Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology

Mathematical modelling and deep learning algorithms to automate assessment of single and digitally multiplexed immunohistochemical stains in tumoural stroma

Whilst automated analysis of immunostains in pathology research has focused predominantly on the epithelial compartment, automated analysis of stains in the stromal compartment is challenging and therefore requires time-consuming pathological input and guidance to adjust to tissue morphometry as perceived by pathologists. This study aimed to develop a robust method to automate stromal stain analyses using 2 of the commonest stromal stains (SMA and desmin) employed in clinical pathology practice as examples. An effective computational method capable of automatically assessing and quantifying tumour-associated stromal stains was developed and applied on cores of colorectal cancer tissue microarrays. The methodology combines both mathematical models and deep learning techniques with the former requiring no training data and the latter as many inputs as possible. The novel mathematical model was used to produce a digital double marker overlay allowing for fast automated digital multiplex analysis of stromal stains. The results show that deep learning methodologies in combination with mathematical modelling allow for an accurate means of quantifying stromal stains whilst also opening up new possibilities of digital multiplex analyses.

Image-based multi-omics analysis for oral science: Recent progress and perspectives

OBJECTIVES

The diagnosis and treatment of oral and dental diseases rely heavily on various types of medical imaging. Deep learning-mediated multi-omics analysis can extract more representative features than those identified through traditional diagnostic methods. This review aims to discuss the applications and recent advances in image-based multi-omics analysis in oral science and to highlight its potential to enhance traditional diagnostic approaches for oral diseases.

STUDY SELECTION, DATA, AND SOURCES

A systematic search was conducted in the PubMed, Web of Science, and Google Scholar databases, covering all available records. This search thoroughly examined and summarized advances in image-based multi-omics analysis in oral and maxillofacial medicine.

CONCLUSIONS

This review comprehensively summarizes recent advancements in image-based multi-omics analysis for oral science, including radiomics, pathomics, and photographic-based omics analysis. It also discusses the ongoing challenges and future perspectives that could provide new insights into exploiting the potential of image-based omics analysis in the field of oral science.

CLINICAL SIGNIFICANCE

This review article presents the state of image-based multi-omics analysis in stomatology, aiming to help oral clinicians recognize the utility of combining omics analyses with imaging during diagnosis and treatment, which can improve diagnostic accuracy, shorten times to diagnosis, save medical resources, and reduce disparity in professional knowledge among clinicians.

Transformative artificial intelligence in gastric cancer: Advancements in diagnostic techniques

Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.

Dynamic changes in AI-based analysis of endometrial cellular composition: Analysis of PCOS and RIF endometrium

Background

The human endometrium undergoes a monthly cycle of tissue growth and degeneration. During the mid-secretory phase, the endometrium establishes an optimal niche for embryo implantation by regulating cellular composition (e.g., epithelial and stromal cells) and differentiation. Impaired endometrial development observed in conditions such as polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) contributes to infertility. Surprisingly, despite the importance of the endometrial lining properly developing prior to pregnancy, precise measures of endometrial cellular composition in these two infertility-associated conditions are entirely lacking. Additionally, current methods for measuring the epithelial and stromal area have limitations, including intra- and inter-observer variability and efficiency.

Methods

We utilized a deep-learning artificial intelligence (AI) model, created on a cloud-based platform and developed in our previous study. The AI model underwent training to segment both areas populated by epithelial and stromal endometrial cells. During the training step, a total of 28.36 mm2 areas were annotated, comprising 2.56 mm2 of epithelium and 24.87 mm2 of stroma. Two experienced pathologists validated the performance of the AI model. 73 endometrial samples from healthy control women were included in the sample set to establish cycle phase-dependent dynamics of the endometrial epithelial-to-stroma ratio from the proliferative (PE) to secretory (SE) phases. In addition, 91 samples from PCOS cases, accounting for the presence or absence of ovulation and representing all menstrual cycle phases, and 29 samples from RIF patients on day 5 after progesterone administration in the hormone replacement treatment cycle were also included and analyzed in terms of cellular composition.

Results

Our AI model exhibited reliable and reproducible performance in delineating epithelial and stromal compartments, achieving an accuracy of 92.40% and 99.23%, respectively. Moreover, the performance of the AI model was comparable to the pathologists' assessment, with F1 scores exceeding 82% for the epithelium and >96% for the stroma. Next, we compared the endometrial epithelial-to-stromal ratio during the menstrual cycle in women with PCOS and in relation to endometrial receptivity status in RIF patients. The ovulatory PCOS endometrium exhibited epithelial cell proportions similar to those of control and healthy women's samples in every cycle phase, from the PE to the late SE, correlating with progesterone levels (control SE, r2 = 0.64, FDR < 0.001; PCOS SE, r2 = 0.52, FDR < 0.001). The mid-SE endometrium showed the highest epithelial percentage compared to both the early and late SE endometrium in both healthy women and PCOS patients. Anovulatory PCOS cases showed epithelial cellular fractions comparable to those of PCOS cases in the PE (Anovulatory, 14.54%; PCOS PE, 15.56%, p = 1.00). We did not observe significant differences in the epithelial-to-stroma ratio in the hormone-induced endometrium in RIF patients with different receptivity statuses.

Conclusion

The AI model rapidly and accurately identifies endometrial histology features by calculating areas occupied by epithelial and stromal cells. The AI model demonstrates changes in epithelial cellular proportions according to the menstrual cycle phase and reveals no changes in epithelial cellular proportions based on PCOS and RIF conditions. In conclusion, the AI model can potentially improve endometrial histology assessment by accelerating the analysis of the cellular composition of the tissue and by ensuring maximal objectivity for research and clinical purposes.

AI-algorithm training and validation for identification of endometrial CD138+ cells in infertility-associated conditions; polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF)

Background

Endometrial CD138+ plasma cells serve as a diagnostic biomarker for endometrial inflammation, and their elevated occurrence correlates positively with adverse pregnancy outcomes. Infertility-related conditions like polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF) are closely associated with systemic and local chronic inflammatory status, wherein endometrial CD138+ plasma cell accumulation could also contribute to endometrial pathology. Current methods for quantifying CD138+ cells typically involve laborious and time-consuming microscopic assessments of only a few random areas from a slide. These methods have limitations in accurately representing the entire slide and are susceptible to significant biases arising from intra- and interobserver variations. Implementing artificial intelligence (AI) for CD138+ cell identification could enhance the accuracy, reproducibility, and reliability of analysis.

Methods

Here, an AI algorithm was developed to identify CD138+ plasma cells within endometrial tissue. The AI model comprised two layers of convolutional neural networks (CNNs). CNN1 was trained to segment epithelium and stroma across 28,363 mm2 (2.56 mm2 of epithelium and 24.87 mm2 of stroma), while CNN2 was trained to distinguish stromal cells based on CD138 staining, encompassing 7345 cells in the object layers (6942 CD138- cells and 403 CD138+ cells). The training and performance of the AI model were validated by three experienced pathologists. We collected 193 endometrial tissues from healthy controls (n = 73), women with PCOS (n = 91), and RIF patients (n = 29) and compared the CD138+ cell percentages based on cycle phases, ovulation status, and endometrial receptivity utilizing the AI model.

Results

The AI algorithm consistently and reliably distinguished CD138- and CD138+ cells, with total error rates of 6.32% and 3.23%, respectively. During the training validation, there was a complete agreement between the decisions made by the pathologists and the AI algorithm, while the performance validation demonstrated excellent accuracy between the AI and human evaluation methods (intraclass correlation; 0.76, 95% confidence intervals; 0.36-0.93, p = 0.002) and a positive correlation (Spearman's rank correlation coefficient: 0.79, p < 0.01). In the AI analysis, the AI model revealed higher CD138+ cell percentages in the proliferative phase (PE) endometrium compared to the secretory phase or anovulatory PCOS endometrium, irrespective of PCOS diagnosis. Interestingly, CD138+ percentages differed according to PCOS phenotype in the PE (p = 0.03). On the other hand, the receptivity status had no impact on the cell percentages in RIF samples.

Conclusion

Our findings emphasize the potential and accuracy of the AI algorithm in detecting endometrial CD138+ plasma cells, offering distinct advantages over manual inspection, such as rapid analysis of whole slide images, reduction of intra- and interobserver variations, sparing the valuable time of trained specialists, and consistent productivity. This supports the application of AI technology to help clinical decision-making, for example, in understanding endometrial cycle phase-related dynamics, as well as different reproductive disorders.

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.

Models for the marrow: A comprehensive review of AI-based cell classification methods and malignancy detection in bone marrow aspirate smears

Given the high prevalence of artificial intelligence (AI) research in medicine, the development of deep learning (DL) algorithms based on image recognition, such as the analysis of bone marrow aspirate (BMA) smears, is rapidly increasing in the field of hematology and oncology. The models are trained to identify the optimal regions of the BMA smear for differential cell count and subsequently detect and classify a number of cell types, which can ultimately be utilized for diagnostic purposes. Moreover, AI is capable of identifying genetic mutations phenotypically. This pipeline has the potential to offer an accurate and rapid preliminary analysis of the bone marrow in the clinical routine. However, the intrinsic complexity of hematological diseases presents several challenges for the automatic morphological assessment. To ensure general applicability across multiple medical centers and to deliver high accuracy on prospective clinical data, AI models would require highly heterogeneous training datasets. This review presents a systematic analysis of models for cell classification and detection of hematological malignancies published in the last 5 years (2019-2024). It provides insight into the challenges and opportunities of these DL-assisted tasks.

Computational pathology in the identification of HER2-low breast cancer: Opportunities and challenges

For the past 2 decades, pathologists have been accustomed to reporting the HER2 status of breast cancer as either positive or negative, based on HER2 IHC. Today, however, there is a clinical imperative to employ a 3-tier approach to interpreting HER2 IHC that can also identify tumours categorised as HER2-low. Meeting this need for a finer degree of discrimination may be challenging, and in this article, we consider the potential for the integration of computational approaches to support pathologists in achieving accurate and reproducible HER2 IHC scoring as well as outlining some of the practicalities involved.

Pathobiology of myocardial and cardiomyocyte injury in ischemic heart disease: Perspective from seventy years of cell injury research

This review presents a perspective on the pathobiology of acute myocardial infarction, a major manifestation of ischemic heart disease, and related mechanisms of ischemic and toxic cardiomyocyte injury, based on advances and insights that have accrued over the last seventy years, including my sixty years of involvement in the field as a physician-scientist-pathologist. This analysis is based on integration of my research within the broader context of research in the field. A particular focus has been on direct measurements in cardiomyocytes of electrolyte content by electron probe X-ray microanalysis (EPXMA) and Ca2+ fluxes by fura-2 microspectrofluorometry. These studies established that increased intracellular Ca2+ develops at a transitional stage in the progression of cardiomyocyte injury in association with ATP depletion, other electrolyte alterations, altered cell volume regulation, and altered membrane phospholipid composition. Subsequent increase in total calcium with mitochondrial calcium accumulation can occur. These alterations are characteristic of oncosis, which is an initial pre-lethal state of cell injury with cell swelling due to cell membrane dysfunction in ATP depleted cells; oncosis rapidly progresses to necrosis/necroptosis with physical disruption of the cell membrane, unless the adverse stimulus is rapidly reversed. The observed sequential changes fit a three-stage model of membrane injury leading to irreversible cell injury. The data establish oncosis as the primary mode of cardiomyocyte injury in evolving myocardial infarcts. Oncosis also has been documented to be the typical form of non-ischemic cell injury due to toxins. Cardiomyocytes with less energy impairment have the capability of undergoing apoptosis and autophagic death as well as oncosis, as is seen in pathological remodeling in chronic heart failure. Work is ongoing to apply the insights from experimental studies to better understand and ameliorate myocardial ischemia and reperfusion injury in patients. The perspective and insights in this review are derived from basic principles of pathology, an integrative discipline focused on mechanisms of disease affecting the cell, the organizing unit of living organisms.

Validation and three years of clinical experience in using an artificial intelligence algorithm as a second read system for prostate cancer diagnosis-real-world experience

Background

Prostate cancer ranks as the most frequently diagnosed cancer in men in the USA, with significant mortality rates. Early detection is pivotal for optimal patient outcomes, providing increased treatment options and potentially less invasive interventions. There remain significant challenges in prostate cancer histopathology, including the potential for missed diagnoses due to pathologist variability and subjective interpretations.

Methods

To address these challenges, this study investigates the ability of artificial intelligence (AI) to enhance diagnostic accuracy. The Galen™ Prostate AI algorithm was validated on a cohort of Puerto Rican men to demonstrate its efficacy in cancer detection and Gleason grading. Subsequently, the AI algorithm was integrated into routine clinical practice during a 3-year period at a CLIA certified precision pathology laboratory.

Results

The Galen™ Prostate AI algorithm showed a 96.7% (95% CI 95.6-97.8) specificity and a 96.6% (95% CI 93.3-98.8) sensitivity for prostate cancer detection and 82.1% specificity (95% CI 73.9-88.5) and 81.1% sensitivity (95% CI 73.7-87.2) for distinction of Gleason Grade Group 1 from Grade Group 2+. The subsequent AI integration into routine clinical use examined prostate cancer diagnoses on >122,000 slides and 9200 cases over 3 years and had an overall AI Impact ™ factor of 1.8%.

Conclusions

The potential of AI to be a powerful, reliable, and effective diagnostic tool for pathologists is highlighted, while the AI Impact™ in a real-world setting demonstrates the ability of AI to standardize prostate cancer diagnosis at a high level of performance across pathologists.

NecroGlobalGCN: Integrating micronecrosis information in HCC prognosis prediction via graph convolutional neural networks

BACKGROUND AND OBJECTIVE

Hepatocellular carcinoma (HCC) ranks fourth in cancer mortality, underscoring the importance of accurate prognostic predictions to improve postoperative survival rates in patients. Although micronecrosis has been shown to have high prognostic value in HCC, its application in clinical prognosis prediction requires specialized knowledge and complex calculations, which poses challenges for clinicians. It would be of interest to develop a model to help clinicians make full use of micronecrosis to assess patient survival.

METHODS

To address these challenges, we propose a HCC prognosis prediction model that integrates pathological micronecrosis information through Graph Convolutional Neural Networks (GCN). This approach enables GCN to utilize micronecrosis, which has been shown to be highly correlated with prognosis, thereby significantly enhancing prognostic stratification quality. We developed our model using 3622 slides from 752 patients with primary HCC from the FAH-ZJUMS dataset and conducted internal and external validations on the FAH-ZJUMS and TCGA-LIHC datasets, respectively.

RESULTS

Our method outperformed the baseline by 8.18% in internal validation and 9.02% in external validations. Overall, this paper presents a deep learning research paradigm that integrates HCC micronecrosis, enhancing both the accuracy and interpretability of prognostic predictions, with potential applicability to other pathological prognostic markers.

CONCLUSIONS

This study proposes a composite GCN prognostic model that integrates information on HCC micronecrosis, collecting large dataset of HCC histopathological images. This approach could assist clinicians in analyzing HCC patient survival and precisely locating and visualizing necrotic tissues that affect prognosis. Following the research paradigm outlined in this paper, other prognostic biomarker integration models with GCN could be developed, significantly enhancing the predictive performance and interpretability of prognostic model.

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.

Artificial intelligence (AI) for tumor microenvironment (TME) and tumor budding (TB) identification in colorectal cancer (CRC) patients: A systematic review

Evaluation of the parameters such as tumor microenvironment (TME) and tumor budding (TB) is one of the most important steps in colorectal cancer (CRC) diagnosis and cancer development prognosis. In recent years, artificial intelligence (AI) has been successfully used to solve such problems. In this paper, we summarize the latest data on the use of artificial intelligence to predict tumor microenvironment and tumor budding in histological scans of patients with colorectal cancer. We performed a systematic literature search using 2 databases (Medline and Scopus) with the following search terms: ("tumor microenvironment" OR "tumor budding") AND ("colorectal cancer" OR CRC) AND ("artificial intelligence" OR "machine learning " OR "deep learning"). During the analysis, we gathered from the articles performance scores such as sensitivity, specificity, and accuracy of identifying TME and TB using artificial intelligence. The systematic review showed that machine learning and deep learning successfully cope with the prediction of these parameters. The highest accuracy values in TB and TME prediction were 97.7% and 97.3%, respectively. This review led us to the conclusion that AI platforms can already be used as diagnostic aids, which will greatly facilitate the work of pathologists in detection and estimation of TB and TME as instruments and second-opinion services. A key limitation in writing this systematic review was the heterogeneous use of performance metrics for machine learning models by different authors, as well as relatively small datasets used in some studies.

The analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?

Background

Pathologist-read tumor-infiltrating lymphocytes (TILs) have showcased their predictive and prognostic potential for early and metastatic triple-negative breast cancer (TNBC) but it is still subject to variability. Artificial intelligence (AI) is a promising approach toward eliminating variability and objectively automating TILs assessment. However, demonstrating robust analytical and prognostic validity is the key challenge currently preventing their integration into clinical workflows.

Methods

We evaluated the impact of ten AI models on TILs scoring, emphasizing their distinctions in TILs analytical and prognostic validity. Several AI-based TILs scoring models (seven developed and three previously validated AI models) were tested in a retrospective analytical cohort and in an independent prospective cohort to compare prognostic validation against invasive disease-free survival endpoint with 4 years median follow-up. The development and analytical validity set consisted of diagnostic tissue slides of 79 women with surgically resected primary invasive TNBC tumors diagnosed between 2012 and 2016 from the Yale School of Medicine. An independent set comprising of 215 TNBC patients from Sweden diagnosed between 2010 and 2015, was used for testing prognostic validity.

Findings

A significant difference in analytical validity (Spearman's r = 0.63-0.73, p < 0.001) is highlighted across AI methodologies and training strategies. Interestingly, the prognostic performance of digital TILs is demonstrated for eight out of ten AI models, even less extensively trained ones, with similar and overlapping hazard ratios (HR) in the external validation cohort (Cox regression analysis based on IDFS-endpoint, HR = 0.40-0.47; p < 0.004).

Interpretation

The demonstrated prognostic validity for most of the AI TIL models can be attributed to the intrinsic robustness of host anti-tumor immunity (measured by TILs) as a biomarker. However, the discrepancies between AI models should not be overlooked; rather, we believe that there is a critical need for an accessible, large, multi-centric dataset that will serve as a benchmark ensuring the comparability and reliability of different AI tools in clinical implementation.

Funding

Nikos Tsiknakis is supported by the Swedish Research Council (Grant Number 2021-03061, Theodoros Foukakis). Balazs Acs is supported by The Swedish Society for Medical Research (Svenska Sällskapet för Medicinsk Forskning) postdoctoral grant. Roberto Salgado is supported by a grant from Breast Cancer Research Foundation (BCRF).

Machine learning approaches for spatial omics data analysis in digital pathology: tools and applications in genitourinary oncology

Recent advances in spatial omics technologies have enabled new approaches for analyzing tissue morphology, cell composition, and biomolecule expression patterns in situ. These advances are promoting the development of new computational tools and quantitative techniques in the emerging field of digital pathology. In this review, we survey current trends in the development of computational methods for spatially mapped omics data analysis using digitized histopathology slides and supplementary materials, with an emphasis on tools and applications relevant to genitourinary oncological research. The review contains three sections: 1) an overview of image processing approaches for histopathology slide analysis; 2) machine learning integration with spatially resolved omics data analysis; 3) a discussion of current limitations and future directions for integration of machine learning in the clinical decision-making process.

Use of a Pathomics Nomogram to Predict Postoperative Liver Metastasis in Patients with Stage III Colorectal Cancer

BACKGROUND

Approximately 25% of patients with stage III colorectal cancer experience liver metastasis after radical resection; however, there is currently a lack of methods to predict liver metastasis. This study aims to develop and validate a pathomics nomogram to predict liver metastasis in patients with stage III colorectal cancer.

METHODS

A total of 318 enrolled patients were divided into three cohorts: a training cohort (n = 139), a validation cohort (n = 69), and an external cohort (n = 110). A competitive risk nomogram was established by the pathomics signature and clinicopathological characteristics and assessed by calibration, discrimination, and clinical usefulness.

RESULTS

A significant correlation between the pathomics signature and liver metastasis in stage III colorectal cancer was found. Multivariate Fine-Gray analysis indicated that preoperative carcinoembryonic antigen level, postoperative chemotherapy, and pathomics signature were independent predictors of liver metastasis. A competitive risk nomogram was developed to predict liver metastasis in patients with stage III colorectal cancer. The predicting nomogram shows good discrimination and calibration, with C-indexes of 0.811 (95% confidence interval [CI] 0.651-0.971), 0.759 (95% CI 0.531-0.987), and 0.845 (95% CI 0.641-0.999), with area under the receiver operating characteristic (AUROC) curves at 5 years of 0.833 (95% CI 0.742-0.925), 0.760 (95% CI 0.652-0.893), and 0.812 (95% CI 0.692-0.931) in the training, validation, and external cohorts, respectively. Compared with the clinicopathological nomogram, the nomogram combined with the pathomics signature had better performance (AUROC 0.823 [95% CI 0.764-0.881] vs. 0.678 [95% CI 0.606-0.751]; p < 0.001).

CONCLUSIONS

The pathomics signature is a predictive indicator for liver metastasis in patients with stage III colorectal cancer, and the integrated nomogram can be used to predict liver metastasis better than the clinicopathological nomogram alone.

Prognostic and predictive value of pathohistological features in gastric cancer and identification of SLITRK4 as a potential biomarker for gastric cancer

The aim of this study was to develop a quantitative feature-based model from histopathologic images to assess the prognosis of patients with gastric cancer. Whole slide image (WSI) images of H&E-stained histologic specimens of gastric cancer patients from The Cancer Genome Atlas were included and randomly assigned to training and test groups in a 7:3 ratio. A systematic preprocessing approach was employed as well as a non-overlapping segmentation method that combined patch-level prediction with a multi-instance learning approach to integrate features across the slide images. Subjects were categorized into high- or low-risk groups based on the median risk score derived from the model, and the significance of this stratification was assessed using a log-rank test. In addition, combining transcriptomic data from patients and data from other large cohort studies, we further searched for genes associated with pathological features and their prognostic value. A total of 165 gastric cancer patients were included for model training, and a total of 26 features were integrated through multi-instance learning, with each process generating 11 probabilistic features and 2 predictive labeling features. We applied a 10-fold Lasso-Cox regression model to achieve dimensionality reduction of these features. The predictive accuracy of the model was verified using Kaplan-Meyer (KM) curves for stratification with a consistency index of 0.741 for the training set and 0.585 for the test set. Deep learning-based resultant supervised pathohistological features have the potential for superior prognostic stratification of gastric cancer patients, transforming image pixels into an effective and labor-saving tool to optimize the clinical management of gastric cancer patients. Also, SLITRK4 was identified as a prognostic marker for gastric cancer.

Cancer Biomarkers and Precision Oncology: A Review of Recent Trends and Innovations

The discovery of cancer-specific biomarkers has resulted in major advancements in the field of cancer diagnostics and therapeutics, therefore significantly lowering cancer-related morbidity and mortality. Cancer biomarkers can be generally classified as prognostic biomarkers that predict specific disease outcomes and predictive biomarkers that predict disease response to targeted therapeutic interventions. As research in the area of predictive biomarkers continues to grow, precision medicine becomes far more integrated in cancer treatment. This article presents a general overview on the most recent advancements in the area of cancer biomarkers, immunotherapy, artificial intelligence, and pharmacogenomics of the Middle East.

Hepatocellular Carcinoma Immune Microenvironment Analysis: A Comprehensive Assessment with Computational and Classical Pathology

PURPOSE

The spatial variability and clinical relevance of the tumor immune microenvironment (TIME) are still poorly understood for hepatocellular carcinoma (HCC). In this study, we aim to develop a deep learning (DL)-based image analysis model for the spatial analysis of immune cell biomarkers and microscopically evaluate the distribution of immune infiltration.

EXPERIMENTAL DESIGN

Ninety-two HCC surgical liver resections and 51 matched needle biopsies were histologically classified according to their immunophenotypes: inflamed, immune-excluded, and immune-desert. To characterize the TIME on immunohistochemistry (IHC)-stained slides, we designed a multistage DL algorithm, IHC-TIME, to automatically detect immune cells and their localization in the TIME in tumor-stroma and center-border segments.

RESULTS

Two models were trained to detect and localize the immune cells on IHC-stained slides. The framework models (i.e., immune cell detection models and tumor-stroma segmentation) reached 98% and 91% accuracy, respectively. Patients with inflamed tumors showed better recurrence-free survival than those with immune-excluded or immune-desert tumors. Needle biopsies were found to be 75% accurate in representing the immunophenotypes of the main tumor. Finally, we developed an algorithm that defines immunophenotypes automatically based on the IHC-TIME analysis, achieving an accuracy of 80%.

CONCLUSIONS

Our DL-based tool can accurately analyze and quantify immune cells on IHC-stained slides of HCC. Microscopic classification of the TIME can stratify HCC according to the patient prognosis. Needle biopsies can provide valuable insights for TIME-related prognostic prediction, albeit with specific constraints. The computational pathology tool provides a new way to study the HCC TIME.

Applications of Machine Learning on Electronic Health Record Data to Combat Antibiotic Resistance

There is growing excitement about the clinical use of artificial intelligence and machine learning (ML) technologies. Advancements in computing and the accessibility of ML frameworks enable researchers to easily train predictive models using electronic health record data. However, several practical factors must be considered when employing ML on electronic health record data. We provide a primer on ML and approaches commonly taken to address these challenges. To illustrate how these approaches have been applied to address antimicrobial resistance, we review the use of electronic health record data to construct ML models for predicting pathogen carriage or infection, optimizing empiric therapy, and aiding antimicrobial stewardship tasks. ML shows promise in promoting the appropriate use of antimicrobials, although clinical deployment is limited. We conclude by describing the potential dangers of, and barriers to, implementation of ML models in the clinic.

Classifying driver mutations of papillary thyroid carcinoma on whole slide image: an automated workflow applying deep convolutional neural network

Background

Informative biomarkers play a vital role in guiding clinical decisions regarding management of cancers. We have previously demonstrated the potential of a deep convolutional neural network (CNN) for predicting cancer driver gene mutations from expert-curated histopathologic images in papillary thyroid carcinomas (PTCs). Recognizing the importance of whole slide image (WSI) analysis for clinical application, we aimed to develop an automated image preprocessing workflow that uses WSI inputs to categorize PTCs based on driver mutations.

Methods

Histopathology slides from The Cancer Genome Atlas (TCGA) repository were utilized for diagnostic purposes. These slides underwent an automated tile extraction and preprocessing pipeline to ensure analysis-ready quality. Next, the extracted image tiles were utilized to train a deep learning CNN model, specifically Google's Inception v3, for the classification of PTCs. The model was trained to distinguish between different groups based on BRAFV600E or RAS mutations.

Results

The newly developed pipeline performed equally well as the expert-curated image classifier. The best model achieved Area Under the Curve (AUC) values of 0.86 (ranging from 0.847 to 0.872) for validation and 0.865 (ranging from 0.854 to 0.876) for the final testing subsets. Notably, it accurately predicted 90% of tumors in the validation set and 84.2% in the final testing set. Furthermore, the performance of our new classifier showed a strong correlation with the expert-curated classifier (Spearman rho = 0.726, p = 5.28 e-08), and correlated with the molecular expression-based classifier, BRS (BRAF-RAS scores) (Spearman rho = 0.418, p = 1.92e-13).

Conclusions

Utilizing WSIs, we implemented an automated workflow with deep CNN model that accurately classifies driver mutations in PTCs.

Multitask machine learning-based tumor-associated collagen signatures predict peritoneal recurrence and disease-free survival in gastric cancer

BACKGROUND

Accurate prediction of peritoneal recurrence for gastric cancer (GC) is crucial in clinic. The collagen alterations in tumor microenvironment affect the migration and treatment response of cancer cells. Herein, we proposed multitask machine learning-based tumor-associated collagen signatures (TACS), which are composed of quantitative collagen features derived from multiphoton imaging, to simultaneously predict peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS).

METHODS

Among 713 consecutive patients, with 275 in training cohort, 222 patients in internal validation cohort, and 216 patients in external validation cohort, we developed and validated a multitask machine learning model for simultaneously predicting peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS). The accuracy of the model for prediction of peritoneal recurrence and prognosis as well as its association with adjuvant chemotherapy were evaluated.

RESULTS

The TACSPR and TACSDFS were independently associated with peritoneal recurrence and disease-free survival in three cohorts, respectively (all P < 0.001). The TACSPR demonstrated a favorable performance for peritoneal recurrence in all three cohorts. In addition, the TACSDFS also showed a satisfactory accuracy for disease-free survival among included patients. For stage II and III diseases, adjuvant chemotherapy improved the survival of patients with low TACSPR and low TACSDFS, or high TACSPR and low TACSDFS, or low TACSPR and high TACSDFS, but had no impact on patients with high TACSPR and high TACSDFS.

CONCLUSIONS

The multitask machine learning model allows accurate prediction of peritoneal recurrence and survival for GC and could distinguish patients who might benefit from adjuvant chemotherapy.

Shifting the paradigm in personalized cancer care through next-generation therapeutics and computational pathology

The incorporation of novel therapeutic agents such as antibody-drug conjugates, radio-conjugates, T-cell engagers, and chimeric antigen receptor cell therapies represents a paradigm shift in oncology. Cell-surface target quantification, quantitative assessment of receptor internalization, and changes in the tumor microenvironment (TME) are essential variables in the development of biomarkers for patient selection and therapeutic response. Assessing these parameters requires capabilities that transcend those of traditional biomarker approaches based on immunohistochemistry, in situ hybridization and/or sequencing assays. Computational pathology is emerging as a transformative solution in this new therapeutic landscape, enabling detailed assessment of not only target presence, expression levels, and intra-tumor distribution but also of additional phenotypic features of tumor cells and their surrounding TME. Here, we delineate the pivotal role of computational pathology in enhancing the efficacy and specificity of these advanced therapeutics, underscoring the integration of novel artificial intelligence models that promise to revolutionize biomarker discovery and drug development.

Multimodal Co-Attention Fusion Network With Online Data Augmentation for Cancer Subtype Classification

It is an essential task to accurately diagnose cancer subtypes in computational pathology for personalized cancer treatment. Recent studies have indicated that the combination of multimodal data, such as whole slide images (WSIs) and multi-omics data, could achieve more accurate diagnosis. However, robust cancer diagnosis remains challenging due to the heterogeneity among multimodal data, as well as the performance degradation caused by insufficient multimodal patient data. In this work, we propose a novel multimodal co-attention fusion network (MCFN) with online data augmentation (ODA) for cancer subtype classification. Specifically, a multimodal mutual-guided co-attention (MMC) module is proposed to effectively perform dense multimodal interactions. It enables multimodal data to mutually guide and calibrate each other during the integration process to alleviate inter- and intra-modal heterogeneities. Subsequently, a self-normalizing network (SNN)-Mixer is developed to allow information communication among different omics data and alleviate the high-dimensional small-sample size problem in multi-omics data. Most importantly, to compensate for insufficient multimodal samples for model training, we propose an ODA module in MCFN. The ODA module leverages the multimodal knowledge to guide the data augmentations of WSIs and maximize the data diversity during model training. Extensive experiments are conducted on the public TCGA dataset. The experimental results demonstrate that the proposed MCFN outperforms all the compared algorithms, suggesting its effectiveness.

Pathomics signatures and cuproptosis-related genes signatures for prediction of prognosis in patients with hepatocellular carcinoma

Background

Hepatocellular carcinoma (HCC) is a common malignant tumor with high heterogeneity and poor prognosis, so early prediction and treatment are still difficult. Cuproptosis is a newly discovered type of programmed cell death that has been shown to be closely related to the occurrence and progression of HCC. Cancer morphology is influenced by genetic drivers, and computational pathology methods typically use tissue images such as entire slide images as input to predict clinical or genetic features. Therefore, the comprehensive analysis of pathological features and genomic data provides a feasible way to explore the potential mechanism of the tumor. The objective of this study was to develop a prediction model for HCC prognosis based on the pathomics signatures (PS) and the genomics signatures (GS).

Methods

A dataset comprising 315 HCC patients was randomly divided into a training set (n=200) and a validation set (n=115). Prognostic models related to PS and GS were constructed by univariate and multivariate Cox regression analyses and least absolute shrinkage and selection operator (LASSO) regression analysis. Kaplan-Meier survival analysis, receiver operating characteristic (ROC) curve, univariate and multivariate Cox analyses, and nomogram were used to evaluate the predictive performance of the prognostic model. The prognostic value of the model was internally validated.

Results

A prognostic model incorporating clinical features, PS, and GS was developed using Cox regression analysis and LASSO regression analyses. Kaplan-Meier survival analysis revealed statistically significant differences in survival time between high-risk and low-risk subgroups in both the training and validation datasets (PS: P=0.003 and <0.001, respectively; GS: P=0.008 and 0.004, respectively). The time-dependent ROC curve showed favorable predictive value for survival in both the training and validation sets. The area under the ROC curves at 1, 3, and 5 years was 0.750, 0.830, and 0.870 in the training set, and 0.780, 0.810, and 0.760 in the validation set, respectively. A nomogram model based on the risk model score could effectively predict the survival probability of HCC patients. The calibration curves further demonstrated the good predictive capability of the nomogram model.

Conclusions

The prognostic model incorporating PS and GS could effectively predict the prognosis of HCC patients.

Relationship between EZH2 expression and prognosis of patients with hepatocellular carcinoma using a pathomics predictive model

Background

Enhancer of zeste 2 polycomb repressive complex 2 subunit (EZH2) is overexpressed in hepatocellular carcinoma, promoting tumorigenesis and correlating with poor prognosis. Traditional histopathological examinations are insufficient to accurately predict hepatocellular carcinoma (HCC) survival; however, pathomics models can predict EZH2 expression and HCC prognosis. This study aimed to investigate the relationship between pathomics features and EZH2 expression for predicting overall survival of patients with HCC.

Methods

We analyzed 267 patients with HCC from the Cancer Genome Atlas database, with available pathological images and gene expression data. RNA sequencing data were divided into high and low EZH2 expression groups for prognosis and survival analysis. Pathological image features were screened using mRMR_RFE. A pathological model was constructed using a gradient boosting machine (GBM) algorithm, and efficiency evaluation and survival analysis of the model were performed. The R package "survminer" took the pathomics score (PS) cutoff value of 0.4628 to divide the patients into two groups: high and low PS expression. Survival analyses included Kaplan-Meier curve analysis, univariate and multivariate Cox regression analyses, and interaction tests. Potential pathomechanisms were explored through enrichment, differential, immune cell infiltration abundance, and gene mutation analyses.

Result

EZH2 was highly expressed in tumor samples but poorly expressed in normal tissue samples. Univariate and multivariate Cox regression analyses revealed that EZH2 was an independent risk factor for HCC (hazard ratio [HR], 2.792 and 3.042, respectively). Seven imaging features were selected to construct a pathomics model to predict EZH2. Decision curve analysis showed that the model had high clinical utility. Multivariate Cox regression analysis showed that high PS expression was an independent risk factor for HCC prognosis (HR, 2.446). The Kaplan-Meier curve showed that high PS expression was a risk factor for overall survival.

Conclusion

EZH2 expression can affect the prognosis of patients with liver cancer. Our pathological model could predict EZH2 expression and prognosis of patients with HCC with high accuracy and robustness, making it a new and potentially valuable tool.

Deep learning application in prediction of cancer molecular alterations based on pathological images: a bibliographic analysis via CiteSpace

BACKGROUND

The advancements in artificial intelligence (AI) technology for image recognition were propelling molecular pathology research into a new era.

OBJECTIVE

To summarize the hot spots and research trends in the field of molecular pathology image recognition.

METHODS

Relevant articles from January 1st, 2010, to August 25th, 2023, were retrieved from the Web of Science Core Collection. Subsequently, CiteSpace was employed for bibliometric and visual analysis, generating diverse network diagrams illustrating keywords, highly cited references, hot topics, and research trends.

RESULTS

A total of 110 relevant articles were extracted from a pool of 10,205 articles. The overall publication count exhibited a rising trend each year. The leading contributors in terms of institutions, countries, and authors were Maastricht University (11 articles), the United States (38 articles), and Kather Jacob Nicholas (9 articles), respectively. Half of the top ten research institutions, based on publication volume, were affiliated with Germany. The most frequently cited article was authored by Nicolas Coudray et al. accumulating 703 citations. The keyword "Deep learning" had the highest frequency in 2019. Notably, the highlighted keywords from 2022 to 2023 included "microsatellite instability", and there were 21 articles focusing on utilizing algorithms to recognize microsatellite instability (MSI) in colorectal cancer (CRC) pathological images.

CONCLUSION

The use of DL is expected to provide a new strategy to effectively solve the current problem of time-consuming and expensive molecular pathology detection. Therefore, further research is needed to address issues, such as data quality and standardization, model interpretability, and resource and infrastructure requirements.

Identification of middle cerebral artery stenosis in transcranial Doppler using a modified VGG-16

Objectives

The diagnosis of intracranial atherosclerotic stenosis (ICAS) is of great significance for the prevention of stroke. Deep learning (DL)-based artificial intelligence techniques may aid in the diagnosis. The study aimed to identify ICAS in the middle cerebral artery (MCA) based on a modified DL model.

Methods

This retrospective study included two datasets. Dataset1 consisted of 3,068 transcranial Doppler (TCD) images of the MCA from 1,729 patients, which were assessed as normal or stenosis by three physicians with varying levels of experience, in conjunction with other medical imaging data. The data were used to improve and train the VGG16 models. Dataset2 consisted of TCD images of 90 people who underwent physical examination, which were used to verify the robustness of the model and compare the consistency between the model and human physicians.

Results

The accuracy, precision, specificity, sensitivity, and area under curve (AUC) of the best model VGG16 + Squeeze-and-Excitation (SE) + skip connection (SC) on dataset1 reached 85.67 ± 0.43(%),87.23 ± 1.17(%),87.73 ± 1.47(%),83.60 ± 1.60(%), and 0.857 ± 0.004, while those of dataset2 were 93.70 ± 2.80(%),62.65 ± 11.27(%),93.00 ± 3.11(%),100.00 ± 0.00(%), and 0.965 ± 0.016. The kappa coefficient showed that it reached the recognition level of senior doctors.

Conclusion

The improved DL model has a good diagnostic effect for MCV stenosis in TCD images and is expected to help in ICAS screening.

A Genomics-Driven Artificial Intelligence-Based Model Classifies Breast Invasive Lobular Carcinoma and Discovers CDH1 Inactivating Mechanisms

Artificial intelligence (AI) systems can improve cancer diagnosis, yet their development often relies on subjective histologic features as ground truth for training. Herein, we developed an AI model applied to histologic whole-slide images using CDH1 biallelic mutations, pathognomonic for invasive lobular carcinoma (ILC) in breast neoplasms, as ground truth. The model accurately predicted CDH1 biallelic mutations (accuracy = 0.95) and diagnosed ILC (accuracy = 0.96). A total of 74% of samples classified by the AI model as having CDH1 biallelic mutations but lacking these alterations displayed alternative CDH1 inactivating mechanisms, including a deleterious CDH1 fusion gene and noncoding CDH1 genetic alterations. Analysis of internal and external validation cohorts demonstrated 0.95 and 0.89 accuracy for ILC diagnosis, respectively. The latent features of the AI model correlated with human-explainable histopathologic features. Taken together, this study reports the construction of an AI algorithm trained using a genetic rather than histologic ground truth that can robustly classify ILCs and uncover CDH1 inactivating mechanisms, providing the basis for orthogonal ground truth utilization for development of diagnostic AI models applied to whole-slide image. Significance: Genetic alterations linked to strong genotypic-phenotypic correlations can be utilized to develop AI systems applied to pathology that facilitate cancer diagnosis and biologic discoveries.

Holomics and Artificial Intelligence-Driven Precision Oncology for Medullary Thyroid Carcinoma: Addressing Challenges of a Rare and Aggressive Disease

Background/Objective: Medullary thyroid carcinoma (MTC) is a rare yet aggressive form of thyroid cancer comprising a disproportionate share of thyroid cancer-related mortalities, despite its low prevalence. MTC differs from other differentiated thyroid malignancies due to its heterogeneous nature, presenting complexities in both hereditary and sporadic cases. Traditional management guidelines, which are designed primarily for papillary thyroid carcinoma (PTC), fall short in providing the individualized care required for patients with MTC. In recent years, the sheer volume of data generated from clinical evaluations, radiological imaging, pathological assessments, genetic mutations, and immunological profiles has made it humanly impossible for clinicians to simultaneously analyze and integrate these diverse data streams effectively. This data deluge necessitates the adoption of advanced technologies to assist in decision-making processes. Holomics, which is an integrated approach that combines various omics technologies, along with artificial intelligence (AI), emerges as a powerful solution to address these challenges. Methods: This article reviews how AI-driven precision oncology can enhance the diagnostic workup, staging, risk stratification, management, and follow-up care of patients with MTC by processing vast amounts of complex data quickly and accurately. Articles published in English language and indexed in Pubmed were searched. Results: AI algorithms can identify patterns and correlations that may not be apparent to human clinicians, thereby improving the precision of personalized treatment plans. Moreover, the implementation of AI in the management of MTC enables the collation and synthesis of clinical experiences from across the globe, facilitating a more comprehensive understanding of the disease and its treatment outcomes. Conclusions: The integration of holomics and AI in the management of patients with MTC represents a significant advancement in precision oncology. This innovative approach not only addresses the complexities of a rare and aggressive disease but also paves the way for global collaboration and equitable healthcare solutions, ultimately transforming the landscape of treatment and care of patients with MTC. By leveraging AI and holomics, we can strive toward making personalized healthcare accessible to every individual, regardless of their economic status, thereby improving overall survival rates and quality of life for MTC patients worldwide. This global approach aligns with the United Nations Sustainable Development Goal 3, which aims to ensure healthy lives and promote well-being at all ages.

Advancements in Hyperspectral Imaging and Computer-Aided Diagnostic Methods for the Enhanced Detection and Diagnosis of Head and Neck Cancer

Background/Objectives: Head and neck cancer (HNC), predominantly squamous cell carcinoma (SCC), presents a significant global health burden. Conventional diagnostic approaches often face challenges in terms of achieving early detection and accurate diagnosis. This review examines recent advancements in hyperspectral imaging (HSI), integrated with computer-aided diagnostic (CAD) techniques, to enhance HNC detection and diagnosis. Methods: A systematic review of seven rigorously selected studies was performed. We focused on CAD algorithms, such as convolutional neural networks (CNNs), support vector machines (SVMs), and linear discriminant analysis (LDA). These are applicable to the hyperspectral imaging of HNC tissues. Results: The meta-analysis findings indicate that LDA surpasses other algorithms, achieving an accuracy of 92%, sensitivity of 91%, and specificity of 93%. CNNs exhibit moderate performance, with an accuracy of 82%, sensitivity of 77%, and specificity of 86%. SVMs demonstrate the lowest performance, with an accuracy of 76% and sensitivity of 48%, but maintain a high specificity level at 89%. Additionally, in vivo studies demonstrate superior performance when compared to ex vivo studies, reporting higher accuracy (81%), sensitivity (83%), and specificity (79%). Conclusion: Despite these promising findings, challenges persist, such as HSI's sensitivity to external conditions, the need for high-resolution and high-speed imaging, and the lack of comprehensive spectral databases. Future research should emphasize dimensionality reduction techniques, the integration of multiple machine learning models, and the development of extensive spectral libraries to enhance HSI's clinical utility in HNC diagnostics. This review underscores the transformative potential of HSI and CAD techniques in revolutionizing HNC diagnostics, facilitating more accurate and earlier detection, and improving patient outcomes.

Enhancing Prostate Cancer Diagnosis: Artificial Intelligence-Driven Virtual Biopsy for Optimal Magnetic Resonance Imaging-Targeted Biopsy Approach and Gleason Grading Strategy

An optimal approach to magnetic resonance imaging fusion targeted prostate biopsy (PBx) remains unclear (number of cores, intercore distance, Gleason grading [GG] principle). The aim of this study was to develop a precise pixel-wise segmentation diagnostic artificial intelligence (AI) algorithm for tumor detection and GG as well as an algorithm for virtual prostate biopsy that are used together to systematically investigate and find an optimal approach to targeted PBx. Pixel-wise AI algorithms for tumor detection and GG were developed using a high-quality, manually annotated data set (slides n = 442) after fast-track annotation transfer into segmentation style. To this end, a virtual biopsy algorithm was developed that can perform random biopsies from tumor regions in whole-mount whole-slide images with predefined parameters. A cohort of 115 radical prostatectomy (RP) patient cases with clinically significant, magnetic resonance imaging-visible tumors (n = 121) was used for systematic studies of the optimal biopsy approach. Three expert genitourinary (GU) pathologists (Y.T., A.P., A.Q.) participated in the validation. The tumor detection algorithm (aware version sensitivity/specificity 0.99/0.90, balanced version 0.97/0.97) and GG algorithm (quadratic kappa range vs pathologists 0.77-0.78) perform on par with expert GU pathologists. In total, 65,340 virtual biopsies were performed to study different biopsy approaches with the following results: (1) 4 biopsy cores is the optimal number for a targeted PBx, (2) cumulative GG strategy is superior to using maximal Gleason score for single cores, (3) controlling for minimal intercore distance does not improve the predictive accuracy for the RP Gleason score, (4) using tertiary Gleason pattern principle (for AI tool) in cumulative GG strategy might allow better predictions of final RP Gleason score. The AI algorithm (based on cumulative GG strategy) predicted the RP Gleason score of the tumor better than 2 of the 3 expert GU pathologists. In this study, using an original approach of virtual prostate biopsy on the real cohort of patient cases, we find the optimal approach to the biopsy procedure and the subsequent GG of a targeted PBx. We publicly release 2 large data sets with associated expert pathologists' GG and our virtual biopsy algorithm.

Evaluation of AI-enhanced non-mydriatic fundus photography for diabetic retinopathy screening

OBJECTIVE

To assess the feasibility of using non-mydriatic fundus photography in conjunction with an artificial intelligence (AI) reading platform for large-scale screening of diabetic retinopathy (DR).

METHODS

In this study, we selected 120 patients with diabetes hospitalized in our institution from December 2019 to April 2021. Retinal imaging of 240 eyes was obtained using non-mydriatic fundus photography. The fundus images of these patients were divided into two groups based on different interpretation methods. In Experiment Group 1, the images were analyzed and graded for DR diagnosis using an AI reading platform. In Experiment Group 2, the images were analyzed and graded for DR diagnosis by an associate chief physician in ophthalmology, specializing in fundus diseases. Concurrently, all patients underwent the gold standard for DR diagnosis and grading-fundus fluorescein angiography (FFA)-with the outcomes serving as the Control Group. The diagnostic value of the two methods was assessed by comparing the results of Experiment Groups 1 and 2 with those of the Control Group.

RESULTS

Keeping the control group (FFA results) as the gold standard, no significant differences were observed between the two experimental groups regarding diagnostic sensitivity, specificity, false positive rate, false negative rate, positive predictive value, negative predictive value, Youden's index, Kappa value, and diagnostic accuracy (X2 = 0.371, P > 0.05).

CONCLUSION

Compared with the manual reading group, the AI reading group revealed no significant differences across all diagnostic indicators, exhibiting high sensitivity and specificity, as well as a relatively high positive predictive value. Additionally, it demonstrated a high level of diagnostic consistency with the gold standard. This technology holds potential for suitability in large-scale screening of DR.

The ACROBAT 2022 challenge: Automatic registration of breast cancer tissue

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.

Pathology Report Interpretation and Disease Diagnosis Using Fuzzy Logic Embedded in an Artificial Intelligence Framework: A New Paradigm for Digital Technologies

Introduction Accurate diagnosis is essential for effective treatment in healthcare settings. Digital technologies have revolutionized medical diagnostics, particularly in pathology laboratory report analyses, by enhancing speed, quality, and precision. Diagnostic pathology has advanced significantly with digital imaging, AI algorithms, and computer-assisted techniques. Traditional machine learning methods require extensive training data, struggle with decision-making flexibility, and lack interpretability when handling new data. Methods This paper introduces a novel approach to address these challenges: a fuzzy logic-based system for interpreting pathology laboratory reports and diagnosing diseases, while considering the restrictions of engineered interpretations so that the degree of reliability of the output of the system is at par with human perception. Results The analysis highlights the impressive accuracy of the fuzzy logic-based diagnosis system, which is closely aligned with professional diagnoses. Notably, it correctly identified "normal" with an 83% probability, showcasing its potential for early disease detection. Performance evaluations indicated that the precision, recall, and F-measure significantly improved as the number of probable diagnoses considered increased. Furthermore, the system exhibited enhanced predictive accuracy for disease recurrence when incorporating multiple probable diagnoses, underscoring its robust clinical effectiveness. Conclusion A fuzzy logic-based system within an AI framework for interpreting pathology laboratory reports and diagnosing 17 diseases across various demographics is presented. The performance of the algorithm, assessed using specialized classification metrics, showed stable and satisfactory results. The analysis revealed a direct correlation between the number of probable diagnoses considered and improved diagnostic accuracy with enhancements in precision, recall, and F-measure. Broadening the diagnostic scope optimizes immediate patient care and long-term treatment planning, potentially enhancing patient outcomes and healthcare quality.

Next-generation lung cancer pathology: Development and validation of diagnostic and prognostic algorithms

Non-small cell lung cancer (NSCLC) is one of the most common malignant tumors. In this study, we develop a clinically useful computational pathology platform for NSCLC that can be a foundation for multiple downstream applications and provide immediate value for patient care optimization and individualization. We train the primary multi-class tissue segmentation algorithm on a substantial, high-quality, manually annotated dataset of whole-slide images with lung adenocarcinoma and squamous cell carcinomas. We investigate two downstream applications. NSCLC subtyping algorithm is trained and validated using a large, multi-institutional (n = 6), multi-scanner (n = 5), international cohort of NSCLC cases (slides/patients 4,097/1,527). Moreover, we develop four AI-derived, fully explainable, quantitative, prognostic parameters (based on tertiary lymphoid structure and necrosis assessment) and validate them for different clinical endpoints. The computational platform enables the high-precision, quantitative analysis of H&E-stained slides. The developed prognostic parameters facilitate robust and independent risk stratification of patients with NSCLC.

An artificial intelligence-based model exploiting H&E images to predict recurrence in negative sentinel lymph-node melanoma patients

BACKGROUND

Risk stratification and treatment benefit prediction models are urgent to improve negative sentinel lymph node (SLN-) melanoma patient selection, thus avoiding costly and toxic treatments in patients at low risk of recurrence. To this end, the application of artificial intelligence (AI) could help clinicians to better calculate the recurrence risk and choose whether to perform adjuvant therapy.

METHODS

We made use of AI to predict recurrence-free status (RFS) within 2-years from diagnosis in 94 SLN- melanoma patients. In detail, we detected quantitative imaging information from H&E slides of a cohort of 71 SLN- melanoma patients, who registered at Istituto Tumori "Giovanni Paolo II" in Bari, Italy (investigational cohort, IC). For each slide, two expert pathologists firstly annotated two Regions of Interest (ROIs) containing tumor cells alone (TUMOR ROI) or with infiltrating cells (TUMOR + INF ROI). In correspondence of the two kinds of ROIs, two AI-based models were developed to extract information directly from the tiles in which each ROI was automatically divided. This information was then used to predict RFS. Performances of the models were computed according to a 5-fold cross validation scheme. We further validated the prediction power of the two models on an independent external validation cohort of 23 SLN- melanoma patients (validation cohort, VC).

RESULTS

The TUMOR ROIs have revealed more informative than the TUMOR + INF ROIs. An Area Under the Curve (AUC) value of 79.1% and 62.3%, a sensitivity value of 81.2% and 76.9%, a specificity value of 70.0% and 43.3%, an accuracy value of 73.2% and 53.4%, were achieved on the TUMOR and TUMOR + INF ROIs extracted for the IC cohort, respectively. An AUC value of 76.5% and 65.2%, a sensitivity value of 66.7% and 41.6%, a specificity value of 70.0% and 55.9%, an accuracy value of 70.0% and 56.5%, were achieved on the TUMOR and TUMOR + INF ROIs extracted for the VC cohort, respectively.

CONCLUSIONS

Our approach represents a first effort to develop a non-invasive prognostic method to better define the recurrence risk and improve the management of SLN- melanoma patients.

Large language model triaging of simulated nephrology patient inbox messages

Background

Efficient triage of patient communications is crucial for timely medical attention and improved care. This study evaluates ChatGPT's accuracy in categorizing nephrology patient inbox messages, assessing its potential in outpatient settings.

Methods

One hundred and fifty simulated patient inbox messages were created based on cases typically encountered in everyday practice at a nephrology outpatient clinic. These messages were triaged as non-urgent, urgent, and emergent by two nephrologists. The messages were then submitted to ChatGPT-4 for independent triage into the same categories. The inquiry process was performed twice with a two-week period in between. ChatGPT responses were graded as correct (agreement with physicians), overestimation (higher priority), or underestimation (lower priority).

Results

In the first trial, ChatGPT correctly triaged 140 (93%) messages, overestimated the priority of 4 messages (3%), and underestimated the priority of 6 messages (4%). In the second trial, it correctly triaged 140 (93%) messages, overestimated the priority of 9 (6%), and underestimated the priority of 1 (1%). The accuracy did not depend on the urgency level of the message (p = 0.19). The internal agreement of ChatGPT responses was 92% with an intra-rater Kappa score of 0.88.

Conclusion

ChatGPT-4 demonstrated high accuracy in triaging nephrology patient messages, highlighting the potential for AI-driven triage systems to enhance operational efficiency and improve patient care in outpatient clinics.

Perovskite Probe-Based Machine Learning Imaging Model for Rapid Pathologic Diagnosis of Cancers

Accurately distinguishing tumor cells from normal cells is a key issue in tumor diagnosis, evaluation, and treatment. Fluorescence-based immunohistochemistry as the standard method faces the inherent challenges of the heterogeneity of tumor cells and the lack of big data analysis of probing images. Here, we have demonstrated a machine learning-driven imaging method for rapid pathological diagnosis of five types of cancers (breast, colon, liver, lung, and stomach) using a perovskite nanocrystal probe. After conducting the bioanalysis of survivin expression in five different cancers, high-efficiency perovskite nanocrystal probes modified with the survivin antibody can recognize the cancer tissue section at the single cell level. The tumor to normal (T/N) ratio is 10.3-fold higher than that of a conventional fluorescent probe, which can successfully differentiate between tumors and adjacent normal tissues within 10 min. The features of the fluorescence intensity and pathological texture morphology have been extracted and analyzed from 1000 fluorescence images by machine learning. The final integrated decision model makes the area under the receiver operating characteristic curve (area under the curve) value of machine learning classification of breast, colon, liver, lung, and stomach above 90% while predicting the tumor organ of 92% of positive patients. This method demonstrates a high T/N ratio probe in the precise diagnosis of multiple cancers, which will be good for improving the accuracy of surgical resection and reducing cancer mortality.

Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning

BACKGROUND

Deployment and access to state-of-the-art precision medicine technologies remains a fundamental challenge in providing equitable global cancer care in low-resource settings. The expansion of digital pathology in recent years and its potential interface with diagnostic artificial intelligence algorithms provides an opportunity to democratize access to personalized medicine. Current digital pathology workstations, however, cost thousands to hundreds of thousands of dollars. As cancer incidence rises in many low- and middle-income countries, the validation and implementation of low-cost automated diagnostic tools will be crucial to helping healthcare providers manage the growing burden of cancer.

METHODS

Here we describe a low-cost ($230) workstation for digital slide capture and computational analysis composed of open-source components. We analyze the predictive performance of deep learning models when they are used to evaluate pathology images captured using this open-source workstation versus images captured using common, significantly more expensive hardware. Validation studies assessed model performance on three distinct datasets and predictive models: head and neck squamous cell carcinoma (HPV positive versus HPV negative), lung cancer (adenocarcinoma versus squamous cell carcinoma), and breast cancer (invasive ductal carcinoma versus invasive lobular carcinoma).

FINDINGS

When compared to traditional pathology image capture methods, low-cost digital slide capture and analysis with the open-source workstation, including the low-cost microscope device, was associated with model performance of comparable accuracy for breast, lung, and HNSCC classification. At the patient level of analysis, AUROC was 0.84 for HNSCC HPV status prediction, 1.0 for lung cancer subtype prediction, and 0.80 for breast cancer classification.

INTERPRETATION

Our ability to maintain model performance despite decreased image quality and low-power computational hardware demonstrates that it is feasible to massively reduce costs associated with deploying deep learning models for digital pathology applications. Improving access to cutting-edge diagnostic tools may provide an avenue for reducing disparities in cancer care between high- and low-income regions.

FUNDING

Funding for this project including personnel support was provided via grants from NIH/NCIR25-CA240134, NIH/NCIU01-CA243075, NIH/NIDCRR56-DE030958, NIH/NCIR01-CA276652, NIH/NCIK08-CA283261, NIH/NCI-SOAR25CA240134, SU2C (Stand Up to Cancer) Fanconi Anemia Research Fund - Farrah Fawcett Foundation Head and Neck Cancer Research Team Grant, and the European UnionHorizon Program (I3LUNG).

Clinical translation of nanomedicine with integrated digital medicine and machine learning interventions

Nanomaterials based therapeutics transform the ways of disease prevention, diagnosis and treatment with increasing sophistications in nanotechnology at a breakneck pace, but very few could reach to the clinic due to inconsistencies in preclinical studies followed by regulatory hinderances. To tackle this, integrating the nanomedicine discovery with digital medicine provide technologies as tools of specific biological activity measurement. Hence, overcome the redundancies in nanomedicine discovery by the on-site data acquisition and analytics through integrating intelligent sensors and artificial intelligence (AI) or machine learning (ML). Integrated AI/ML wearable sensors directly gather clinically relevant biochemical information from the subject's body and process data for physicians to make right clinical decision(s) in a time and cost-effective way. This review summarizes insights and recommend the infusion of actionable big data computation enabled sensors in burgeoning field of nanomedicine at academia, research institutes, and pharmaceutical industries, with a potential of clinical translation. Furthermore, many blind spots are present in modern clinically relevant computation, one of which could prevent ML-guided low-cost new nanomedicine development from being successfully translated into the clinic was also discussed.

The Impact of Artificial Intelligence on Internal Medicine Physicians: A Survey of Procedural and Non-procedural Specialties

BACKGROUND

Artificial intelligence (AI) is increasingly being integrated into various aspects of healthcare, including internal medicine. However, the impact of AI on physicians across different internal medicine specialties remains unclear. This study assesses AI's adoption, utilization, and perceived impact among procedural and non-procedural internal medicine physicians.

METHODS

A comprehensive survey questionnaire was designed to cover current AI use, perceived impact on diagnostic accuracy, treatment decisions, patient outcomes, challenges, ethical concerns, and future expectations. The survey was distributed to a diverse sample of internal medicine physicians across various specialties, including procedural (e.g., interventional cardiology, gastroenterology) and non-procedural (e.g., endocrinology, rheumatology) fields. Responses were analyzed using descriptive statistics, chi-square tests, t-tests, and logistic regression.

RESULTS

The survey received responses from 22 internal medicine physicians, with 64% (n=14) representing procedural specialties and 36% (n=8) representing non-procedural specialties. Sixty-eight percent (n=15) of respondents reported using AI tools in their practice, with higher adoption rates among procedural specialties (n=11, 79%) compared to non-procedural specialties (n=4, 50%). Surveyed physicians reported that AI improved diagnostic accuracy (n=12, 80%), treatment decisions (n=10, 67%), and patient outcomes (n=13, 87%). However, 55% (n=12) of respondents expressed concerns about the interpretability and transparency of AI algorithms. Non-procedural specialists were more likely to perceive AI as a threat to their job security (n=3, 38%) than procedural specialists (n=3, 21%). The most common challenges to AI adoption were lack of training (n=16, 73%), cost (n=13, 59%), and data privacy concerns (n=11, 50%).

CONCLUSION

This study assesses the perceived impact of AI on internal medicine physicians, highlighting the differences between procedural and non-procedural specialties. The findings underscore the need for specialty-specific considerations in developing and implementing AI tools. While AI can potentially improve diagnostic accuracy, treatment decisions, and patient outcomes, addressing challenges such as lack of training, cost, and data privacy concerns is crucial for widespread adoption. Moreover, the study emphasizes the importance of ensuring the interpretability and transparency of AI algorithms to foster trust among physicians. As AI continues to evolve, it is essential to engage internal medicine physicians across specialties in the development process to create AI tools that effectively complement their expertise and improve patient care. Further research should focus on developing best practices for AI integration in internal medicine and evaluating the long-term impact on patient outcomes and healthcare systems.

Staff Experiences Transitioning to Digital Dermatopathology in a Tertiary Academic Medical Center: Lessons Learned From Implementation Science

Digital pathology (DP) transforms practice by replacing traditional glass slide review with digital whole slide images and workflows. Although digitization may improve accuracy and efficiency, transitioning to digital practice requires staff to learn new skills and adopt new ways of working and collaborating. In this study, we aimed to evaluate the experiences and perceptions of individuals involved in the day-to-day work of implementing DP in a tertiary academic medical center using Normalization Process Theory, a social theory that explains the processes by which innovations are operationalized and sustained in practice. Between September 2021 and June 2022, dermatopathologists, referring clinicians, and support staff at Mayo Clinic (Minnesota, Florida, and Arizona) participated in interviews (n=22) and completed surveys (n=34) concerning the transition. Normalization Process Theory informed the selection of validated survey items (Normalization Measure Development Questionnaire) and guided qualitative analysis. Participants reported high agreement with statements related to shared understanding and potential value of DP for workflow integration and working relationships. Qualitative themes reflecting the way organization and social context enable these processes were mapped onto implementation stages and related key activities. We found that earlier processes of implementation (understanding and working out participation) were better supported than later stages (doing it and reflecting on it). Our analysis helps identify targets for further intervention to hasten and help sustain implementation, including additional support in software and technological integration, workflows and work redesign, and regular monitoring and feedback systems. The use of implementation theory, such as Normalization Process Theory, may provide useful pointers to enable other similar digital system transition efforts.

Image stitching algorithm for super-resolution localization microscopy combined with fluorescence noise prior

Super-resolution panoramic pathological imaging provides a powerful tool for biologists to observe the ultrastructure of samples. Localization data can maintain the essential ultrastructural information of biological samples with a small storage space, and also provides a new opportunity for stitching super-resolution images. However, the existing image stitching methods based on localization data cannot accurately calculate the registration offset of sample regions with no or few structural points and thus lead to registration errors. Here, we proposed a stitching framework called PNanoStitcher. The framework fully utilizes the distribution characteristics of the background fluorescence noise in the stitching region and solves the stitching failure in sample regions with no or few structural points. We verified our method using both simulated and experimental datasets, and compared it with existing stitching methods. PNanoStitcher achieved superior stitching results on biological samples with no structural and few structural regions. The study provides an important driving force for the development of super-resolution digital pathology.

The Role of Artificial Intelligence on Tumor Boards: Perspectives from Surgeons, Medical Oncologists and Radiation Oncologists

The integration of multidisciplinary tumor boards (MTBs) is fundamental in delivering state-of-the-art cancer treatment, facilitating collaborative diagnosis and management by a diverse team of specialists. Despite the clear benefits in personalized patient care and improved outcomes, the increasing burden on MTBs due to rising cancer incidence and financial constraints necessitates innovative solutions. The advent of artificial intelligence (AI) in the medical field offers a promising avenue to support clinical decision-making. This review explores the perspectives of clinicians dedicated to the care of cancer patients-surgeons, medical oncologists, and radiation oncologists-on the application of AI within MTBs. Additionally, it examines the role of AI across various clinical specialties involved in cancer diagnosis and treatment. By analyzing both the potential and the challenges, this study underscores how AI can enhance multidisciplinary discussions and optimize treatment plans. The findings highlight the transformative role that AI may play in refining oncology care and sustaining the efficacy of MTBs amidst growing clinical demands.

Advanced image generation for cancer using diffusion models

Deep neural networks have significantly advanced the field of medical image analysis, yet their full potential is often limited by relatively small dataset sizes. Generative modeling, particularly through diffusion models, has unlocked remarkable capabilities in synthesizing photorealistic images, thereby broadening the scope of their application in medical imaging. This study specifically investigates the use of diffusion models to generate high-quality brain MRI scans, including those depicting low-grade gliomas, as well as contrast-enhanced spectral mammography (CESM) and chest and lung X-ray images. By leveraging the DreamBooth platform, we have successfully trained stable diffusion models utilizing text prompts alongside class and instance images to generate diverse medical images. This approach not only preserves patient anonymity but also substantially mitigates the risk of patient re-identification during data exchange for research purposes. To evaluate the quality of our synthesized images, we used the Fréchet inception distance metric, demonstrating high fidelity between the synthesized and real images. Our application of diffusion models effectively captures oncology-specific attributes across different imaging modalities, establishing a robust framework that integrates artificial intelligence in the generation of oncological medical imagery.

Expanding role and scope of artificial intelligence in the field of gastrointestinal pathology

Digital pathology (DP) and its subsidiaries including artificial intelligence (AI) are rapidly making inroads into the area of diagnostic anatomic pathology (AP) including gastrointestinal (GI) pathology. It is poised to revolutionize the field of diagnostic AP. Historically, AP has been slow to adopt digital technology, but this is changing rapidly, with many centers worldwide transitioning to DP. Coupled with advanced techniques of AI such as deep learning and machine learning, DP is likely to transform histopathology from a subjective field to an objective, efficient, and transparent discipline. AI is increasingly integrated into GI pathology, offering numerous advancements and improvements in overall diagnostic accuracy, efficiency, and patient care. Specifically, AI in GI pathology enhances diagnostic accuracy, streamlines workflows, provides predictive insights, integrates multimodal data, supports research, and aids in education and training, ultimately improving patient care and outcomes. This review summarized the latest developments in the role and scope of AI in AP with a focus on GI pathology. The main aim was to provide updates and create awareness among the pathology community.

Deep Learning for Histopathological Assessment of Esophageal Adenocarcinoma Precursor Lesions

Histopathological assessment of esophageal biopsies is a key part in the management of patients with Barrett esophagus (BE) but prone to observer variability and reliable diagnostic methods are needed. Artificial intelligence (AI) is emerging as a powerful tool for aided diagnosis but often relies on abstract test and validation sets while real-world behavior is unknown. In this study, we developed a 2-stage AI system for histopathological assessment of BE-related dysplasia using deep learning to enhance the efficiency and accuracy of the pathology workflow. The AI system was developed and trained on 290 whole-slide images (WSIs) that were annotated at glandular and tissue levels. The system was designed to identify individual glands, grade dysplasia, and assign a WSI-level diagnosis. The proposed method was evaluated by comparing the performance of our AI system with that of a large international and heterogeneous group of 55 gastrointestinal pathologists assessing 55 digitized biopsies spanning the complete spectrum of BE-related dysplasia. The AI system correctly graded 76.4% of the WSIs, surpassing the performance of 53 out of the 55 participating pathologists. Furthermore, the receiver-operating characteristic analysis showed that the system's ability to predict the absence (nondysplastic BE) versus the presence of any dysplasia was with an area under the curve of 0.94 and a sensitivity of 0.92 at a specificity of 0.94. These findings demonstrate that this AI system has the potential to assist pathologists in assessment of BE-related dysplasia. The system's outputs could provide a reliable and consistent secondary diagnosis in challenging cases or be used for triaging low-risk nondysplastic biopsies, thereby reducing the workload of pathologists and increasing throughput.

Prognostic Analysis Combining Histopathological Features and Clinical Information to Predict Colorectal Cancer Survival from Whole-Slide Images

BACKGROUND

Colorectal cancer (CRC) is a malignant tumor within the digestive tract with both a high incidence rate and mortality. Early detection and intervention could improve patient clinical outcomes and survival.

METHODS

This study computationally investigates a set of prognostic tissue and cell features from diagnostic tissue slides. With the combination of clinical prognostic variables, the pathological image features could predict the prognosis in CRC patients. Our CRC prognosis prediction pipeline sequentially consisted of three modules: (1) A MultiTissue Net to delineate outlines of different tissue types within the WSI of CRC for further ROI selection by pathologists. (2) Development of three-level quantitative image metrics related to tissue compositions, cell shape, and hidden features from a deep network. (3) Fusion of multi-level features to build a prognostic CRC model for predicting survival for CRC.

RESULTS

Experimental results suggest that each group of features has a particular relationship with the prognosis of patients in the independent test set. In the fusion features combination experiment, the accuracy rate of predicting patients' prognosis and survival status is 81.52%, and the AUC value is 0.77.

CONCLUSION

This paper constructs a model that can predict the postoperative survival of patients by using image features and clinical information. Some features were found to be associated with the prognosis and survival of patients.