Immunomarker Support Vector Machine Classifier for Prediction of Gastric Cancer Survival and Adjuvant Chemotherapeutic Benefit

Virtual multiplexed immunofluorescence staining from non-antibody-stained fluorescence imaging for gastric cancer prognosis

BACKGROUND

Multiplexed immunofluorescence (mIF) staining, such as CODEX and MIBI, holds significant clinical value for various fields, such as disease diagnosis, biological research, and drug development. However, these techniques are often hindered by high time and cost requirements.

METHODS

Here we present a Multimodal-Attention-based virtual mIF Staining (MAS) system that utilises a deep learning model to extract potential antibody-related features from dual-modal non-antibody-stained fluorescence imaging, specifically autofluorescence (AF) and DAPI imaging. The MAS system simultaneously generates predictions of mIF with multiple survival-associated biomarkers in gastric cancer using self- and multi-attention learning mechanisms.

FINDINGS

Experimental results with 180 pathological slides from 94 patients with gastric cancer demonstrate the efficiency and consistent performance of the MAS system in both cancer and noncancer gastric tissues. Furthermore, we showcase the prognostic accuracy of the virtual mIF images of seven gastric cancer related biomarkers, including CD3, CD20, FOXP3, PD1, CD8, CD163, and PD-L1, which is comparable to those obtained from the standard mIF staining.

INTERPRETATION

The MAS system rapidly generates reliable multiplexed staining, greatly reducing the cost of mIF and improving clinical workflow.

FUNDING

Stanford 2022 HAI Seed Grant; National Institutes of Health 1R01CA256890.

Screening of gastric cancer diagnostic biomarkers in the homologous recombination signaling pathway and assessment of their clinical and radiomic correlations

BACKGROUND

Homologous recombination plays a vital role in the occurrence and drug resistance of gastric cancer. This study aimed to screen new gastric cancer diagnostic biomarkers in the homologous recombination pathway and then used radiomic features to construct a prediction model of biomarker expression to guide the selection of chemotherapy regimens.

METHODS

Gastric cancer transcriptome data were downloaded from The Cancer Genome Atlas database. Machine learning methods were used to screen for diagnostic biomarkers of gastric cancer and validate them experimentally. Computed Tomography image data of gastric cancer patients and corresponding clinical data were downloaded from The Cancer Imaging Archive and our imaging centre, and then the Computed Tomography images were subjected to feature extraction, and biomarker expression prediction models were constructed to analyze the correlation between the biomarker radiomics scores and clinicopathological features.

RESULTS

We screened RAD51D and XRCC2 in the homologous recombination pathway as biomarkers for gastric cancer diagnosis by machine learning, and the expression of RAD51D and XRCC2 was significantly positively correlated with pathological T stage, N stage, and TNM stage. Homologous recombination pathway blockade inhibits gastric cancer cell proliferation, promotes apoptosis, and reduces the sensitivity of gastric cancer cells to chemotherapeutic drugs. Our predictive RAD51D and XRCC2 expression models were constructed using radiomics features, and all the models had high accuracy. In the external validation cohort, the predictive models still had decent accuracy. Moreover, the radiomics scores of RAD51D and XRCC2 were also significantly positively correlated with the pathologic T, N, and TNM stages.

CONCLUSIONS

The gastric cancer diagnostic biomarkers RAD51D and XRCC2 that we screened can, to a certain extent, reflect the expression status of genes through radiomic characteristics, which is of certain significance in guiding the selection of chemotherapy regimens for gastric cancer patients.

Comparative assessment of the capability of machine learning-based radiomic models for predicting omental metastasis in locally advanced gastric cancer

The study aims to investigate the predictive capability of machine learning algorithms for omental metastasis in locally advanced gastric cancer (LAGC) and to compare the performance metrics of various machine learning predictive models. A retrospective collection of 478 pathologically confirmed LAGC patients was undertaken, encompassing both clinical features and arterial phase computed tomography images. Radiomic features were extracted using 3D Slicer software. Clinical and radiomic features were further filtered through lasso regression. Selected clinical and radiomic features were used to construct omental metastasis predictive models using support vector machine (SVM), decision tree (DT), random forest (RF), K-nearest neighbors (KNN), and logistic regression (LR). The models' performance metrics included accuracy, area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In the training cohort, the RF predictive model surpassed LR, SVM, DT, and KNN in terms of accuracy, AUC, sensitivity, specificity, PPV, and NPV. Compared to the other four predictive models, the RF model significantly improved PPV. In the test cohort, all five machine learning predictive models exhibited lower PPVs. The DT model demonstrated the most significant variation in performance metrics relative to the other models, with a sensitivity of 0.231 and specificity of 0.990. The LR-based predictive model had the lowest PPV at 0.210, compared to the other four models. In the external validation cohort, the performance metrics of the predictive models were generally consistent with those in the test cohort. The LR-based model for predicting omental metastasis exhibited a lower PPV. Among the machine learning algorithms, the RF predictive model demonstrated higher accuracy and improved PPV relative to LR, SVM, KNN, and DT models.

Dissecting gastric cancer heterogeneity and exploring therapeutic strategies using bulk and single-cell transcriptomic analysis and experimental validation of tumor microenvironment and metabolic interplay

Gastric cancer, the fifth most prevalent cancer worldwide, is often diagnosed in advanced stages with limited treatment options. Examining the tumor microenvironment (TME) and its metabolic reprogramming can provide insights for better diagnosis and treatment. This study investigates the link between TME factors and metabolic activity in gastric cancer using bulk and single-cell RNA-sequencing data. We identified two molecular subtypes in gastric cancer by analyzing the distinct expression patterns of 81 prognostic genes related to the TME and metabolism, which exhibited significant protein-level interactions. The high-risk subtype had increased stromal content, fibroblast and M2 macrophage infiltration, elevated glycosaminoglycans/glycosphingolipids biosynthesis, and fat metabolism, along with advanced clinicopathological features. It also exhibited low mutation rates and microsatellite instability, associating it with the mesenchymal phenotype. In contrast, the low-risk group showed higher tumor content and upregulated protein and sugar metabolism. We identified a 15-gene prognostic signature representing these characteristics, including CPVL, KYNU, CD36, and GPX3, strongly correlated with M2 macrophages, validated through single-cell analysis and an internal cohort. Despite resistance to immunotherapy, the high-risk group showed sensitivity to molecular targeted agents directed at IGF-1R (BMS-754807) and the PI3K-mTOR pathways (AZD8186, AZD8055). We experimentally validated these promising drugs for their inhibitory effects on MKN45 and MKN28 gastric cells. This study unveils the intricate interplay between TME and metabolic pathways in gastric cancer, offering potential for enhanced diagnosis, patient stratification, and personalized treatment. Understanding molecular features in each subtype enriches our comprehension of gastric cancer heterogeneity and potential therapeutic targets.

Artificial intelligence in screening and diagnosis of surgical diseases: A narrative review

Artificial intelligence (AI) is playing an increasing role in several fields of medicine. It is also gaining popularity among surgeons as a valuable screening and diagnostic tool for many conditions such as benign and malignant colorectal, gastric, thyroid, parathyroid, and breast disorders. In the literature, there is no review that groups together the various application domains of AI when it comes to the screening and diagnosis of main surgical diseases. The aim of this review is to describe the use of AI in these settings. We performed a literature review by searching PubMed, Web of Science, Scopus, and Embase for all studies investigating the role of AI in the surgical setting, published between January 01, 2000, and June 30, 2023. Our focus was on randomized controlled trials (RCTs), meta-analysis, systematic reviews, and observational studies, dealing with large cohorts of patients. We then gathered further relevant studies from the reference list of the selected publications. Based on the studies reviewed, it emerges that AI could strongly enhance the screening efficiency, clinical ability, and diagnostic accuracy for several surgical conditions. Some of the future advantages of this technology include implementing, speeding up, and improving the automaticity with which AI recognizes, differentiates, and classifies the various conditions.

Global analysis of T-cell groups reveals immunological features and common antigen targets of digestive tract tumors

BACKGROUND

T cells are key players in the tumor immune microenvironment (TIME), as they can recognize and eliminate cancer cells that express neoantigens derived from somatic mutations. However, the diversity and specificity of T-cell receptors (TCRs) that recognize neoantigens are largely unknown, due to the high variability of TCR sequences among individuals.

METHODS

To address this challenge, we applied GLIPH2, a novel algorithm that groups TCRs based on their predicted antigen specificity and HLA restriction, to cluster the TCR repertoire of 1,702 patients with digestive tract cancer. The patients were divided into five groups based on whether they carried tumor-infiltrating or clonal-expanded TCRs and calculated their TCR diversity. The prognosis, tumor subtype, gene mutation, gene expression, and immune microenvironment of these groups were compared. Viral specificity inference and immunotherapy relevance analysis performed for the TCR groups.

RESULTS

This approach reduced the complexity of TCR sequences to 249 clonally expanded and 150 tumor-infiltrating TCR groups, which revealed distinct patterns of TRBV usage, HLA association, and TCR diversity. In gastric adenocarcinoma (STAD), patients with tumor-infiltrating TCRs (Patients-TI) had significantly worse prognosis than other patients (Patients-nonTI). Patients-TI had richer CD8+ T cells in the immune microenvironment, and their gene expression features were positively correlated with immunotherapy response. We also found that tumor-infiltrating TCR groups were associated with four distinct tumor subtypes, 26 common gene mutations, and 39 gene expression signatures. We discovered that tumor-infiltrating TCRs had cross-reactivity with viral antigens, indicating a possible link between viral infections and tumor immunity.

CONCLUSION

By applying GLIPH2 to TCR sequences from digestive tract tumors, we uncovered novel insights into the tumor immune landscape and identified potential candidates for shared TCRs and neoantigens.

From pixels to patient care: deep learning-enabled pathomics signature offers precise outcome predictions for immunotherapy in esophageal squamous cell cancer

BACKGROUND

Immunotherapy has significantly improved survival of esophageal squamous cell cancer (ESCC) patients, however the clinical benefit was limited to only a small portion of patients. This study aimed to perform a deep learning signature based on H&E-stained pathological specimens to accurately predict the clinical benefit of PD-1 inhibitors in ESCC patients.

METHODS

ESCC patients receiving PD-1 inhibitors from Shandong Cancer Hospital were included. WSI images of H&E-stained histological specimens of included patients were collected, and randomly divided into training (70%) and validation (30%) sets. The labels of images were defined by the progression-free survival (PFS) with the interval of 4 months. The pretrained ViT model was used for patch-level model training, and all patches were projected into probabilities after linear classifier. Then the most predictive patches were passed to RNN for final patient-level prediction to construct ESCC-pathomics signature (ESCC-PS). Accuracy rate and survival analysis were performed to evaluate the performance of ViT-RNN survival model in validation cohort.

RESULTS

163 ESCC patients receiving PD-1 inhibitors were included for model training. There were 486,188 patches of 1024*1024 pixels from 324 WSI images of H&E-stained histological specimens after image pre-processing. There were 120 patients with 227 images in training cohort and 43 patients with 97 images in validation cohort, with balanced baseline characteristics between two groups. The ESCC-PS achieved an accuracy of 84.5% in the validation cohort, and could distinguish patients into three risk groups with the median PFS of 2.6, 4.5 and 12.9 months (P < 0.001). The multivariate cox analysis revealed ESCC-PS could act as an independent predictor of survival from PD-1 inhibitors (P < 0.001). A combined signature incorporating ESCC-PS and expression of PD-L1 shows significantly improved accuracy in outcome prediction of PD-1 inhibitors compared to ESCC-PS and PD-L1 anlone, with the area under curve value of 0.904, 0.924, 0.610 for 6-month PFS and C-index of 0.814, 0.806, 0.601, respectively.

CONCLUSIONS

The outcome supervised pathomics signature based on deep learning has the potential to enable superior prognostic stratification of ESCC patients receiving PD-1 inhibitors, which convert the images pixels to an effective and labour-saving tool to optimize clinical management of ESCC patients.

Comprehensive assessment of immune context and immunotherapy response via noninvasive imaging in gastric cancer

BACKGROUNDThe tumor immune microenvironment can provide prognostic and therapeutic information. We aimed to develop noninvasive imaging biomarkers from computed tomography (CT) for comprehensive evaluation of immune context and investigate their associations with prognosis and immunotherapy response in gastric cancer (GC).METHODSThis study involved 2,600 patients with GC from 9 independent cohorts. We developed and validated 2 CT imaging biomarkers (lymphoid radiomics score [LRS] and myeloid radiomics score [MRS]) for evaluating the IHC-derived lymphoid and myeloid immune context respectively, and integrated them into a combined imaging biomarker [LRS/MRS: low(-) or high(+)] with 4 radiomics immune subtypes: 1 (-/-), 2 (+/-), 3 (-/+), and 4 (+/+). We further evaluated the imaging biomarkers' predictive values on prognosis and immunotherapy response.RESULTSThe developed imaging biomarkers (LRS and MRS) had a high accuracy in predicting lymphoid (AUC range: 0.765-0.773) and myeloid (AUC range: 0.736-0.750) immune context. Further, similar to the IHC-derived immune context, 2 imaging biomarkers (HR range: 0.240-0.761 for LRS; 1.301-4.012 for MRS) and the combined biomarker were independent predictors for disease-free and overall survival in the training and all validation cohorts (all P < 0.05). Additionally, patients with high LRS or low MRS may benefit more from immunotherapy (P < 0.001). Further, a highly heterogeneous outcome on objective response ​rate was observed in 4 imaging subtypes: 1 (-/-) with 27.3%, 2 (+/-) with 53.3%, 3 (-/+) with 10.2%, and 4 (+/+) with 30.0% (P < 0.0001).CONCLUSIONThe noninvasive imaging biomarkers could accurately evaluate the immune context and provide information regarding prognosis and immunotherapy for GC.

Artificial Intelligence-Enabled Gastric Cancer Interpretations: Are We There yet?

The integration of digital pathology and artificial intelligence (AI) is revolutionizing pathology by providing pathologists with new tools to improve workflow, enhance diagnostic accuracy, and undertake novel discovery. The capability of AI to recognize patterns and features in digital images beyond human perception is particularly valuable, thereby providing additional information for prognostic and predictive purposes. AI-based tools diagnose gastric carcinoma in digital images, detect gastric carcinoma metastases in lymph nodes, automate Ki-67 scoring in gastric neuroendocrine tumors, and quantify tumor-infiltrating lymphocytes. This article provides an overview of all of these applications of AI pertaining to gastric cancer.

Identification of disulfidptosis-related subtypes and development of a prognosis model based on stacking framework in renal clear cell carcinoma

BACKGROUND

Clear cell renal cell carcinoma (ccRCC) is a common malignant tumor with an unsatisfactory prognosis. This study aims to identify the expression patterns of disulfidptosis-related genes (DRGs), develop a prognostic model, and predict immunological profiles.

METHODS

First, we identified differentially expressed DRGs in TCGA-KIRC cohort and analyzed their mutational profiles, methylation levels, and interaction networks. Subsequently, we identified disulfidptosis-associated molecular subtypes and investigated their prognostic and immunological characteristics. Simultaneously, a disulfidptosis-related prognostic signature (DRPS) was developed using a two-stage stacking framework consisting of 5 machine learning models. The effect of DRPS on immune cell infiltration levels was explored using seven different algorithms, and the status and function of T cells for distinct risk-score groups were evaluated based on T cell exhaustion and dysfunction scores. Additionally, the study also examined differences in clinical characteristics and therapy efficacy between high- and low-risk groups.

RESULTS

We found two disulfidptosis-associated clusters, one of which had a poor prognosis and was linked to high immune cell infiltration but impaired T cell function. DRPS showed excellent predictive performance in all four cohorts and could accurately identified disulfidptosis-related molecular subtypes. The DRPS-based risk score was positively associated with poor prognosis, malignant pathological features, high immune cell infiltration levels, and T cell exhaustion or dysfunction, and better respond to immunotherapy and targeted therapy. Additionally, we have identified a close association between ISG20 and disulfidptosis as well as tumor immunity.

CONCLUSION

Our study identified distinct disulfidptosis-related subtypes in ccRCC patients, and constructed the highly accurate and robust DRPS based on an ensemble learning framework, which has critical reference value in clinical decision-making and individualized treatment. And this work also revealed ISG20 exhibits promising potential as a therapeutic target for ccRCC.

Early prediction of response to palliative chemotherapy in patients with stage-IV gastric and esophageal cancer

BACKGROUND

The goal of therapy for many patients with advanced stage malignancies, including those with metastatic gastric and esophageal cancers, is to extend overall survival while also maintaining quality of life. After weighing the risks and benefits of treatment with palliative chemotherapy (PC) with non-curative intent, many patients decide to pursue treatment. It is known that a subset of patients who are treated with PC experience significant side effects without clinically significant survival benefits from PC.

METHODS

We use data from 150 patients with stage-IV gastric and esophageal cancers to train machine learning models that predict whether a patient with stage-IV gastric or esophageal cancers would benefit from PC, in terms of increased survival duration, at very early stages of the treatment.

RESULTS

Our findings show that machine learning can predict with high accuracy whether a patient will benefit from PC at the time of diagnosis. More accurate predictions can be obtained after only two cycles of PC (i.e., about 4 weeks after diagnosis). The results from this study are promising with regard to potential improvements in quality of life for patients near the end of life and a potential overall survival benefit by optimizing systemic therapy earlier in the treatment course of patients.

Personalized prediction for multiple chronic diseases by developing the multi-task Cox learning model

Personalized prediction of chronic diseases is crucial for reducing the disease burden. However, previous studies on chronic diseases have not adequately considered the relationship between chronic diseases. To explore the patient-wise risk of multiple chronic diseases, we developed a multitask learning Cox (MTL-Cox) model for personalized prediction of nine typical chronic diseases on the UK Biobank dataset. MTL-Cox employs a multitask learning framework to train semiparametric multivariable Cox models. To comprehensively estimate the performance of the MTL-Cox model, we measured it via five commonly used survival analysis metrics: concordance index, area under the curve (AUC), specificity, sensitivity, and Youden index. In addition, we verified the validity of the MTL-Cox model framework in the Weihai physical examination dataset, from Shandong province, China. The MTL-Cox model achieved a statistically significant (p<0.05) improvement in results compared with competing methods in the evaluation metrics of the concordance index, AUC, sensitivity, and Youden index using the paired-sample Wilcoxon signed-rank test. In particular, the MTL-Cox model improved prediction accuracy by up to 12% compared to other models. We also applied the MTL-Cox model to rank the absolute risk of nine chronic diseases in patients on the UK Biobank dataset. This was the first known study to use the multitask learning-based Cox model to predict the personalized risk of the nine chronic diseases. The study can contribute to early screening, personalized risk ranking, and diagnosing of chronic diseases.

Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics

The tumor microenvironment (TME) plays a critical role in disease progression and is a key determinant of therapeutic response in cancer patients. Here, we propose a noninvasive approach to predict the TME status from radiological images by combining radiomics and deep learning analyses. Using multi-institution cohorts of 2,686 patients with gastric cancer, we show that the radiological model accurately predicted the TME status and is an independent prognostic factor beyond clinicopathologic variables. The model further predicts the benefit from adjuvant chemotherapy for patients with localized disease. In patients treated with checkpoint blockade immunotherapy, the model predicts clinical response and further improves predictive accuracy when combined with existing biomarkers. Our approach enables noninvasive assessment of the TME, which opens the door for longitudinal monitoring and tracking response to cancer therapy. Given the routine use of radiologic imaging in oncology, our approach can be extended to many other solid tumor types.

Development of a machine learning algorithm to predict complications of total laparoscopic anterior resection and natural orifice specimen extraction surgery in rectal cancer

BACKGROUND

Total laparoscopic anterior resection (tLAR) and natural orifice specimen extraction surgery (NOSES) has been widely adopted in the treatment of rectal cancer (RC). However, no study has been performed to predict the short-term outcomes of tLAR using machine learning algorithms to analyze a national cohort.

METHODS

Data from consecutive RC patients who underwent tLAR were collected from the China NOSES Database (CNDB). The random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), deep neural network (DNN), logistic regression (LR) and K-nearest neighbor (KNN) algorithms were used to develop risk models to predict short-term complications of tLAR. The area under the receiver operating characteristic curve (AUROC), Gini coefficient, specificity and sensitivity were calculated to assess the performance of each risk model. The selected factors from the models were evaluated by relative importance.

RESULTS

A total of 4313 RC patients were identified, and 667 patients (15.5%) developed postoperative complications. The machine learning model of XGBoost showed more promising results in the prediction of complication than other models (AUROC 0.90, P < 0.001). The performance was similar when internal and external validation was used. In the XGBoost model, the top four influential factors were the distance from the lower edge of the tumor to the anus, age at diagnosis, surgical time and comorbidities. In risk stratification analysis, the rate of postoperative complications in the high-risk group was significantly higher than in the medium- and low-risk groups (P < 0.001).

CONCLUSION

The machine learning model shows potential benefits in predicting the risk of complications in RC patients after tLAR. This novel approach can provide reliable individual information for surgical treatment recommendations.

Artificial intelligence in theranostics of gastric cancer, a review

Gastric cancer (GC) is one of the commonest cancers with high morbidity and mortality in the world. How to realize precise diagnosis and therapy of GC owns great clinical requirement. In recent years, artificial intelligence (AI) has been actively explored to apply to early diagnosis and treatment and prognosis of gastric carcinoma. Herein, we review recent advance of AI in early screening, diagnosis, therapy and prognosis of stomach carcinoma. Especially AI combined with breath screening early GC system improved 97.4 % of early GC diagnosis ratio, AI model on stomach cancer diagnosis system of saliva biomarkers obtained an overall accuracy of 97.18 %, specificity of 97.44 %, and sensitivity of 96.88 %. We also discuss concept, issues, approaches and challenges of AI applied in stomach cancer. This review provides a comprehensive view and roadmap for readers working in this field, with the aim of pushing application of AI in theranostics of stomach cancer to increase the early discovery ratio and curative ratio of GC patients.

Evaluation the benefits of additional radiotherapy for gastric cancer patients after D2 resection using CT based radiomics

OBJECTIVES

The value of adding radiotherapy (RT) is still unclear for patients with gastric cancer (GC) after D2 lymphadenectomy. The purpose of this study is to predict and compare the overall survival (OS) and disease-free survival (DFS) of GC patients treated by chemotherapy and chemoradiation based on contrast-enhanced CT (CECT) radiomics.

METHODS

A total of 154 patients treated by chemotherapy and chemoradiation in authors' hospital were retrospectively reviewed and randomly divided into the training and testing cohorts (7:3). Radiomics features were extracted from contoured tumor volumes in CECT using the pyradiomics software. Radiomics score and nomogram with integrated clinical factors were developed to predict the OS and DFS and evaluated with Harrell's Consistency Index (C-index).

RESULTS

Radiomics score achieved a C index of 0.721(95%CI: 0.681-0.761) and 0.774 (95%CI: 0.738-0.810) in the prediction of DFS and OS for GC patients treated by chemotherapy and chemoradiation, respectively. The benefits of additional RT only demonstrated in subgroup of GC patients with Lauren intestinal type and perineural invasion (PNI). Integrating clinical factors further improved the prediction ability of radiomics models with a C-index of 0.773 (95%CI: 0.736-0.810) and 0.802 (95%CI: 0.765-0.839) for DFS and OS, respectively.

CONCLUSIONS

CECT based radiomics is feasible to predict the OS and DFS for GC patients underwent chemotherapy and chemoradiation after D2 resection. The benefits of additional RT only observed in GC patients with intestinal cancer and PNI.

Gene signature developed for predicting early relapse and survival in early-stage pancreatic cancer

BACKGROUND

The aim of this study was to construct a predictive signature integrating tumour-mutation- and copy-number-variation-associated features using machine learning to precisely predict early relapse and survival in patients with resected stage I-II pancreatic ductal adenocarcinoma.

METHODS

Patients with microscopically confirmed stage I-II pancreatic ductal adenocarcinoma undergoing R0 resection at the Chinese PLA General Hospital between March 2015 and December 2016 were enrolled. Whole exosome sequencing was performed, and genes with different mutation or copy number variation statuses between patients with and without relapse within 1 year were identified using bioinformatics analysis. A support vector machine was used to evaluate the importance of the differential gene features and to develop a signature. Signature validation was performed in an independent cohort. The associations of the support vector machine signature and single gene features with disease-free survival and overall survival were assessed. Biological functions of integrated genes were further analysed.

RESULTS

Overall, 30 and 40 patients were included in the training and validation cohorts, respectively. Some 11 genes with differential patterns were first identified; using a support vector machine, four features (mutations of DNAH9, TP53, and TUBGCP6, and copy number variation of TMEM132E) were further selected and integrated to construct a predictive signature (the support vector machine classifier). In the training cohort, the 1-year disease-free survival rates were 88 per cent (95 per cent c.i. 73 to 100) and 7 per cent (95 per cent c.i. 1 to 47) in the low-support vector machine subgroup and the high-support vector machine subgroup respectively (P < 0.001). Multivariable analyses showed that high support vector machine was significantly and independently associated with both worse overall survival (HR 29.20 (95 per cent c.i. 4.48 to 190.21); P < 0.001) and disease-free survival (HR 72.04 (95 per cent c.i. 6.74 to 769.96); P < 0.001). The area under the curve of the support vector machine signature for 1-year disease-free survival (0.900) was significantly larger than the area under the curve values of the mutations of DNAH9 (0.733; P = 0.039), TP53 (0.767; P = 0.024), and TUBGCP6 (0.733; P = 0.023), the copy number variation of TMEM132E (0.700; P = 0.014), TNM stage (0.567; P = 0.002), and differentiation grade (0.633; P = 0.005), suggesting higher predictive accuracy for prognosis. The value of the signature was further validated in the validation cohort. The four genes included in the support vector machine signature (DNAH9, TUBGCP6, and TMEM132E were novel in pancreatic ductal adenocarcinoma) were significantly associated with the tumour immune microenvironment, G protein-coupled receptor binding and signalling, cell-cell adhesion, etc.

CONCLUSION

The newly constructed support vector machine signature precisely and powerfully predicted relapse and survival in patients with stage I-II pancreatic ductal adenocarcinoma after R0 resection.

Dual-Regulated Mechanism of EZH2 and KDM6A on SALL4 Modulates Tumor Progression via Wnt/β-Catenin Pathway in Gastric Cancer

BACKGROUND

SALL4 has been demonstrated in many cancers and participated in tumorigenesis and tumor progression, however, its expression and function still remain ambiguous in GC, especially its upstream mechanistic modulators.

PURPOSE

We explored whether the dual mediation of EZH2 and KDM6A could be involved in upstream regulation of SALL4, which promotes GC cell progression via the Wnt/β-catenin pathway.

METHOD

Analysis of discrepant gene expression in GC and normal gastric tissues from The Cancer Genome Atlas (TCGA) dataset. GC cell lines were transfected by siEZH2 and siKDM6A, the transduction molecules of KDM6A/EZH2-SALL4-β-catenin signaling were quantified in the GC cells.

RESULTS

Here, we showed that only SALL4 levels of SALL family members were upregulated in nonpaired and paired GC tissues than those in corresponding normal tissues and were associated with its histological types, pathological stages, TNM stages including T stage (local invasion), N stage (lymph node metastasis), M stage (distant metastasis), and overall survival from the TCGA dataset. SALL4 level was elevated in GC cells compared to normal gastric epithelial cell line (GES-1) and was correlated to cancer cell progression and invasion through the Wnt/β-catenin pathway in GC, which levels would be separately upregulated or downregulated by KDM6A or EZH2.

CONCLUSION

We first proposed and demonstrated that SALL4 promoted GC cell progression via the Wnt/β-catenin pathway, which was mediated by the dual regulation of EZH2 and KDM6A on SALL4. This mechanistic pathway in gastric cancer represents a novel targetable pathway.

An open source pipeline for quantitative immunohistochemistry image analysis of inflammatory skin disease using artificial intelligence

BACKGROUND

The application of artificial intelligence (AI) to whole slide images has the potential to improve research reliability and ultimately diagnostic efficiency and service capacity. Image annotation plays a key role in AI and digital pathology. However, the work-streams required for tissue-specific (skin) and immunostain-specific annotation has not been extensively studied compared with the development of AI algorithms.

OBJECTIVES

The objective of this study is to develop a common workflow for annotating whole slide images of biopsies from inflammatory skin disease immunostained with a variety of epidermal and dermal markers prior to the development of the AI-assisted analysis pipeline.

METHODS

A total of 45 slides containing 3-5 sections each were scanned using Aperio AT2 slide scanner (Leica Biosystems). These slides were annotated by hand using a commonly used image analysis tool which resulted in more than 4000 images blocks. We used deep learning (DL) methodology to first sequentially segment (epidermis and upper dermis), with the exclusion of common artefacts and second to quantify the immunostained signal in those two compartments of skin biopsies and the ratio of positive cells.

RESULTS

We validated two DL models using 10-fold validation runs and by comparing to ground truth manually annotated data. The models achieved an average (global) accuracy of 95.0% for the segmentation of epidermis and dermis and 86.1% for the segmentation of positive/negative cells.

CONCLUSIONS

The application of two DL models in sequence facilitates accurate segmentation of epidermal and dermal structures, exclusion of common artefacts and enables the quantitative analysis of the immunostained signal. However, inaccurate annotation of the slides for training the DL model can decrease the accuracy of the output. Our open source code will facilitate further external validation across different immunostaining platforms and slide scanners.

Contribution of macro- and micronutrients intake to gastrointestinal cancer mortality in the ONCONUT cohort: Classical vs. modern approaches

The aim of this study was to evaluate the contribution of macro- and micronutrients intake to mortality in patients with gastrointestinal cancer, comparing the classical statistical approaches with a new generation algorithm. In 1992, the ONCONUT project was started with the aim of evaluating the relationship between diet and cancer development in a Southern Italian elderly population. Patients who died of specific death causes (ICD-10 from 150.0 to 159.9) were included in the study (n = 3,505) and survival analysis was applied. This cohort was used to test the performance of different techniques, namely Cox proportional-hazards model, random survival forest (RSF), Survival Support Vector Machine (SSVM), and C-index, applied to quantify the performance. Lastly, the new prediction mode, denominated Shapley Additive Explanation (SHAP), was adopted. RSF had the best performance (0.7653711 and 0.7725246, for macro- and micronutrients, respectively), while SSVM had the worst C-index (0.5667753 and 0.545222). SHAP was helpful to understand the role of single patient features on mortality. Using SHAP together with RSF and classical CPH was most helpful, and shows promise for future clinical applications.

Increased expression of LINC00323 correlates with tumor progression and poor prognosis of gastric cancer

BACKGROUD/AIMS

LINC00323 is a novel lncRNA which has reported to play an important role in the development and recurrence in several cancers. However, the expression and predictive value of LINC00323 in gastric cancer (GC) remain mysterious.

METHODS

LINC00323 expression in GC tissues and adjacent normal tissues was evaluated by quantitative reverse-transcription PCR (qRT-PCR). The relationship between LINC00323 expression and clinicopathological features and patients' survival were analyzed. Univariate and multivariate survival analyses were performed.

RESULTS

LINC00323 expression were found to be significantly increased in GC tissues. High expression of LINC00323 exerted a pro-tumor effect in the late stage of GC development. Kaplan-Meier analysis showed that patients with high LINC00323 were associated with poor overall survival (OS) and progression-free survival (PFS). Moreover, the combination of TNM stage and drinking status better identified GC patient outcome than those of TNM stage alone.

CONCLUSIONS

Our data showed that LINC00323 overexpression might serve as a novel independent prognostic factor for survival of GC patients, suggesting LINC00323 was a potential biomarker and therapeutic target for GC.

ImmuneScore of eight-gene signature predicts prognosis and survival in patients with endometrial cancer

Background

Endometrial cancer (EC) is a common gynecological cancer worldwide and the sixth most common female malignant tumor. A large number of studies conducted through database mining have identified many biomarkers that may be related to survival and prognosis. However, the predictive ability of single-gene biomarkers is not sufficiently accurate. In recent years, tumors have been shown to interact closely with their microenvironment, and tumor-infiltrating immune cells in the tumor microenvironment were associated with therapeutic effects. Furthermore, sequencing technology has evolved and allowed the identification of genetic signatures that may improve prediction results. The purpose of this research was to discover the Cancer Genome Atlas (TCGA) data to evaluate new genetic features that can predict the prognosis of EC.

Methods

mRNA expression profiling was analyzed in patients with EC identified in the TCGA database (n = 530). Differentially expressed genes at different stages of EC were screened using the immune cell enrichment score (ImmuneScore). Univariate and multivariate Cox regression analyses was applied to evaluate genes significantly related to overall survival and establish the prognostic risk parameter formula. Kaplan-Meier survival curves and the logarithmic rank method were applied to verify the importance of risk parameters for the prognostic forecast. The accuracy of survival prediction was confirmed using the nomogram and Receiver Operating Characteristic (ROC) curve analysis. The mRNA expression of eight genes were measured by qRT-PCR. According to COX and HR values, NBAT1, a representative gene among 8 genes, was selected for CCK-8 assay, colony formation assay and transwell invasion assay to verify the effect on survival.

Results

Eight related genes (NBAT1, GFRA4, PTPRT, DLX4, RANBP3L, UNQ6494, KLRB1, and PRAC1) were discovered to be significantly associated with the overall survival rate. According to these eight-gene signatures, 530 patients with EC were assigned to high- and low-risk subgroups. The prognostic capability of the eight-gene signature was not influenced by other elements.

Conclusions

Eight related gene markers were identified using ImmuneScore, which could predict prognosis and survival in patients with EC. These findings provide a basis for understanding the application of biological information in tumors and identifying the poor prognosis of EC.

Artificial intelligence applications in predicting the behavior of gastrointestinal cancers in pathology

Recent research has provided a wealth of data supporting the application of artificial intelligence (AI)-based applications in routine pathology practice. Indeed, it is clear that these methods can significantly support an accurate and rapid diagnosis by eliminating errors, increasing reliability, and improving workflow. In addition, the effectiveness of AI in the pathological evaluation of prognostic parameters associated with behavior, course, and treatment in many types of tumors has also been noted. Regarding gastrointestinal system (GIS) cancers, the contribution of AI methods to pathological diagnosis has been investigated in many studies. On the other hand, studies focusing on AI applications in evaluating parameters to determine tumor behavior are relatively few. For this purpose, the potential of AI models has been studied over a broad spectrum, from tumor subtyping to the identification of new digital biomarkers. The capacity of AI to infer genetic alterations of cancer tissues from digital slides has been demonstrated. Although current data suggest the merit of AI-based approaches in assessing tumor behavior in GIS cancers, a wide range of challenges still need to be solved, from laboratory infrastructure to improving the robustness of algorithms, before incorporating AI applications into real-life GIS pathology practice. This review aims to present data from AI applications in evaluating pathological parameters related to the behavior of GIS cancer with an overview of the opportunities and challenges encountered in implementing AI in pathology.

DKK1 as a robust predictor for adjuvant platinum chemotherapy benefit in resectable pStage II-III gastric cancer

BACKGROUND

Adjuvant chemotherapy (ACT) with 5-FU alone or 5-FU plus platinum after curative surgery improves the prognosis of pStage II-III gastric cancer (GC). However, only a subset of patients benefits from adjuvant platinum. To avoid the side effects of platinum, it is significant to accurately screen the patients who would benefit maximally with this treatment. The present study aimed to assess the value of DKK1 in predicting the benefit of adjuvant platinum chemotherapy in patients with pStage II -III GC.

METHODS

Platinum sensitivity-related genes were screened by bioinformatics. DKK1 expression in 380 GC specimens was detected by immunohistochemistry (IHC) staining, and the correlation with adjuvant platinum-specific benefits were analyzed.

RESULTS

DKK1 was screened as the most significant platinum sensitivity-related gene. In patients with DKK1^high GC, the estimated absolute 5-year overall survival (OS) benefits from adjuvant platinum for pStage II-III, II, IIIA, IIIB, and IIIC were 25.5%, 17.3%, 36.4%, 29.2% and 31.1%, respectively, and the estimated absolute 5-year disease-free survival (DFS) benefits in the corresponding stages were 27.4%, 17.5%, 36.7%, 29.7% and 31.5%, respectively. These benefits were significantly higher than those in the same TNM stage without adjusting for DKK1 status. The performance of DKK1 was independent of the TNM stage and other clinicopathological variables. Similar results were obtained in the TCGA and ACRG cohorts. Furthermore, nomograms were constructed to predict the survival benefits in DKK1 subgroups.

CONCLUSIONS

The stratification strategy based on DKK1 status is more precise than the TNM staging system for the selection of pStage II-III GC patients suitable for platinum-containing ACT.

Post-operative anastomotic leakage and collagen changes in patients with rectal cancer undergoing neoadjuvant chemotherapy vs chemoradiotherapy

Background

A significant difference in the anastomotic leakage (AL) rate has been observed between patients with locally advanced rectal cancer who have undergone preoperative chemotherapy and those undergoing preoperative chemoradiotherapy. This study aimed to quantitatively analyse collagen structural changes caused by preoperative chemoradiotherapy and illuminate the relationship between collagen changes and AL.

Methods

Anastomotic distal and proximal "doughnut" specimens from the Sixth Affiliated Hospital of Sun Yat-sen University (Guangzhou, China) were quantitatively assessed for collagen structural changes between patients with and without preoperative radiotherapy using multiphoton imaging. Then, patients treated with preoperative chemoradiotherapy were used as a training cohort to construct an AL-SVM classifier by the Mann-Whitney U test and support vector machine (SVM). An independent test cohort from the Fujian Province Cancer Hospital (Fuzhou, China) was used to validate the AL-SVM classifier.

Results

A total of 207 patients were included from the Sixth Affiliated Hospital of Sun Yat-sen University. The AL rate in the preoperative chemoradiotherapy group (n = 107) was significantly higher than that in the preoperative chemotherapy group (n = 100) (21.5% vs 7.0%, P = 0.003). A fully quantitative analysis showed notable morphological and spatial distribution feature changes in collagen in the preoperative chemoradiotherapy group. Then, the patients who received preoperative chemoradiotherapy were used as a training cohort to construct the AL-SVM classifier based on five collagen features and the tumor distance from the anus. The AL-SVM classifier showed satisfactory discrimination and calibration with areas under the curve of 0.907 and 0.856 in the training and test cohorts, respectively.

Conclusions

The collagen structure may be notably altered by preoperative radiotherapy. The AL-SVM classifier was useful for the individualized prediction of AL in rectal cancer patients undergoing preoperative chemoradiotherapy.

Non-invasive measurement of tumor immune microenvironment and prediction of survival and chemotherapeutic benefits from 18F fluorodeoxyglucose PET/CT images in gastric cancer

BACKGROUND

The tumor immune microenvironment could provide prognostic and predictive information. It is necessary to develop a noninvasive radiomics-based biomarker of a previously validated tumor immune microenvironment signature of gastric cancer (GC) with immunohistochemistry staining.

METHODS

A total of 230 patients (training (n = 153) or validation (n = 77) cohort) with gastric cancer were subjected to (Positron Emission Tomography-Computed Tomography) radiomics feature extraction (80 features). A radiomics tumor immune microenvironment score (RTIMS) was developed to predict the tumor immune microenvironment signature with LASSO logistic regression. Furthermore, we evaluated its relation with prognosis and chemotherapy benefits.

RESULTS

A 8-feature radiomics signature was established and validated (area under the curve=0.692 and 0.713). The RTIMS signature was significantly associated with disease-free survival and overall survival both in the training and validation cohort (all P<0.001). RTIMS was an independent prognostic factor in the Multivariate analysis. Further analysis revealed that high RTIMS patients benefitted from adjuvant chemotherapy (for DFS, stage II: HR 0.208(95% CI 0.061-0.711), p=0.012; stage III: HR 0.321(0.180-0.570), p<0.001, respectively); while there were no benefits from chemotherapy in a low RTIMS patients.

CONCLUSION

This PET/CT radiomics model provided a promising way to assess the tumor immune microenvironment and to predict clinical outcomes and chemotherapy response. The RTIMS signature could be useful in estimating tumor immune microenvironment and predicting survival and chemotherapy benefit for patients with gastric cancer, when validated by further prospective randomized trials.

The genetic algorithm-aided three-stage ensemble learning method identified a robust survival risk score in patients with glioma

Ensemble learning is a kind of machine learning method which can integrate multiple basic learners together and achieve higher accuracy. Recently, single machine learning methods have been established to predict survival for patients with cancer. However, it still lacked a robust ensemble learning model with high accuracy to pick out patients with high risks. To achieve this, we proposed a novel genetic algorithm-aided three-stage ensemble learning method (3S score) for survival prediction. During the process of constructing the 3S score, double training sets were used to avoid over-fitting; the gene-pairing method was applied to reduce batch effect; a genetic algorithm was employed to select the best basic learner combination. When used to predict the survival state of glioma patients, this model achieved the highest C-index (0.697) as well as area under the receiver operating characteristic curve (ROC-AUCs) (first year = 0.705, third year = 0.825 and fifth year = 0.839) in the combined test set (n = 1191), compared with 12 other baseline models. Furthermore, the 3S score can distinguish survival significantly in eight cohorts among the total of nine independent test cohorts (P &lt; 0.05), achieving significant improvement of ROC-AUCs. Notably, ablation experiments demonstrated that the gene-pairing method, double training sets and genetic algorithm make sure the robustness and effectiveness of the 3S score. The performance exploration on pan-cancer showed that the 3S score has excellent ability on survival prediction in five kinds of cancers, which was verified by Cox regression, survival curves and ROC curves together. To enable its clinical adoption, we implemented the 3S score and other two clinical factors as an easy-to-use web tool for risk scoring and therapy stratification in glioma patients.

An artificial intelligence model to predict survival and chemotherapy benefits for gastric cancer patients after gastrectomy development and validation in international multicenter cohorts

BACKGROUND

Gastric cancer (GC) is a major health problem worldwide, with high prevalence and mortality. The present GC staging system provides inadequate prognostic information and does not reflect the chemotherapy benefit of GC.

METHODS

Two hundred fifty-five patients who underwent surgical resection were enrolled in our study (training cohort = 212, internal validation cohort = 43). Nine clinicopathologic features were obtained to construct an support vector machine (SVM) model. The cohorts from 4 domestic centres and The Cancer Genome Atlas (TCGA) were used for external validation.

RESULTS

In the training cohort, the AUCs were 0.773 (95% CI 0.708-0.838) for 5-year overall survival (OS) and 0.751 (95% CI 0.683-0.820) for 5-year disease-free survival (DFS); in the domestic validation cohort, the AUCs were 0.852 (95% CI 0.810-0.894) and 0.837 (95% CI 0.792-0.882), respectively. The model performed better than the TNM staging system according to the receiver operator characteristic(ROC) curve. GC patients were significantly divided into low, moderate and high risk based on the SVM. High-risk TNM stage Ⅱ and Ⅲ patients were more likely to benefit from adjuvant chemotherapy than low-risk patients.

CONCLUSIONS

The SVM-based model may be used to predict OS and DFS in GC patients and the benefit of adjuvant chemotherapy in TNM stage Ⅱ and Ⅲ GC patients.

Noninvasive imaging of the tumor immune microenvironment correlates with response to immunotherapy in gastric cancer

The tumor immune microenvironment (TIME) is associated with tumor prognosis and immunotherapy response. Here we develop and validate a CT-based radiomics score (RS) using 2272 gastric cancer (GC) patients to investigate the relationship between the radiomics imaging biomarker and the neutrophil-to-lymphocyte ratio (NLR) in the TIME, including its correlation with prognosis and immunotherapy response in advanced GC. The RS achieves an AUC of 0.795-0.861 in predicting the NLR in the TIME. Notably, the radiomics imaging biomarker is indistinguishable from the IHC-derived NLR status in predicting DFS and OS in each cohort (HR range: 1.694-3.394, P < 0.001). We find the objective responses of a cohort of anti-PD-1 immunotherapy patients is significantly higher in the low-RS group (60.9% and 42.9%) than in the high-RS group (8.1% and 14.3%). The radiomics imaging biomarker is a noninvasive method to evaluate TIME, and may correlate with prognosis and anti PD-1 immunotherapy response in GC patients.

Design and Development of an Intelligent System for Predicting 5-Year Survival in Gastric Cancer

Background

Gastric cancer remains one of the leading causes of worldwide cancer-specific deaths. Accurately predicting the survival likelihood of gastric cancer patients can inform caregivers to boost patient prognostication and choose the best possible treatment path. This study intends to develop an intelligent system based on machine learning (ML) algorithms for predicting the 5-year survival status in gastric cancer patients.

Methods

A data set that includes the records of 974 gastric cancer patients retrospectively was used. First, the most important predictors were recognized using the Boruta feature selection algorithm. Five classifiers, including J48 decision tree (DT), support vector machine (SVM) with radial basic function (RBF) kernel, bootstrap aggregating (Bagging), hist gradient boosting (HGB), and adaptive boosting (AdaBoost), were trained for predicting gastric cancer survival. The performance of the used techniques was evaluated with specificity, sensitivity, likelihood ratio, and total accuracy. Finally, the system was developed according to the best model.

Results

The stage, position, and size of tumor were selected as the 3 top predictors for gastric cancer survival. Among the 6 selected ML algorithms, the HGB classifier with the mean accuracy, mean specificity, mean sensitivity, mean area under the curve, and mean F1-score of 88.37%, 86.24%, 89.72%, 88.11%, and 89.91%, respectively, gained the best performance.

Conclusions

The ML models can accurately predict the 5-year survival and potentially act as a customized recommender for decision-making in gastric cancer patients. The developed system in our study can improve the quality of treatment, patient safety, and survival rates; it may guide prescribing more personalized medicine.

Current Developments of Artificial Intelligence in Digital Pathology and Its Future Clinical Applications in Gastrointestinal Cancers

The implementation of DP will revolutionize current practice by providing pathologists with additional tools and algorithms to improve workflow. Furthermore, DP will open up opportunities for development of AI-based tools for more precise and reproducible diagnosis through computational pathology. One of the key features of AI is its capability to generate perceptions and recognize patterns beyond the human senses. Thus, the incorporation of AI into DP can reveal additional morphological features and information. At the current rate of AI development and adoption of DP, the interest in computational pathology is expected to rise in tandem. There have already been promising developments related to AI-based solutions in prostate cancer detection; however, in the GI tract, development of more sophisticated algorithms is required to facilitate histological assessment of GI specimens for early and accurate diagnosis. In this review, we aim to provide an overview of the current histological practices in AP laboratories with respect to challenges faced in image preprocessing, present the existing AI-based algorithms, discuss their limitations and present clinical insight with respect to the application of AI in early detection and diagnosis of GI cancer.

Genomic Analysis Uncovers the Prognostic and Immunogenetic Feature of Pyroptosis in Gastric Carcinoma: Indication for Immunotherapy

Crosstalk between pyroptosis and tumor immune microenvironment (TIME) in cancer has yet to be elucidated. Herein, we aimed to explore the role of pyroptosis and its association with TIME in gastric cancer. Unsupervised clustering was performed to identify the pyroptosis-related clusters. Pyroptosis risk score was constructed using LASSO Cox regression. Clinicopathological and genetic data of pyroptosis clusters and pyroptosis risk scores were explored. Reproducibility of pyroptosis risk score in predicting response to immunotherapy and screening potential antitumor drugs was also investigated. Three pyroptosis clusters with distinct prognosis, immune cell fractions and signatures, were constructed. A low-pyroptosis risk score was characterized by increased activated T-cell subtype and M1 macrophage, decreased M2 macrophage, higher MSI status, and TMB. Meanwhile, low-score significantly correlated with PD-L1 expression, antigen presentation markers, and IFN-γ signature. The 5-year AUCs of PRS were 0.67, 0.62, 0.65, 0.67, and 0.67 in the TCGA, three external public and one real-world validation (SYSUCC) cohorts. Multivariable analyses further validated the prognostic performance of the pyroptosis risk scoring system, with HRs of 2.43, 1.83, 1.78, 2.35, and 2.67 (all p &lt; 0.05) in the five cohorts. GSEA indicated significant enrichment of DNA damage repair pathways in the low-score group. Finally, the pyroptosis risk scoring system was demonstrated to be useful in predicting response to immunotherapy, and in screening potential antitumor drugs. Our study highlights the crucial role of interaction between pyroptosis and TIME in gastric cancer. The pyroptosis risk scoring system can be used independently to predict the survival of individuals and their response to immunotherapy.

Cell graph neural networks enable the precise prediction of patient survival in gastric cancer

Gastric cancer is one of the deadliest cancers worldwide. An accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the multiplexed immunohistochemistry (mIHC) images as Cell-Graphs, we propose a graph neural network-based approach, termed Cell−GraphSignatureorCG_Signature, powered by artificial intelligence, for the digital staging of TME and precise prediction of patient survival in gastric cancer. In this study, patient survival prediction is formulated as either a binary (short-term and long-term) or ternary (short-term, medium-term, and long-term) classification task. Extensive benchmarking experiments demonstrate that the CG_Signature achieves outstanding model performance, with Area Under the Receiver Operating Characteristic curve of 0.960 ± 0.01, and 0.771 ± 0.024 to 0.904 ± 0.012 for the binary- and ternary-classification, respectively. Moreover, Kaplan–Meier survival analysis indicates that the “digital grade” cancer staging produced by CG_Signature provides a remarkable capability in discriminating both binary and ternary classes with statistical significance (P value < 0.0001), significantly outperforming the AJCC 8th edition Tumor Node Metastasis staging system. Using Cell-Graphs extracted from mIHC images, CG_Signature improves the assessment of the link between the TME spatial patterns and patient prognosis. Our study suggests the feasibility and benefits of such an artificial intelligence-powered digital staging system in diagnostic pathology and precision oncology.

A novel epithelial-mesenchymal transition gene signature for the immune status and prognosis of hepatocellular carcinoma

Background

This study clarified whether EMT-related genes can predict immunotherapy efficacy and overall survival in patients with HCC.

Methods

The RNA-sequencing profiles and patient information of 370 samples were derived from the Cancer Genome Atlas (TCGA) dataset, and EMT-related genes were obtained from the Molecular Signatures database. The signature model was constructed using the least absolute shrinkage and selection operator Cox regression analysis in TCGA cohort. Validation data were obtained from the International Cancer Genome Consortium (ICGC) dataset of patients with HCC. Kaplan–Meier analysis and multivariate Cox analyses were employed to estimate the prognostic value. Immune status and tumor microenvironment were estimated using a single-sample gene set enrichment analysis (ssGSEA). The expression of prognostic genes was verified using qRT-PCR analysis of HCC cell lines.

Results

A signature model was constructed using EMT-related genes to determine HCC prognosis, based on which patients were divided into high-risk and low-risk groups. The risk score, as an independent factor, was related to tumor stage, grade, and immune cells infiltration. The results indicated that the most prognostic genes were highly expressed in the HCC cell lines, but GADD45B was down-regulated. Enrichment analysis suggested that immunoglobulin receptor binding and material metabolism were essential in the prognostic signature.

Conclusion

Our novel prognostic signature model has a vital impact on immune status and prognosis, significantly helping the decision-making related to the diagnosis and treatment of patients with HCC.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12072-022-10354-3.

Tumor Microenvironment Evaluation for Gastrointestinal Cancer in the Era of Immunotherapy and Machine Learning

A dynamic and mutualistic interplay between tumor cells and the surrounding tumor microenvironment (TME) triggered the initiation, progression, metastasis, and therapy response of solid tumors. Recent clinical breakthroughs in immunotherapy for gastrointestinal cancer conferred considerable attention to the estimation of TME, and the maturity of next-generation sequencing (NGS)-based technology contributed to the availability of increasing datasets and computational toolbox for deciphering TME compartments. In the current review, we demonstrated the components of TME, multiple methodologies involved in TME detection, and prognostic and predictive TME signatures derived from corresponding methods for gastrointestinal cancer. The TME evaluation comprises traditional, radiomics, and NGS-based high-throughput methodologies, and the computational algorithms are comprehensively discussed. Moreover, we systemically elucidated the existing TME-relevant signatures in the prognostic, chemotherapeutic, and immunotherapeutic settings. Collectively, we highlighted the clinical and technological advances in TME estimation for clinical translation and anticipated that TME-associated biomarkers may be promising in optimizing the future precision treatment for gastrointestinal cancer.

FAT1 and MSH2 Are Predictive Prognostic Markers for Chinese Osteosarcoma Patients Following Chemotherapeutic Treatment

Osteosarcoma is characterized by diverse genetic mutations, including single-nucleotide variants (SNVs), which can complicate clinical outcomes of the treatment. This study identified key mutations or polymorphisms in genes that correlate with osteosarcoma prognoses. A total of 110 patients with osteosarcoma were assigned to "good" or "poor" cohorts depending on their 5-year disease-free survival (DFS) after surgery and chemotherapeutic treatment. We performed next-generation sequencing analysis of tumor tissues for prognosis-associated SNVs in 315 tumorigenesis-related genes, followed by modeling of clinical outcomes for these patients using random forest classification via a support vector machine (SVM). Data from the Chinese Millionome Database were used to compare SNV frequency in osteosarcoma patients and healthy people. SVM screening identified 17 nonsynonymous SNVs located in 15 genes, of which rs17224367 and rs3733406 (located in MSH2 and FAT1, respectively) were strongly correlated with osteosarcoma prognosis. These results were verified in a 26-patient validation cohort, confirming that these SNVs could be used to predict prognosis. These results demonstrated that two SNVs located in MSH2 and FAT1 are associated with prognosis of osteosarcoma patients. © 2022 American Society for Bone and Mineral Research (ASBMR).

Tumor Microenvironment Characterization for Assessment of Recurrence and Survival Outcome in Gastric Cancer to Predict Chemotherapy and Immunotherapy Response

Background

The tumor microenvironment (TME) is crucial for tumor recurrence, prognosis, and therapeutic responses. We comprehensively investigated the TME characterization associated with relapse and survival outcomes of gastric cancer (GC) to predict chemotherapy and immunotherapy response.

Methods

A total of 2,456 GC patients with complete gene-expression data and clinical annotations from twelve cohorts were included. The TME characteristics were evaluated using three proposed computational algorithms. We then developed a TME-classifier, a TME-cluster, and a TME-based risk score for the assessment of tumor recurrence and prognosis in patients with GC to predict chemotherapy and immunotherapy response.

Results

Patients with tumor recurrence presented with inactive immunogenicity, namely, high infiltration of tumor-associated stromal cells, low infiltration of tumor-associated immunoactivated lymphocytes, high stromal score, and low immune score. The TME-classifier of 4 subtypes with distinct clinicopathology, genomic, and molecular characteristics was significantly associated with tumor recurrence (P = 0.002), disease-free survival (DFS, P <0.001), and overall survival (OS, P <0.001) adjusted by confounding variables in 1,193 stage I–III GC patients who underwent potential radical surgery. The TME cluster and TME-based risk score can also predict DFS (P <0.001) and OS (P <0.001). More importantly, we found that patients in the TMEclassifier-A, TMEclassifier-C, and TMEclassifier-D groups benefited from adjuvant chemotherapy, and patients in the TMEclassifier-B group without chemotherapy benefit responded best to pembrolizumab treatment (PD-1 inhibitor), followed by patients in the TMEclassifier-A, while patients in the C and D groups of the TMEclassifier responded poorly to immunotherapy.

Conclusion

We determined that TME characterization is significantly associated with tumor recurrence and prognosis. The TME-classifier we proposed can guide individualized chemotherapy and immunotherapy decision-making.

Comparison of treatment strategies and survival of early-onset gastric cancer: a population-based study

Treatments for early-onset gastric cancer (EOGC) patients are rarely included in clinical trials, resulting in an unclear impact on survival. This study aimed to investigate the treatment patterns of EOGC patients and their impact on survival. Based on the Surveillance, Epidemiology, and End Results database, we conducted a retrospective analysis of 1639 EOGC patients (< 50 years) diagnosed between 2010 and 2018. Patients with larger tumours, distant metastasis, and AJCC TNM stage in IV were prone to receive nonsurgical treatment. Patients treated with surgery alone had a better prognosis than those receiving SROC or SCRT or nonsurgical treatment. However, analyses stratified by histological type, tumour size and TNM stage showed that patients did not benefit more from SROC and SCRT than from surgery alone. Similar results were observed in the stratified Cox regression risk analysis. Patients who received nonsurgical treatment had the highest risk of overall death [hazard ratio (HR) = 2.443, 95% confidence interval (CI) 1.865–3.200, P < 0.001]. This study indicated that additional radiotherapy, chemotherapy or chemoradiotherapy did not provide a coordinated survival benefit to EOGC patients.

A Novel Deep Learning Method to Predict Lung Cancer Long-Term Survival With Biological Knowledge Incorporated Gene Expression Images and Clinical Data

Lung cancer is the leading cause of the cancer deaths. Therefore, predicting the survival status of lung cancer patients is of great value. However, the existing methods mainly depend on statistical machine learning (ML) algorithms. Moreover, they are not appropriate for high-dimensionality genomics data, and deep learning (DL), with strong high-dimensional data learning capability, can be used to predict lung cancer survival using genomics data. The Cancer Genome Atlas (TCGA) is a great database that contains many kinds of genomics data for 33 cancer types. With this enormous amount of data, researchers can analyze key factors related to cancer therapy. This paper proposes a novel method to predict lung cancer long-term survival using gene expression data from TCGA. Firstly, we select the most relevant genes to the target problem by the supervised feature selection method called mutual information selector. Secondly, we propose a method to convert gene expression data into two kinds of images with KEGG BRITE and KEGG Pathway data incorporated, so that we could make good use of the convolutional neural network (CNN) model to learn high-level features. Afterwards, we design a CNN-based DL model and added two kinds of clinical data to improve the performance, so that we finally got a multimodal DL model. The generalized experiments results indicated that our method performed much better than the ML models and unimodal DL models. Furthermore, we conduct survival analysis and observe that our model could better divide the samples into high-risk and low-risk groups.

Construction and Validation of Convenient Clinicopathologic Signatures for Predicting the Prognosis of Stage I-III Gastric Cancer

Background

Patients with stage I-III gastric cancer (GC) undergoing R0 radical resection display extremely different prognoses. How to discriminate high-risk patients with poor survival conveniently is a clinical conundrum to be solved urgently.

Methods

Patients with stage I-III GC from 2010 to 2016 were included in our study. The associations of clinicopathological features with disease-free survival (DFS) and overall survival (OS) were examined via Cox proportional hazard model. Nomograms were developed which systematically integrated prognosis-related features. Kaplan–Meier survival analysis was performed to compare DFS and OS among groups. The results were then externally validated by The Sixth Affiliated Hospital, Sun Yat-sen University.

Results

A total of 585 and 410 patients were included in the discovery cohort and the validation cohort, respectively. T stage, N stage, lymphatic/vascular/nerve infiltration, preoperative CEA, and CA19-9 were independent prognostic factors (P < 0.05). Two prognostic signatures with a concordance index (C-index) of 0.7502 for DFS and 0.7341 for OS were developed based on the nomograms. The 3-year and 5-year calibration curves showed a perfect correlation between predicted and observed outcomes. Patients were divided into three risk groups (low, intermediate, high), and distinct differences were noticed (p < 0.001). Similar results were achieved in the validation cohort. Notably, a free website was constructed based on our signatures to predict the recurrence risk and survival time of patients with stage I-III GC.

Conclusions

The signatures demonstrate the powerful ability to conveniently identify distinct subpopulations, which may provide significant suggestions for individual follow-up and adjuvant therapy.

Deep-learning model for predicting the survival of rectal adenocarcinoma patients based on a surveillance, epidemiology, and end results analysis

Background

We collected information on patients with rectal adenocarcinoma in the United States from the Surveillance, Epidemiology, and EndResults (SEER) database. We used this information to establish a model that combined deep learning with a multilayer neural network (the DeepSurv model) for predicting the survival rate of patients with rectal adenocarcinoma.

Methods

We collected patients with rectal adenocarcinoma in the United States and older than 20 yearswho had been added to the SEER database from 2004 to 2015. We divided these patients into training and test cohortsat a ratio of 7:3. The training cohort was used to develop a seven-layer neural network based on the analysis method established by Katzman and colleagues to construct a DeepSurv prediction model. We then used the C-index and calibration plots to evaluate the prediction performance of the DeepSurv model.

Results

The 49,275 patients with rectal adenocarcinoma included in the study were randomly divided into the training cohort (70%, n = 34,492) and the test cohort (30%, n = 14,783). There were no statistically significant differences in clinical characteristics between the two cohorts (p > 0.05). We applied Cox proportional-hazards regression to the data in the training cohort, which showed that age, sex, marital status, tumor grade, surgery status, and chemotherapy status were significant factors influencing survival (p < 0.05). Using the training cohort to construct the DeepSurv model resulted in a C-index of the model of 0.824, while using the test cohort to verify the DeepSurv model yielded a C-index of 0.821. Thesevalues show that the prediction effect of the DeepSurv model for the test-cohort patients was highly consistent with the prediction resultsfor the training-cohort patients.

Conclusion

The DeepSurv prediction model of the seven-layer neural network that we have established can accurately predict the survival rateand time of rectal adenocarcinoma patients.

An artificial intelligence method to assess the tumor microenvironment with treatment outcomes for gastric cancer patients after gastrectomy

Background

The tumor microenvironment (TME) plays an important role in the occurrence and development of gastric cancer (GC) and is widely used to assess the treatment outcomes of GC patients. Immunohistochemistry (IHC) and gene sequencing are the main analysis methods for the TME but are limited due to the subjectivity of observers, the high cost of equipment and the need for professional analysts.

Methods

The ImmunoScore (IS) was developed in the TCGA cohort and validated in GEO cohorts. The Radiomic ImmunoScore (RIS) was developed in the TCGA cohort and validated in the Nanfang cohort. A nomogram was developed and validated in the Nanfang cohort based on RIS and clinical features.

Results

For IS, the area under the curves (AUCs) were 0.798 for 2-year overall survival (OS) and 0.873 for 4-year overall survival. For RIS, in the TCGA cohort, the AUCs distinguishing High-IS or Low-IS and predicting prognosis were 0.85 and 0.81, respectively; in the Nanfang cohort, the AUC predicting prognosis was 0.72. The nomogram performed better than the TNM staging system according to the ROC curve (all P < 0.01). Patients with TNM stage II and III in the High-nomogram group were more likely to benefit from adjuvant chemotherapy than Low-nomogram group patients.

Conclusions

The RIS and the nomogram can be used to assess the TME, prognosis and adjuvant chemotherapy benefit of GC patients after radical gastrectomy and are valuable additions to the current TNM staging system. High-nomogram GC patients may benefit more from adjuvant chemotherapy than Low-nomogram GC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03298-7.

Machine Learning-Based Model for the Prognosis of Postoperative Gastric Cancer

Background

The use of machine learning (ML) in predicting disease prognosis has increased, and scientists have adopted different methods for cancer classification to optimize the early screening of cancer to determine its prognosis in advance. In this study, we aimed at improving the prediction accuracy of gastric cancer in postoperation patients by constructing a highly effective prognostic model.

Methods

The study used postoperative gastric cancer patient data from the SEER database. The LASSO regression method was used to construct a clinical prognostic model, and four machine learning methods (Boruta algorithm, neural network, support vector machine, and random forest) were used to screen and recombine the features to construct an ML prognostic model. Clinical information on 955 postoperative gastric cancer patients collected from the Affiliated Tumor Hospital of Harbin Medical University was used for external verification.

Results

Experimental results showed that the AUC values of 1, 3 and 5 years in the training set, validation set and external validation set of clinical prognosis model and ML prognosis model directly established by LASSO regression are all around 0.8.

Conclusion

Both models can accurately evaluate the prognosis of postoperative patients with gastric cancer, which may be helpful for accurate and personalized treatment of postoperative patients with gastric cancer.

Artificial intelligence in pathological evaluation of gastrointestinal cancers

The integration of artificial intelligence (AI) has shown promising benefits in many fields of diagnostic histopathology, including for gastrointestinal cancers (GCs), such as tumor identification, classification, and prognosis prediction. In parallel, recent evidence suggests that AI may help reduce the workload in gastrointestinal pathology by automatically detecting tumor tissues and evaluating prognostic parameters. In addition, AI seems to be an attractive tool for biomarker/genetic alteration prediction in GC, as it can contain a massive amount of information from visual data that is complex and partially understandable by pathologists. From this point of view, it is suggested that advances in AI could lead to revolutionary changes in many fields of pathology. Unfortunately, these findings do not exclude the possibility that there are still many hurdles to overcome before AI applications can be safely and effectively applied in actual pathology practice. These include a broad spectrum of challenges from needs identification to cost-effectiveness. Therefore, unlike other disciplines of medicine, no histopathology-based AI application, including in GC, has ever been approved either by a regulatory authority or approved for public reimbursement. The purpose of this review is to present data related to the applications of AI in pathology practice in GC and present the challenges that need to be overcome for their implementation.

N6-Methyladenosine RNA Modification in the Tumor Immune Microenvironment: Novel Implications for Immunotherapy

N6-methyladenosine (m⁶A) methylation is one of the most common modifications of RNA in eukaryotic cells, and is mainly regulated by m⁶A methyltransferases (writers), m⁶A demethylases (erasers), and m⁶A binding proteins (readers). Recently, accumulating evidence has shown that m⁶A methylation plays crucial roles in the regulation of the tumor immune microenvironment, greatly impacting the initiation, progression, and metastasis processes of various cancers. In this review we first briefly summarizes the m⁶A-related concepts and detection methods, and then describes in detail the associations of m⁶A methylation modification with various tumor immune components especially immune cells (e.g., regulatory T cells, dendritic cells, macrophages, and myeloid-derived suppressor cells) in a variety of cancers. We discuss the relationship between m⁶A methylation and cancer occurrence and development with the involvement of tumor immunity highlighted, suggesting novel markers and potential targets for molecular pathological diagnosis and immunotherapy of various cancers.

Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer

Background

In recent years, the availability of high throughput technologies, establishment of large molecular patient data repositories, and advancement in computing power and storage have allowed elucidation of complex mechanisms implicated in therapeutic response in cancer patients. The breadth and depth of such data, alongside experimental noise and missing values, requires a sophisticated human-machine interaction that would allow effective learning from complex data and accurate forecasting of future outcomes, ideally embedded in the core of machine learning design.

Objective

In this review, we will discuss machine learning techniques utilized for modeling of treatment response in cancer, including Random Forests, support vector machines, neural networks, and linear and logistic regression. We will overview their mathematical foundations and discuss their limitations and alternative approaches in light of their application to therapeutic response modeling in cancer.

Conclusion

We hypothesize that the increase in the number of patient profiles and potential temporal monitoring of patient data will define even more complex techniques, such as deep learning and causal analysis, as central players in therapeutic response modeling.

A Support Vector Machine Based on Liquid Immune Profiling Predicts Major Pathological Response to Chemotherapy Plus Anti-PD-1/PD-L1 as a Neoadjuvant Treatment for Patients With Resectable Non-Small Cell Lung Cancer

The biomarkers for the pathological response of neoadjuvant chemotherapy plus anti-programmed cell death protein-1/programmed cell death-ligand 1 (PD-1/PD-L1) (CAPD) are unclear in non-small cell lung cancer (NSCLC). Two hundred and eleven patients with stage Ib-IIIa NSCLC undergoing CAPD prior to surgical resection were enrolled, and 11 immune cell subsets in peripheral blood were prospectively analyzed using multicolor flow cytometry. Immune cell subtypes were selected by recursive feature elimination and least absolute shrinkage and selection operator methods. The support vector machine (SVM) was used to build a model. Multivariate analysis for major pathological response (MPR) was also performed. Finally, five immune cell subtypes were identified and an SVM based on liquid immune profiling (LIP-SVM) was developed. The LIP-SVM model achieved high accuracies in discovery and validation sets (AUC = 0.886, 95% CI: 0.823–0.949, P < 0.001; AUC = 0.874, 95% CI: 0.791–0.958, P < 0.001, respectively). Multivariate analysis revealed that age, radiological response, and LIP-SVM were independent factors for MPR in the two sets (each P < 0.05). The integration of LIP-SVM, clinical factors, and radiological response showed significantly high accuracies for predicting MPR in discovery and validation sets (AUC = 0.951, 95% CI: 0.916–0.986, P < 0.001; AUC = 0.943, 95% CI: 0.912–0.993, P < 0.001, respectively). Based on immune cell profiling of peripheral blood, our study developed a predictive model for the MPR of patients with NSCLC undergoing CAPD treatment that can potentially guide clinical therapy.

Fluorescence and Photoacoustic Spectroscopy-Based Assessment of Mitochondrial Dysfunction in Oral Cancer Together with Machine Learning: A Pilot Study

The current study reports an integrated approach of machine learning and tryptophan fluorescence and photoacoustic spectral properties to assess the mitochondrial status under oral pathological conditions. The mitochondria in the study were isolated from oral cancer tissues and adjacent normal counterparts, and the corresponding fluorescence and photoacoustic spectra of tryptophan were recorded at 281 nm pulsed laser excitations. A set of features were selected from the pre-processed spectra and were used to classify the data using support vector machine (SVM) learning in the MATLAB platform. SVM analysis demonstrated clear differentiation between mitochondria isolated from normal and cancer tissues for fluorescence (sensitivity, 86.6%; specificity, 90%) and photoacoustic (sensitivity, 86.6%; specificity, 96.6%) measurements. Further investigation into the influence of change in protein conformation on the nature of tryptophan spectral properties was evaluated by 8-anilino-1-naphthalene sulfonic acid (ANS) fluorescence assay. The impact of protein structural changes on the mitochondrial functions was also estimated by mitochondrial membrane potential (MMP), reactive oxygen species (ROS), and cytochrome c oxidase (COX) assays, suggesting an altered mitochondrial function. The findings indicate that tryptophan fluorescence and photoacoustic spectral properties together with machine learning algorithms may delineate the mitochondrial functional status in vitro, indicating its translational potential.

Artificial intelligence in gastroenterology: A state-of-the-art review

The development of artificial intelligence (AI) has increased dramatically in the last 20 years, with clinical applications progressively being explored for most of the medical specialties. The field of gastroenterology and hepatology, substantially reliant on vast amounts of imaging studies, is not an exception. The clinical applications of AI systems in this field include the identification of premalignant or malignant lesions (e.g., identification of dysplasia or esophageal adenocarcinoma in Barrett’s esophagus, pancreatic malignancies), detection of lesions (e.g., polyp identification and classification, small-bowel bleeding lesion on capsule endoscopy, pancreatic cystic lesions), development of objective scoring systems for risk stratification, predicting disease prognosis or treatment response [e.g., determining survival in patients post-resection of hepatocellular carcinoma), determining which patients with inflammatory bowel disease (IBD) will benefit from biologic therapy], or evaluation of metrics such as bowel preparation score or quality of endoscopic examination. The objective of this comprehensive review is to analyze the available AI-related studies pertaining to the entirety of the gastrointestinal tract, including the upper, middle and lower tracts; IBD; the hepatobiliary system; and the pancreas, discussing the findings and clinical applications, as well as outlining the current limitations and future directions in this field.