A deep learning model and human-machine fusion for prediction of EBV-associated gastric cancer from histopathology

Harbor seal whiskers optimization algorithm with deep learning-based medical imaging analysis for gastrointestinal cancer detection

Gastrointestinal (GI) cancer detection includes the detection of cancerous or potentially cancerous lesions within the GI tract. Earlier diagnosis is critical for increasing the success of treatment and improving patient outcomes. Medical imaging plays a major role in diagnosing and detecting GI cancer. CT scans, endoscopy, MRI, ultrasound, and positron emission tomography (PET) scans can help detect lesions, abnormal masses, and changes in tissue structure. Artificial intelligence (AI) and machine learning (ML) methods are being gradually applied to medical imaging for cancer diagnosis. ML algorithms, including deep learning methodologies like convolutional neural network (CNN), are applied frequently for cancer diagnosis. These models learn features and patterns from labelled datasets to discriminate between normal and abnormal areas in medical images. This article presents a new Harbor Seal Whiskers Optimization Algorithm with Deep Learning based Medical Imaging Analysis for Gastrointestinal Cancer Detection (HSWOA-DLGCD) technique. The goal of the HSWOA-DLGCD algorithm is to explore the GI images for the cancer diagnosis. In order to accomplish this, the HSWOA-DLGCD system applies bilateral filtering (BF) approach for the removal of noise. In addition, the HSWOA-DLGCD technique makes use of HSWOA with Xception model for feature extraction. For cancer recognition, the HSWOA-DLGCD technique applies extreme gradient boosting (XGBoost) model. Finally, the parameters compared with the XGBoost system can be selected by moth flame optimization (MFO) system. The experimental results of the HSWOA-DLGCD technique could be verified on the Kvasir database. The simulation outcome demonstrated a best possible solution of the HSWOA-DLGCD method than other recent methods.

Computational pathology: A survey review and the way forward

Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.

Prognostic prediction of gastric cancer based on H&E findings and machine learning pathomics

AIM

In this research, we aimed to develop a model for the accurate prediction of gastric cancer based on H&E findings combined with machine learning pathomics.

METHODS

Transcriptome data, pathological images, and clinical data from 443 cases were retrieved from TCGA (The Cancer Genome Atlas Program) for survival analysis. The images were segmented using the Otsu algorithm, and features were extracted using the PyRadiomics package. Subsequently, the cases were randomly divided into a training cohort of 165 cases and a validation cohort of 69 cases. Features selected via minimum Redundancy - Maximum Relevance (mRMR)- recursive feature elimination (RFE) screening were used to train a model using the Gradient Boosting Machine (GBM) algorithm. The model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), calibration curves, and decision curves. Additionally, the correlation between the Pathomics score (PS) and immune genes was examined.

RESULTS

In the multivariate analysis, heightened infiltration of activated CD4 memory T cells was strongly associated with improved overall survival (HR = 0.505, 95 % CI = 0.342-0.745, P < 0.001). The pathomic model, exhibiting robust predictive capability, demonstrated impressive AUC values of 0.844 and 0.750 in both study cohorts. The Decision Curve Analysis (DCA) unequivocally underscored the model's exceptional clinical utility. In a subsequent multivariate analysis, heightened infiltration of the PS also emerged as a significant protective factor for overall survival (HR = 0.506, 95 % CI = 0.329-0.777, P = 0.002).

CONCLUSION

The pathomic model based on H&E slides for predicting the infiltration degree of activated CD4 memory T cells, along with integrated bioinformatics analysis elucidating potential molecular mechanisms, offers novel prognostic indicators for the precise stratification and individualized prognosis of gastric cancer patients.

Significance of Artificial Intelligence in the Study of Virus-Host Cell Interactions

A highly critical event in a virus's life cycle is successfully entering a given host. This process begins when a viral glycoprotein interacts with a target cell receptor, which provides the molecular basis for target virus-host cell interactions for novel drug discovery. Over the years, extensive research has been carried out in the field of virus-host cell interaction, generating a massive number of genetic and molecular data sources. These datasets are an asset for predicting virus-host interactions at the molecular level using machine learning (ML), a subset of artificial intelligence (AI). In this direction, ML tools are now being applied to recognize patterns in these massive datasets to predict critical interactions between virus and host cells at the protein-protein and protein-sugar levels, as well as to perform transcriptional and translational analysis. On the other end, deep learning (DL) algorithms-a subfield of ML-can extract high-level features from very large datasets to recognize the hidden patterns within genomic sequences and images to develop models for rapid drug discovery predictions that address pathogenic viruses displaying heightened affinity for receptor docking and enhanced cell entry. ML and DL are pivotal forces, driving innovation with their ability to perform analysis of enormous datasets in a highly efficient, cost-effective, accurate, and high-throughput manner. This review focuses on the complexity of virus-host cell interactions at the molecular level in light of the current advances of ML and AI in viral pathogenesis to improve new treatments and prevention strategies.

Learning generalizable AI models for multi-center histopathology image classification

Investigation of histopathology slides by pathologists is an indispensable component of the routine diagnosis of cancer. Artificial intelligence (AI) has the potential to enhance diagnostic accuracy, improve efficiency, and patient outcomes in clinical pathology. However, variations in tissue preparation, staining protocols, and histopathology slide digitization could result in over-fitting of deep learning models when trained on the data from only one center, thereby underscoring the necessity to generalize deep learning networks for multi-center use. Several techniques, including the use of grayscale images, color normalization techniques, and Adversarial Domain Adaptation (ADA) have been suggested to generalize deep learning algorithms, but there are limitations to their effectiveness and discriminability. Convolutional Neural Networks (CNNs) exhibit higher sensitivity to variations in the amplitude spectrum, whereas humans predominantly rely on phase-related components for object recognition. As such, we propose Adversarial fourIer-based Domain Adaptation (AIDA) which applies the advantages of a Fourier transform in adversarial domain adaptation. We conducted a comprehensive examination of subtype classification tasks in four cancers, incorporating cases from multiple medical centers. Specifically, the datasets included multi-center data for 1113 ovarian cancer cases, 247 pleural cancer cases, 422 bladder cancer cases, and 482 breast cancer cases. Our proposed approach significantly improved performance, achieving superior classification results in the target domain, surpassing the baseline, color augmentation and normalization techniques, and ADA. Furthermore, extensive pathologist reviews suggested that our proposed approach, AIDA, successfully identifies known histotype-specific features. This superior performance highlights AIDA's potential in addressing generalization challenges in deep learning models for multi-center histopathology datasets.

Deep learning-enabled classification of kidney allograft rejection on whole slide histopathologic images

Background

Diagnosis of kidney transplant rejection currently relies on manual histopathological assessment, which is subjective and susceptible to inter-observer variability, leading to limited reproducibility. We aim to develop a deep learning system for automated assessment of whole-slide images (WSIs) from kidney allograft biopsies to enable detection and subtyping of rejection and to predict the prognosis of rejection.

Method

We collected H&E-stained WSIs of kidney allograft biopsies at 400x magnification from January 2015 to September 2023 at two hospitals. These biopsy specimens were classified as T cell-mediated rejection, antibody-mediated rejection, and other lesions based on the consensus reached by two experienced transplant pathologists. To achieve feature extraction, feature aggregation, and global classification, we employed multi-instance learning and common convolution neural networks (CNNs). The performance of the developed models was evaluated using various metrics, including confusion matrix, receiver operating characteristic curves, the area under the curve (AUC), classification map, heat map, and pathologist-machine confrontations.

Results

In total, 906 WSIs from 302 kidney allograft biopsies were included for analysis. The model based on multi-instance learning enables detection and subtyping of rejection, named renal rejection artificial intelligence model (RRAIM), with the overall 3-category AUC of 0.798 in the independent test set, which is superior to that of three transplant pathologists under nearly routine assessment conditions. Moreover, the prognosis models accurately predicted graft loss within 1 year following rejection and treatment response for rejection, achieving AUC of 0.936 and 0.756, respectively.

Conclusion

We first developed deep-learning models utilizing multi-instance learning for the detection and subtyping of rejection and prediction of rejection prognosis in kidney allograft biopsies. These models performed well and may be useful in assisting the pathological diagnosis.

Epstein-Barr virus positive gastric cancer: the pathological basis of CT findings and radiomics models prediction

PURPOSE

To analyze the clinicopathologic information and CT imaging features of Epstein-Barr virus (EBV)-positive gastric cancer (GC) and establish CT-based radiomics models to predict the EBV status of GC.

METHODS

This retrospective study included 144 GC cases, including 48 EBV-positive cases. Pathological and immunohistochemical information was collected. CT enlarged LN and morphological characteristics were also assessed. Radiomics models were constructed to predict the EBV status, including decision tree (DT), logistic regression (LR), random forest (RF), and support vector machine (SVM).

RESULTS

T stage, Lauren classification, histological differentiation, nerve invasion, VEGFR2, E-cadherin, PD-L1, and Ki67 differed significantly between the EBV-positive and -negative groups (p = 0.015, 0.030, 0.006, 0.022, 0.028, 0.030, < 0.001, and < 0.001, respectively). CT enlarged LN and large ulceration differed significantly between the two groups (p = 0.019 and 0.043, respectively). The number of patients in the training and validation cohorts was 100 (with 33 EBV-positive cases) and 44 (with 15 EBV-positive cases). In the training cohort, the radiomics models using DT, LR, RF, and SVM yielded areas under the curve (AUCs) of 0.905, 0.771, 0.836, and 0.886, respectively. In the validation cohort, the diagnostic efficacy of radiomics models using the four classifiers were 0.737, 0.722, 0.751, and 0.713, respectively.

CONCLUSION

A significantly higher proportion of CT enlarged LN and a significantly lower proportion of large ulceration were found in EBV-positive GC. The prediction efficiency of radiomics models with different classifiers to predict EBV status in GC was good.

Clinically Applicable Pan-Origin Cancer Detection for Lymph Nodes via Artificial Intelligence-Based Pathology

INTRODUCTION

Lymph node metastasis is one of the most common ways of tumour metastasis. The presence or absence of lymph node involvement influences the cancer's stage, therapy, and prognosis. The integration of artificial intelligence systems in the histopathological diagnosis of lymph nodes after surgery is urgent.

METHODS

Here, we propose a pan-origin lymph node cancer metastasis detection system. The system is trained by over 700 whole-slide images (WSIs) and is composed of two deep learning models to locate the lymph nodes and detect cancers.

RESULTS

It achieved an area under the receiver operating characteristic curve (AUC) of 0.958, with a 95.2% sensitivity and 72.2% specificity, on 1,402 WSIs from 49 organs at the National Cancer Center, China. Moreover, we demonstrated that the system could perform robustly with 1,051 WSIs from 52 organs from another medical centre, with an AUC of 0.925.

CONCLUSION

Our research represents a step forward in a pan-origin lymph node metastasis detection system, providing accurate pathological guidance by reducing the probability of missed diagnosis in routine clinical practice.

A multicenter proof-of-concept study on deep learning-based intraoperative discrimination of primary central nervous system lymphoma

Accurate intraoperative differentiation of primary central nervous system lymphoma (PCNSL) remains pivotal in guiding neurosurgical decisions. However, distinguishing PCNSL from other lesions, notably glioma, through frozen sections challenges pathologists. Here we sought to develop and validate a deep learning model capable of precisely distinguishing PCNSL from non-PCNSL lesions, especially glioma, using hematoxylin and eosin (H&E)-stained frozen whole-slide images. Also, we compared its performance against pathologists of varying expertise. Additionally, a human-machine fusion approach integrated both model and pathologic diagnostics. In external cohorts, LGNet achieved AUROCs of 0.965 and 0.972 in distinguishing PCNSL from glioma and AUROCs of 0.981 and 0.993 in differentiating PCNSL from non-PCNSL lesions. Outperforming several pathologists, LGNet significantly improved diagnostic performance, further augmented to some extent by fusion approach. LGNet's proficiency in frozen section analysis and its synergy with pathologists indicate its valuable role in intraoperative diagnosis, particularly in discriminating PCNSL from glioma, alongside other lesions.

Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning

Cancer of unknown primary (CUP) site poses diagnostic challenges due to its elusive nature. Many cases of CUP manifest as pleural and peritoneal serous effusions. Leveraging cytological images from 57,220 cases at four tertiary hospitals, we developed a deep-learning method for tumor origin differentiation using cytological histology (TORCH) that can identify malignancy and predict tumor origin in both hydrothorax and ascites. We examined its performance on three internal (n = 12,799) and two external (n = 14,538) testing sets. In both internal and external testing sets, TORCH achieved area under the receiver operating curve values ranging from 0.953 to 0.991 for cancer diagnosis and 0.953 to 0.979 for tumor origin localization. TORCH accurately predicted primary tumor origins, with a top-1 accuracy of 82.6% and top-3 accuracy of 98.9%. Compared with results derived from pathologists, TORCH showed better prediction efficacy (1.677 versus 1.265, P < 0.001), enhancing junior pathologists' diagnostic scores significantly (1.326 versus 1.101, P < 0.001). Patients with CUP whose initial treatment protocol was concordant with TORCH-predicted origins had better overall survival than those who were administrated discordant treatment (27 versus 17 months, P = 0.006). Our study underscores the potential of TORCH as a valuable ancillary tool in clinical practice, although further validation in randomized trials is warranted.

Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides

Programmed cell death ligand 1 (PDL1), as an important biomarker, is quantified by immunohistochemistry (IHC) with few established histopathological patterns. Deep learning aids in histopathological assessment, yet heterogeneity and lacking spatially resolved annotations challenge precise analysis. Here, we present a weakly supervised learning approach using bulk RNA sequencing for PDL1 expression prediction from hematoxylin and eosin (H&E) slides. Our method extends the multiple instance learning paradigm with the teacher-student framework, which assigns dynamic pseudo-labels for intra-slide heterogeneity and retrieves unlabeled instances using temporal ensemble model distillation. The approach, evaluated on 12,299 slides across 20 solid tumor types, achieves a weighted average area under the curve of 0.83 on fresh-frozen and 0.74 on formalin-fixed specimens for 9 tumors with PDL1 as an established biomarker. Our method predicts PDL1 expression patterns, validated by IHC on 20 slides, offering insights into histologies relevant to PDL1. This demonstrates the potential of deep learning in identifying diverse histological patterns for molecular changes from H&E images.

An interpretable deep learning model for identifying the morphological characteristics of dMMR/MSI-H gastric cancer

Accurate tumor diagnosis by pathologists relies on identifying specific morphological characteristics. However, summarizing these unique morphological features in tumor classifications can be challenging. Although deep learning models have been extensively studied for tumor classification, their indirect and subjective interpretation obstructs pathologists from comprehending the model and discerning the morphological features accountable for classifications. In this study, we introduce a new approach utilizing Style Generative Adversarial Networks, which enables a direct interpretation of deep learning models to detect significant morphological characteristics within datasets representing patients with deficient mismatch repair/microsatellite instability-high gastric cancer. Our approach effectively identifies distinct morphological features crucial for tumor classification, offering valuable insights for pathologists to enhance diagnostic accuracy and foster professional growth.

Investigating the relationship between Epstein-Barr virus infection and gastric cancer: A systematic review and meta-analysis

Background and Aims

Gastric cancer (GC) is a common cancer type worldwide, and various factors can be involved in its occurrence. One of these factors is Epstein-Barr virus (EBV) infection. In this regard, a systematic review and meta-analysis was conducted to achieve a better understanding of the EBV prevalence in GC samples.

Methods

English databases were searched and studies that reported the prevalence and etiological factors of EBV related to GC from July 2007 to November 2022 were retrieved. The reported data were selected based on the inclusion and exclusion criteria. The pooled prevalence of EBV infection with 95% confidence intervals was calculated. Quality assessment, heterogeneity testing, and publication bias assessment were also performed. The literature search showed 953 studies, of which 87 studies met our inclusion criteria and were used for meta-analysis.

Results

The pooled prevalence of EBV infection related to GC was estimated to be 9.5% (95% confidence interval [CI]: 8.2%-11%) in the general population. The prevalence of EBV infection related to GC by gender was 13.5% (95% CI: 11.1%-16.3%) in males and 7.6% (95% CI: 5.4%-10.6%) in females. No significant differences were observed in terms of geographical region. Out of the 87 studies included in the meta-analysis, the most common diagnostic test was in situ hybridization (58 cases).

Conclusions

Altogether, the results indicated that EBV infection is one of the important factors in the development of GC. However, this does not necessarily mean that EBV infection directly causes GC since other factors may also be involved in the development of GC. Therefore, it is recommended to conduct extensive epidemiological studies on various aspects of the relationship between this virus and GC, which can provide valuable information for understanding the relationship between EBV and GC.

Heterogeneity and predictors of the effects of AI assistance on radiologists

The integration of artificial intelligence (AI) in medical image interpretation requires effective collaboration between clinicians and AI algorithms. Although previous studies demonstrated the potential of AI assistance in improving overall clinician performance, the individual impact on clinicians remains unclear. This large-scale study examined the heterogeneous effects of AI assistance on 140 radiologists across 15 chest X-ray diagnostic tasks and identified predictors of these effects. Surprisingly, conventional experience-based factors, such as years of experience, subspecialty and familiarity with AI tools, fail to reliably predict the impact of AI assistance. Additionally, lower-performing radiologists do not consistently benefit more from AI assistance, challenging prevailing assumptions. Instead, we found that the occurrence of AI errors strongly influences treatment outcomes, with inaccurate AI predictions adversely affecting radiologist performance on the aggregate of all pathologies and on half of the individual pathologies investigated. Our findings highlight the importance of personalized approaches to clinician-AI collaboration and the importance of accurate AI models. By understanding the factors that shape the effectiveness of AI assistance, this study provides valuable insights for targeted implementation of AI, enabling maximum benefits for individual clinicians in clinical practice.

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.

Machine learning constructs color features to accelerate development of long-term continuous water quality monitoring

Long-term continuous water quality monitoring (LTCM) is crucial to ensure the safety of water resources. However, lab-based pollutant detection via machine learning (ML) usually involves colorimetric materials or sensors, and it cannot be ignored that sensor limitations prevent their use for LTCM. To address this challenge, we propose a novel method that leverages image recognition to establish a relationship between pollutant concentration and color. By extracting efficient color variation features from raw pixel matrices using a combination of Kmeans clustering and RGB average features, the concentrations of pollutants that are difficult to distinguish by the naked eyes can be directly captured without the need for sensors and preprocessing. Four ML models (XGBoost, Linear, support vector regression (SVR), and Ridge) achieved up to a 95.9% increase in coefficient of determination (R2) compared to principal component analysis (PCA). In the prediction of the concentration of simulated pollutants such as Cu2+, Co2+, Rhodamine B, and the concentration of Cr(VI) in actual electroplating wastewater, natural resource water and drinking water, over 95% R2 was achieved. The method reported in our work can effectively capture subtle color changes that cannot be observed by the naked eyes without any preprocessing of water samples, providing a reliable method for LTCM.

A Novel Deep Learning Algorithm for Human Papillomavirus Infection Prediction in Head and Neck Cancers Using Routine Histology Images

The etiology of head and neck squamous cell carcinoma (HNSCC) involves multiple carcinogens, such as alcohol, tobacco, and infection with human papillomavirus (HPV). Because HPV infection influences the prognosis, treatment, and survival of patients with HNSCC, it is important to determine the HPV status of these tumors. In this article, we propose a novel deep learning pipeline for HPV infection status prediction with state-of-the-art performance in HPV detection using only whole-slide images of routine hematoxylin and eosin-stained HNSCC sections. We show that our Digital-HPV score generated from hematoxylin and eosin slides produces statistically significant patient stratifications in terms of overall and disease-specific survival. In addition, quantitative profiling of the spatial tumor microenvironment and analysis of the immune profiles show relatively high levels of lymphocytic infiltration in tumor and tumor-associated stroma. High levels of B cells and T cells and low macrophage levels were also identified in HPV-positive patients compared to HPV-negative patients, confirming different immune response patterns elicited by HPV infection in patients with HNSCC.

Measuring the binary thickness of buccal bone of anterior maxilla in low-resolution cone-beam computed tomography via a bilinear convolutional neural network

Background

The thickness of the buccal bone of the anterior maxilla is an important aesthetic-determining factor for dental implant, which is divided into the thick (≥1 mm) and thin type (<1 mm). However, as a micro-scale structure that is evaluated through low-resolution cone-beam computed tomography (CBCT), its thickness measurement is error-prone under the circumstance of enormous patients and relatively inexperienced primary dentists. Further, the challenges of deep learning-based analysis of the binary thickness of buccal bone include the substantial real-world variance caused by pixel error, the extraction of fine-grained features, and burdensome annotations.

Methods

This study built bilinear convolutional neural network (BCNN) with 2 convolutional neural network (CNN) backbones and a bilinear pooling module to predict the binary thickness of buccal bone (thick or thin) of the anterior maxilla in an end-to-end manner. The methods of 5-fold cross-validation and model ensemble were adopted at the training and testing stages. The visualization methods of Gradient Weighted Class Activation Mapping (Grad-CAM), Guided Grad-CAM, and layer-wise relevance propagation (LRP) were used for revealing the important features on which the model focused. The performance metrics and efficacy were compared between BCNN, dentists of different clinical experience (i.e., dental student, junior dentist, and senior dentist), and the fusion of BCNN and dentists to investigate the clinical feasibility of BCNN.

Results

Based on the dataset of 4,000 CBCT images from 1,000 patients (aged 36.15±13.09 years), the BCNN with visual geometry group (VGG)16 backbone achieved an accuracy of 0.870 [95% confidence interval (CI): 0.838-0.902] and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.924 (95% CI: 0.896-0.948). Compared with the conventional CNNs, BCNN precisely located the buccal bone wall over irrelevant regions. The BCNN generally outperformed the expert-level dentists. The clinical diagnostic performance of the dentists was improved with the assistance of BCNN.

Conclusions

The application of BCNN to the quantitative analysis of binary buccal bone thickness validated the model's excellent ability of subtle feature extraction and achieved expert-level performance. This work signals the potential of fine-grained image recognition networks to the precise quantitative analysis of micro-scale structures.

Emerging biomolecules for practical theranostics of liver hepatocellular carcinoma

Most cases of hepatocellular carcinoma (HCC) are able to be diagnosed through regular surveillance in an identifiable patient population with chronic hepatitis B or cirrhosis. Nevertheless, 50% of global cases might present incidentally owing to symptomatic advanced-stage HCC after worsening of liver dysfunction. A systematic search based on PUBMED was performed to identify relevant outcomes, covering newer surveillance modalities including secretory proteins, DNA methylation, miRNAs, and genome sequencing analysis which proposed molecular expression signatures as ideal tools in the early-stage HCC detection. In the face of low accuracy without harmonization on the analytical approaches and data interpretation for liquid biopsy, a more accurate incidence of HCC will be unveiled by using deep machine learning system and multiplex immunohistochemistry analysis. A combination of molecular-secretory biomarkers, high-definition imaging and bedside clinical indexes in a surveillance setting offers a comprehensive range of HCC potential indicators. In addition, the sequential use of numerous lines of systemic anti-HCC therapies will simultaneously benefit more patients in survival. This review provides an overview on the most recent developments in HCC theranostic platform.

Development and validation of novel immune-inflammation-based clinical predictive nomograms in HER2-negative advanced gastric cancer

Purpose

To explore the predictive value of multiple immune-inflammatory biomarkers including serum VEGFA and systemic immune-inflammation index (SII) in HER2-negative advanced gastric cancer (AGC) and establish nomograms for predicting the first-line chemotherapeutic efficacy, progression-free survival (PFS) and overall survival (OS) of patients with this fatal disease.

Methods

From November 2017 to April 2022, 102 and 34 patients with a diagnosis of HER2-negative AGC at the First Affiliated Hospital of Bengbu Medical College were enrolled as development and validation cohorts, respectively. Univariate and multivariate analyses were performed to evaluate the clinical value of the candidate indicators. The variables were screened using LASSO regression analysis. Predictive models were developed using significant predictors and are displayed as nomograms.

Results

Baseline VEGFA expression was significantly higher in HER2-negative AGC patients than in nonneoplastic patients and was associated with malignant serous effusion and therapeutic efficacy (all p<0.001). Multivariate analysis indicated that VEGFA was an independent predictor for first-line therapeutic efficacy and PFS (both p<0.01) and SII was an independent predictor for first-line PFS and OS (both p<0.05) in HER2-negative AGC patients. The therapeutic efficacy model had an R2 of 0.37, a Brier score of 0.15, and a Harrell's C-index of 0.82 in the development cohort and 0.90 in the validation cohort. The decision curve analysis indicated that the model added more net benefits than VEGFA assessment alone. The PFS/OS models had Harrell's C-indexes of 0.71/0.69 in the development cohort and 0.71/0.62 in the validation cohort.

Conclusion

The established nomograms integrating serum VEGFA/SII and commonly available baseline characteristics provided satisfactory performance in predicting the therapeutic efficacy and prognosis of HER2-negative AGC patients.

The role of fungi in the diagnosis of colorectal cancer

Colorectal cancer (CRC) is a prevalent tumour with high morbidity rates worldwide, and its incidence among younger populations is rising. Early diagnosis of CRC can help control the associated mortality. Fungi are common microorganisms in nature. Recent studies have shown that fungi may have a similar association with tumours as bacteria do. As an increasing number of tumour-associated fungi are discovered, this provides new ideas for the diagnosis and prognosis of tumours. The relationship between fungi and colorectal tumours has also been recently identified by scientists. Therefore, this paper describes the limitations and prospects of the application of fungi in diagnosing CRC and predicting CRC prognosis.

Epigenetic Modification-Associated Molecular Classification of Gastric Cancer

Epigenetic modification is involved in tumorigenesis and cancer progression. We developed an epigenetic modification-associated molecular classification of gastric cancer (GC) to identify signature genes that accurately predict prognosis and the efficacy of immunotherapy. Least absolute shrinkage and selection operator and multivariate Cox regression analysis were conducted to develop an epigenetic modification-associated molecular classification. We investigated the significance of PIP4P2, an independent prognostic factor of the classification system, in predicting the prognosis and immunotherapy efficacy of patients with GC. The epigenetic modification-associated molecular classification was highly associated with the clinicopathological characteristics of patients and the existing classification of GC. PIP4P2 was highly expressed in GC tissue and tumor-associated macrophages. High PIP4P2 expression in GC tissue-induced tumor progression by activating PI3K/AKT signal transduction had a negative impact on immunotherapy efficacy. High expression of PIP4P2 in macrophages was correlated with poor prognosis in patients with GC. PIP4P2 is an independent unfavorable prognostic factor of epigenetic modification-associated molecular classification, is involved in tumorigenic progression, and is essential for assessing the prognosis and immunotherapy efficacy of GC.

Development of a Pathomics-Based Model for the Prediction of Malignant Transformation in Oral Leukoplakia

Accurate prognostic stratification of oral leukoplakia (OLK) with risk of malignant transformation into oral squamous cell carcinoma is crucial. We developed an objective and powerful pathomics-based model for the prediction of malignant transformation in OLK using hematoxylin and eosin (H&E)-stained images. In total, 759 H&E-stained images from multicenter cohorts were included. A training set (n = 489), validation set (n = 196), and testing set (n = 74) were used for model development. Four deep learning methods were used to train and validate the model constructed using H&E-stained images. Pathomics features generated through deep learning combined with machine learning algorithms were used to develop a pathomics-based model. Immunohistochemical staining of Ki67, p53, and PD-L1 was used to interpret the black box of the model. Pathomics-based models predicted the malignant transformation of OLK (validation set area under curve [AUC], 0.899; testing set AUC, 0.813) and significantly identified high-risk and low-risk populations. The prediction performance of malignant transformation from dysplasia grading (validation set AUC, 0.743) was lower than that of the pathomics-based model. The expressions of Ki67, p53, and PD-L1 were correlated with various pathomics features. The pathomics-based model accurately predicted the malignant transformation of OLK and may be useful for the objective and rapid assessment of the prognosis of patients with OLK.

Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology

Gastric cancer is a leading contributor to cancer incidence and mortality globally. Recently, artificial intelligence approaches, particularly machine learning and deep learning, are rapidly reshaping the full spectrum of clinical management for gastric cancer. Machine learning is formed from computers running repeated iterative models for progressively improving performance on a particular task. Deep learning is a subtype of machine learning on the basis of multilayered neural networks inspired by the human brain. This review summarizes the application of artificial intelligence algorithms to multi-dimensional data including clinical and follow-up information, conventional images (endoscope, histopathology, and computed tomography (CT)), molecular biomarkers, etc. to improve the risk surveillance of gastric cancer with established risk factors; the accuracy of diagnosis, and survival prediction among established gastric cancer patients; and the prediction of treatment outcomes for assisting clinical decision making. Therefore, artificial intelligence makes a profound impact on almost all aspects of gastric cancer from improving diagnosis to precision medicine. Despite this, most established artificial intelligence-based models are in a research-based format and often have limited value in real-world clinical practice. With the increasing adoption of artificial intelligence in clinical use, we anticipate the arrival of artificial intelligence-powered gastric cancer care.

Epstein‒Barr virus-associated cellular immunotherapy

Epstein‒Barr virus (EBV) is a human herpes virus that is saliva-transmissible and universally asymptomatic. It has been confirmed that more than 90% of the population is latently infected with EBV for life. EBV can cause a variety of related cancers, such as nasopharyngeal carcinoma, diffuse large B-cell lymphoma, and Burkitt lymphoma. Currently, many clinical studies have demonstrated that EBV-specific cytotoxic T lymphocytes and other cell therapies can be safely and effectively transfused to prevent and treat some diseases caused by EBV. This review will mainly focus on discussing EBV-specific cytotoxic T lymphocytes and will touch on therapeutic EBV vaccines and chimeric antigen receptor T-cell therapy briefly.

Immunotherapeutic approaches in EBV-associated nasopharyngeal carcinoma

Epstein-Barr virus (EBV) was the first tumor virus in humans. Nasopharyngeal carcinoma (NPC) accounts for approximately 60% of the 200,000 new tumor cases caused by EBV infection worldwide each year. NPC has an insidious onset and is highly malignant, with more than 70% of patients having intermediate to advanced disease at the time of initial diagnosis, and is strongly implicated in epithelial cancers as well as malignant lymphoid and natural killer/T cell lymphomas. Over 90% of patients with confirmed undifferentiated NPC are infected with EBV. In recent decades, much progress has been made in understanding the molecular mechanisms of NPC and developing therapeutic approaches. Radiotherapy and chemotherapy are the main treatment options for NPC; however, they have a limited efficacy in patients with locally advanced or distant metastatic tumors. Tumor immunotherapy, including vaccination, adoptive cell therapy, and immune checkpoint blockade, represents a promising therapeutic approach for NPC. Significant breakthroughs have recently been made in the application of immunotherapy for patients with recurrent or metastatic NPC (RM-NPC), indicating a broad prospect for NPC immunotherapy. Here, we review important research findings regarding immunotherapy for NPC patients and provide insights for future research.

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.

A comparative study of gastric histopathology sub-size image classification: From linear regression to visual transformer

Introduction

Gastric cancer is the fifth most common cancer in the world. At the same time, it is also the fourth most deadly cancer. Early detection of cancer exists as a guide for the treatment of gastric cancer. Nowadays, computer technology has advanced rapidly to assist physicians in the diagnosis of pathological pictures of gastric cancer. Ensemble learning is a way to improve the accuracy of algorithms, and finding multiple learning models with complementarity types is the basis of ensemble learning. Therefore, this paper compares the performance of multiple algorithms in anticipation of applying ensemble learning to a practical gastric cancer classification problem.

Methods

The complementarity of sub-size pathology image classifiers when machine performance is insufficient is explored in this experimental platform. We choose seven classical machine learning classifiers and four deep learning classifiers for classification experiments on the GasHisSDB database. Among them, classical machine learning algorithms extract five different image virtual features to match multiple classifier algorithms. For deep learning, we choose three convolutional neural network classifiers. In addition, we also choose a novel Transformer-based classifier.

Results

The experimental platform, in which a large number of classical machine learning and deep learning methods are performed, demonstrates that there are differences in the performance of different classifiers on GasHisSDB. Classical machine learning models exist for classifiers that classify Abnormal categories very well, while classifiers that excel in classifying Normal categories also exist. Deep learning models also exist with multiple models that can be complementarity.

Discussion

Suitable classifiers are selected for ensemble learning, when machine performance is insufficient. This experimental platform demonstrates that multiple classifiers are indeed complementarity and can improve the efficiency of ensemble learning. This can better assist doctors in diagnosis, improve the detection of gastric cancer, and increase the cure rate.

Deep learning model to predict Epstein-Barr virus associated gastric cancer in histology

The detection of Epstein-Barr virus (EBV) in gastric cancer patients is crucial for clinical decision making, as it is related with specific treatment responses and prognoses. Despite its importance, the limited medical resources preclude universal EBV testing. Herein, we propose a deep learning-based EBV prediction method from H&E-stained whole-slide images (WSI). Our model was developed using 319 H&E stained WSI (26 EBV positive; TCGA dataset) from the Cancer Genome Atlas, and 108 WSI (8 EBV positive; ISH dataset) from an independent institution. Our deep learning model, EBVNet consists of two sequential components: a tumor classifier and an EBV classifier. We visualized the learned representation by the classifiers using UMAP. We externally validated the model using 60 additional WSI (7 being EBV positive; HGH dataset). We compared the model's performance with those of four pathologists. EBVNet achieved an AUPRC of 0.65, whereas the four pathologists yielded a mean AUPRC of 0.41. Moreover, EBVNet achieved an negative predictive value, sensitivity, specificity, precision, and F1-score of 0.98, 0.86, 0.92, 0.60, and 0.71, respectively. Our proposed model is expected to contribute to prescreen patients for confirmatory testing, potentially to save test-related cost and labor.