Explainability and causability in digital pathology

Joining forces for pathology diagnostics with AI assistance: The EMPAIA initiative

Over the past decade, artificial intelligence (AI) methods in pathology have advanced substantially. However, integration into routine clinical practice has been slow due to numerous challenges, including technical and regulatory hurdles in translating research results into clinical diagnostic products and the lack of standardized interfaces. The open and vendor-neutral EMPAIA initiative addresses these challenges. Here, we provide an overview of EMPAIA's achievements and lessons learned. EMPAIA integrates various stakeholders of the pathology AI ecosystem, i.e., pathologists, computer scientists, and industry. In close collaboration, we developed technical interoperability standards, recommendations for AI testing and product development, and explainability methods. We implemented the modular and open-source EMPAIA Platform and successfully integrated 14 AI-based image analysis apps from eight different vendors, demonstrating how different apps can use a single standardized interface. We prioritized requirements and evaluated the use of AI in real clinical settings with 14 different pathology laboratories in Europe and Asia. In addition to technical developments, we created a forum for all stakeholders to share information and experiences on digital pathology and AI. Commercial, clinical, and academic stakeholders can now adopt EMPAIA's common open-source interfaces, providing a unique opportunity for large-scale standardization and streamlining of processes. Further efforts are needed to effectively and broadly establish AI assistance in routine laboratory use. To this end, a sustainable infrastructure, the non-profit association EMPAIA International, has been established to continue standardization and support broad implementation and advocacy for an AI-assisted digital pathology future.

Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities

This paper discusses some overlooked challenges faced when working with machine learning models for histopathology and presents a novel opportunity to support "Learning Health Systems" with them. Initially, the authors elaborate on these challenges after separating them according to their mitigation strategies: those that need innovative approaches, time, or future technological capabilities and those that require a conceptual reappraisal from a critical perspective. Then, a novel opportunity to support "Learning Health Systems" by integrating hidden information extracted by ML models from digitalized histopathology slides with other healthcare big data is presented.

Moonshot. Long shot. Or sure shot. What needs to happen to realize the full potential of AI in the fertility sector?

Quality healthcare requires two critical components: patients' best interests and best decisions to achieve that goal. The first goal is the lodestar, unchanged and unchanging over time. The second component is a more dynamic and rapidly changing paradigm in healthcare. Clinical decision-making has transitioned from an opinion-based paradigm to an evidence-based and data-driven process. A realization that technology and artificial intelligence can bring value adds a third component to the decision process. And the fertility sector is not exempt. The debate about AI is front and centre in reproductive technologies. Launching the transition from a conventional provider-driven decision paradigm to a software-enhanced system requires a roadmap to enable effective and safe implementation. A key nodal point in the ascending arc of AI in the fertility sector is how and when to bring these innovations into the ART routine to improve workflow, outcomes, and bottom-line performance. The evolution of AI in other segments of clinical care would suggest that caution is needed as widespread adoption is urged from several fronts. But the lure and magnitude for the change that these tech tools hold for fertility care remain deeply engaging. Exploring factors that could enhance thoughtful implementation and progress towards a tipping point (or perhaps not) should be at the forefront of any 'next steps' strategy. The objective of this Opinion is to discuss four critical areas (among many) considered essential to successful uptake of any new technology. These four areas include value proposition, innovative disruption, clinical agency, and responsible computing.

Applications of Artificial Intelligence in Lung Pathology

Artificial intelligence/machine learning tools are being created for use in pathology. Some examples related to lung pathology include acid-fast stain evaluation, programmed death ligand-1 (PDL-1) interpretation, evaluating histologic patterns of non-small-cell lung carcinoma, evaluating histologic features in mesothelioma associated with adverse outcomes, predicting response to anti-PDL-1 therapy from hematoxylin and eosin-stained slides, evaluation of tumor microenvironment, evaluating patterns of interstitial lung disease, nondestructive methods for tissue evaluation, and others. There are still some frameworks (regulatory, workflow, and payment) that need to be established for these tools to be integrated into pathology.

Explanatory argumentation in natural language for correct and incorrect medical diagnoses

BACKGROUND

A huge amount of research is carried out nowadays in Artificial Intelligence to propose automated ways to analyse medical data with the aim to support doctors in delivering medical diagnoses. However, a main issue of these approaches is the lack of transparency and interpretability of the achieved results, making it hard to employ such methods for educational purposes. It is therefore necessary to develop new frameworks to enhance explainability in these solutions.

RESULTS

In this paper, we present a novel full pipeline to generate automatically natural language explanations for medical diagnoses. The proposed solution starts from a clinical case description associated with a list of correct and incorrect diagnoses and, through the extraction of the relevant symptoms and findings, enriches the information contained in the description with verified medical knowledge from an ontology. Finally, the system returns a pattern-based explanation in natural language which elucidates why the correct (incorrect) diagnosis is the correct (incorrect) one. The main contribution of the paper is twofold: first, we propose two novel linguistic resources for the medical domain (i.e, a dataset of 314 clinical cases annotated with the medical entities from UMLS, and a database of biological boundaries for common findings), and second, a full Information Extraction pipeline to extract symptoms and findings from the clinical cases and match them with the terms in a medical ontology and to the biological boundaries. An extensive evaluation of the proposed approach shows the our method outperforms comparable approaches.

CONCLUSIONS

Our goal is to offer AI-assisted educational support framework to form clinical residents to formulate sound and exhaustive explanations for their diagnoses to patients.

Prognostic stratification of glioblastoma patients by unsupervised clustering of morphology patterns on whole slide images furthering our disease understanding

Introduction

Glioblastoma (GBM) is a highly aggressive malignant tumor of the central nervous system that displays varying molecular and morphological profiles, leading to challenging prognostic assessments. Stratifying GBM patients according to overall survival (OS) from H&E-stained whole slide images (WSI) using advanced computational methods is challenging, but with direct clinical implications.

Methods

This work is focusing on GBM (IDH-wildtype, CNS WHO Gr.4) cases, identified from the TCGA-GBM and TCGA-LGG collections after considering the 2021 WHO classification criteria. The proposed approach starts with patch extraction in each WSI, followed by comprehensive patch-level curation to discard artifactual content, i.e., glass reflections, pen markings, dust on the slide, and tissue tearing. Each patch is then computationally described as a feature vector defined by a pre-trained VGG16 convolutional neural network. Principal component analysis provides a feature representation of reduced dimensionality, further facilitating identification of distinct groups of morphology patterns, via unsupervised k-means clustering.

Results

The optimal number of clusters, according to cluster reproducibility and separability, is automatically determined based on the rand index and silhouette coefficient, respectively. Our proposed approach achieved prognostic stratification accuracy of 83.33% on a multi-institutional independent unseen hold-out test set with sensitivity and specificity of 83.33%.

Discussion

We hypothesize that the quantification of these clusters of morphology patterns, reflect the tumor's spatial heterogeneity and yield prognostic relevant information to distinguish between short and long survivors using a decision tree classifier. The interpretability analysis of the obtained results can contribute to furthering and quantifying our understanding of GBM and potentially improving our diagnostic and prognostic predictions.

Computational pathology: an evolving concept

The initial enthusiasm about computational pathology (CP) and artificial intelligence (AI) was that they will replace pathologists entirely on the way to fully automated diagnostics. It is becoming clear that currently this is not the immediate model to pursue. On top of the legal and regulatory complexities surrounding its implementation, the majority of tested machine learning (ML)-based predictive algorithms do not display the exquisite performance needed to render them unequivocal, standalone decision makers for matters with direct implications to human health. We are thus moving into a different model of "computer-assisted diagnostics", where AI is there to provide support, rather than replacing, the pathologist. Herein we focus on the practical aspects of CP, from a pathologist perspective. There is a wide range of potential applications where CP can enhance precision of pathology diagnosis, tailor prognostic and predictive information, as well as save time. There are, however, a number of potential limitations for CP that currently hinder their wider adoption in the clinical setting. We address the key necessary steps towards clinical implementation of computational pathology, discuss the significant obstacles that hinders its adoption in the clinical context and summarize some proposed solutions. We conclude that the advancement of CP in the clinic is a promising resource-intensive endeavour that requires broad and inclusive collaborations between academia, industry, and regulatory bodies.

Using digital pathology to analyze the murine cerebrovasculature

Research on the cerebrovasculature may provide insights into brain health and disease. Immunohistochemical staining is one way to visualize blood vessels, and digital pathology has the potential to revolutionize the measurement of blood vessel parameters. These tools provide opportunities for translational mouse model research. However, mouse brain tissue presents a formidable set of technical challenges, including potentially high background staining and cross-reactivity of endogenous IgG. Formalin-fixed paraffin-embedded (FFPE) and fixed frozen sections, both of which are widely used, may require different methods. In this study, we optimized blood vessel staining in mouse brain tissue, testing both FFPE and frozen fixed sections. A panel of immunohistochemical blood vessel markers were tested (including CD31, CD34, collagen IV, DP71, and VWF), to evaluate their suitability for digital pathological analysis. Collagen IV provided the best immunostaining results in both FFPE and frozen fixed murine brain sections, with highly-specific staining of large and small blood vessels and low background staining. Subsequent analysis of collagen IV-stained sections showed region and sex-specific differences in vessel density and vessel wall thickness. We conclude that digital pathology provides a useful tool for relatively unbiased analysis of the murine cerebrovasculature, provided proper protein markers are used.

Closing the loop - the role of pathologists in digital and computational pathology research

An increasing number of manuscripts related to digital and computational pathology are being submitted to The Journal of Pathology: Clinical Research as part of the continuous evolution from digital imaging and algorithm-based digital pathology to computational pathology and artificial intelligence. However, despite these technological advances, tissue analysis still relies heavily on pathologists' annotations. There are three crucial elements to the pathologist's role during annotation tasks: granularity, time constraints, and responsibility for the interpretation of computational results. Granularity involves detailed annotations, including case level, regional, and cellular features; and integration of attributions from different sources. Time constraints due to pathologist shortages have led to the development of techniques to expedite annotation tasks from cell-level attributions up to so-called unsupervised learning. The impact of pathologists may seem diminished, but their role is crucial in providing ground truth and connecting pathological knowledge generation with computational advancements. Measures to display results back to pathologists and reflections about correctly applied diagnostic criteria are mandatory to maintain fidelity during human-machine interactions. Collaboration and iterative processes, such as human-in-the-loop machine learning are key for continuous improvement, ensuring the pathologist's involvement in evaluating computational results and closing the loop for clinical applicability. The journal is interested particularly in the clinical diagnostic application of computational pathology and invites submissions that address the issues raised in this editorial.

Computational pathology-based weakly supervised prediction model for MGMT promoter methylation status in glioblastoma

Introduction

The methylation status of oxygen 6-methylguanine-DNA methyltransferase (MGMT) is closely related to the treatment and prognosis of glioblastoma. However, there are currently some challenges in detecting the methylation status of MGMT promoters. The hematoxylin and eosin (H&E)-stained histopathological slides have always been the gold standard for tumor diagnosis.

Methods

In this study, based on the TCGA database and H&E-stained Whole slide images (WSI) of Beijing Tiantan Hospital, we constructed a weakly supervised prediction model of MGMT promoter methylation status in glioblastoma by using two Transformer structure models.

Results

The accuracy scores of this model in the TCGA dataset and our independent dataset were 0.79 (AUC = 0.86) and 0.76 (AUC = 0.83), respectively.

Conclusion

The model demonstrates effective prediction of MGMT promoter methylation status in glioblastoma and exhibits some degree of generalization capability. At the same time, our study also shows that adding Patches automatic screening module to the computational pathology research framework of glioma can significantly improve the model effect.

CLARUS: An interactive explainable AI platform for manual counterfactuals in graph neural networks

BACKGROUND

Lack of trust in artificial intelligence (AI) models in medicine is still the key blockage for the use of AI in clinical decision support systems (CDSS). Although AI models are already performing excellently in systems medicine, their black-box nature entails that patient-specific decisions are incomprehensible for the physician. Explainable AI (XAI) algorithms aim to "explain" to a human domain expert, which input features influenced a specific recommendation. However, in the clinical domain, these explanations must lead to some degree of causal understanding by a clinician.

RESULTS

We developed the CLARUS platform, aiming to promote human understanding of graph neural network (GNN) predictions. CLARUS enables the visualisation of patient-specific networks, as well as, relevance values for genes and interactions, computed by XAI methods, such as GNNExplainer. This enables domain experts to gain deeper insights into the network and more importantly, the expert can interactively alter the patient-specific network based on the acquired understanding and initiate re-prediction or retraining. This interactivity allows us to ask manual counterfactual questions and analyse the effects on the GNN prediction.

CONCLUSION

We present the first interactive XAI platform prototype, CLARUS, that allows not only the evaluation of specific human counterfactual questions based on user-defined alterations of patient networks and a re-prediction of the clinical outcome but also a retraining of the entire GNN after changing the underlying graph structures. The platform is currently hosted by the GWDG on https://rshiny.gwdg.de/apps/clarus/.

Histopathology image classification: highlighting the gap between manual analysis and AI automation

The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.

AI and professional liability assessment in healthcare. A revolution in legal medicine?

The adoption of advanced artificial intelligence (AI) systems in healthcare is transforming the healthcare-delivery landscape. Artificial intelligence may enhance patient safety and improve healthcare outcomes, but it presents notable ethical and legal dilemmas. Moreover, as AI streamlines the analysis of the multitude of factors relevant to malpractice claims, including informed consent, adherence to standards of care, and causation, the evaluation of professional liability might also benefit from its use. Beginning with an analysis of the basic steps in assessing professional liability, this article examines the potential new medical-legal issues that an expert witness may encounter when analyzing malpractice cases and the potential integration of AI in this context. These changes related to the use of integrated AI, will necessitate efforts on the part of judges, experts, and clinicians, and may require new legislative regulations. A new expert witness will be likely necessary in the evaluation of professional liability cases. On the one hand, artificial intelligence will support the expert witness; however, on the other hand, it will introduce specific elements into the activities of healthcare workers. These elements will necessitate an expert witness with a specialized cultural background. Examining the steps of professional liability assessment indicates that the likely path for AI in legal medicine involves its role as a collaborative and integrated tool. The combination of AI with human judgment in these assessments can enhance comprehensiveness and fairness. However, it is imperative to adopt a cautious and balanced approach to prevent complete automation in this field.

Current status, challenges and future prospects in computational psychiatry: a narrative review

BACKGROUND

Computational psychiatry is an area of scientific knowledge which lies at the intersection of neuroscience, psychiatry, and computer science. It employs mathematical models and computational simulations to shed light on the complexities inherent to mental disorders.

AIM

The aim of this narrative review is to offer insight into the current landscape of computational psychiatry, to discuss its significant challenges, as well as the potential opportunities for the fields growth.

METHODS

The authors have carried out a narrative review of the scientific literature published on the topic of computational psychiatry. The literature search was performed in the PubMed, eLibrary, PsycINFO, and Google Scholar databases. A descriptive analysis was used to summarize the published information on the theoretical and practical aspects of computational psychiatry.

RESULTS

The article relates the development of the scientific approach in computational psychiatry since the mid-1980s. The data on the practical application of computational psychiatry in modeling psychiatric disorders and explaining the mechanisms of how psychopathological symptomatology develops (in schizophrenia, attention-deficit/hyperactivity disorder, autism spectrum disorder, anxiety disorders, obsessive-compulsive disorder, substance use disorders) are summarized. Challenges, limitations, and the prospects of computational psychiatry are discussed.

CONCLUSION

The capacity of current computational technologies in psychiatry has reached a stage where its integration into psychiatric practice is not just feasible but urgently needed. The hurdles that now need to be addressed are no longer rooted in technological advancement, but in ethics, education, and understanding.