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.

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.

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.

Curcumin-loaded oil body emulsions prepared by an ultrasonic and pH-driven method: Fundamental properties, stability, and digestion characteristics.

In this study, oil bodies (OBs) loaded with curcumin (Cur) were successfully prepared via an ultrasonic and pH-driven method. Ultrasonic treatment significantly improved the encapsulation efficiency (EE) and loading capacity (LC) of Cur, producing OB particles with small size, uniform distribution, and high ζ-potential absolute values. When the ultrasonic power was 200 W, the EE, LC, and ζ-potential absolute value were the greatest (88.27 %, 0.044 %, and -25.71 mV, respectively), and the OBs possessed the highest yellowness, representing the best treatment result. The confocal laser scanning microscopy (CLSM) and cryo-scanning electron microscopy (cryo-SEM) results was also intuitionally shown that. Moreover, circular dichroism (CD) proved that ultrasonic treatment could unfold the surface protein structure, further enhancing the stability. Therefore, the cream index (CI), peroxide value (POV), and thiobarbituric acid reactive substances (TBARS) were the lowest when the ultrasonic power was 200 W. In this case, the Cur loaded in OBs was well protected against hostile conditions, evidenced by the highest Cur retention rate and the lowest degradation rate constant. Finally, the in vitro gastrointestinal digestion simulation results showed that the ultrasonic treatment effectively increased the release of FFA, bioaccessibility, and stability of Cur, especially when the ultrasonic power was 200 W. This research offers a new OB-based delivery system to stabilize, deliver, and protect Cur for food processing.

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.

Effects of ultrasonic treatment on the structural, functional properties and beany flavor of soy protein isolate: Comparison with traditional thermal treatment.

This research explored the influences of ultrasonic and thermal treatments on the structure, functional properties, and beany flavor of soy protein isolate (SPI). In comparison with traditional thermal treatment, ultrasonic treatment effectively induced protein structural unfolding and exposure of hydrophobic groups, which reduced relative content of α-helix, increased relative content of ß-turn, ß-sheet and random coil, and improved the solubility, emulsifying and foaming properties of SPI. Both treatments significantly decreased the species and contents of flavor compounds, such as hexanal, (E)-2-nonenal, (Z)-2-heptenal and (E)-2-hexenal in SPI. The relative content of hexanal in the major beany flavor compound decreased from 11.69% to 6.13% and 5.99% at 350 W ultrasonic power and 150 s thermal treatment procedure, respectively. After ultrasonic treatment, structural changes in SPI were significantly correlated with functional properties but showed a weak correlation with flavor. Conversely, the opposite trend was observed for thermal treatment. Thus, using ultrasonic treatment to induce and stabilise the denatured state of proteins is feasible to improve the functional properties and beany flavor of SPI.

Grain Quality Characterization before and after Processing.

Grains are an important part of a healthy diet, and provide most of the daily calories and nutrients [...].

Innovative minimally invasive implants for osteoporosis vertebral compression fractures.

With increasing population aging, osteoporosis vertebral compression fractures (OVCFs), resulting in severe back pain and functional impairment, have become progressively common. Percutaneous vertebroplasty (PVP) and percutaneous kyphoplasty (PKP) as minimally invasive procedures have revolutionized OVCFs treatment. However, PVP- and PKP-related complications, such as symptomatic cement leakage and adjacent vertebral fractures, continue to plague physicians. Consequently, progressively more implants for OVCFs have been developed recently to overcome the shortcomings of traditional procedures. Therefore, we conducted a literature review on several new implants for OVCFs, including StaXx FX, Vertebral Body Stenting, Vesselplasty, Sky Bone Expander, Kiva, Spine Jack, Osseofix, Optimesh, Jack, and V-strut. Additionally, this review highlights the individualized applications of these implants for OVCFs. Nevertheless, current clinical studies on these innovative implants remain limited. Future prospective, randomized, and controlled studies are needed to elucidate the effectiveness and indications of these new implants for OVCFs.

Kernel Attention Transformer for Histopathology Whole Slide Image Analysis and Assistant Cancer Diagnosis.

Transformer has been widely used in histopathology whole slide image analysis. However, the design of token-wise self-attention and positional embedding strategy in the common Transformer limits its effectiveness and efficiency when applied to gigapixel histopathology images. In this paper, we propose a novel kernel attention Transformer (KAT) for histopathology WSI analysis and assistant cancer diagnosis. The information transmission in KAT is achieved by cross-attention between the patch features and a set of kernels related to the spatial relationship of the patches on the whole slide images. Compared to the common Transformer structure, KAT can extract the hierarchical context information of the local regions of the WSI and provide diversified diagnosis information. Meanwhile, the kernel-based cross-attention paradigm significantly reduces the computational amount. The proposed method was evaluated on three large-scale datasets and was compared with 8 state-of-the-art methods. The experimental results have demonstrated the proposed KAT is effective and efficient in the task of histopathology WSI analysis and is superior to the state-of-the-art methods.

TFormer: A throughout fusion transformer for multi-modal skin lesion diagnosis.

Multi-modal skin lesion diagnosis (MSLD) has achieved remarkable success by modern computer-aided diagnosis (CAD) technology based on deep convolutions. However, the information aggregation across modalities in MSLD remains challenging due to severity unaligned spatial resolution (e.g., dermoscopic image and clinical image) and heterogeneous data (e.g., dermoscopic image and patients' meta-data). Limited by the intrinsic local attention, most recent MSLD pipelines using pure convolutions struggle to capture representative features in shallow layers, thus the fusion across different modalities is usually done at the end of the pipelines, even at the last layer, leading to an insufficient information aggregation. To tackle the issue, we introduce a pure transformer-based method, which we refer to as "Throughout Fusion Transformer (TFormer)", for sufficient information integration in MSLD. Different from the existing approaches with convolutions, the proposed network leverages transformer as feature extraction backbone, bringing more representative shallow features. We then carefully design a stack of dual-branch hierarchical multi-modal transformer (HMT) blocks to fuse information across different image modalities in a stage-by-stage way. With the aggregated information of image modalities, a multi-modal transformer post-fusion (MTP) block is designed to integrate features across image and non-image data. Such a strategy that information of the image modalities is firstly fused then the heterogeneous ones enables us to better divide and conquer the two major challenges while ensuring inter-modality dynamics are effectively modeled. Experiments conducted on the public Derm7pt dataset validate the superiority of the proposed method. Our TFormer achieves an average accuracy of 77.99% and diagnostic accuracy of 80.03% , which outperforms other state-of-the-art methods. Ablation experiments also suggest the effectiveness of our designs. The codes can be publicly available from https://github.com/zylbuaa/TFormer.git.

Skin lesion classification based on two-modal images using a multi-scale fully-shared fusion network.

BACKGROUND AND OBJECTIVE: Due to the complexity of skin lesion features, computer-aided diagnosis of skin diseases based on multi-modal images is considered a challenging task. Dermoscopic images and clinical images are commonly used to diagnose skin diseases in clinical scenarios, and the complementarity of their features promotes the research of multi-modality classification in the computer-aided diagnosis field. Most current methods focus on the fusion between modalities and ignore the complementary information within each of them, which leads to the loss of the intra-modality relation. Multi-modality models for integrating features both within single modalities and across multiple modalities are limited in the literature. Therefore, a multi-modality model based on dermoscopic and clinical images is proposed to address this issue. METHODS: We propose a Multi-scale Fully-shared Fusion Network (MFF-Net) that gathers features of dermoscopic images and clinical images for skin lesion classification. In MFF-Net, the multi-scale fusion structure combines deep and shallow features within individual modalities to reduce the loss of spatial information in high-level feature maps. Then Dermo-Clinical Block (DCB) integrates the feature maps from dermoscopic images and clinical images through channel-wise concatenation and using a fully-shared fusion strategy that explores complementary information at different stages. RESULTS: We validated our model on a four-class two-modal skin diseases dataset, and proved that the proposed multi-scale structure, the fusion module DCBs, and the fully-shared fusion strategy improve the performance of MFF-Net independently. Our method achieved the highest average accuracy of 72.9% on the 7-point checklist dataset, outperforming the state-of-the-art single-modality and multi-modality methods with an accuracy boost of 7.1% and 3.4%, respectively. CONCLUSIONS: The multi-scale fusion structure demonstrates the significance of intra-modality relations between clinical images and dermoscopic images. The proposed network combined with the multi-scale structure, DCBs, and the fully-shared fusion strategy, can effectively integrate the features of the skin lesions across the two modalities and achieved a promising accuracy among different skin diseases.

A rotation meanout network with invariance for dermoscopy image classification and retrieval.

The computer-aided diagnosis (CAD) system can provide a reference basis for the clinical diagnosis of skin diseases. Convolutional neural networks (CNNs) can not only extract visual elements such as colors and shapes but also semantic features. As such they have made great improvements in many tasks of dermoscopy images. The imaging of dermoscopy has no principal orientation, indicating that there are a large number of skin lesion rotations in the datasets. However, CNNs lack rotation invariance, which is bound to affect the robustness of CNNs against rotations. To tackle this issue, we propose a rotation meanout (RM) network to extract rotation-invariant features from dermoscopy images. In RM, each set of rotated feature maps corresponds to a set of outputs of the weight-sharing convolutions and they are fused using meanout strategy to obtain the final feature maps. Through theoretical derivation, the proposed RM network is rotation-equivariant and can extract rotation-invariant features when followed by the global average pooling (GAP) operation. The extracted rotation-invariant features can better represent the original data in classification and retrieval tasks for dermoscopy images. The RM is a general operation, which does not change the network structure or increase any parameters, and can be flexibly embedded in any part of CNNs. Extensive experiments are conducted on a dermoscopy image dataset. The results show that our method outperforms other anti-rotation methods and achieves great improvements in skin disease classification and retrieval tasks, indicating the potential of rotation invariance in the field of dermoscopy images.

Dermoscopic image retrieval based on rotation-invariance deep hashing.

Dermoscopic image retrieval technology can provide dermatologists with valuable information such as similar confirmed skin disease cases and diagnosis reports to assist doctors in their diagnosis. In this study, we design a dermoscopic image retrieval algorithm using convolutional neural networks (CNNs) and hash coding. A hybrid dilated convolution spatial attention module is proposed, which can focus on important information and suppress irrelevant information based on the complex morphological characteristics of dermoscopic images. Furthermore, we also propose a Cauchy rotation invariance loss function in view of the skin lesion target without the main direction. This function constrains CNNs to learn output differences in samples from different angles and to make CNNs obtain a certain rotation invariance. Extensive experiments are conducted on dermoscopic image datasets to verify the effectiveness and versatility of the proposed module, algorithm, and loss function. Experiment results show that the rotation-invariance deep hashing network with the proposed spatial attention module obtains better performance on the task of dermoscopic image retrieval.

Encoding histopathology whole slide images with location-aware graphs for diagnostically relevant regions retrieval.

Content-based histopathological image retrieval (CBHIR) has become popular in recent years in histopathological image analysis. CBHIR systems provide auxiliary diagnosis information for pathologists by searching for and returning regions that are contently similar to the region of interest (ROI) from a pre-established database. It is challenging and yet significant in clinical applications to retrieve diagnostically relevant regions from a database consisting of histopathological whole slide images (WSIs). In this paper, we propose a novel framework for regions retrieval from WSI database based on location-aware graphs and deep hash techniques. Compared to the present CBHIR framework, both structural information and global location information of ROIs in the WSI are preserved by graph convolution and self-attention operations, which makes the retrieval framework more sensitive to regions that are similar in tissue distribution. Moreover, benefited from the graph structure, the proposed framework has good scalability for both the size and shape variation of ROIs. It allows the pathologist to define query regions using free curves according to the appearance of tissue. Thirdly, the retrieval is achieved based on the hash technique, which ensures the framework is efficient and adequate for practical large-scale WSI database. The proposed method was evaluated on an in-house endometrium dataset with 2650 WSIs and the public ACDC-LungHP dataset. The experimental results have demonstrated that the proposed method achieved a mean average precision above 0.667 on the endometrium dataset and above 0.869 on the ACDC-LungHP dataset in the task of irregular region retrieval, which are superior to the state-of-the-art methods. The average retrieval time from a database containing 1855 WSIs is 0.752 ms. The source code is available at https://github.com/zhengyushan/lagenet.

Dynamic gastric stability and in vitro lipid digestion of soybean protein isolate and three storage protein-stabilized emulsions: Effects of ultrasonic treatment.

The emulsification of vegetable protein is closely related to solubility. The purpose of this study was to evaluate the effect of ultrasound on protein emulsification and to provide a prospective method for assessing the digestive properties of emulsions. In this article, we investigate the emulsion stability of ultrasonic pretreated soy protein isolate (SPI), and its three storage proteins, namely ß-conglycinin (7S), lipophilic protein (LP), and glycinin (11S), under dynamic gastric conditions. The effects of these emulsions on lipolysis during digestion in the small intestine are also assessed using an in vitro dynamic human stomach simulator and a small intestine model. Particle size and ζ-potential measurements, as well as confocal laser scanning microscopy, revealed that during dynamic gastric digestion, the flocculation degree and floc size of 7S and soybean LP emulsions are larger than that of 11S and SPI emulsions. Meanwhile, ultrasound pretreatment of the proteins was found to prevent the agglomeration of the emulsion in a dynamic gastric environment. Moreover, enhanced flocculation delayed oil droplet delivery to the small intestine and subsequently retarded the release of lipophilic nutrients. The droplet size, molecular weight, and protein secondary structures of the ultrasonicated proteins were conducive to relatively higher rates and degrees of lipolysis in intestinal digestion than those of unsonicated proteins. Additionally, the slow-release effect of LP was superior to that of 11S and SPI, whereas 7S was comparatively more difficult to digest. The present study elucidated the fate of soy protein in the digestive tract and may facilitate microstructural food design to regulate physiological responses during digestion.

A convolutional neural network trained with dermoscopic images of psoriasis performed on par with 230 dermatologists.

BACKGROUND: Psoriasis is a common chronic inflammatory skin disease that causes physical and psychological burden to patients. A Convolutional Neural Network (CNN) focused on dermoscopic images would substantially aid the classification and increase the accuracy of diagnosis of psoriasis. OBJECTIVES: This study aimed to train an efficient deep-learning network to recognize dermoscopic images of psoriasis (and other papulosquamous diseases), improving the accuracy of the diagnosis of psoriasis. METHODS: EfficientNet-B4 architecture was trained with 7033 dermoscopic images from 1166 patients collected from the Department of Dermatology, Peking Union Medical College Hospital (China). We performed a five-fold cross-validation on the training set to compare the classification performance of EfficientNet-B4 over different networks commonly used in previous studies. From the test set, 90 images were used to compare the performance between our four-class model and that of board-certified dermatologists, whose diagnoses and information (e.g., age, titles) were obtained through an online questionnaire. RESULTS: The mean sensitivity and specificity of EfficientNet-B4 on the training set was 0.927± 0.028 and 0.827 ± 0.043 for the two-class task, and 0.889 ± 0.014 and 0.968 ± 0.004 four-class task. The diagnostic sensitivity and specificity of the 230 dermatologists were 0.688 and 0.903 for psoriasis, 0.677 and 0.838 for eczema, 0.669 and 0.953 for lichen planus, and 0.832 and 0.932 for the "others" group, respectively; the diagnostic sensitivity and specificity of our four-class CNN was 0.929 and 0.952 for psoriasis, 0.773 and 0.926 for eczema, 0.933 and 0.960 for lichen planus, and 0.840 and 0.985 for the "others" group, respectively. Both the 230 dermatologists and CNN achieved at least moderate consistency with the reference standard, and there was no significant difference between them (P > 0.05). CONCLUSIONS: The two-classification and four-classification models of psoriasis established in our study could accurately classify papulosquamous skin diseases. They showed generally comparable performances to the average level of dermatologists and would provide a strong support for the diagnosis of psoriasis.

Effect of ultrasound on the properties of rice bran protein and its chlorogenic acid complex.

Ultrasound technology was used to treat rice bran protein (RBP), and the structural and functional properties of ultrasonically treated RBP (URBP) and its chlorogenic acid (CA) complex were studied. When ultrasonic power of 200 W was applied for 10 min, the maximum emission peak λmax of the URBP-CA complex in the fluorescence spectrum was red-shifted by 3.6 nm compared to that of the untreated complex. The atomic force microscope (AFM) analysis indicated that the surface roughness of the complex was minimized (3.89 nm) at the ultrasonic power of 200 W and treatment time of 10 min. Under these conditions, the surface hydrophobicity (H0) was 1730, the contents of the α-helix and ß-sheet in the complex were 2.97% and 6.17% lower than those in the untreated sample, respectively, the particle size decreased from 106 nm to 18.2 nm, and the absolute value of the zeta-potential increased by 11.0 mV. Therefore, ultrasonic treatment and the addition of CA changed the structural and functional properties of RBP. Moreover, when ultrasonic power of 200 W was applied for 10 min, the solubility, emulsifying activity index (EAI), and emulsion stability index (ESI) were 68%, 126 m2/g, and 37 min, respectively.

A Deep Learning Based Framework for Diagnosing Multiple Skin Diseases in a Clinical Environment.

Background: Numerous studies have attempted to apply artificial intelligence (AI) in the dermatological field, mainly on the classification and segmentation of various dermatoses. However, researches under real clinical settings are scarce. Objectives: This study was aimed to construct a novel framework based on deep learning trained by a dataset that represented the real clinical environment in a tertiary class hospital in China, for better adaptation of the AI application in clinical practice among Asian patients. Methods: Our dataset was composed of 13,603 dermatologist-labeled dermoscopic images, containing 14 categories of diseases, namely lichen planus (LP), rosacea (Rosa), viral warts (VW), acne vulgaris (AV), keloid and hypertrophic scar (KAHS), eczema and dermatitis (EAD), dermatofibroma (DF), seborrheic dermatitis (SD), seborrheic keratosis (SK), melanocytic nevus (MN), hemangioma (Hem), psoriasis (Pso), port wine stain (PWS), and basal cell carcinoma (BCC). In this study, we applied Google's EfficientNet-b4 with pre-trained weights on ImageNet as the backbone of our CNN architecture. The final fully-connected classification layer was replaced with 14 output neurons. We added seven auxiliary classifiers to each of the intermediate layer groups. The modified model was retrained with our dataset and implemented using Pytorch. We constructed saliency maps to visualize our network's attention area of input images for its prediction. To explore the visual characteristics of different clinical classes, we also examined the internal image features learned by the proposed framework using t-SNE (t-distributed Stochastic Neighbor Embedding). Results: Test results showed that the proposed framework achieved a high level of classification performance with an overall accuracy of 0.948, a sensitivity of 0.934 and a specificity of 0.950. We also compared the performance of our algorithm with three most widely used CNN models which showed our model outperformed existing models with the highest area under curve (AUC) of 0.985. We further compared this model with 280 board-certificated dermatologists, and results showed a comparable performance level in an 8-class diagnostic task. Conclusions: The proposed framework retrained by the dataset that represented the real clinical environment in our department could accurately classify most common dermatoses that we encountered during outpatient practice including infectious and inflammatory dermatoses, benign and malignant cutaneous tumors.

Effects of covalent modification with epigallocatechin-3-gallate on oleosin structure and ability to stabilize artificial oil body emulsions.

The purpose of this study was to enhance the stability and functional properties of artificial oil body (AOB) emulsions. Herein, we covalently conjugated oleosin (OL) and epigallocatechin-3-gallate (EGCG) under alkaline conditions to obtain OL-EGCG conjugates. The results revealed that the structural characteristics of OL are improved by covalent binding to EGCG, with the OL-EGCG yield maximized at an EGCG concentration of 150 µM. We prepared AOB emulsions using native OL, the OL-EGCG conjugates, phosphatidylcholine (PC), and soybean oil for embedding curcumin. The results show that the protein components and phospholipids are bound in the AOB emulsion by hydrogen bonding and hydrophobic interactions. The covalent OL-EGCG/PC-stabilized emulsions exhibited more uniform droplet distributions, stronger thermal stabilities, and higher curcumin retentions than the other samples. These results indicated that the OL-EGCG/PC complexes are potential stabilizers for AOB emulsions and provided fresh insight into preparing highly stable emulsion embedding systems with good encapsulation efficiencies.

Stain Standardization Capsule for Application-Driven Histopathological Image Normalization.

Color consistency is crucial to developing robust deep learning methods for histopathological image analysis. With the increasing application of digital histopathological slides, the deep learning methods are probably developed based on the data from multiple medical centers. This requirement makes it a challenging task to normalize the color variance of histopathological images from different medical centers. In this paper, we propose a novel color standardization module named stain standardization capsule based on the capsule network and the corresponding dynamic routing algorithm. The proposed module can learn and generate uniform stain separation outputs for histopathological images in various color appearance without the reference to manually selected template images. The proposed module is light and can be jointly trained with the application-driven CNN model. The proposed method was validated on three histopathology datasets and a cytology dataset, and was compared with state-of-the-art methods. The experimental results have demonstrated that the SSC module is effective in improving the performance of histopathological image analysis and has achieved the best performance in the compared methods.