Artificial intelligence and pathology: From principles to practice and future applications in histomorphology and molecular profiling

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.

Application of 3D, 4D, 5D, and 6D bioprinting in cancer research: what does the future look like?

The application of three- and four-dimensional (3D/4D) printing in cancer research represents a significant advancement in understanding and addressing the complexities of cancer biology. 3D/4D materials provide more physiologically relevant environments compared to traditional two-dimensional models, allowing for a more accurate representation of the tumor microenvironment that enables researchers to study tumor progression, drug responses, and interactions with surrounding tissues under conditions similar to in vivo conditions. The dynamic nature of 4D materials introduces the element of time, allowing for the observation of temporal changes in cancer behavior and response to therapeutic interventions. The use of 3D/4D printing in cancer research holds great promise for advancing our understanding of the disease and improving the translation of preclinical findings to clinical applications. Accordingly, this review aims to briefly discuss 3D and 4D printing and their advantages and limitations in the field of cancer. Moreover, new techniques such as 5D/6D printing and artificial intelligence (AI) are also introduced as methods that could be used to overcome the limitations of 3D/4D printing and opened promising ways for the fast and precise diagnosis and treatment of cancer.

The journey towards clinical adoption of MALDI-MS-based imaging proteomics: from current challenges to future expectations

Among the spatial omics techniques available, mass spectrometry imaging (MSI) represents one of the most promising owing to its capability to map the distribution of hundreds of peptides and proteins, as well as other classes of biomolecules, within a complex sample background in a multiplexed and relatively high-throughput manner. In particular, matrix-assisted laser desorption/ionisation (MALDI-MSI) has come to the fore and established itself as the most widely used technique in clinical research. However, the march of this technique towards clinical utility has been hindered by issues related to method reproducibility, appropriate biocomputational tools, and data storage. Notwithstanding these challenges, significant progress has been achieved in recent years regarding multiple facets of the technology and has rendered it more suitable for a possible clinical role. As such, there is now more robust and extensive evidence to suggest that the technology has the potential to support clinical decision-making processes under appropriate circumstances. In this review, we will discuss some of the recent developments that have facilitated this progress and outline some of the more promising clinical proteomics applications which have been developed with a clear goal towards implementation in mind.

[The model transferability of AI in digital pathology : Potential and reality]

OBJECTIVE

Artificial intelligence (AI) holds the potential to make significant advancements in pathology. However, its actual implementation and certification for practical use are currently limited, often due to challenges related to model transferability. In this context, we investigate the factors influencing transferability and present methods aimed at enhancing the utilization of AI algorithms in pathology.

MATERIALS AND METHODS

Various convolutional neural networks (CNNs) and vision transformers (ViTs) were trained using datasets from two institutions, along with the publicly available TCGA-MIBC dataset. These networks conducted predictions in urothelial tissue and intrahepatic cholangiocarcinoma (iCCA). The objective was to illustrate the impact of stain normalization, the influence of various artifacts during both training and testing, as well as the effects of the NoisyEnsemble method.

RESULTS

We were able to demonstrate that stain normalization of slides from different institutions has a significant positive effect on the inter-institutional transferability of CNNs and ViTs (respectively +13% and +10%). In addition, ViTs usually achieve a higher accuracy in the external test (here +1.5%). Similarly, we showcased how artifacts in test data can negatively affect CNN predictions and how incorporating these artifacts during training leads to improvements. Lastly, NoisyEnsembles of CNNs (better than ViTs) were shown to enhance transferability across different tissues and research questions (+7% Bladder, +15% iCCA).

DISCUSSION

It is crucial to be aware of the transferability challenge: achieving good performance during development does not necessarily translate to good performance in real-world applications. The inclusion of existing methods to enhance transferability, such as stain normalization and NoisyEnsemble, and their ongoing refinement, is of importance.

Current challenges and practical aspects of molecular pathology for bone and soft tissue tumors

This review shows the extraordinary change molecular pathology has induced in the classification, diagnosis, and clinical practice of molecular pathologists dealing with sarcomas. We have primarily focused on the practical aspects of molecular studies and the current and mid-term challenges for our subspecialty, ending with ten tips for the next generation of sarcoma molecular pathologists.

The effect of machine learning algorithms in the prediction, and diagnosis of meningitis: A systematic review

Background and Aims

This systematic review aimed to evaluating the effectiveness of machine learning (ML) algorithms for the prediction and diagnosis of meningitis.

Methods

On November 12, 2022, a systematic review was carried out using a keyword search in the reliable scientific databases PubMed, EMBASE, Scopus, and Web of Science. The recommendations of Preferred Reporting for Systematic Reviews and Meta-Analyses (PRISMA) were adhered to. Studies conducted in English that employed ML to predict and identify meningitis were deemed to match the inclusion criteria. The eligibility requirements were used to independently review the titles and abstracts. The whole text was then obtained and independently reviewed in accordance with the eligibility requirements.

Results

After all the research matched the inclusion criteria, a total of 16 studies were added to the systematic review. Studies on the application of ML algorithms in the three categories of disease diagnosis ability (8.16) and disease prediction ability (8.16) (including cases related to identifying patients (50%), risk of death in patients (25%), the consequences of the disease in childhood (12.5%), and its etiology [12.5%]) were placed. Among the ML algorithms used in this study, logistic regression (LR) (4.16, 25%) and multiple logistic regression (MLR) (4.16, 25%) were the most used. All the included studies indicated improvements in the processes of diagnosis, prediction, and disease outbreak with the help of ML algorithms.

Conclusion

The results of the study showed that in all included studies, ML algorithms were an effective approach to facilitate diagnosis, predict consequences for risk classification, and improve resource utilization by predicting the volume of patients or services as well as discovering risk factors. The role of ML algorithms in improving disease diagnosis was more significant than disease prediction and prevalence. Meanwhile, the use of combined methods can optimize differential diagnoses and facilitate the decision-making process for healthcare providers.

ChatGPT as an aid for pathological diagnosis of cancer

Diagnostic workup of cancer patients is highly reliant on the science of pathology using cytopathology, histopathology, and other ancillary techniques like immunohistochemistry and molecular cytogenetics. Data processing and learning by means of artificial intelligence (AI) has become a spearhead for the advancement of medicine, with pathology and laboratory medicine being no exceptions. ChatGPT, an artificial intelligence (AI)-based chatbot, that was recently launched by OpenAI, is currently a talk of the town, and its role in cancer diagnosis is also being explored meticulously. Pathology workflow by integration of digital slides, implementation of advanced algorithms, and computer-aided diagnostic techniques extend the frontiers of the pathologist's view beyond a microscopic slide and enables effective integration, assimilation, and utilization of knowledge that is beyond human limits and boundaries. Despite of it's numerous advantages in the pathological diagnosis of cancer, it comes with several challenges like integration of digital slides with input language parameters, problems of bias, and legal issues which have to be addressed and worked up soon so that we as a pathologists diagnosing malignancies are on the same band wagon and don't miss the train.

Enhancing diagnosis of Hirschsprung's disease using deep learning from histological sections of post pull-through specimens: preliminary results

PURPOSE

Accurate histological diagnosis in Hirschsprung disease (HD) is challenging, due to its complexity and potential for errors. In this study, we present an artificial intelligence (AI)-based method designed to identify ganglionic cells and hypertrophic nerves in HD histology.

METHODS

Formalin-fixed samples were used and an expert pathologist and a surgeon annotated these slides on a web-based platform, identifying ganglionic cells and nerves. Images were partitioned into square sections, augmented through data manipulation techniques and used to develop two distinct U-net models: one for detecting ganglionic cells and normal nerves; the other to recognise hypertrophic nerves.

RESULTS

The study included 108 annotated samples, resulting in 19,600 images after data augmentation and manually segmentation. Subsequently, 17,655 slides without target elements were excluded. The algorithm was trained using 1945 slides (930 for model 1 and 1015 for model 2) with 1556 slides used for training the supervised network and 389 for validation. The accuracy of model 1 was found to be 92.32%, while model 2 achieved an accuracy of 91.5%.

CONCLUSION

The AI-based U-net technique demonstrates robustness in detecting ganglion cells and nerves in HD. The deep learning approach has the potential to standardise and streamline HD diagnosis, benefiting patients and aiding in training of pathologists.

Effects of adding tea tree oil on growth performance, immune function, and intestinal function of broilers

The aim of this study was to investigate the effects of adding tea tree oil (TTO) in the basal diet on growth performance, immune function, and intestinal function in broilers. This study utilized 1,650 one-day-old broilers with good health and similar body weight. Subjects were randomized into 5 groups with 6 replicates each: the control group (CON, basal diet), positive control group (PCG, basal diet + 100 mg/kg oregano oil in diet), low-dose TTO group (TTO-L, 50 mg/kg TTO added in the basal diet), medium-dose TTO group (TTO-M, 100 mg/kg TTO added in the basal diet), and high-dose TTO group (TTO-H, 200 mg/kg TTO added in the basal diet). The whole test period lasted 28 d. The results showed that the broilers fed with TTO supplemented diet had significantly higher body weight and average daily gain (ADG) (P = 0.013), and had a lower feed conversion ratio (F/G) (P = 0.010) throughout the trial period. The index of thymus in TTO-M increased significantly compared to CON (P = 0.015) on d 28. On d 14 and 28, C3, IFN-γ, TNF-α, and IL-2 levels in TTO-L serum were significantly increased (P < 0.001); the 3 test groups supplemented with TTO had significantly higher titers of avian influenza H9 subtype in their serum (P < 0.05). Tea tree oil supplement in the diet also had a positive and significant effect on the intestinal morphology of broilers throughout the experiment (P < 0.05). These results indicate that TTO has the ability to promote broiler growth, regulate immunity, and improve intestinal morphology. The proposed dosage of adding 50 mg/kg in broiler basal diets provides a theoretical basis for its subsequent use in livestock feeds.

Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance

The pathology is decisive for disease diagnosis but relies heavily on experienced pathologists. In recent years, there has been growing interest in the use of artificial intelligence in pathology (AIP) to enhance diagnostic accuracy and efficiency. However, the impressive performance of deep learning-based AIP in laboratory settings often proves challenging to replicate in clinical practice. As the data preparation is important for AIP, the paper has reviewed AIP-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. An in-depth analysis of data preparation methods is conducted, encompassing the acquisition of pathological tissue slides, data cleaning, screening, and subsequent digitization. Expert review, image annotation, dataset division for model training and validation are also discussed. Furthermore, we delve into the reasons behind the challenges in reproducing the high performance of AIP in clinical settings and present effective strategies to enhance AIP's clinical performance. The robustness of AIP depends on a randomized collection of representative disease slides, incorporating rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and sufficient data volume. Digital pathology is fundamental in clinical-grade AIP, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. The key to performance reproducibility lies in having representative data, an adequate amount of labeling, and ensuring consistency across multiple centers. Digital pathology for clinical diagnosis, data standardization and the technique of WSI-based weakly supervised learning will hopefully build clinical-grade AIP.

[Molecular tumor diagnostics as the driving force behind precision oncology]

Molecular pathological diagnostics plays a central role in personalized oncology and requires multidisciplinary teamwork. It is just as relevant for the individual patient who is being treated with an approved therapy method or an individual treatment attempt as it is for prospective clinical studies that require the identification of specific therapeutic target structures or complex biomarkers for study inclusion. It is also of crucial importance for the generation of real-world data, which is becoming increasingly important for drug development. Future developments will be significantly shaped by improvements in scalable molecular diagnostics, in which increasingly complex and multi-layered data sets must be quickly converted into clinically useful information. One focus will be on the development of adaptive diagnostic strategies in order to be able to depict the enormous plasticity of a cancer disease over time.

Applications of artificial intelligence in clinical laboratory genomics

The transition from analog to digital technologies in clinical laboratory genomics is ushering in an era of "big data" in ways that will exceed human capacity to rapidly and reproducibly analyze those data using conventional approaches. Accurately evaluating complex molecular data to facilitate timely diagnosis and management of genomic disorders will require supportive artificial intelligence methods. These are already being introduced into clinical laboratory genomics to identify variants in DNA sequencing data, predict the effects of DNA variants on protein structure and function to inform clinical interpretation of pathogenicity, link phenotype ontologies to genetic variants identified through exome or genome sequencing to help clinicians reach diagnostic answers faster, correlate genomic data with tumor staging and treatment approaches, utilize natural language processing to identify critical published medical literature during analysis of genomic data, and use interactive chatbots to identify individuals who qualify for genetic testing or to provide pre-test and post-test education. With careful and ethical development and validation of artificial intelligence for clinical laboratory genomics, these advances are expected to significantly enhance the abilities of geneticists to translate complex data into clearly synthesized information for clinicians to use in managing the care of their patients at scale.

Novel tools for early diagnosis and precision treatment based on artificial intelligence

Lung cancer has the highest mortality rate among all cancers in the world. Hence, early diagnosis and personalized treatment plans are crucial to improving its 5-year survival rate. Chest computed tomography (CT) serves as an essential tool for lung cancer screening, and pathology images are the gold standard for lung cancer diagnosis. However, medical image evaluation relies on manual labor and suffers from missed diagnosis or misdiagnosis, and physician heterogeneity. The rapid development of artificial intelligence (AI) has brought a whole novel opportunity for medical task processing, demonstrating the potential for clinical application in lung cancer diagnosis and treatment. AI technologies, including machine learning and deep learning, have been deployed extensively for lung nodule detection, benign and malignant classification, and subtype identification based on CT images. Furthermore, AI plays a role in the non-invasive prediction of genetic mutations and molecular status to provide the optimal treatment regimen, and applies to the assessment of therapeutic efficacy and prognosis of lung cancer patients, enabling precision medicine to become a reality. Meanwhile, histology-based AI models assist pathologists in typing, molecular characterization, and prognosis prediction to enhance the efficiency of diagnosis and treatment. However, the leap to extensive clinical application still faces various challenges, such as data sharing, standardized label acquisition, clinical application regulation, and multimodal integration. Nevertheless, AI holds promising potential in the field of lung cancer to improve cancer care.

Artificial intelligence in ovarian cancer histopathology: a systematic review

This study evaluates the quality of published research using artificial intelligence (AI) for ovarian cancer diagnosis or prognosis using histopathology data. A systematic search of PubMed, Scopus, Web of Science, Cochrane CENTRAL, and WHO-ICTRP was conducted up to May 19, 2023. Inclusion criteria required that AI was used for prognostic or diagnostic inferences in human ovarian cancer histopathology images. Risk of bias was assessed using PROBAST. Information about each model was tabulated and summary statistics were reported. The study was registered on PROSPERO (CRD42022334730) and PRISMA 2020 reporting guidelines were followed. Searches identified 1573 records, of which 45 were eligible for inclusion. These studies contained 80 models of interest, including 37 diagnostic models, 22 prognostic models, and 21 other diagnostically relevant models. Common tasks included treatment response prediction (11/80), malignancy status classification (10/80), stain quantification (9/80), and histological subtyping (7/80). Models were developed using 1-1375 histopathology slides from 1-776 ovarian cancer patients. A high or unclear risk of bias was found in all studies, most frequently due to limited analysis and incomplete reporting regarding participant recruitment. Limited research has been conducted on the application of AI to histopathology images for diagnostic or prognostic purposes in ovarian cancer, and none of the models have been demonstrated to be ready for real-world implementation. Key aspects to accelerate clinical translation include transparent and comprehensive reporting of data provenance and modelling approaches, and improved quantitative evaluation using cross-validation and external validations. This work was funded by the Engineering and Physical Sciences Research Council.

The Biomarker Ki-67: Promise, Potential, and Problems in Breast Cancer

Ki-67 is a nuclear protein serendipitously discovered by monoclonal antibody selection in the early 1980s. While it has been applied for decades in the context of breast cancer as a putative prognostic and, more recently, predictive, biomarker, even after all this time there is incomplete agreement as to the validity of the immunohistochemical assays employed for Ki-67 assessment, given possible effects of the disparate methodologies employed and possible confounding preanalytical, analytical, and interpretive variables. In this brief review, the history of Ki-67 and the problems, particularly with the analytical and interpretive variables, are highlighted through a selective review of the published literature. The contributions of the International Ki-67 Breast Cancer Working Group are highlighted, and in particular, the recommendations made by this group are reviewed. The potential of Ki-67 as a biomarker for breast cancer has not yet been fully realized, but an understanding of the power as well as the limitations of the methods of Ki-67 assessment are important if this biomarker can realize its potential.

Artificial Intelligence in the Pathology of Gastric Cancer

Recent advances in artificial intelligence (AI) have provided novel tools for rapid and precise pathologic diagnosis. The introduction of digital pathology has enabled the acquisition of scanned slide images that are essential for the application of AI. The application of AI for improved pathologic diagnosis includes the error-free detection of potentially negligible lesions, such as a minute focus of metastatic tumor cells in lymph nodes, the accurate diagnosis of potentially controversial histologic findings, such as very well-differentiated carcinomas mimicking normal epithelial tissues, and the pathological subtyping of the cancers. Additionally, the utilization of AI algorithms enables the precise decision of the score of immunohistochemical markers for targeted therapies, such as human epidermal growth factor receptor 2 and programmed death-ligand 1. Studies have revealed that AI assistance can reduce the discordance of interpretation between pathologists and more accurately predict clinical outcomes. Several approaches have been employed to develop novel biomarkers from histologic images using AI. Moreover, AI-assisted analysis of the cancer microenvironment showed that the distribution of tumor-infiltrating lymphocytes was related to the response to the immune checkpoint inhibitor therapy, emphasizing its value as a biomarker. As numerous studies have demonstrated the significance of AI-assisted interpretation and biomarker development, the AI-based approach will advance diagnostic pathology.

Diagnostic quality model (DQM): an integrated framework for the assessment of diagnostic quality when using AI/ML

BACKGROUND

Laboratory medicine has reached the era where promises of artificial intelligence and machine learning (AI/ML) seem palpable. Currently, the primary responsibility for risk-benefit assessment in clinical practice resides with the medical director. Unfortunately, there is no tool or concept that enables diagnostic quality assessment for the various potential AI/ML applications. Specifically, we noted that an operational definition of laboratory diagnostic quality - for the specific purpose of assessing AI/ML improvements - is currently missing.

METHODS

A session at the 3rd Strategic Conference of the European Federation of Laboratory Medicine in 2022 on "AI in the Laboratory of the Future" prompted an expert roundtable discussion. Here we present a conceptual diagnostic quality framework for the specific purpose of assessing AI/ML implementations.

RESULTS

The presented framework is termed diagnostic quality model (DQM) and distinguishes AI/ML improvements at the test, procedure, laboratory, or healthcare ecosystem level. The operational definition illustrates the nested relationship among these levels. The model can help to define relevant objectives for implementation and how levels come together to form coherent diagnostics. The affected levels are referred to as scope and we provide a rubric to quantify AI/ML improvements while complying with existing, mandated regulatory standards. We present 4 relevant clinical scenarios including multi-modal diagnostics and compare the model to existing quality management systems.

CONCLUSIONS

A diagnostic quality model is essential to navigate the complexities of clinical AI/ML implementations. The presented diagnostic quality framework can help to specify and communicate the key implications of AI/ML solutions in laboratory diagnostics.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Artificial intelligence aids in development of nanomedicines for cancer management

Over the last decade, the nanomedicine has experienced unprecedented development in diagnosis and management of diseases. A number of nanomedicines have been approved in clinical use, which has demonstrated the potential value of clinical transition of nanotechnology-modified medicines from bench to bedside. The application of artificial intelligence (AI) in development of nanotechnology-based products could transform the healthcare sector by realizing acquisition and analysis of large datasets, and tailoring precision nanomedicines for cancer management. AI-enabled nanotechnology could improve the accuracy of molecular profiling and early diagnosis of patients, and optimize the design pipeline of nanomedicines by tuning the properties of nanomedicines, achieving effective drug synergy, and decreasing the nanotoxicity, thereby, enhancing the targetability, personalized dosing and treatment potency of nanomedicines. Herein, the advances in AI-enabled nanomedicines in cancer management are elaborated and their application in diagnosis, monitoring and therapy as well in precision medicine development is discussed.

An artificial intelligence model for the pathological diagnosis of invasion depth and histologic grade in bladder cancer

BACKGROUND

Accurate pathological diagnosis of invasion depth and histologic grade is key for clinical management in patients with bladder cancer (BCa), but it is labour-intensive, experience-dependent and subject to interobserver variability. Here, we aimed to develop a pathological artificial intelligence diagnostic model (PAIDM) for BCa diagnosis.

METHODS

A total of 854 whole slide images (WSIs) from 692 patients were included and divided into training and validation sets. The PAIDM was developed using the training set based on the deep learning algorithm ScanNet, and the performance was verified at the patch level in validation set 1 and at the WSI level in validation set 2. An independent validation cohort (validation set 3) was employed to compare the PAIDM and pathologists. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value and negative predictive value.

RESULTS

The AUCs of the PAIDM were 0.878 (95% CI 0.875-0.881) at the patch level in validation set 1 and 0.870 (95% CI 0.805-0.923) at the WSI level in validation set 2. In comparing the PAIDM and pathologists, the PAIDM achieved an AUC of 0.847 (95% CI 0.779-0.905), which was non-inferior to the average diagnostic level of pathologists. There was high consistency between the model-predicted and manually annotated areas, improving the PAIDM's interpretability.

CONCLUSIONS

We reported an artificial intelligence-based diagnostic model for BCa that performed well in identifying invasion depth and histologic grade. Importantly, the PAIDM performed admirably in patch-level recognition, with a promising application for transurethral resection specimens.

Artificial intelligence assists precision medicine in cancer treatment

Cancer is a major medical problem worldwide. Due to its high heterogeneity, the use of the same drugs or surgical methods in patients with the same tumor may have different curative effects, leading to the need for more accurate treatment methods for tumors and personalized treatments for patients. The precise treatment of tumors is essential, which renders obtaining an in-depth understanding of the changes that tumors undergo urgent, including changes in their genes, proteins and cancer cell phenotypes, in order to develop targeted treatment strategies for patients. Artificial intelligence (AI) based on big data can extract the hidden patterns, important information, and corresponding knowledge behind the enormous amount of data. For example, the ML and deep learning of subsets of AI can be used to mine the deep-level information in genomics, transcriptomics, proteomics, radiomics, digital pathological images, and other data, which can make clinicians synthetically and comprehensively understand tumors. In addition, AI can find new biomarkers from data to assist tumor screening, detection, diagnosis, treatment and prognosis prediction, so as to providing the best treatment for individual patients and improving their clinical outcomes.

Perspective Toward Machine Learning Implementation in Pediatric Medicine: Mixed Methods Study

Background

Given the costs of machine learning implementation, a systematic approach to prioritizing which models to implement into clinical practice may be valuable.

Objective

The primary objective was to determine the health care attributes respondents at 2 pediatric institutions rate as important when prioritizing machine learning model implementation. The secondary objective was to describe their perspectives on implementation using a qualitative approach.

Methods

In this mixed methods study, we distributed a survey to health system leaders, physicians, and data scientists at 2 pediatric institutions. We asked respondents to rank the following 5 attributes in terms of implementation usefulness: the clinical problem was common, the clinical problem caused substantial morbidity and mortality, risk stratification led to different actions that could reasonably improve patient outcomes, reducing physician workload, and saving money. Important attributes were those ranked as first or second most important. Individual qualitative interviews were conducted with a subsample of respondents.

Results

Among 613 eligible respondents, 275 (44.9%) responded. Qualitative interviews were conducted with 17 respondents. The most common important attributes were risk stratification leading to different actions (205/275, 74.5%) and clinical problem causing substantial morbidity or mortality (177/275, 64.4%). The attributes considered least important were reducing physician workload and saving money. Qualitative interviews consistently prioritized implementations that improved patient outcomes.

Conclusions

Respondents prioritized machine learning model implementation where risk stratification would lead to different actions and clinical problems that caused substantial morbidity and mortality. Implementations that improved patient outcomes were prioritized. These results can help provide a framework for machine learning model implementation.

The Third Joint Meeting on Lung Cancer of the FHU OncoAge (University Côte d'Azur, Nice, France) and the University of Texas MD Anderson Cancer Center (Houston, TX, USA). Understanding New Therapeutic Options and Promising Predictive Biomarkers for Lung Cancer Patients

We are proud and happy to present this Special Issue, a follow-up to the third joint meeting on lung cancer of the FHU OncoAge (University Côte d'Azur, Nice, France) and the University of Texas MD Anderson Cancer Center (Houston, TX, USA), which was held virtually on 4 October 2021 [...].

The state of the art for artificial intelligence in lung digital pathology

Lung diseases carry a significant burden of morbidity and mortality worldwide. The advent of digital pathology (DP) and an increase in computational power have led to the development of artificial intelligence (AI)-based tools that can assist pathologists and pulmonologists in improving clinical workflow and patient management. While previous works have explored the advances in computational approaches for breast, prostate, and head and neck cancers, there has been a growing interest in applying these technologies to lung diseases as well. The application of AI tools on radiology images for better characterization of indeterminate lung nodules, fibrotic lung disease, and lung cancer risk stratification has been well documented. In this article, we discuss methodologies used to build AI tools in lung DP, describing the various hand-crafted and deep learning-based unsupervised feature approaches. Next, we review AI tools across a wide spectrum of lung diseases including cancer, tuberculosis, idiopathic pulmonary fibrosis, and COVID-19. We discuss the utility of novel imaging biomarkers for different types of clinical problems including quantification of biomarkers like PD-L1, lung disease diagnosis, risk stratification, and prediction of response to treatments such as immune checkpoint inhibitors. We also look briefly at some emerging applications of AI tools in lung DP such as multimodal data analysis, 3D pathology, and transplant rejection. Lastly, we discuss the future of DP-based AI tools, describing the challenges with regulatory approval, developing reimbursement models, planning clinical deployment, and addressing AI biases. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

The significance of the fusion partner gene genomic neighborhood analysis in translocation-defined tumors

INTRODUCTION

This study presents a novel molecular parameter potentially co-defining tumor biology-the total tumor suppressor gene (TSG) count at chromosomal loci harboring genes rearranged in fusion-defined tumors. It belongs to the family of molecular parameters created using a black-box approach.

METHOD

It is based on a public curated Texas TSG database. Its data are regrouped based on individual genes loci using another public database (Genecards). The total TSG count for NTRK (NTRK1; OMIM: 191315; NTRK2; OMIM: 600456; NTRK3; OMIM: 191316), NRG1 (OMIM: 142445), and RET (OMIM: 164761) rearranged tumors in patients treated with a theranostic approach is calculated using the results of recently published studies.

RESULTS

Altogether 138 loci containing at least three TSGs are identified. These include 21 "extremely hot" spots, with 10 to 28 TSGs mapping to a given locus. However, the study falls short of finding a correlation between tumor regression or patient survival and the TSG count owing to a low number of cases meeting the study criteria.

CONCLUSION

The total TSG count alone cannot predict the biology of translocation-defined tumors. The addition of other parameters, including microsatellite instability (MSI), tumor mutation burden (TMB), homologous recombination repair deficiency (HRD), and copy number heterogeneity (CNH), might be helpful. Thus a multi-modal data integration is advocated. We believe that large scale studies should evaluate the significance and value of the total TSG count.

[Artificial intelligence: a solution for the lack of pathologists?]

Given the rapid developments, there is no doubt that artificial intelligence (AI) will substantially impact pathological diagnostics. However, it remains an open question if AI will primarily be another diagnostic tool, such as immunohistochemistry, or if AI will also be able to replace human expertise. Most current studies on AI in histopathology deal with relatively simple diagnostic problems and are not yet capable of coping with the complexity of routine diagnostics. While some methods in molecular pathology would already be unthinkable without AI, it remains to be shown how AI will also be able to help with difficult histomorphological differential diagnoses in the future.

[Histopathological evaluation of nonalcoholic fatty liver disease : Automated evaluation of liver biopsies]

Nonalcoholic fatty liver disease (NAFLD) is one of the most frequent chronic liver diseases with a rising incidence in industrial countries. This is accompanied by an increased prevalence for NAFLD-associated liver cirrhosis and an increased risk for developing hepatocellular carcinoma. The current gold standard in the diagnostics is a liver biopsy. The histopathological evaluation is performed through semiquantitative scoring. To optimize the standardization and quantification of the existing scoring systems, in the coming years procedures with artificial intelligence, such as deep learning models could be used. Fields of application could be the supplementation of conventional histopathological diagnostics, the identification of new predictive parameters for estimating the prognosis and the prediction of a possible response to treatment.

A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer

Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive’s unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists’ annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into ‘low risk’ (benign, inflammation) and ‘high risk’ (dysplasia, malignancy) categories. We further trained the composite AI-model’s performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.

Fusion-positive non-small cell lung carcinoma: Biological principles, clinical practice, and diagnostic implications

Based on superior efficacy and tolerability, targeted therapy is currently preferred over chemotherapy and/or immunotherapy for actionable gene fusions that occur in late-stage non-small cell lung carcinoma (NSCLC). Consequently, current clinical practice guidelines mandate testing for ALK, ROS1, NTRK, and RET gene fusions in all patients with newly diagnosed advanced non-squamous NSCLC (NS-NSCLC). Gene fusions can be detected using different approaches, but today RNA next-generation sequencing (NGS) or combined DNA/RNA NGS is the method of choice. The discovery of other gene fusions (involving, eg, NRG1, NUT, FGFR1, FGFR2, MET, BRAF, EGFR, SMARC fusions) and their partners has increased progressively in recent years, leading to the development of new and promising therapies and mandating the development and implementation of comprehensive detection methods. The purpose of this review is to focus on recent data concerning the main gene fusions identified in NSCLC, followed by the discussion of major challenges in this domain.

Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation

In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic workup for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models (random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), support vector machine (SVM)) that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF=83%, NN=88%, LOGREG=SVM=89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic workup of HNSC-CUP. This article is protected by copyright. All rights reserved.

Ethics of AI in Pathology: Current Paradigms and Emerging Issues

Deep learning has rapidly advanced artificial intelligence (AI) and algorithmic decision-making (ADM) paradigms, affecting many traditional fields of medicine, including pathology, which is a heavily data-centric specialty of medicine. The structured nature of pathology data repositories makes it highly attractive to AI researchers to train deep learning models to improve health care delivery. Additionally, there are enormous financial incentives driving adoption of AI and ADM due to promise of increased efficiency of the health care delivery process. AI, if used unethically, may exacerbate existing inequities of health care, especially if not implemented correctly. There is an urgent need to harness the vast power of AI in an ethically and morally justifiable manner. This review explores the key issues involving AI ethics in pathology. Issues related to ethical design of pathology AI studies and the potential risks associated with implementation of AI and ADM within the pathology workflow are discussed. Three key foundational principles of ethical AI: transparency, accountability, and governance, are described in the context of pathology. The future practice of pathology must be guided by these principles. Pathologists should be aware of the potential of AI to deliver superlative health care and the ethical pitfalls associated with it. Finally, pathologists must have a seat at the table to drive future implementation of ethical AI in the practice of pathology.

EGFR Status Assessment for Better Care of Early Stage Non-Small Cell Lung Carcinoma: What Is Changing in the Daily Practice of Pathologists?

The recent emergence of novel neoadjuvant and/or adjuvant therapies for early stage (I-IIIA) non-small cell lung carcinoma (NSCLC), mainly tyrosine kinase inhibitors (TKIs) targeting EGFR mutations and immunotherapy or chemo-immunotherapy, has suddenly required the evaluation of biomarkers predictive of the efficacy of different treatments in these patients. Currently, the choice of one or another of these treatments mainly depends on the results of immunohistochemistry for PD-L1 and of the status of EGFR and ALK. This new development has led to the setup of different analyses for clinical and molecular pathology laboratories, which have had to rapidly integrate a number of new challenges into daily practice and to establish new organization for decision making. This review outlines the impact of the management of biological samples in laboratories and discusses perspectives for pathologists within the framework of EGFR TKIs in early stage NSCLC.

Correlation of manual semi-quantitative and automated quantitative Ki-67 proliferative index with OncotypeDXTM recurrence score in invasive breast carcinoma

BACKGROUND

Ki-67 immunohistochemistry (IHC) staining is a widely used cancer proliferation assay; however, its limitations could be improved with automated scoring. The OncotypeDXTM Recurrence Score (ORS), which primarily evaluates cancer proliferation genes, is a prognostic indicator for breast cancer chemotherapy response; however, it is more expensive and slower than Ki-67.

OBJECTIVE

To compare manual Ki-67 (mKi-67) with automated Ki-67 (aKi-67) algorithm results based on manually selected Ki-67 "hot spots" in breast cancer, and correlate both with ORS.

METHODS

105 invasive breast carcinoma cases from 100 patients at our institution (2011-2013) with available ORS were evaluated. Concordance was assessed via Cohen's Kappa (κ).

RESULTS

57/105 cases showed agreement between mKi-67 and aKi-67 (κ 0.31, 95% CI 0.18-0.45), with 41 cases overestimated by aKi-67. Concordance was higher when estimated on the same image (κ 0.53, 95% CI 0.37-0.69). Concordance between mKi-67 score and ORS was fair (κ 0.27, 95% CI 0.11-0.42), and concordance between aKi-67 and ORS was poor (κ 0.10, 95% CI -0.03-0.23).

CONCLUSIONS

These results highlight the limits of Ki-67 algorithms that use manual "hot spot" selection. Due to suboptimal concordance, Ki-67 is likely most useful as a complement to, rather than a surrogate for ORS, regardless of scoring method.