Prognostic and predictive value of a pathomics signature in gastric cancer

Role of artificial intelligence in digital pathology for gynecological cancers

The diagnosis of cancer is typically based on histopathological sections or biopsies on glass slides. Artificial intelligence (AI) approaches have greatly enhanced our ability to extract quantitative information from digital histopathology images as a rapid growth in oncology data. Gynecological cancers are major diseases affecting women's health worldwide. They are characterized by high mortality and poor prognosis, underscoring the critical importance of early detection, treatment, and identification of prognostic factors. This review highlights the various clinical applications of AI in gynecological cancers using digitized histopathology slides. Particularly, deep learning models have shown promise in accurately diagnosing, classifying histopathological subtypes, and predicting treatment response and prognosis. Furthermore, the integration with transcriptomics, proteomics, and other multi-omics techniques can provide valuable insights into the molecular features of diseases. Despite the considerable potential of AI, substantial challenges remain. Further improvements in data acquisition and model optimization are required, and the exploration of broader clinical applications, such as the biomarker discovery, need to be explored.

A diagnostic strategy for pulmonary fat embolism based on routine H&E staining using computational pathology

Pulmonary fat embolism (PFE) as a cause of death often occurs in trauma cases such as fractures and soft tissue contusions. Traditional PFE diagnosis relies on subjective methods and special stains like oil red O. This study utilizes computational pathology, combining digital pathology and deep learning algorithms, to precisely quantify fat emboli in whole slide images using conventional hematoxylin-eosin (H&E) staining. The results demonstrate deep learning's ability to identify fat droplet morphology in lung microvessels, achieving an area under the receiver operating characteristic (ROC) curve (AUC) of 0.98. The AI-quantified fat globules generally matched the Falzi scoring system with oil red O staining. The relative quantity of fat emboli against lung area was calculated by the algorithm, determining a diagnostic threshold of 8.275% for fatal PFE. A diagnostic strategy based on this threshold achieved a high AUC of 0.984, similar to manual identification with special stains but surpassing H&E staining. This demonstrates computational pathology's potential as an affordable, rapid, and precise method for fatal PFE diagnosis in forensic practice.

Deep learning-based multi-model prediction for disease-free survival status of patients with clear cell renal cell carcinoma after surgery: a multicenter cohort study

BACKGROUND

Although separate analysis of individual factor can somewhat improve the prognostic performance, integration of multimodal information into a single signature is necessary to stratify patients with clear cell renal cell carcinoma (ccRCC) for adjuvant therapy after surgery.

METHODS

A total of 414 patients with whole slide images, computed tomography images, and clinical data from three patient cohorts were retrospectively analyzed. The authors performed deep learning and machine learning algorithm to construct three single-modality prediction models for disease-free survival of ccRCC based on whole slide images, cell segmentation, and computed tomography images, respectively. A multimodel prediction signature (MMPS) for disease-free survival were further developed by combining three single-modality prediction models and tumor stage/grade system. Prognostic performance of the prognostic model was also verified in two independent validation cohorts.

RESULTS

Single-modality prediction models performed well in predicting the disease-free survival status of ccRCC. The MMPS achieved higher area under the curve value of 0.742, 0.917, and 0.900 in three independent patient cohorts, respectively. MMPS could distinguish patients with worse disease-free survival, with HR of 12.90 (95% CI: 2.443-68.120, P <0.0001), 11.10 (95% CI: 5.467-22.520, P <0.0001), and 8.27 (95% CI: 1.482-46.130, P <0.0001) in three different patient cohorts. In addition, MMPS outperformed single-modality prediction models and current clinical prognostic factors, which could also provide complements to current risk stratification for adjuvant therapy of ccRCC.

CONCLUSION

Our novel multimodel prediction analysis for disease-free survival exhibited significant improvements in prognostic prediction for patients with ccRCC. After further validation in multiple centers and regions, the multimodal system could be a potential practical tool for clinicians in the treatment for ccRCC patients.

Machine learning-based pathomics signature of histology slides as a novel prognostic indicator in primary central nervous system lymphoma

PURPOSE

To develop and validate a pathomics signature for predicting the outcomes of Primary Central Nervous System Lymphoma (PCNSL).

METHODS

In this study, 132 whole-slide images (WSIs) of 114 patients with PCNSL were enrolled. Quantitative features of hematoxylin and eosin (H&E) stained slides were extracted using CellProfiler. A pathomics signature was established and validated. Cox regression analysis, receiver operating characteristic (ROC) curves, Calibration, decision curve analysis (DCA), and net reclassification improvement (NRI) were performed to assess the significance and performance.

RESULTS

In total, 802 features were extracted using a fully automated pipeline. Six machine-learning classifiers demonstrated high accuracy in distinguishing malignant neoplasms. The pathomics signature remained a significant factor of overall survival (OS) and progression-free survival (PFS) in the training cohort (OS: HR 7.423, p < 0.001; PFS: HR 2.143, p = 0.022) and independent validation cohort (OS: HR 4.204, p = 0.017; PFS: HR 3.243, p = 0.005). A significantly lower response rate to initial treatment was found in high Path-score group (19/35, 54.29%) as compared to patients in the low Path-score group (16/70, 22.86%; p < 0.001). The DCA and NRI analyses confirmed that the nomogram showed incremental performance compared with existing models. The ROC curve demonstrated a relatively sensitive and specific profile for the nomogram (1-, 2-, and 3-year AUC = 0.862, 0.932, and 0.927, respectively).

CONCLUSION

As a novel, non-invasive, and convenient approach, the newly developed pathomics signature is a powerful predictor of OS and PFS in PCNSL and might be a potential predictive indicator for therapeutic response.

Deep learning on tertiary lymphoid structures in hematoxylin-eosin predicts cancer prognosis and immunotherapy response

Tertiary lymphoid structures (TLSs) have been associated with favorable immunotherapy responses and prognosis in various cancers. Despite their significance, their quantification using multiplex immunohistochemistry (mIHC) staining of T and B lymphocytes remains labor-intensive, limiting its clinical utility. To address this challenge, we curated a dataset from matched mIHC and H&E whole-slide images (WSIs) and developed a deep learning model for automated segmentation of TLSs. The model achieved Dice coefficients of 0.91 on the internal test set and 0.866 on the external validation set, along with intersection over union (IoU) scores of 0.819 and 0.787, respectively. The TLS ratio, defined as the segmented TLS area over the total tissue area, correlated with B lymphocyte levels and the expression of CXCL13, a chemokine associated with TLS formation, in 6140 patients spanning 16 tumor types from The Cancer Genome Atlas (TCGA). The prognostic models for overall survival indicated that the inclusion of the TLS ratio with TNM staging significantly enhanced the models' discriminative ability, outperforming the traditional models that solely incorporated TNM staging, in 10 out of 15 TCGA tumor types. Furthermore, when applied to biopsied treatment-naïve tumor samples, higher TLS ratios predicted a positive immunotherapy response across multiple cohorts, including specific therapies for esophageal squamous cell carcinoma, non-small cell lung cancer, and stomach adenocarcinoma. In conclusion, our deep learning-based approach offers an automated and reproducible method for TLS segmentation and quantification, highlighting its potential in predicting immunotherapy response and informing cancer prognosis.

Development and validation of a Radiopathomics model based on CT scans and whole slide images for discriminating between Stage I-II and Stage III gastric cancer

OBJECTIVE

This study aimed to develop and validate an artificial intelligence radiopathological model using preoperative CT scans and postoperative hematoxylin and eosin (HE) stained slides to predict the pathological staging of gastric cancer (stage I-II and stage III).

METHODS

This study included a total of 202 gastric cancer patients with confirmed pathological staging (training cohort: n = 141; validation cohort: n = 61). Pathological histological features were extracted from HE slides, and pathological models were constructed using logistic regression (LR), support vector machine (SVM), and NaiveBayes. The optimal pathological model was selected through receiver operating characteristic (ROC) curve analysis. Machine learnin algorithms were employed to construct radiomic models and radiopathological models using the optimal pathological model. Model performance was evaluated using ROC curve analysis, and clinical utility was estimated using decision curve analysis (DCA).

RESULTS

A total of 311 pathological histological features were extracted from the HE images, including 101 Term Frequency-Inverse Document Frequency (TF-IDF) features and 210 deep learning features. A pathological model was constructed using 19 selected pathological features through dimension reduction, with the SVM model demonstrating superior predictive performance (AUC, training cohort: 0.949; validation cohort: 0.777). Radiomic features were constructed using 6 selected features from 1834 radiomic features extracted from CT scans via SVM machine algorithm. Simultaneously, a radiopathomics model was built using 17 non-zero coefficient features obtained through dimension reduction from a total of 2145 features (combining both radiomics and pathomics features). The best discriminative ability was observed in the SVM_radiopathomics model (AUC, training cohort: 0.953; validation cohort: 0.851), and clinical decision curve analysis (DCA) demonstrated excellent clinical utility.

CONCLUSION

The radiopathomics model, combining pathological and radiomic features, exhibited superior performance in distinguishing between stage I-II and stage III gastric cancer. This study is based on the prediction of pathological staging using pathological tissue slides from surgical specimens after gastric cancer curative surgery and preoperative CT images, highlighting the feasibility of conducting research on pathological staging using pathological slides and CT images.

Digital pathology-based artificial intelligence models for differential diagnosis and prognosis of sporadic odontogenic keratocysts

Odontogenic keratocyst (OKC) is a common jaw cyst with a high recurrence rate. OKC combined with basal cell carcinoma as well as skeletal and other developmental abnormalities is thought to be associated with Gorlin syndrome. Moreover, OKC needs to be differentiated from orthokeratinized odontogenic cyst and other jaw cysts. Because of the different prognosis, differential diagnosis of several cysts can contribute to clinical management. We collected 519 cases, comprising a total of 2 157 hematoxylin and eosin-stained images, to develop digital pathology-based artificial intelligence (AI) models for the diagnosis and prognosis of OKC. The Inception_v3 neural network was utilized to train and test models developed from patch-level images. Finally, whole slide image-level AI models were developed by integrating deep learning-generated pathology features with several machine learning algorithms. The AI models showed great performance in the diagnosis (AUC = 0.935, 95% CI: 0.898-0.973) and prognosis (AUC = 0.840, 95%CI: 0.751-0.930) of OKC. The advantages of multiple slides model for integrating of histopathological information are demonstrated through a comparison with the single slide model. Furthermore, the study investigates the correlation between AI features generated by deep learning and pathological findings, highlighting the interpretative potential of AI models in the pathology. Here, we have developed the robust diagnostic and prognostic models for OKC. The AI model that is based on digital pathology shows promise potential for applications in odontogenic diseases of the jaw.

Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer

Gastric cancer (GC) represents a significant burden of cancer-related mortality worldwide, underscoring an urgent need for the development of early detection strategies and precise postoperative interventions. However, the identification of non-invasive biomarkers for early diagnosis and patient risk stratification remains underexplored. Here, we conduct a targeted metabolomics analysis of 702 plasma samples from multi-center participants to elucidate the GC metabolic reprogramming. Our machine learning analysis reveals a 10-metabolite GC diagnostic model, which is validated in an external test set with a sensitivity of 0.905, outperforming conventional methods leveraging cancer protein markers (sensitivity < 0.40). Additionally, our machine learning-derived prognostic model demonstrates superior performance to traditional models utilizing clinical parameters and effectively stratifies patients into different risk groups to guide precision interventions. Collectively, our findings reveal the metabolic landscape of GC and identify two distinct biomarker panels that enable early detection and prognosis prediction respectively, thus facilitating precision medicine in GC.

DeepRisk network: an AI-based tool for digital pathology signature and treatment responsiveness of gastric cancer using whole-slide images

BACKGROUND

Digital histopathology provides valuable information for clinical decision-making. We hypothesized that a deep risk network (DeepRisk) based on digital pathology signature (DPS) derived from whole-slide images could improve the prognostic value of the tumor, node, and metastasis (TNM) staging system and offer chemotherapeutic benefits for gastric cancer (GC).

METHODS

DeepRisk is a multi-scale, attention-based learning model developed on 1120 GCs in the Zhongshan dataset and validated with two external datasets. Then, we assessed its association with prognosis and treatment response. The multi-omics analysis and multiplex Immunohistochemistry were conducted to evaluate the potential pathogenesis and spatial immune contexture underlying DPS.

RESULTS

Multivariate analysis indicated that the DPS was an independent prognosticator with a better C-index (0.84 for overall survival and 0.71 for disease-free survival). Patients with low-DPS after neoadjuvant chemotherapy responded favorably to treatment. Spatial analysis indicated that exhausted immune clusters and increased infiltration of CD11b+CD11c+ immune cells were present at the invasive margin of high-DPS group. Multi-omics data from the Cancer Genome Atlas-Stomach adenocarcinoma (TCGA-STAD) hint at the relevance of DPS to myeloid derived suppressor cells infiltration and immune suppression.

CONCLUSION

DeepRisk network is a reliable tool that enhances prognostic value of TNM staging and aid in precise treatment, providing insights into the underlying pathogenic mechanisms.

Deep learning algorithm-based multimodal MRI radiomics and pathomics data improve prediction of bone metastases in primary prostate cancer

PURPOSE

Bone metastasis is a significant contributor to morbidity and mortality in advanced prostate cancer, and early diagnosis is challenging due to its insidious onset. The use of machine learning to obtain prognostic information from pathological images has been highlighted. However, there is a limited understanding of the potential of early prediction of bone metastasis through the feature combination method from various sources. This study presents a method of integrating multimodal data to enhance the feasibility of early diagnosis of bone metastasis in prostate cancer.

METHODS AND MATERIALS

Overall, 211 patients diagnosed with prostate cancer (PCa) at Gansu Provincial Hospital between January 2017 and February 2023 were included in this study. The patients were randomized (8:2) into a training group (n = 169) and a validation group (n = 42). The region of interest (ROI) were segmented from the three magnetic resonance imaging (MRI) sequences (T2WI, DWI, and ADC), and pathological features were extracted from tissue sections (hematoxylin and eosin [H&E] staining, 10 × 20). A deep learning (DL) model using ResNet 50 was employed to extract deep transfer learning (DTL) features. The least absolute shrinkage and selection operator (LASSO) regression method was utilized for feature selection, feature construction, and reducing feature dimensions. Different machine learning classifiers were used to build predictive models. The performance of the models was evaluated using receiver operating characteristic curves. The net clinical benefit was assessed using decision curve analysis (DCA). The goodness of fit was evaluated using calibration curves. A joint model nomogram was eventually developed by combining clinically independent risk factors.

RESULTS

The best prediction models based on DTL and pathomics features showed area under the curve (AUC) values of 0.89 (95% confidence interval [CI], 0.799-0.989) and 0.85 (95% CI, 0.714-0.989), respectively. The AUC for the best prediction model based on radiomics features and combining radiomics features, DTL features, and pathomics features were 0.86 (95% CI, 0.735-0.979) and 0.93 (95% CI, 0.854-1.000), respectively. Based on DCA and calibration curves, the model demonstrated good net clinical benefit and fit.

CONCLUSION

Multimodal radiomics and pathomics serve as valuable predictors of the risk of bone metastases in patients with primary PCa.

A comprehensive radiopathological nomogram for the prediction of pathological staging in gastric cancer using CT-derived and WSI-based features

OBJECTIVE

This study aims to develop and validate an innovative radiopathomics model that combines radiomics and pathomics features to effectively differentiate between stages I-II and stage III gastric cancer (pathological staging).

METHODS

Our study included 200 patients with well-defined stages of gastric cancer divided into a training cohort (n = 140) and a test cohort (n = 60). Radiomics features were extracted from contrast-enhanced CT images using PyRadiomics, while pathomics features were obtained from whole slide images of pathological specimens through a fine-tuned deep learning model (ResNet-18). After rigorous feature dimensionality reduction and selection, we constructed radiomics models (SVM_rad, LR_rad, and MLP_rad) and pathomics models (SVM_path, LR_path, and MLP_path) utilizing support vector machine (SVM), logistic regression (LR), and multilayer perceptron (MLP) algorithms. The optimal radiomics and pathomics models were chosen based on comprehensive evaluation criteria such as ROC curves, Hosmer‒Lemeshow tests, and calibration curve tests. Feature patterns extracted from the best-performing radiomics model (MLP_rad) and pathomics model (SVM_rad) were integrated to create a powerful radiopathomics nomogram.

RESULTS

From a pool of 1834 radiomics features extracted from CT images, 14 were selected to construct radiomics models. Among these, the MLP_rad model exhibited the most robust predictive performance (AUC, training cohort: 0.843; test cohort: 0.797). Likewise, 10 pathomics features were chosen from 512 extracted from whole slide images to build pathomics models, with the SVM_path model demonstrating the highest predictive efficiency (AUC, training cohort: 0.937; test cohort: 0.792). The combined radiopathomics nomogram model exhibited optimal discriminative ability (AUC, training cohort: 0.951; test cohort: 0.837), as confirmed by decision curve analysis (DCA), which indicated superior clinical effectiveness.

CONCLUSION

This study presents a cutting-edge radiopathomics nomogram model designed to predict pathological staging in gastric cancer, distinguishing between stages I-II and stage III. Our research leverages preoperative CT images and histopathological slides to forecast gastric cancer staging accurately, potentially facilitating the estimation of staging before radical gastric cancer surgery in the future.

Development and Validation of a Pathomics Model Using Machine Learning to Predict CXCL8 Expression and Prognosis in Head and Neck Cancer

OBJECTIVES

The necessity to develop a method for prognostication and to identify novel biomarkers for personalized medicine in patients with head and neck squamous cell carcinoma (HNSCC) cannot be overstated. Recently, pathomics, which relies on quantitative analysis of medical imaging, has come to the forefront. CXCL8, an essential inflammatory cytokine, has been shown to correlate with overall survival (OS). This study examined the relationship between CXCL8 mRNA expression and pathomics features and aimed to explore the biological underpinnings of CXCL8.

METHODS

Clinical information and transcripts per million mRNA sequencing data were obtained from The Cancer Genome Atlas (TCGA)-HNSCC dataset. We identified correlations between CXCL8 mRNA expression and patient survival rates using a Kaplan-Meier survival curve. A retrospective analysis of 313 samples diagnosed with HNSCC in the TCGA database was conducted. Pathomics features were extracted from hematoxylin and eosin-stained images, and then the minimum redundancy maximum relevance, with recursive feature elimination (mRMR-RFE) method was applied, followed by screening with the logistic regression algorithm.

RESULTS

Kaplan-Meier curves indicated that high expression of CXCL8 was significantly associated with decreased OS. The logistic regression pathomics model incorporated 16 radiomics features identified by the mRMR-RFE method in the training set and demonstrated strong performance in the testing set. Calibration plots showed that the probability of high gene expression predicted by the pathomics model was in good agreement with actual observations, suggesting the model's high clinical applicability.

CONCLUSION

The pathomics model of CXCL8 mRNA expression serves as an effective tool for predicting prognosis in patients with HNSCC and can aid in clinical decision-making. Elevated levels of CXCL8 expression may lead to reduced DNA damage and are associated with a pro-inflammatory tumor microenvironment, offering a potential therapeutic target.

An analysis of the relationship of triglyceride glucose index with gastric cancer prognosis: A retrospective study

AIMS/INTRODUCTION

Gastric cancer, one of the most common malignant tumors worldwide, is affected by insulin resistance. The triglyceride glucose (TYG) index is considered a surrogate indicator of insulin resistance; however, its prognostic value in patients with gastric cancer remains obscure. This study aimed to determine whether the TYG index could predict the long-term prognosis of patients with gastric cancer after radical resection gastrectomy.

MATERIALS AND METHODS

We retrospectively analyzed patients with gastric cancer who underwent radical resection gastrectomy. The preoperative TYG index was calculated using the patients' laboratory data. Patients were divided into two groups based on a high or low TYG index. We observed overall survival and evaluated the clinical application value of the index using Cox proportional hazards regression to calculate independent parameters. A prediction model was also established.

RESULTS

In total, 822 patients with gastric cancer were included. The high and low TYG index groups comprised 353 and 469 patients, respectively. The overall survival time was significantly longer in the high-index group than in the low-index group. In the multivariate analysis, TYG index, preoperative age, surgical procedure, tumor node metastasis (TNM) stage, N stage, and postoperative complications (all p < 0.01) were considered independent prognostic predictors. Based on the multivariate analysis, the riglyceride glucose (TYG) index hazard ratio was 0.70 (95% confidence interval, 0.54-0.89, p = 0.004).

CONCLUSIONS

We established a model with a high clinical application value and clinical practice relevance to predict the prognosis of gastric cancer. In this model, TYG was an independent protective factor for gastric cancer prognosis.

Identification and characterization of CLEC11A and its derived immune signature in gastric cancer

Introduction

C-type lectin domain family 11 member A (CLEC11A) was characterized as a growth factor that mainly regulates hematopoietic function and differentiation of bone cells. However, the involvement of CLEC11A in gastric cancer (GC) is not well understood.

Methods

Transcriptomic data and clinical information pertaining to GC were obtained and analyzed from publicly available databases. The relationships between CLEC11A and prognoses, genetic alterations, tumor microenvironment (TME), and therapeutic responses in GC patients were analyzed by bioinformatics methods. A CLEC11A-derived immune signature was developed and validated, and its mutational landscapes, immunological characteristics as well as drug sensitivities were explored. A nomogram was established by combining CLEC11A-derived immune signature and clinical factors. The expression and carcinogenic effects of CLEC11A in GC were verified by qRT-PCR, cell migration, invasion, cell cycle analysis, and in vivo model analysis. Myeloid-derived suppressor cells (MDSCs), regulatory T cells (Tregs), M2 macrophages, and T cells in tumor samples extracted from mice were analyzed utilizing flow cytometry analysis.

Results

CLEC11A was over-expressed in GC, and the elevated CLEC11A expression indicated an unfavorable prognosis in GC patients. CLEC11A was involved in genomic alterations and associated with the TME in GC. Moreover, elevated CLEC11A was found to reduce the benefit of immunotherapy according to immunophenoscore (IPS) and the tumor immune dysfunction, exclusion (TIDE). After validation, the CLEC11A-derived immune signature demonstrated a consistent ability to predict the survival outcomes in GC patients. A nomogram that quantifies survival probability was constructed to improve the accuracy of prognosis prediction in GC patients. Using shRNA to suppress the expression of CLEC11A led to significant inhibitions of cell cycle progression, migration, and invasion, as well as a marked reduction of in vivo tumor growth. Moreover, the flow cytometry assay showed that the knock-down of CLEC11A increased the infiltration of cytotoxic CD8+ T cells and helper CD4+ T into tumors while decreasing the percentage of M2 macrophages, MDSCs, and Tregs.

Conclusion

Collectively, our findings revealed that CLEC11A could be a prognostic and immunological biomarker in GC, and CLEC11A-derived immune signature might serve as a new option for clinicians to predict outcomes and formulate personalized treatment plans for GC patients.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Establishment of a pathomic-based machine learning model to predict CD276 (B7-H3) expression in colon cancer

CD276 is a promising prognostic indicator and an attractive therapeutic target in various malignancies. However, current methods for CD276 detection are time-consuming and expensive, limiting extensive studies and applications of CD276. We aimed to develop a pathomic model for CD276 prediction from H&E-stained pathological images, and explore the underlying mechanism of the pathomic features by associating the pathomic model with transcription profiles. A dataset of colon adenocarcinoma (COAD) patients was retrieved from the Cancer Genome Atlas (TCGA) database. The dataset was divided into the training and validation sets according to the ratio of 8:2 by a stratified sampling method. Using the gradient boosting machine (GBM) algorithm, we established a pathomic model to predict CD276 expression in COAD. Univariate and multivariate Cox regression analyses were conducted to assess the predictive performance of the pathomic model for overall survival in COAD. Gene Set Enrichment Analysis (GESA) was performed to explore the underlying biological mechanisms of the pathomic model. The pathomic model formed by three pathomic features for CD276 prediction showed an area under the curve (AUC) of 0.833 (95%CI: 0.784-0.882) in the training set and 0.758 (95%CI: 0.637-0.878) in the validation set, respectively. The calibration curves and Hosmer-Lemeshow goodness of fit test showed that the prediction probability of high/low expression of CD276 was in favorable agreement with the real situation in both the training and validation sets (P=0.176 and 0.255, respectively). The DCA curves suggested that the pathomic model acquired high clinical benefit. All the subjects were categorized into high pathomic score (PS) (PS-H) and low PS (PS-L) groups according to the cutoff value of PS. Univariate and multivariate Cox regression analysis indicated that PS was a risk factor for overall survival in COAD. Furthermore, through GESA analysis, we found several immune and inflammatory-related pathways and genes were associated with the pathomic model. We constructed a pathomics-based machine learning model for CD276 prediction directly from H&E-stained images in COAD. Through integrated analysis of the pathomic model and transcriptomics, the interpretability of the pathomic model provide a theoretical basis for further hypothesis and experimental research.

Analysis of the risk factors of radiation pneumonitis in patients after radiotherapy for esophageal squamous cell carcinoma

Objective

To predict the risk factors of radiation pneumonitis (RP) in patients with esophageal squamous cell carcinoma (ESCC) who received radiotherapy.

Methods

From January 2015 to October 2021, 477 ESCC patients were enrolled and were assessed retrospectively. All these patients received radiotherapy for primary lesions or mediastinal metastatic lymph nodes. Clinical efficacy and adverse events (AEs) were observed. Univariate analysis identified clinical and dosimetric factors associated with the development of RP, and multivariate logistic regression analysis identified independent potential risk factors associated with the development of RP. Nomograms were constructed to predict RP based on the results of multivariate logistic regression analysis.

Results

Among the 477 ESCC patients, the incidence of RP was 22.2%, and the incidence of grade 4 or higher RP was 1.5%. Univariate analysis indicated that chronic obstructive pulmonary disease (COPD), pulmonary infection, leucopenia, PTV volume, V5, V20, V30 and MLD affected the occurrence of RP. The multivariate logistic regression analysis indicated that COPD (OR:1.821, 95%CI:1.111-2.985; P=0.017), pulmonary infection (OR:2.528, 95%CI:1.530-4.177; P<0.001), higher V20 (OR: 1.129, 95% CI:1.006-1.266; P=0.029) were significant independent predictors of RP in ESCC patients. COPD, pulmonary infection, V20 have been integrated for the RP nomogram. The rate of RP was significantly reduced in the V20<21.45% group. Further analysis indicated that the old age, diabetes, higher V20, and higher MLD were risk factors for grade 4 or higher RP. The area under the curve (AUC) value for V20 was 0.73 (95% CI, 0.567-0.893, P < 0.05).

Conclusion

We have determined the risk factors of RP and grade 4 or higher RP in ESCC patients after radiotherapy. MLD, V20, COPD were independent factors for RP. It was necessary to take measures to reduce or avoid the occurrence of RP for patients with these risk factors at the early stage.

A novel postoperative nomogram and risk classification system for individualized estimation of survival among patients with parotid gland carcinoma after surgery

BACKGROUND

Parotid gland carcinoma (PGC) is a rare but aggressive head and neck cancer, and the prognostic model associated with survival after surgical resection has not yet been established. This study aimed to construct a novel postoperative nomogram and risk classification system for the individualized prediction of overall survival (OS) among patients with resected PGC.

METHODS

Patients with PGC who underwent surgery between 2004 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) database were randomized into training and validation cohorts (7:3). A nomogram developed using independent prognostic factors based on the results of the multivariate Cox regression analysis. Harrell's concordance index (C-index), time-dependent area under the curve (AUC), and calibration plots were used to validate the performance of the nomogram. Moreover, decision curve analysis (DCA) was performed to compare the clinical use of the nomogram with that of traditional TNM staging.

RESULTS

In this study, 5077 patients who underwent surgery for PGC were included. Age, sex, marital status, tumor grade, histology, TNM stage, surgery type, radiotherapy, and chemotherapy were independent prognostic factors. Based on these independent factors, a postoperative nomogram was developed. The C-index of the proposed nomogram was 0.807 (95% confidence interval 0.797-0.817). Meanwhile, the time-dependent AUC (> 0.8) indicated that the nomogram had a satisfactory discriminative ability. The calibration curves showed good concordance between the predicted and actual probabilities of OS, and DCA curves indicated that the nomogram had a better clinical application value than the traditional TNM staging. Moreover, a risk classification system was built that could perfectly classify patients with PGC into three risk groups.

CONCLUSIONS

This study constructed a novel postoperative nomogram and corresponding risk classification system to predict the OS of patients with PGC after surgery. These tools can be used to stratify patients with high or low risk of mortality and provide high-risk patients with more directed therapies and closer follow-up.

Radiomics based on machine learning algorithms could predict prognosis and postoperative chemotherapy benefits of patients with gastric cancer: a retrospective cohort study

Background

Traditional clinical characteristics have certain limitations in evaluating cancer prognosis. The radiomics features provide information on tumor morphology, tissue texture, and hemodynamics, which can accurately reflect personalized predictions. This study investigated the clinical value of radiomics features on contrast-enhanced computed tomography (CT) images in predicting prognosis and postoperative chemotherapy benefits for patients with gastric cancer (GC).

Methods

For this study, 171 GC patients who underwent radical gastrectomy and pathology confirmation of the malignancy at the First Affiliated Hospital of Wenzhou Medical University were retrospectively enrolled. The general information, pathological characteristics, and postoperative chemotherapy information were collected. Patients were also monitored through telephone interviews or outpatient treatment. GC patients were randomly divided into the developing cohort (n=120) and validation cohort (n=51). The intra-tumor areas of interest inside the tumors were delineated, and 1,218 radiomics features were extracted. The optimal radiomics risk score (RRS) was constructed using 8 machine learning algorithms and 29 algorithm combinations. Furthermore, a radiomics nomogram that included clinicopathological characteristics was constructed and validated through univariate and multivariate Cox analyses.

Results

Eleven prognosis-related features were selected, and an RRS was constructed. Kaplan-Meier curve analysis showed that the RRS had a high prognostic ability in the developing and validation cohorts (log-rank P<0.01). The RRS was higher in patients with a larger tumor size (≥3 cm), higher Charlson score (≥2), and higher clinical stage (Stages III and IV) (all P<0.001). Furthermore, GC patients with a higher RRS significantly benefited from postoperative chemotherapy. The results of univariate and multivariate Cox regression analyses demonstrated that the RRS was an independent risk factor for overall survival (OS) and disease-free survival (DFS) (P<0.001). A visual nomogram was established based on the significant factors in multivariate Cox analysis (P<0.05). The C-index was 0.835 (0.793-0.877) for OS and 0.733 (0.677-0.789) for DFS in the developing cohort. The calibration curve also showed that the nomogram had good agreement.

Conclusions

A nomogram that combines the RRS and clinicopathological characteristics could serve as a novel noninvasive preoperative prediction model with the potential to accurately predict the prognosis and chemotherapy benefits of GC patients.

Application of radiomics-based multiomics combinations in the tumor microenvironment and cancer prognosis

The advent of immunotherapy, a groundbreaking advancement in cancer treatment, has given rise to the prominence of the tumor microenvironment (TME) as a critical area of research. The clinical implications of an improved understanding of the TME are significant and far-reaching. Radiomics has been increasingly utilized in the comprehensive assessment of the TME and cancer prognosis. Similarly, the advancement of pathomics, which is based on pathological images, can offer additional insights into the panoramic view and microscopic information of tumors. The combination of pathomics and radiomics has revolutionized the concept of a "digital biopsy". As genomics and transcriptomics continue to evolve, integrating radiomics with genomic and transcriptomic datasets can offer further insights into tumor and microenvironment heterogeneity and establish correlations with biological significance. Therefore, the synergistic analysis of digital image features (radiomics, pathomics) and genetic phenotypes (genomics) can comprehensively decode and characterize the heterogeneity of the TME as well as predict cancer prognosis. This review presents a comprehensive summary of the research on important radiomics biomarkers for predicting the TME, emphasizing the interplay between radiomics, genomics, transcriptomics, and pathomics, as well as the application of multiomics in decoding the TME and predicting cancer prognosis. Finally, we discuss the challenges and opportunities in multiomics research. In conclusion, this review highlights the crucial role of radiomics and multiomics associations in the assessment of the TME and cancer prognosis. The combined analysis of radiomics, pathomics, genomics, and transcriptomics is a promising research direction with substantial research significance and value for comprehensive TME evaluation and cancer prognosis assessment.

Identification and Validation of a Metabolism-Related Prognostic Signature Associated with M2 Macrophage Infiltration in Gastric Cancer

High levels of M2 macrophage infiltration invariably contribute to poor cancer prognosis and can be manipulated by metabolic reprogramming in the tumor microenvironment. However, the metabolism-related genes (MRGs) affecting M2 macrophage infiltration and their clinical implications are not fully understood. In this study, we identified 173 MRGs associated with M2 macrophage infiltration in cases of gastric cancer (GC) using the TCGA and GEO databases. Twelve MRGs were eventually adopted as the prognostic signature to develop a risk model. In the high-risk group, the patients showed poorer survival outcomes than patients in the low-risk group. Additionally, the patients in the high-risk group were less sensitive to certain drugs, such as 5-Fluorouracil, Oxaliplatin, and Cisplatin. Risk scores were positively correlated with the infiltration of multiple immune cells, including CD8+ T cells and M2 macrophages. Furthermore, a difference was observed in the expression and distribution between the 12 signature genes in the tumor microenvironment through single-cell sequencing analysis. In vitro experiments proved that the M2 polarization of macrophages was suppressed by Sorcin-knockdown GC cells, thereby hindering the proliferation and migration of GC cells. These findings provide a valuable prognostic signature for evaluating clinical outcomes and corresponding treatment options and identifying potential targets for GC treatment.

Association between radiomics features of DCE-MRI and CD8+ and CD4+ TILs in advanced gastric cancer

Objective: The aim of this investigation was to explore the correlation between the levels of tumor-infiltrating CD8⁺ and CD4⁺ T cells and the quantitative pharmacokinetic parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in patients with advanced gastric cancer. Methods: We retrospectively analyzed the data of 103 patients with histopathologically confirmed advanced gastric cancer (AGC). Three pharmacokinetic parameters, K_ep, K^trans, and V_e, and their radiomics characteristics were obtained by Omni Kinetics software. Immunohistochemical staining was used to determine CD4⁺ and CD8⁺ TILs. Statistical analysis was subsequently performed to assess the correlation between radiomics characteristics and CD4⁺ and CD8⁺ TIL density. Results: All patients included in this study were finally divided into either a CD8⁺ TILs low-density group (n = 51) (CD8⁺ TILs < 138) or a high-density group (n = 52) (CD8⁺ TILs ≥ 138), and a CD4⁺ TILs low-density group (n = 51) (CD4⁺ TILs < 87) or a high-density group (n = 52) (CD4⁺ TILs ≥ 87). ClusterShade and Skewness based on K_ep and Skewness based on K^trans both showed moderate negative correlation with CD8⁺ TIL levels (r = 0.630-0.349, p < 0.001), with ClusterShade based on K_ep having the highest negative correlation (r = -0.630, p < 0.001). Inertia-based K_ep showed a moderate positive correlation with the CD4⁺ TIL level (r = 0.549, p < 0.001), and the Correlation based on K_ep showed a moderate negative correlation with the CD4⁺ TIL level, which also had the highest correlation coefficient (r = -0.616, p < 0.001). The diagnostic efficacy of the above features was assessed by ROC curves. For CD8⁺ TILs, ClusterShade of K_ep had the highest mean area under the curve (AUC) (0.863). For CD4⁺ TILs, the Correlation of K_ep had the highest mean AUC (0.856). Conclusion: The radiomics features of DCE-MRI are associated with the expression of tumor-infiltrating CD8⁺ and CD4⁺ T cells in AGC, which have the potential to noninvasively evaluate the expression of CD8⁺ and CD4⁺ TILs in AGC patients.

Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer

Background: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes. Results: This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers. Conclusions: This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.

Development and validation of a radiopathomic model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer patients

BACKGROUND

Neoadjuvant chemotherapy (NAC) has become the standard therapeutic option for early high-risk and locally advanced breast cancer. However, response rates to NAC vary between patients, causing delays in treatment and affecting the prognosis for patients who do not sensitive to NAC.

MATERIALS AND METHODS

In total, 211 breast cancer patients who completed NAC (training set: 155, validation set: 56) were retrospectively enrolled. we developed a deep learning radiopathomics model(DLRPM) by Support Vector Machine (SVM) method based on clinicopathological features, radiomics features, and pathomics features. Furthermore, we comprehensively validated the DLRPM and compared it with three single-scale signatures.

RESULTS

DLRPM had favourable performance for the prediction of pathological complete response (pCR) in the training set (AUC 0.933[95% CI 0.895-0.971]), and in the validation set (AUC 0.927 [95% CI 0.858-0.996]). In the validation set, DLRPM also significantly outperformed the radiomics signature (AUC 0.821[0.700-0.942]), pathomics signature (AUC 0.766[0.629-0.903]), and deep learning pathomics signature (AUC 0.804[0.683-0.925]) (all p < 0.05). The calibration curves and decision curve analysis also indicated the clinical effectiveness of the DLRPM.

CONCLUSIONS

DLRPM can help clinicians accurately predict the efficacy of NAC before treatment, highlighting the potential of artificial intelligence to improve the personalized treatment of breast cancer patients.

Predicting peritoneal recurrence in gastric cancer with serosal invasion using a pathomics nomogram

Peritoneal recurrence is the most frequent and lethal recurrence pattern in gastric cancer (GC) with serosal invasion after radical surgery. However, current evaluation methods are not adequate for predicting peritoneal recurrence in GC with serosal invasion. Emerging evidence shows that pathomics analyses could be advantageous for risk stratification and outcome prediction. Herein, we propose a pathomics signature composed of multiple pathomics features extracted from digital hematoxylin and eosin-stained images. We found that the pathomics signature was significantly associated with peritoneal recurrence. A competing-risk pathomics nomogram including carbohydrate antigen 19-9 level, depth of invasion, lymph node metastasis, and pathomics signature was developed for predicting peritoneal recurrence. The pathomics nomogram had favorable discrimination and calibration. Thus, the pathomics signature is a predictive indicator of peritoneal recurrence, and the pathomics nomogram may provide a helpful reference for predicting an individual's risk in peritoneal recurrence of GC with serosal invasion.

Subjective and objective quality assessment of gastrointestinal endoscopy images: From manual operation to artificial intelligence

Gastrointestinal endoscopy has been identified as an important tool for cancer diagnosis and therapy, particularly for treating patients with early gastric cancer (EGC). It is well known that the quality of gastroscope images is a prerequisite for achieving a high detection rate of gastrointestinal lesions. Owing to manual operation of gastroscope detection, in practice, it possibly introduces motion blur and produces low-quality gastroscope images during the imaging process. Hence, the quality assessment of gastroscope images is the key process in the detection of gastrointestinal endoscopy. In this study, we first present a novel gastroscope image motion blur (GIMB) database that includes 1,050 images generated by imposing 15 distortion levels of motion blur on 70 lossless images and the associated subjective scores produced with the manual operation of 15 viewers. Then, we design a new artificial intelligence (AI)-based gastroscope image quality evaluator (GIQE) that leverages the newly proposed semi-full combination subspace to learn multiple kinds of human visual system (HVS) inspired features for providing objective quality scores. The results of experiments conducted on the GIMB database confirm that the proposed GIQE showed more effective performance compared with its state-of-the-art peers.

USP51/ZEB1/ACTA2 axis promotes mesenchymal phenotype in gastric cancer and is associated with low cohesion characteristics

poorly cohesive (PC) gastric cancer (GC) (PC-GC) is a distinct histological subtype of GC and is defined as a tumor consisting of isolated or small clusters of tumor cells with poorly differentiated and metastatic characteristics. According to multiple studies, PC-GC is intrinsically heterogeneous, with mesenchymal variants being the most aggressive. However, to date, the molecular mechanisms associated with PC-GC are still not fully understood. This study investigated the role of the USP51/ZEB1/ACTA2 axis in promoting GC metastasis. Single-cell sequencing revealed that E-box binding homeobox 1 (ZEB1) expression was significantly increased in a subpopulation of low-adherent cells and was an independent prognostic factor in GC patients. Furthermore, the bulk transcriptome analysis revealed a significant positive correlation between Ubiquitin Specific Peptidase 51 (USP51), ZEB1, and Actin Alpha 2 (ACTA2), and our data further confirmed that all three were highly co-localized in PC-GC tissues. According to the findings of in vitro and in vivo experiments, USP51 was able to maintain ZEB1 expression to promote ACTA2 transcription, thereby activating the mesenchymal phenotype of GC cells and promoting tumor metastasis. Moreover, USP51 could recruit and activate stromal cells, including M2-like macrophages and fibroblasts, through cancer cells. Clinical data suggested that overexpression of USP51 predicts that patients have difficulty benefiting from immunotherapy and is associated with immune-exclusion tumor characteristics. Collectively, the findings of this study shed light on a key mechanism by which elevated USP51 expression induces Epithelial-mesenchymal transition (EMT) in GC cells, hence facilitating GC cell proliferation, survival, and dissemination. In this view, USP51/ZEB1/ACTA2 may serve as a candidate therapeutic target against GC metastasis.

Cervical lymph node metastasis prediction of postoperative papillary thyroid carcinoma before 131I therapy based on clinical and ultrasound characteristics

BACKGROUND

The status of lymph nodes is crucial to determine the dose of radioiodine-131(¹³¹I) for postoperative papillary thyroid carcinoma (PTC). We aimed to develop a nomogram for predicting residual and recurrent cervical lymph node metastasis (CLNM) in postoperative PTC before ¹³¹I therapy.

METHOD

Data from 612 postoperative PTC patients who underwent ¹³¹I therapy from May 2019 to December 2020 were retrospectively analyzed. Clinical and ultrasound features were collected. Univariate and multivariate logistic regression analyses were performed to determine the risk factors of CLNM. Receiver operating characteristic (ROC) analysis was used to weigh the discrimination of prediction models. To generate nomograms, models with high area under the curves (AUC) were selected. Bootstrap internal validation, calibration curves and decision curves were used to assess the prediction model's discrimination, calibration, and clinical usefulness.

RESULTS

A total of 18.79% (115/612) of postoperative PTC patients had CLNM. Univariate logistic regression analysis found serum thyroglobulin (Tg), serum thyroglobulin antibodies (TgAb), overall ultrasound diagnosis and seven ultrasound features (aspect transverse ratio, cystic change, microcalcification, mass hyperecho, echogenicity, lymphatic hilum structure and vascularity) were significantly associated with CLNM. Multivariate analysis revealed higher Tg, higher TgAb, positive overall ultrasound and ultrasound features such as aspect transverse ratio ≥ 2, microcalcification, heterogeneous echogenicity, absence of lymphatic hilum structure and abundant vascularity were independent risk factors for CLNM. ROC analysis showed the use of Tg and TgAb combined with ultrasound (AUC = 0.903 for "Tg+TgAb+Overall ultrasound" model, AUC = 0.921 for "Tg+TgAb+Seven ultrasound features" model) was superior to any single variant. Nomograms constructed for the above two models were validated internally and the C-index were 0.899 and 0.914, respectively. Calibration curves showed satisfied discrimination and calibration of the two nomograms. DCA also proved that the two nomograms were clinically useful.

CONCLUSION

Through the two accurate and easy-to-use nomograms, the possibility of CLNM can be objectively quantified before ¹³¹I therapy. Clinicians can use the nomograms to evaluate the status of lymph nodes in postoperative PTC patients and consider a higher dose of ¹³¹I for those with high scores.