A two-dimensional vertex model for curvy cell-cell interfaces at the subcellular scale.

Cross-sections of cell shapes in a tissue monolayer typically resemble a tiling of convex polygons. Yet, examples exist where the polygons are not convex with curved cell-cell interfaces, as seen in the adaxial epidermis. To date, two-dimensional vertex models predicting the structure and mechanics of cell monolayers have been mostly limited to convex polygons. To overcome this limitation, we introduce a framework to study curvy cell-cell interfaces at the subcellular scale within vertex models by using a parametrized curve between vertices that is expanded in a Fourier series and whose coefficients represent additional degrees of freedom. This extension to non-convex polygons allows for cells with the same shape index, or dimensionless perimeter, to be, for example, either elongated or globular with lobes. In the presence of applied, anisotropic stresses, we find that local, subcellular curvature or buckling can be energetically more favourable than larger scale deformations involving groups of cells. Inspired by recent experiments, we also find that local, subcellular curvature at cell-cell interfaces emerges in a group of cells in response to the swelling of additional cells surrounding the group. Our framework, therefore, can account for a wider array of multicellular responses to constraints in the tissue environment.

Spatially-constrained and -unconstrained bi-graph interaction network for multi-organ pathology image classification.

In computational pathology, graphs have shown to be promising for pathology image analysis. There exist various graph structures that can discover differing features of pathology images. However, the combination and interaction between differing graph structures have not been fully studied and utilized for pathology image analysis. In this study, we propose a parallel, bi-graph neural network, designated as SCUBa-Net, equipped with both graph convolutional networks and Transformers, that processes a pathology image as two distinct graphs, including a spatially-constrained graph and a spatially-unconstrained graph. For efficient and effective graph learning, we introduce two inter-graph interaction blocks and an intra-graph interaction block. The inter-graph interaction blocks learn the node-to-node interactions within each graph. The intra-graph interaction block learns the graph-to-graph interactions at both global- and local-levels with the help of the virtual nodes that collect and summarize the information from the entire graphs. SCUBa-Net is systematically evaluated on four multi-organ datasets, including colorectal, prostate, gastric, and bladder cancers. The experimental results demonstrate the effectiveness of SCUBa-Net in comparison to the state-of-the-art convolutional neural networks, Transformer, and graph neural networks.

Enhanced extracellular matrix remodeling due to embedded spheroid fluidization.

Tumor spheroids are in vitro three-dimensional, cellular collectives consisting of cancerous cells. Embedding these spheroids in an in vitro fibrous environment, such as a collagen network, to mimic the extracellular matrix (ECM) provides an essential platform to quantitatively investigate the biophysical mechanisms leading to tumor invasion of the ECM. To understand the mechanical interplay between tumor spheroids and the ECM, we computationally construct and study a three-dimensional vertex model for a tumor spheroid that is mechanically coupled to a cross-linked network of fibers. In such a vertex model, cells are represented as deformable polyhedrons that share faces. Some fraction of the boundary faces of the tumor spheroid contain linker springs connecting the center of the boundary face to the nearest node in the fiber network. As these linker springs actively contract, the fiber network remodels. By toggling between fluid-like and solid-like spheroids via changing the dimensionless cell shape index, we find that the spheroid rheology affects the remodeling of the fiber network. More precisely, fluid-like spheroids displace the fiber network more on average near the vicinity of the spheroid than solid-like spheroids. We also find more densification of the fiber network near the spheroid for the fluid-like spheroids. These spheroid rheology-dependent effects are the result of cellular motility due to active cellular rearrangements that emerge over time in the fluid-like spheroids to generate spheroid shape fluctuations. Our results uncover intricate morphological-mechanical interplay between an embedded spheroid and its surrounding fiber network with both spheroid contractile strength and spheroid shape fluctuations playing important roles in the pre-invasion stages of tumor invasion.

DAX-Net: A dual-branch dual-task adaptive cross-weight feature fusion network for robust multi-class cancer classification in pathology images.

BACKGROUND AND OBJECTIVE: Multi-class cancer classification has been extensively studied in digital and computational pathology due to its importance in clinical decision-making. Numerous computational tools have been proposed for various types of cancer classification. Many of them are built based on convolutional neural networks. Recently, Transformer-style networks have shown to be effective for cancer classification. Herein, we present a hybrid design that leverages both convolutional neural networks and transformer architecture to obtain superior performance in cancer classification. METHODS: We propose a dual-branch dual-task adaptive cross-weight feature fusion network, called DAX-Net, which exploits heterogeneous feature representations from the convolutional neural network and Transformer network, adaptively combines them to boost their representation power, and conducts cancer classification as categorical classification and ordinal classification. For an efficient and effective optimization of the proposed model, we introduce two loss functions that are tailored to the two classification tasks. RESULTS: To evaluate the proposed method, we employed colorectal and prostate cancer datasets, of which each contains both in-domain and out-of-domain test sets. For colorectal cancer, the proposed method obtained an accuracy of 88.4%, a quadratic kappa score of 0.945, and an F1 score of 0.831 for the in-domain test set, and 84.4%, 0.910, and 0.768 for the out-of-domain test set. For prostate cancer, it achieved an accuracy of 71.6%, a kappa score of 0.635, and an F1 score of 0.655 for the in-domain test set, 79.2% accuracy, 0.721 kappa score, and 0.686 F1 score for the first out-of-domain test set, and 58.1% accuracy, 0.564 kappa score, and 0.493 F1 score for the second out-of-domain test set. It is worth noting that the performance of the proposed method outperformed other competitors by significant margins, in particular, with respect to the out-of-domain test sets. CONCLUSIONS: The experimental results demonstrate that the proposed method is not only accurate but also robust to varying conditions of the test sets in comparison to several, related methods. These results suggest that the proposed method can facilitate automated cancer classification in various clinical settings.

The Effect of Chemical and Thermal Treatment for Desizing on the Properties and Chemical Functional Groups of Carbon Fiber.

In this paper, in order to upcycle carbon fibers (CF), the changes in their mechanical and chemical properties in accordance with time and temperature were investigated, in addition to the oxygen functional group mechanism. When acetone as a chemical desizing agent was used, treatment with acetone for 0.5 h at 60 °C was the optimal condition for the complete removal of the sizing agent, and there was no deterioration in tensile strength. At 25 °C, the carbonyl group (C=O) and hydroxyl group (C-O) declined in comparison to commercial CF, but a novel lactone group (O=C-O) was created. At 60 °C, the oxygen present in the sizing agent was removed and C=O, C-O, and O=C-O decreased. On the contrary, in the case of thermal desizing in an inert gas nitrogen atmosphere, by increasing the temperature, functional groups combining carbon and oxygen were reduced, because nitrogen and oxygen atoms combined with C=O and C-O on the CF surface were eliminated in the form of CO, NO, CO2, NO2, and O2. When desizing via chemical and thermal methods, the amount of functional groups combining carbon and oxygen on the CF surface decreased. Desizing was performed as a pretreatment for surface treatment, so the methods and conditions were different, and related research is insufficient. In this study, we attempted to derive the optimal conditions for desizing treatment by identifying the surface characteristics and mechanisms according to chemical and thermal desizing treatment methods.

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.

CaMeL-Net: Centroid-aware metric learning for efficient multi-class cancer classification in pathology images.

BACKGROUND AND OBJECTIVE: Cancer grading in pathology image analysis is a major task due to its importance in patient care, treatment, and management. The recent developments in artificial neural networks for computational pathology have demonstrated great potential to improve the accuracy and quality of cancer diagnosis. These improvements are generally ascribable to the advance in the architecture of the networks, often leading to increase in the computation and resources. In this work, we propose an efficient convolutional neural network that is designed to conduct multi-class cancer classification in an accurate and robust manner via metric learning. METHODS: We propose a centroid-aware metric learning network for an improved cancer grading in pathology images. The proposed network utilizes centroids of different classes within the feature embedding space to optimize the relative distances between pathology images, which manifest the innate similarities/dissimilarities between them. For improved optimization, we introduce a new loss function and a training strategy that are tailored to the proposed network and metric learning. RESULTS: We evaluated the proposed approach on multiple datasets of colorectal and gastric cancers. For the colorectal cancer, two different datasets were employed that were collected from different acquisition settings. the proposed method achieved an accuracy, F1-score, quadratic weighted kappa of 88.7%, 0.849, and 0.946 for the first dataset and 83.3%, 0.764, and 0.907 for the second dataset, respectively. For the gastric cancer, the proposed method obtained an accuracy of 85.9%, F1-score of 0.793, and quadratic weighted kappa of 0.939. We also found that the proposed method outperforms other competing models and is computationally efficient. CONCLUSIONS: The experimental results demonstrate that the prediction results by the proposed network are both accurate and reliable. The proposed network not only outperformed other related methods in cancer classification but also achieved superior computational efficiency during training and inference. The future study will entail further development of the proposed method and the application of the method to other problems and domains.

Ablation of the deubiquitinase USP15 ameliorates nonalcoholic fatty liver disease and nonalcoholic steatohepatitis.

Nonalcoholic fatty liver disease (NAFLD) occurs due to the accumulation of fat in the liver, leading to fatal liver diseases such as nonalcoholic steatohepatitis (NASH) and cirrhosis. Elucidation of the molecular mechanisms underlying NAFLD is critical for its prevention and therapy. Here, we observed that deubiquitinase USP15 expression was upregulated in the livers of mice fed a high-fat diet (HFD) and liver biopsies of patients with NAFLD or NASH. USP15 interacts with lipid-accumulating proteins such as FABPs and perilipins to reduce ubiquitination and increase their protein stability. Furthermore, the severity of NAFLD induced by an HFD and NASH induced by a fructose/palmitate/cholesterol/trans-fat (FPC) diet was significantly ameliorated in hepatocyte-specific USP15 knockout mice. Thus, our findings reveal an unrecognized function of USP15 in the lipid accumulation of livers, which exacerbates NAFLD to NASH by overriding nutrients and inducing inflammation. Therefore, targeting USP15 can be used in the prevention and treatment of NAFLD and NASH.

Serum 25-Hydroxyvitamin D Levels and Risk of Colorectal Cancer: An Age-Stratified Analysis.

BACKGROUND & AIMS: The role of circulating 25-hydroxyvitamin D (25(OH)D) in the prevention of early-onset colorectal cancer (CRC) in young adults aged <50 years is uncertain. We evaluated the age-stratified associations (<50 vs ≥50 years) between circulating 25(OH)D levels and the risk of CRC in a large sample of Korean adults. METHODS: Our cohort study included 236,382 participants (mean age, 38.0 [standard deviation, 9.0] years) who underwent a comprehensive health examination, including measurement of serum 25(OH)D levels. Serum 25(OH)D levels were categorized as <10, 10 to 20, and ≥20 ng/mL. CRC, along with the histologic subtype, site, and invasiveness, was ascertained through linkage with the national cancer registry. Cox proportional hazard models were used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for incident CRC according to the serum 25(OH)D status, with adjustment for potential confounders. RESULTS: During the 1,393,741 person-years of follow-up (median, 6.5 years; interquartile range, 4.5-7.5 years), 341 participants developed CRC (incidence rate, 19.2 per 105 person-years). Among young individuals aged <50 years, serum 25(OH)D levels were inversely associated with the risk of incident CRC with HRs (95% CIs) of 0.61 (0.43-0.86) and 0.41 (0.27-0.63) for 25(OH)D 10 to 19 ng/mL and ≥20 ng/mL, respectively, with respect to the reference (<10 ng/mL) (P for trend <.001, time-dependent model). Significant associations were evident for adenocarcinoma, colon cancer, and invasive cancers. For those aged ≥50 years, associations were similar, although slightly attenuated compared with younger individuals. CONCLUSIONS: Serum 25(OH)D levels may have beneficial associations with the risk of developing CRC for both early-onset and late-onset disease.

The Application of Guanidinium to Improve Biomolecule Quality in Fixed, Paraffin-embedded Tissue.

Neutral buffered formalin (NBF) is the most common fixative in clinical applications. However, NBF damages proteins and nucleic acids, limiting the quality of proteomic and nucleic acid-based assays. Prior studies have demonstrated that BE70, a fixative of buffered 70% ethanol, has many benefits over NBF but the degradation of proteins and nucleic acids in archival paraffin blocks remain a challenge. Thus, we evaluated the addition of guanidinium salts to BE70 with the hypothesis that this may protect RNA and protein. Guanidinium salt supplemented BE70 (BE70G)-fixed tissue is comparable with that of BE70 via histology and immunohistochemistry. Western blot analysis also revealed that HSP70, AKT, and glyceraldehyde 3-phosphate dehydrogenase (GAPDH) expression signals in BE70G-fixed tissue were higher than those in BE70-fixed tissue. The quality of nucleic acids extracted from BE70G-fixed, paraffin-embedded tissue was also superior, and BE70G provides improved protein and RNA quality at shorter fixation times than its predecessors. The degradation of proteins, AKT and GAPDH, in archival tissue blocks is also decreased with the addition of guanidinium salt to BE70. In conclusion, BE70G fixative improves the quality of molecular analysis with more rapid fixation of tissue and enhanced long-term storage of paraffin blocks at room temperature for evaluation of protein epitopes.

Mutant pattern of p53 predicts local recurrence and poor survival rate in gastric cancer.

BACKGROUND: TP53 mutation is a poor prognostic factor for various organ malignancies such as colorectal cancer, breast cancer, ovarian cancer, hepatocellular carcinoma, lung adenocarcinoma and clinical pathologists previously evaluated it using immunohistochemistry for p53. The clinicopathologic significance of p53 expression in gastric cancer remains unclear due to inconsistent classification methods. METHODS: Immunohistochemistry for p53 protein was performed using tissue microarray blocks generated from 725 cases of gastric cancer, and p53 expression was divided into three staining patterns using a semi-quantitative ternary classifier: heterogeneous (wild type), overexpression, and absence (mutant pattern). RESULTS: Mutant pattern of p53 expression had a male predominance, greater frequency in cardia/fundus, higher pT stage, frequent lymph node metastasis, local recurrence clinically, and more differentiated histology microscopically compared with wild type. In survival analysis, p53 mutant pattern was associated with worse recurrent-free survival and overall survival rates, and significance was maintained in subgroup analysis of early versus advanced gastric cancers. In Cox regression analysis, p53 mutant pattern was a significant predicting factor for local recurrence (relative risk (RR=4.882, p<0.001)) and overall survival (RR=2.040, p=0.007). The p53 mutant pattern remained significant for local recurrence (RR=2.934, p=0.018) in multivariate analyses. CONCLUSIONS: Mutant p53 pattern on immunohistochemistry was a significant prognostic factor for local recurrence and poor overall survival in gastric cancer.

Quality Assessment of Proteins and RNA Following Storage in Archival Formalin-Fixed Paraffin-Embedded Human Breast Cancer Tissue Microarray Sections.

Although the immunogenicity of formalin-fixed paraffin-embedded tissue sections can decrease during storage and transport, the exact mechanism of antigenic loss and how to prevent it are not clear. Herein, we investigated changes in the expression of estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER-2), E-cadherin, and Ki-67 in human breast tissue microarray (TMA) tissue sections stored for up to 3 months in dry and wet conditions. The positive rates of ER and PR expression were minimally changed after 3 months of storage, but the Allred scores of ER and PR stored in humid conditions decreased remarkably in comparison to fresh-cut tissue. The HER-2 antigenicity and RNA integrity of breast TMA sections stored in dry conditions diminished gradually with storage time, whereas the immunoreactivity and RNA quality of HER-2 in humid conditions decreased sharply as storage length increased. The area and intensity of E-cadherin staining in tissue sections stored in dry conditions did not change significantly and were minimally changed after 3 months, respectively. In contrast, the area and intensity of E-cadherin staining in tissue sections stored in humid conditions decreased significantly as storage length increased. Finally, the Ki-67 labeling index of tissue sections stored for 3 months in dry (9% decrease) and wet (31.9% decrease) conditions was decreased in comparison to fresh sections. In conclusion, these results indicate that water is a crucial factor for protein and RNA degradation in stored tissue sections, and detailed guidelines are required in the clinic.

The interferon-inducible protein viperin controls cancer metabolic reprogramming to enhance cancer progression.

Metabolic reprogramming is an important cancer hallmark. However, the mechanisms driving metabolic phenotypes of cancer cells are unclear. Here, we show that the interferon-inducible (IFN-inducible) protein viperin drove metabolic alteration in cancer cells. Viperin expression was observed in various types of cancer and was inversely correlated with the survival rates of patients with gastric, lung, breast, renal, pancreatic, or brain cancer. By generating viperin knockdown or stably expressing cancer cells, we showed that viperin, but not a mutant lacking its iron-sulfur cluster-binding motif, increased lipogenesis and glycolysis via inhibition of fatty acid ß-oxidation in cancer cells. In the tumor microenvironment, deficiency of fatty acids and oxygen as well as production of IFNs upregulated viperin expression via the PI3K/AKT/mTOR/HIF-1α and JAK/STAT pathways. Moreover, viperin was primarily expressed in cancer stem-like cells (CSCs) and functioned to promote metabolic reprogramming and enhance CSC properties, thereby facilitating tumor growth in xenograft mouse models. Collectively, our data indicate that viperin-mediated metabolic alteration drives the metabolic phenotype and progression of cancer.

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.

High expression of the phosphoinositide 3-kinase p11γ isoform can predict poor prognosis of non-small cell lung cancer.

The protein p110γ is an isoform of the catalytic subunit of class I phosphoinositide 3-kinases (PI3Ks). PI3Ks are involved in the regulation of cell survival, growth, proliferation, and migration and have been implicated in the oncogenesis of various cancers. In this study, p110γ expression in non-small cell lung cancer (NSCLC) and its association with clinicopathological factors and patient survival were evaluated. A total of 230 NSCLC tumors were immunohistochemically stained for p110γ. Of these, 174 (75.7%) and 56 (24.3%) were placed in the low and high expression groups, respectively. The positive rate of p110γ was significantly higher in adenocarcinoma than in squamous cell carcinoma (p⟨0.001). Advanced stage NSCLCs showed higher p110γ expression than those at an early stage (p=0.002). Irrespective of the histological tumor type, the patients with high p110γ expression had significantly worse overall survival than those with low p110γ expression (p=0.004). p110γ expression was an independent poor prognostic factor in the multivariate analysis. Our results suggest that p110γ may be involved in the development and progression of NSCLC, and that p110γ has promising potential as a prognostic factor or novel therapeutic target for NSCLC.

Effects of Heat Treatment Atmosphere and Temperature on the Properties of Carbon Fibers.

In this study, carbon fibers were heat-treated in a nitrogen and oxygen atmosphere according to temperature to elucidate the mechanism of chemical state changes and oxygen functional group changes on the carbon fiber surface by analyzing the mechanical and chemical properties of carbon fibers. Carbon fibers before and after heat treatment were analyzed using FE-SEM (Field Emission Scanning), UTM (Universal Tensile Testers), XPS (X-ray Photoelectron Spectroscopy), and surface-free energy. In the nitrogen atmosphere, which is an inert gas, the tensile strength was equivalent to that of the virgin up to 500 °C but decreased to 71% with respect to the virgin at 1000 °C. Furthermore, as the temperature increased from room temperature to 1000 °C, the oxygen functional group and the polar free energy gradually decreased compared with the virgin. On the other hand, in the oxygen atmosphere, which is an active gas, the tensile properties were not significantly different from those of the virgin up to 300 °C but gradually decreased at 500 °C. Above 600 °C, the carbon fibers deteriorated, and measurement was impossible. The oxygen functional group decreased at 300 °C, but above 300 °C, among the oxygen functional groups, the hydroxyl group and the carbonyl group increased. Furthermore, the lactone group formed and rapidly increased compared with the virgin, and the polar free energy increased as the temperature increased.

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.

Venous Invasion and Perineural Invasion as Upstaging and Poor Prognostic Factors in N0 Gastric Cancers.

BACKGROUND/AIM: Lymph node metastasis is an important prognostic factor in gastric cancer patients. In node-negative (N0) gastric cancer patients, additional prognostic factors are needed to reinforce TNM staging. PATIENTS AND METHODS: We semi-quantitatively recorded the presence of lymphatic, venous, and perineural invasion and evaluated the possibility that they could be used as upstaging factors in N0 gastric cancer by comparing N0 gastric cancer cases with N1 cases. RESULTS: Venous (p<0.001) and perineural (p<0.001) invasion were important factors in the relapse-free survival of N0 patients, but lymphatic invasion was not. N0 cases with venous or perineural invasion had survival curves similar to those of N1 patients. In addition, the number of invasive features (lymphatic, venous, or perineural) was an important factor in predicting poor patient survival. CONCLUSION: Venous and perineural invasion were significant prognostic factors in N0 gastric cancer cases. It is necessary to record lymphatic, venous, and perineural invasion separately in the pathology report, especially in cases of N0 gastric cancer.