Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification.

Multiple instance learning (MIL) based whole slide image (WSI) classification is often carried out on the representations of patches extracted from WSI with a pre-trained patch encoder. The performance of classification relies on both patch-level representation learning and MIL classifier training. Most MIL methods utilize a frozen model pre-trained on ImageNet or a model trained with self-supervised learning on histopathology image dataset to extract patch image representations and then fix these representations in the training of the MIL classifiers for efficiency consideration. However, the invariance of representations cannot meet the diversity requirement for training a robust MIL classifier, which has significantly limited the performance of the WSI classification. In this paper, we propose a Self-Supervised Representation Distribution Learning framework (SSRDL) for patch-level representation learning with an online representation sampling strategy (ORS) for both patch feature extraction and WSI-level data augmentation. The proposed method was evaluated on three datasets under three MIL frameworks. The experimental results have demonstrated that the proposed method achieves the best performance in histopathology image representation learning and data augmentation and outperforms state-of-the-art methods under different WSI classification frameworks. The code is available at https://github.com/lazytkm/SSRDL.

Soybean protein isolate-sodium alginate double network emulsion gels: Mechanism of formation and improved freeze-thaw stability.

Soybean protein isolate (SPI) is widely used in the food industry. However, SPI-based emulsion gels tend to aggregate and undergo oiling-off during freeze-thawing. In this study, emulsion gels were prepared by a combination of heat treatment and ionic cross-linking using SPI and sodium alginate (SA) as raw materials. The focus was on exploring the mechanistic effects of the SPI-SA double network structure on the freeze-thaw stability of emulsion gels. The results showed that the addition of SA could form different types of network structures with SPI, due to different degrees of phase separation. In addition, SA appearing on the SPI network indicated that the addition of Ca2+ shielded the electrostatic repulsion between SPI and SA to form SPI-SA complexes. The disappearance of the characteristic peaks of SA and SPI in Fourier transform infrared spectroscopy analysis also confirmed this view. Low-field nuclear magnetic resonance data revealed that SA played a role in restricting water migration within the emulsion gels, increasing bound water content, and thereby improving the water-holding capacity of the emulsion gels. Therefore, the incorporation of SA improved the freeze-thaw stability of SPI emulsion gels. These findings offer a theoretical basis and technical support for SPI application in frozen products.

Deciphering the interaction mechanism between soy protein isolate and fat-soluble anthocyanin on experiments and molecular simulations.

In this work, the acylated anthocyanin (Ca-An) was prepared by enzymatic modification of black rice anthocyanin with caffeic acid, and the binding mechanism of Ca-An to soybean protein isolate (SPI) was investigated by experiments and computer simulation to expand the potential application of anthocyanin in food industry. Multi-spectroscopic studies revealed that the stable binding of Ca-An to SPI induced the folding of protein polypeptide chain, which transformed the secondary structure of SPI trended to be flexible. The microenvironment of protein was transformed from hydrophobic to hydrophilic, while tyrosine played dominant role in quenching process. The binding sites and forces of the complexes were determined by computer simulation for further explored. The protein conformation of the 7S and 11S binding regions to Ca-An changed, and the amino acid microenvironment shifted to hydrophilic after binding. The results showed that more non-polar amino acids existed in the binding sites, while in binding process van der Waals forces and hydrogen bonding played a major role hydrophobicity played a minor role. Based on MM-PBSA analysis, the binding constants of 7S-Ca-An and 11S-Ca-An were 0.518 × 106 mol-1 and 5.437 × 10-3 mol-1, respectively. This information provides theoretical guidance for further studying the interaction between modified anthocyanins and biomacromolecules.

Histopathology language-image representation learning for fine-grained digital pathology cross-modal retrieval.

Large-scale digital whole slide image (WSI) datasets analysis have gained significant attention in computer-aided cancer diagnosis. Content-based histopathological image retrieval (CBHIR) is a technique that searches a large database for data samples matching input objects in both details and semantics, offering relevant diagnostic information to pathologists. However, the current methods are limited by the difficulty of gigapixels, the variable size of WSIs, and the dependence on manual annotations. In this work, we propose a novel histopathology language-image representation learning framework for fine-grained digital pathology cross-modal retrieval, which utilizes paired diagnosis reports to learn fine-grained semantics from the WSI. An anchor-based WSI encoder is built to extract hierarchical region features and a prompt-based text encoder is introduced to learn fine-grained semantics from the diagnosis reports. The proposed framework is trained with a multivariate cross-modal loss function to learn semantic information from the diagnosis report at both the instance level and region level. After training, it can perform four types of retrieval tasks based on the multi-modal database to support diagnostic requirements. We conducted experiments on an in-house dataset and a public dataset to evaluate the proposed method. Extensive experiments have demonstrated the effectiveness of the proposed method and its advantages to the present histopathology retrieval methods. The code is available at https://github.com/hudingyi/FGCR.

Analyzing changes in volatile flavor compounds of soy protein isolate during ultrasonic-thermal synergistic treatments using electronic nose and HS-SPME-GC-MS combined with chemometrics.

The beany flavor of soy protein isolate (SPI) creates barriers to their application in food processing. This study investigated the effect of ultrasonic-thermal synergistic treatments, combined with vacuum degassing, on the removal of volatile compounds from SPI. The results revealed that ultrasonic-thermal synergistic treatments altered protein secondary structure and increased fluorescence intensity and surface hydrophobicity, which affected the flavor-binding ability of protein, resulting in reduced electronic nose sensor response values. At synergistic treatment (350 W, 120 ℃ and 150 s), the content of hexanal, (E)-2-hexenal, and 1-octen-3-ol reduced by 70.60 %, 95.60 % and 61.23 %. (E)-2-nonenal and 2-pentylfuran were not detected. Chemometric analysis indicated significant flavor differences between control and treated SPI. Furthermore, α-helix, ß-sheet, ß-turn, and surface hydrophobicity highly correlated with volatile compounds through correlation analysis, indicating that altered protein structure affected interactions with volatile compounds. The study reduced beany flavor and further expanded the range of applications of plant protein in food industry.

Enzymatic Acylation of Black Rice Anthocyanins and Evaluation of Antioxidant Capacity and Stability of Their Derivatives.

In this study, the structure of the anthocyanin fractions isolated from black rice (Oryza sativa L.) was modified by the enzyme catalysis method using caffeic acid as an acyl donor. At the same time, the effects of the acylation on the lipophilicity, antioxidant activity, and stability of black rice anthocyanins were comprehensively evaluated. The structural analyses of acylated derivatives based on ultraviolet-visible spectroscopy, Fourier-transform infrared spectroscopy, ultra-high-performance liquid chromatography-high-resolution mass spectrometry, and thermogravimetric analysis revealed that caffeic acid was efficiently grafted onto the anthocyanins of black rice through an acylated reaction, while the acylation binding site was on glucoside. When the mass ratios of anthocyanins to caffeic acid were 1:1, the A319/AVis-max value of acylated anthocyanins reached 6.37. Meanwhile, the lipophilicity of acylated derivatives was enhanced. The antioxidant capacity (DPPH and FRAP) and stability (thermal, pH, and light stability) were significantly increased. Overall, the study results provide deeper insights into controlling anthocyanin homeostasis in food processing, broadening the application of colored grain products.