Search

Purpose To evaluate the utility of non-contrast-enhanced CT texture analysis (CTTA) for predicting the histopathological differentiation of pancreatic ductal adenocarcinomas (PDAC) and to compare non-contrast-enhanced CTTA texture features between primary PDAC and hepatic metastases of PDAC. Methods This retrospective study included 120 patients with histopathologically confirmed PDAC. Sixty-five patients underwent CT-guided biopsy of primary PDAC, while 55 patients underwent CT-guided biopsy of hepatic PDAC metastasis. All lesions were segmented in non-contrast-enhanced CT scans for CTTA based on histogram analysis, co-occurrence matrix, and run-length matrix. Statistical analysis was conducted for 372 texture features using Mann–Whitney U test, Bonferroni–Holm correction, and receiver operating characteristic (ROC) analysis. A p value Results Three features were identified that differed significantly between histopathological G2 and G3 primary tumors. Of these, “low gray-level zone emphasis” yielded the largest AUC (0.87 ± 0.04), reaching a sensitivity and specificity of 0.76 and 0.83, respectively, when a cut-off value of 0.482 was applied. Fifty-four features differed significantly between primary and hepatic metastatic PDAC. Conclusion Non-contrast-enhanced CTTA of PDAC identified differences in texture features between primary G2 and G3 tumors that could be used for non-invasive tumor assessment. Extensive differences between the features of primary and metastatic PDAC on CTTA suggest differences in tumor microenvironment. Graphical Abstract

The exchange of biological material and data has become an issue of major importance for research in biotechnology. At the same time, many reports indicate problems with quality, trustworthiness and reproducibility of research results, mainly due to poor documentation of data generation or collection of samples. Consequently, there is an urgent need for improved and standardized documentation of data and specimen used in research studies. In response to these issues, we are developing a provenance information standard for the biotechnology domain within the ISO Technical Committee 276 “Biotechnology”. The major objectives of the standard, now registered as ISO/WD 23494, are improved reproducibility of research results, enabling the assessment of the quality of biological samples and data, traceability and higher reliability of observations. We are convinced that the standardization project is of substantial interest to a broader audience, who we would also invite to comment and contribute to this comprehensive effort., Manuscript under consideration.

ImportanceIdentifying new prognostic features in colon cancer has the potential to refine histopathologic review and inform patient care. Although prognostic artificial intelligence systems have recently demonstrated significant risk stratification for several cancer types, studies have not yet shown that the machine learning–derived features associated with these prognostic artificial intelligence systems are both interpretable and usable by pathologists.ObjectiveTo evaluate whether pathologist scoring of a histopathologic feature previously identified by machine learning is associated with survival among patients with colon cancer.Design, Setting, and ParticipantsThis prognostic study used deidentified, archived colorectal cancer cases from January 2013 to December 2015 from the University of Milano-Bicocca. All available histologic slides from 258 consecutive colon adenocarcinoma cases were reviewed from December 2021 to February 2022 by 2 pathologists, who conducted semiquantitative scoring for tumor adipose feature (TAF), which was previously identified via a prognostic deep learning model developed with an independent colorectal cancer cohort.Main Outcomes and MeasuresPrognostic value of TAF for overall survival and disease-specific survival as measured by univariable and multivariable regression analyses. Interpathologist agreement in TAF scoring was also evaluated.ResultsA total of 258 colon adenocarcinoma histopathologic cases from 258 patients (138 men [53%]; median age, 67 years [IQR, 65-81 years]) with stage II (n = 119) or stage III (n = 139) cancer were included. Tumor adipose feature was identified in 120 cases (widespread in 63 cases, multifocal in 31, and unifocal in 26). For overall survival analysis after adjustment for tumor stage, TAF was independently prognostic in 2 ways: TAF as a binary feature (presence vs absence: hazard ratio [HR] for presence of TAF, 1.55 [95% CI, 1.07-2.25]; P = .02) and TAF as a semiquantitative categorical feature (HR for widespread TAF, 1.87 [95% CI, 1.23-2.85]; P = .004). Interpathologist agreement for widespread TAF vs lower categories (absent, unifocal, or multifocal) was 90%, corresponding to a κ metric at this threshold of 0.69 (95% CI, 0.58-0.80).Conclusions and RelevanceIn this prognostic study, pathologists were able to learn and reproducibly score for TAF, providing significant risk stratification on this independent data set. Although additional work is warranted to understand the biological significance of this feature and to establish broadly reproducible TAF scoring, this work represents the first validation to date of human expert learning from machine learning in pathology. Specifically, this validation demonstrates that a computationally identified histologic feature can represent a human-identifiable, prognostic feature with the potential for integration into pathology practice.

Various biological resources, such as biobanks and disease-specific registries, have become indispensable resources to better understand the epidemiology and biological mechanisms of disease and are fundamental for advancing medical research. Nevertheless, biobanks and similar resources still face significant challenges to become more findable and accessible by users on both national and global scales. One of the main challenges for users is to find relevant resources using cataloging and search services such as the BBMRI-ERIC Directory, operated by European Research Infrastructure on Biobanking and Biomolecular Resources (BBMRI-ERIC), as these often do not contain the information needed by the researchers to decide if the resource has relevant material/data; these resources are only weakly characterized. Hence, the researcher is typically left with too many resources to explore and investigate. In addition, resources often have complex procedures for accessing holdings, particularly for depletable biological materials. This article focuses on designing a system for effective negotiation of access to holdings, in which a researcher can approach many resources simultaneously, while giving each resource team the ability to implement their own mechanisms to check if the material/data are available and to decide if access should be provided. The BBMRI-ERIC has developed and implemented an access and negotiation tool called the BBMRI-ERIC Negotiator. The Negotiator enables access negotiation to more than 600 biobanks from the BBMRI-ERIC Directory and other discovery services such as GBA/BBMRI-ERIC Locator or RD-Connect Finder. This article summarizes the principles that guided the design of the tool, the terminology used and underlying data model, request workflows, authentication and authorization mechanism(s), and the mechanisms and monitoring processes to stimulate the desired behavior of the resources: to effectively deliver access to biological material and data.

Background: Artificial Intelligence (AI) is becoming more and more important especially in datacentric fields, such as biomedical research and biobanking. However, AI does not only offer advantages and promising benefits, but brings about also ethical risks and perils. In recent years, there has been growing interest in AI ethics, as reflected by a huge number of (scientific) literature dealing with the topic of AI ethics. The main objectives of this review are: (1) to provide an overview about important (upcoming) AI ethics regulations and international recommendations as well as available AI ethics tools and frameworks relevant to biomedical research, (2) to identify what AI ethics can learn from findings in ethics of traditional biomedical research - in particular looking at ethics in the domain of biobanking, and (3) to provide an overview about the main research questions in the field of AI ethics in biomedical research. Methods: We adopted a modified thematic review approach focused on understanding AI ethics aspects relevant to biomedical research. For this review, four scientific literature databases at the cross-section of medical, technical, and ethics science literature were queried: PubMed, BMC Medical Ethics, IEEE Xplore, and Google Scholar. In addition, a grey literature search was conducted to identify current trends in legislation and standardization. Results: More than 2,500 potentially relevant publications were retrieved through the initial search and 57 documents were included in the final review. The review found many documents describing high-level principles of AI ethics, and some publications describing approaches for making AI ethics more actionable and bridging the principles-to-practice gap. Also, some ongoing regulatory and standardization initiatives related to AI ethics were identified. It was found that ethical aspects of AI implementation in biobanks are often like those in biomedical research, for example with regards to handling big data or tackling informed consent. The review revealed current ‘hot’ topics in AI ethics related to biomedical research. Furthermore, several published tools and methods aiming to support practical implementation of AI ethics, as well as tools and frameworks specifically addressing complete and transparent reporting of biomedical studies involving AI are described in the review results. Conclusions: The review results provide a practically useful overview of research strands as well as regulations, guidelines, and tools regarding AI ethics in biomedical research. Furthermore, the review results show the need for an ethical-mindful and balanced approach to AI in biomedical research, and specifically reveal the need for AI ethics research focused on understanding and resolving practical problems arising from the use of AI in science and society.

The distributed nature of modern research emphasizes the importance of collecting and sharing the history of digital and physical material, to improve the reproducibility of experiments and the quality and reusability of results. Yet, the application of the current methodologies to record provenance information is largely scattered, leading to silos of provenance information at different granularities. To tackle this fragmentation, we developed the Common Provenance Model, a set of guidelines for the generation of interoperable provenance information, and to allow the reconstruction and the navigation of a continuous provenance chain. This work presents the first version of the model, available online, based on the W3C PROV Data Model and the Provenance Composition pattern.

Access to large volumes of so-calledwhole-slide images—high-resolution scans of complete pathological slides—has become a cornerstone of the development of novel artificial intelligence methods in pathology for diagnostic use, education/training of pathologists, and research. Nevertheless, a methodology based on risk analysis for evaluating the privacy risks associated with sharing such imaging data and applying the principle “as open as possible and as closed as necessary” is still lacking. In this article, we develop a model for privacy risk analysis for whole-slide images which focuses primarily on identity disclosure attacks, as these are the most important from a regulatory perspective. We introduce a mathematical model for risk assessment and design a taxonomy of whole-slide images with respect to privacy risks. Based on this risk assessment model and the taxonomy, we conduct a series of experiments to demonstrate the risks using real-world imaging data. Finally, we develop guidelines for risk assessment and recommendations for low-risk sharing of whole-slide image data.

Introduction: The Minimum Information About BIobank data Sharing (MIABIS) was initiated in 2012. MIABIS aims to create a common biobank terminology to facilitate data sharing in biobanks and sample collections. The MIABIS Core terminology consists of three components describing biobanks, sample collections, and studies, in which information on samples and sample donors is provided at aggregated form. However, there is also a need to describe samples and sample donors at an individual level to allow more elaborate queries on available biobank samples and data. Therefore the MIABIS terminology has now been extended with components describing samples and sample donors at an individual level.Materials and Methods: The components were defined according to specific scope and use cases by a large group of experts, and through several cycles of reviews, according to the new MIABIS governance model of BBMRI-ERIC (Biobanking and Biomolecular Resources Research Infrastructure-European Research Infrastructure Consortium). The guiding principles applied in developing these components included the following terms: model should consider only samples of human origin, model should be applicable to all types of samples and all sample donors, and model should describe the current status of samples stored in a given biobank.Results: A minimal set of standard attributes for defining samples and sample donors is presented here. We added an "event" component to describe attributes that are not directly describing samples or sample donors but are tightly related to them. To better utilize the generic data model, we suggest a procedure by which interoperability can be promoted, using specific MIABIS profiles.Discussion: The MIABIS sample and donor component extensions and the new generic data model complement the existing MIABIS Core 2.0 components, and substantially increase the potential usability of this terminology for better describing biobank samples and sample donors. They also support the use of individual level data about samples and sample donors to obtain accurate and detailed biobank availability queries.

ZusammenfassungKünstliche Intelligenz (KI) folgt dem Begriff der menschlichen Intelligenz, der leider kein klar definierter Begriff ist. Die gebräuchlichste Definition, wie sie in der Kognitionswissenschaft als mentale Fähigkeit gegeben ist, enthält unter anderem die Fähigkeit, abstrakt, logisch und schlussfolgernd zu denken und gegebene Probleme der realen Welt zu lösen. Ein aktuelles Thema in der KI ist es, herauszufinden, ob und inwieweit Algorithmen in der Lage sind, solches abstraktes Denken und Schlussfolgern ähnlich wie Menschen zu erlernen – oder ob das Lernergebnis auf rein statistischer Korrelation beruht. In diesem Beitrag stellen wir eine von uns entwickelte frei verfügbare, universelle und erweiterbare experimentelle Testumgebung vor. Diese „Kandinsky Patterns“ (https://human-centered.ai/project/kandinsky-patterns, https://www.youtube.com/watch?v=UuiV0icAlRs), benannt nach dem russischen Maler und Kunsttheoretiker Wassily Kandinsky (1866–1944), stellen eine Art „Schweizer Messer“ zum Studium der genannten Problemstellungen dar. Das Gebiet, dass diese Problemstellungen behandelt wird „explainable AI“ (xAI) genannt. Erklärbarkeit/Interpretierbarkeit hat das Ziel, menschlichen Experten zu ermöglichen, zugrundeliegende Erklärungsfaktoren – die Kausalität – zu verstehen, also warum eine KI-Entscheidung getroffen wurde, und so den Weg für eine transparente und verifizierbare KI zu ebnen.

Gleason grading of prostate cancer is an important prognostic factor, but suffers from poor reproducibility, particularly among non-subspecialist pathologists. Although artificial intelligence (A.I.) tools have demonstrated Gleason grading on-par with expert pathologists, it remains an open question whether and to what extent A.I. grading translates to better prognostication. In this study, we developed a system to predict prostate cancer-specific mortality via A.I.-based Gleason grading and subsequently evaluated its ability to risk-stratify patients on an independent retrospective cohort of 2807 prostatectomy cases from a single European center with 5–25 years of follow-up (median: 13, interquartile range 9–17). Here, we show that the A.I.’s risk scores produced a C-index of 0.84 (95% CI 0.80–0.87) for prostate cancer-specific mortality. Upon discretizing these risk scores into risk groups analogous to pathologist Grade Groups (GG), the A.I. has a C-index of 0.82 (95% CI 0.78–0.85). On the subset of cases with a GG provided in the original pathology report (n = 1517), the A.I.’s C-indices are 0.87 and 0.85 for continuous and discrete grading, respectively, compared to 0.79 (95% CI 0.71–0.86) for GG obtained from the reports. These represent improvements of 0.08 (95% CI 0.01–0.15) and 0.07 (95% CI 0.00–0.14), respectively. Our results suggest that A.I.-based Gleason grading can lead to effective risk stratification, and warrants further evaluation for improving disease management. Gleason grading is the process by which pathologists assess the morphology of prostate tumors. The assigned Grade Group tells us about the likely clinical course of people with prostate cancer and helps doctors to make decisions on treatment. The process is complex and subjective, with frequent disagreement amongst pathologists. In this study, we develop and evaluate an approach to Gleason grading based on artificial intelligence, rather than pathologists’ assessment, to predict risk of dying of prostate cancer. Looking back at tumors and data from 2,807 people diagnosed with prostate cancer, we find that our approach is better at predicting outcomes compared to grading by pathologists alone. These findings suggest that artificial intelligence might help doctors to accurately determine the probable clinical course of people with prostate cancer, which, in turn, will guide treatment. Wulczyn et al. utilise a deep learning-based Gleason grading model to predict prostate cancer-specific mortality in a retrospective cohort of radical prostatectomy patients. Their model enables improved risk stratification compared to pathologists’ grading and demonstrates the potential for computational pathology in the management of prostate cancer.

Exchange of research data and samples in biomedical research has become a common phenomenon, demanding for their effective quality assessment. At the same time, several reports address reproducibility of research, where history of biological samples (acquisition, processing, transportation, storage, and retrieval) and data history (data generation and processing) define their fitness for purpose, and hence their quality. This project aims to develop a comprehensive W3C PROV based provenance information standard intended for the biomedical research domain. The standard is being developed by the working group 5 (“data processing and integration”) of the ISO (International Standardisation Organisation) technical committee 276 “biotechnology”. The outcome of the project will be published in parts as international standards or technical specifications. The poster informs about the goals of the standardisation activity, presents the proposed structure of the standards, briefly describes its current state and outlines its future development and open issues.

The study of visual concept learning methodologies has been developed over the last years, becoming the state-of-the art research that challenges the reasoning capabilities of deep learning methods. In this paper we discuss the evolution of those methods, starting from the captioning approaches that prepared the transition to current cutting-edge visual question answering systems. The emergence of specially designed datasets, distilled from visual complexity, but with properties and divisions that challenge abstract reasoning and generalization capabilities, encourages the development of AI systems that will support them by design. Explainability of the decision making process of AI systems, either built-in or as a by-product of the acquired reasoning capabilities, underpins the understanding of those systems robustness, their underlying logic and their improvement potential.

Extracting hierarchical properties from Whole Slide Images automatically and expanding the possibilities of visualising data from digital pathology will not only drastically improve speed and accuracy of the pathologists’ work but also simplify the necessary pre-processing steps for machine learning tool-chains. The introduced pipeline identifies and converts areas of interest into binary masks and finds groups of areas that share similar locations using k-Means. This grouping is evaluated by the Silhouette Score which serves as a measure of confidence for the separability of clusters. Found objects are compared using structural similarities and HU-Moments. These results are then stored as measures of similarities creating virtual groups of the most similar objects. Finally, the information on similarities combined with further structural parameters are visualised.

Training in the medical field depends on the teaching of theoretical and practical skills. The acquisition of theoretical basics can be usually achieved by studying various documents, while the training of practical skills requires more intensive discussion and a special setup, such as an appropriate laboratory environment or a mentor-mentee connection. Aside from the conditions for transferring and gaining practical skills, teaching methods mostly concentrate on the sharing of explicit knowledge that can be designated and transferred easily.Therefore, the presented work focuses on the tracking of how to approach the diagnosis in pathological examinations and the visualization of any interaction with the specimen by recording microscopical exploration of an experienced pathologist. Those interactions include the full navigation path through a specimen, the panning and magnification of areas of interest, the observation duration as well as the spoken comments. Each maneuver and annotation that is relevant for approaching the diagnosis is documented, processed and visually prepared for trainees/residents to be able to comprehend argumentation via the look through the eyes of an expert.The collected data serve as a base for various medical applications like learning management systems to support education in the medical field, as well as machine learning and artificial intelligence applications in the area of digital pathology.

Histopathology and cytopathology developed for the microscopic examination of tissue samples a specific terminology to describe type and shape of objects and patterns in the composition of nuclei, cells, tissue and anatomical elements. We map such a terminology to Bertin’s visual variables and propose three methods to describe “shape grammar” (1) With a formal, mathematical language, (2) with graphs and (3) by natural language descriptions. Finally, we propose practical applications of shape properties and shape grammar for explainability of AI algorithms in computational pathology.

Deriving interpretable prognostic features from deep-learning-based prognostic histopathology models remains a challenge. In this study, we developed a deep learning system (DLS) for predicting disease-specific survival for stage II and III colorectal cancer using 3652 cases (27,300 slides). When evaluated on two validation datasets containing 1239 cases (9340 slides) and 738 cases (7140 slides), respectively, the DLS achieved a 5-year disease-specific survival AUC of 0.70 (95% CI: 0.66–0.73) and 0.69 (95% CI: 0.64–0.72), and added significant predictive value to a set of nine clinicopathologic features. To interpret the DLS, we explored the ability of different human-interpretable features to explain the variance in DLS scores. We observed that clinicopathologic features such as T-category, N-category, and grade explained a small fraction of the variance in DLS scores (R2 = 18% in both validation sets). Next, we generated human-interpretable histologic features by clustering embeddings from a deep-learning-based image-similarity model and showed that they explained the majority of the variance (R2 of 73–80%). Furthermore, the clustering-derived feature most strongly associated with high DLS scores was also highly prognostic in isolation. With a distinct visual appearance (poorly differentiated tumor cell clusters adjacent to adipose tissue), this feature was identified by annotators with 87.0–95.5% accuracy. Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features that can be reliably identified by people for future validation studies.

Within the last ten years, essential steps have been made to bring artificial intelligence (AI) successfully into the field of pathology. However, most pathologists are still far away from using AI in daily pathology practice. If one leaves the pathology annihilation model, this paper focuses on tasks, which could be solved, and which could be done better by AI, or image-based algorithms, compared to a human expert. In particular, this paper focuses on the needs and demands of surgical pathologists; examples include: Finding small tumour deposits within lymph nodes, detection and grading of cancer, quantification of positive tumour cells in immunohistochemistry, pre-check of Papanicolaou-stained gynaecological cytology in cervical cancer screening, text feature extraction, text interpretation for tumour-coding error prevention and AI in the next-generation virtual autopsy. However, in order to make substantial progress in both fields it is important to intensify the cooperation between medical AI experts and pathologists.

A profound understanding of the pathology processes is an essential precondition for successful introduction of changes and innovations, such as for example AI and Machine Learning, into pathology. Process modeling helps to build up such a profound understanding of the pathology processes among all relevant stakeholders. This paper describes the state of the art in modeling pathology processes and shows on an example how to create a reusable multipurpose process model for the diagnostic pathology process.

BACKGROUND amp; AIMS: Steatohepatitis (SH) and SH-associated hepatocellular carcinoma (HCC) are of considerable clinical significance. SH is morphologically characterized by steatosis, liver cell ballooning, cytoplasmic aggregates termedMallory-Denk bodies (MDBs), inflammation, and fibrosis at late stage. Disturbance of the keratin cytoskeleton and aggregation of keratins (KRTs) are essential for MDB formation. METHODS: Weanalyzed livers of aged Krt18(-/-) mice that spontaneously developed in the majority of cases SH-associated HCC independent of sex. Interestingly, the hepatic lipid profile in Krt18(-/-) mice, which accumulate KRT8, closely resembles human SH lipid profiles and shows that the excess of KRT8 over KRT18 determines the likelihood to develop SH-associated HCC linked with enhanced lipogenesis. RESULTS: Our analysis of the genetic profile of Krt18(-/-) mice with 26 human hepatoma cell lines and with data sets of amp;gt;300 patients with HCC, where Krt18(-/-) gene signatures matched human HCC. Interestingly, a high KRT8/18 ratio is associated with an aggressive HCC phenotype. CONCLUSIONS: We can prove that intermediate filaments and their binding partners are tightly linked to hepatic lipid metabolism and to hepatocarcinogenesis. We suggest KRT8/18 ratio as a novel HCC biomarker for HCC. Funding Agencies|Kurt und Senta Herrmann Stiftung; Austrian Genome Programme GEN-AU; DFG [MA1316-15, MA1316-17, MA1316-19, MA1316-21, INST 268/230-1]; German Research Foundation [STR 1095/4-2]; Else Kroner Exzellenzstipendium; Innovative Medicines Initiative Joint Undertaking from the European Unions Seventh Framework Programme (FP7/2007-2013) [115234]; EFPIA companies

Since pathology is supported by information technology new opportunities and questions have arisen. The digital age enables analyzing histopathological data with artificial intelligence methods to reveal further information and correlations. In this paper existing approaches to visualization of medical decision processes are presented as well as the relevance of explainability in decision making. The first step for implementing decision-paths in systems is to retrace an experienced pathologist’s diagnosis finding process. Recording a route through a landscape composed of human tissue in terms of a roadbook is one possible approach to collect information on how diagnoses are found. Choosing the roadbook metaphor provides a simple schema, that holds basic directions enriched with metadata regarding landmarks on a rally - in the context of pathology such landmarks provide information on the decision finding process.

We investigated the acceptance of virtual health avatars in geriatrics and gerontology, prevention and rehabilitation. We produced simulation videos for several scenarios and evaluated the acceptance with focus groups. The following research objectives were addressed: 1) the assessment of the acceptance of virtual health avatars 2) naming of the reasons for approval and rejection of the application of digital health technologies using the example of health avatars.The results obtained on the basis of the focus group discussions reveal a number of positive perspectives. The research results allow the identification of concerns towards the implementation of virtual health avatars and give hints how to improve interfaces for future data driven medicine.

The combination of ontologies with machine learning (ML) approaches is a hot topic and not yet extensively investigated but having great future potential. This is due to the general fact that both, ontologies and ML, constitute two indispensable technologies for domain-specific knowledge extraction, actively used in knowledge-based systems. Whilst the primary goal of both these approaches are the same, knowledge discovery, little is yet known about how the two sources of knowledge can be successfully integrated. The main data source in digital pathology are whole slide images. For the effective generation of sufficiently large and high-quality training data we need to extract in addition information from medical reports, containing non-standardized text. Since full annotation on pixel level would be impracticably expensive, a practical solution is in weakly-supervised ML. In the project described in this paper we used ontology-guided natural language processing (NLP) for term extraction and a decision tree built with an expert-curated classification system. This demonstrates the practical value of our solution to analyze and structure training data sets for ML and as a tool for the generation of biobank catalogues.