Multi-cell type and multi-level graph aggregation network for cancer grading in pathology images.

In pathology, cancer grading is crucial for patient management and treatment. Recent deep learning methods, based upon convolutional neural networks (CNNs), have shown great potential for automated and accurate cancer diagnosis. However, these do not explicitly utilize tissue/cellular composition, and thus difficult to incorporate the existing knowledge of cancer pathology. In this study, we propose a multi-cell type and multi-level graph aggregation network (MMGA-Net) for cancer grading. Given a pathology image, MMGA-Net constructs multiple cell graphs at multiple levels to represent intra- and inter-cell type relationships and to incorporate global and local cell-to-cell interactions. In addition, it extracts tissue contextual information using a CNN. Then, the tissue and cellular information are fused to predict a cancer grade. The experimental results on two types of cancer datasets demonstrate the effectiveness of MMGA-Net, outperforming other competing models. The results also suggest that the information fusion of multiple cell types and multiple levels via graphs is critical for improved pathology image analysis.

Ethno-demographic disparities in humoral responses to the COVID-19 vaccine among healthcare workers.

The COVID-19 pandemic had a profound impact on global health, but rapid vaccine administration resulted in a significant decline in morbidity and mortality rates worldwide. In this study, we sought to explore the temporal changes in the humoral immune response against SARS-CoV-2 healthcare workers (HCWs) in Augusta, GA, USA, and investigate any potential associations with ethno-demographic features. Specifically, we aimed to compare the naturally infected individuals with naïve individuals to understand the immune response dynamics after SARS-CoV-2 vaccination. A total of 290 HCWs were included and assessed prospectively in this study. COVID status was determined using a saliva-based COVID assay. Neutralizing antibody (NAb) levels were quantified using a chemiluminescent immunoassay system, and IgG levels were measured using an enzyme-linked immunosorbent assay method. We examined the changes in antibody levels among participants using different statistical tests including logistic regression and multiple correspondence analysis. Our findings revealed a significant decline in NAb and IgG levels at 8-12 months postvaccination. Furthermore, a multivariable analysis indicated that this decline was more pronounced in White HCWs (odds ratio [OR] = 2.1, 95% confidence interval [CI] = 1.07-4.08, p = 0.02) and IgG (OR = 2.07, 95% CI = 1.04-4.11, p = 0.03) among the whole cohort. Booster doses significantly increased IgG and NAb levels, while a decline in antibody levels was observed in participants without booster doses at 12 months postvaccination. Our results highlight the importance of understanding the dynamics of immune response and the potential influence of demographic factors on waning immunity to SARS-CoV-2. In addition, our findings emphasize the value of booster doses to ensure durable immunity.

Prediction of Epstein-Barr Virus Status in Gastric Cancer Biopsy Specimens Using a Deep Learning Algorithm.

Importance: Epstein-Barr virus (EBV)-associated gastric cancer (EBV-GC) is 1 of 4 molecular subtypes of GC and is confirmed by an expensive molecular test, EBV-encoded small RNA in situ hybridization. EBV-GC has 2 histologic characteristics, lymphoid stroma and lace-like tumor pattern, but projecting EBV-GC at biopsy is difficult even for experienced pathologists. Objective: To develop and validate a deep learning algorithm to predict EBV status from pathology images of GC biopsy. Design, Setting, and Participants: This diagnostic study developed a deep learning classifier to predict EBV-GC using image patches of tissue microarray (TMA) and whole slide images (WSIs) of GC and applied it to GC biopsy specimens from GCs diagnosed at Kangbuk Samsung Hospital between 2011 and 2020. For a quantitative evaluation and EBV-GC prediction on biopsy specimens, the area of each class and the fraction in total tissue or tumor area were calculated. Data were analyzed from March 5, 2021, to February 10, 2022. Main Outcomes and Measures: Evaluation metrics of predictive model performance were assessed on accuracy, recall, precision, F1 score, area under the receiver operating characteristic curve (AUC), and κ coefficient. Results: This study included 137 184 image patches from 16 TMAs (708 tissue cores), 24 WSIs, and 286 biopsy images of GC. The classifier was able to classify EBV-GC image patches from TMAs and WSIs with 94.70% accuracy, 0.936 recall, 0.938 precision, 0.937 F1 score, and 0.909 κ coefficient. The classifier was used for predicting and measuring the area and fraction of EBV-GC on biopsy tissue specimens. A 10% cutoff value for the predicted fraction of EBV-GC to tissue (EBV-GC/tissue area) produced the best prediction results in EBV-GC biopsy specimens and showed the highest AUC value (0.8723; 95% CI, 0.7560-0.9501). That cutoff also obtained high sensitivity (0.895) and moderate specificity (0.745) compared with experienced pathologist sensitivity (0.842) and specificity (0.854) when using the presence of lymphoid stroma and a lace-like pattern as diagnostic criteria. On prediction maps, EBV-GCs with lace-like pattern and lymphoid stroma showed the same prediction results as EBV-GC, but cases lacking these histologic features revealed heterogeneous prediction results of EBV-GC and non-EBV-GC areas. Conclusions and Relevance: This study showed the feasibility of EBV-GC prediction using a deep learning algorithm, even in biopsy samples. Use of such an image-based classifier before a confirmatory molecular test will reduce costs and tissue waste.

SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images.

Automated nuclei segmentation and classification are the keys to analyze and understand the cellular characteristics and functionality, supporting computer-aided digital pathology in disease diagnosis. However, the task still remains challenging due to the intrinsic variations in size, intensity, and morphology of different types of nuclei. Herein, we propose a self-guided ordinal regression neural network for simultaneous nuclear segmentation and classification that can exploit the intrinsic characteristics of nuclei and focus on highly uncertain areas during training. The proposed network formulates nuclei segmentation as an ordinal regression learning by introducing a distance decreasing discretization strategy, which stratifies nuclei in a way that inner regions forming a regular shape of nuclei are separated from outer regions forming an irregular shape. It also adopts a self-guided training strategy to adaptively adjust the weights associated with nuclear pixels, depending on the difficulty of the pixels that is assessed by the network itself. To evaluate the performance of the proposed network, we employ large-scale multi-tissue datasets with 276349 exhaustively annotated nuclei. We show that the proposed network achieves the state-of-the-art performance in both nuclei segmentation and classification in comparison to several methods that are recently developed for segmentation and/or classification.

Multi-Scale Binary Pattern Encoding Network for Cancer Classification in Pathology Images.

Multi-scale approaches have been widely studied in pathology image analysis. These offer an ability to characterize tissues in an image at various scales, in which the tissues may appear differently. Many of such methods have focused on extracting multi-scale hand-crafted features and applied them to various tasks in pathology image analysis. Even, several deep learning methods explicitly adopt the multi-scale approaches. However, most of these methods simply merge the multi-scale features together or adopt the coarse-to-fine/fine-to-coarse strategy, which uses the features one at a time in a sequential manner. Utilizing the multi-scale features in a cooperative and discriminative fashion, the learning capabilities could be further improved. Herein, we propose a multi-scale approach that can identify and leverage the patterns of the multiple scales within a deep neural network and provide the superior capability of cancer classification. The patterns of the features across multiple scales are encoded as a binary pattern code and further converted to a decimal number, which can be easily embedded in the current framework of the deep neural networks. To evaluate the proposed method, multiple sets of pathology images are employed. Under the various experimental settings, the proposed method is systematically assessed and shows an improved classification performance in comparison to other competing methods.

Joint categorical and ordinal learning for cancer grading in pathology images.

Cancer grading in pathology image analysis is one of the most critical tasks since it is related to patient outcomes and treatment planning. Traditionally, it has been considered a categorical problem, ignoring the natural ordering among the cancer grades, i.e., the higher the grade is, the more aggressive it is, and the worse the outcome is. Herein, we propose a joint categorical and ordinal learning framework for cancer grading in pathology images. The approach simultaneously performs both categorical classification and ordinal classification and aims to leverage the distinctive features from the two tasks. Moreover, we propose a new loss function for the ordinal classification task that offers an improved contrast between the correctly classified examples and misclassified examples. The proposed method is evaluated on multiple collections of colorectal and prostate pathology images that underwent different acquisition and processing procedures. Both quantitative and qualitative assessments of the experimental results confirm the effectiveness and robustness of the proposed method in comparison to other competing methods. The results suggest that the proposed approach could permit improved histopathologic analysis of cancer grades in pathology images.

Comparative Study of Ultrasonication-Induced and Naturally Self-Assembled Silk Fibroin-Wool Keratin Hydrogel Biomaterials.

This study reports the formation of biocompatible hydrogels using protein polymers from natural silk cocoon fibroins and sheep wool keratins. Silk fibroin protein contains ß-sheet secondary structures, allowing for the formation of physical cross-linkers in the hydrogels. Comparative studies were performed on two groups of samples. In the first group, ultrasonication was used to induce a quick gelation of a protein aqueous solution, enhancing the ability of Bombyx mori silk fibroin chains to quickly entrap the wool keratin protein molecules homogenously. In the second group, silk/keratin mixtures were left at room temperature for days, resulting in naturally-assembled gelled solutions. It was found that silk/wool blended solutions can form hydrogels at different mixing ratios, with perfectly interconnected gel structure when the wool content was less than 30 weight percent (wt %) for the first group (ultrasonication), and 10 wt % for the second group (natural gel). Differential scanning calorimetry (DSC) and temperature modulated DSC (TMDSC) were used to confirm that the fibroin/keratin hydrogel system was well-blended without phase separation. Fourier transform infrared spectroscopy (FTIR) was used to investigate the secondary structures of blended protein gels. It was found that intermolecular ß-sheet contents significantly increase as the system contains more silk for both groups of samples, resulting in stable crystalline cross-linkers in the blended hydrogel structures. Scanning electron microscopy (SEM) and atomic force microscopy (AFM) were used to analyze the samples' characteristic morphology on both micro- and nanoscales, which showed that ultrasonic waves can significantly enhance the cross-linker formation and avoid phase separation between silk and keratin molecules in the blended systems. With the ability to form cross-linkages non-chemically, these silk/wool hydrogels may be economically useful for various biomedical applications, thanks to the good biocompatibility of protein molecules and the various characteristics of hydrogel systems.