesis in pea and therefore is an ideal target for knock‐out using CRISPR/Cas9 genome editing to produce saponin deficient pea varieties. Here, in an elite yellow pea cultivar (CDC Inca), LC/MS analysis identified embryo tissue, not seed coat, as the main location of saponin storage in pea seeds. Differential expression analysis determined that PsBAS1 was preferentially expressed in embryo tissue relative to seed coat and was selected for CRISPR/Cas9 genome editing. The efficiency of CRISPR/Cas9 genome editing of PsBAS1 was systematically optimized in pea hairy roots. From these optimization procedures, the AtU6‐26 promoter was found to be superior to the CaMV35S promoter for gRNA expression, and the use of 37°C was determined to increase the efficiency of CRISPR/Cas9 genome editing. These promoter and culture conditions were then applied to stable transformations. As a result, a bi‐allelic mutation (deletion and inversion mutations) was generated in the PsBAS1 coding sequence in a T1 plant, and the segregated psbas1 plants from the T2 population showed a 99.8% reduction of saponins in their seeds. Interestingly, a small but statistically significant increase (~12%) in protein content with a slight decrease (~5%) in starch content was observed in the psbas1 mutants under phytotron growth conditions. This work demonstrated that flavor‐improved traits can be readily introduced in any pea cultivar of interest using CRISPR/Cas9. Further field trials and sensory tests for improved flavor are necessary to assess the practical implications of the saponin‐free pea seeds in food applications. [ABSTRACT FROM AUTHOR]

Yellow field peas (Pisum sativum L.) hold significant value for producers, researchers, and ingredient manufacturers due to their wealthy composition of protein, starch, and micronutrients. The protein quality in peas is influenced by both intrinsic factors like amino acid composition and spatial conformations and extrinsic factors including growth and processing conditions. The existing literature substantiates that the structural modulation and optimization of functional, organoleptic, and nutritional attributes of pea proteins can be obtained through a combination of chemical, physical, and enzymatic approaches, resulting in superior protein ingredients. This review underscores recent methodologies in pea protein extraction aimed at enhancing yield and functionality for diverse food systems and also delineates existing research gaps related to mitigating off-flavor issues in pea proteins. A comprehensive examination of conventional dry and wet methods is provided, in conjunction with environmentally friendly approaches like ultrafiltration and enzyme-assisted techniques. Additionally, the innovative application of hydrodynamic cavitation technology in protein extraction is explored, focusing on its prospective role in flavor amelioration. This overview offers a nuanced understanding of the advancements in pea protein extraction methods, catering to the interests of varied stakeholders in the field. [ABSTRACT FROM AUTHOR]