Artificial intelligence-based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients

SOHO State of the Art Updates and Next Questions | Diagnosis, Outcomes, and Management of Prefibrotic Myelofibrosis

Prefibrotic primary myelofibrosis (prefibrotic PMF) is a myeloproliferative neoplasm with distinct characteristics comprising histopathological and clinico-biological parameters. It is classified as a subtype of primary myelofibrosis. In clinical practice, it is essential to correctly distinguish prefibrotic PMF from essential thrombocythemia especially but also overt PMF besides other myeloid neoplasms. Risk stratification and survival outcomes for prefibrotic PMF are worse than that of ET but better than that of overt PMF. Rates of progression to overt PMF and blast phase disease are also higher for prefibrotic PMF than ET. In this review we first discuss the historical context to the evolution of prefibrotic PMF as an entity, its presenting features and diagnostic criteria. We emphasize the differences between prefibrotic PMF, ET, and overt PMF with regards to presenting features and disease outcomes including thrombohemorrhagic events and progression to fibrotic and blast phase disease. Next, we discuss the risk stratification models and contextualize these in the setting of clinical management. We share our view of personalizing treatment to address unique patient needs in the context of currently available management options. Lastly, we discuss areas of critical need in clinical research and speculate on the possibility of future disease course modifying therapies in prefibrotic PMF.

Prediction of inhibitor development in previously untreated and minimally treated children with severe and moderately severe hemophilia A using a machine-learning network

BACKGROUND

Prediction of inhibitor development in patients with hemophilia A (HA) remains a challenge.

OBJECTIVES

To construct a predictive model for inhibitor development in HA using a network of clinical variables and biomarkers based on the individual similarity network.

METHODS

Previously untreated and minimally treated children with severe/moderately severe HA, participants of the HEMFIL Cohort Study, were followed up until reaching 75 exposure days (EDs) without inhibitor (INH-) or upon inhibitor development (INH+). Clinical data and biological samples were collected before the start of factor (F)VIII replacement (T0). A predictive model (HemfilNET) was built to compare the networks and potential global topological differences between INH- and INH+ at T0, considering the network robustness. For validation, the "leave-one-out" cross-validation technique was employed. Accuracy, precision, recall, and F1-score were used as evaluation metrics for the machine-learning model.

RESULTS

We included 95 children with HA (CHA), of whom 31 (33%) developed inhibitors. The algorithm, featuring 37 variables, identified distinct patterns of networks at T0 for INH+ and INH-. The accuracy of the model was 74.2% for CHA INH+ and 98.4% for INH-. By focusing the analysis on CHA with high-risk F8 mutations for inhibitor development, the accuracy in identifying CHA INH+ increased to 82.1%.

CONCLUSION

Our machine-learning algorithm demonstrated an overall accuracy of 90.5% for predicting inhibitor development in CHA, which further improved when restricting the analysis to CHA with a high-risk F8 genotype. However, our model requires validation in other cohorts. Yet, missing data for some variables hindered more precise predictions.

Detection of circulating plasma cells in peripheral blood using deep learning-based morphological analysis

BACKGROUND

The presence of circulating plasma cells (CPCs) is an important laboratory indicator for the diagnosis, staging, risk stratification, and progression monitoring of multiple myeloma (MM). Early detection of CPCs in the peripheral blood (PB) followed by timely interventions can significantly improve MM prognosis and delay its progression. Although the conventional cell morphology examination remains the predominant method for CPC detection because of accessibility, its sensitivity and reproducibility are limited by technician expertise and cell quantity constraints. This study aims to develop an artificial intelligence (AI)-based automated system for a more sensitive and efficient CPC morphology detection.

METHODS

A total of 137 bone marrow smears and 72 PB smears from patients with at Zhongshan Hospital, Fudan University, were retrospectively reviewed. Using an AI-powered digital pathology platform, Morphogo, 305,019 cell images were collected for training. Morphogo's efficacy in CPC detection was evaluated with additional 184 PB smears (94 from patients with MM and 90 from those with other hematological malignancies) and compared with manual microscopy.

RESULTS

Morphogo achieved 99.64% accuracy, 89.03% sensitivity, and 99.68% specificity in classifying CPCs. At a 0.60 threshold, Morphogo achieved a sensitivity of 96.15%, which was approximately twice that of manual microscopy, with a specificity of 78.03%. Patients with CPCs detected by AI scanning had a significantly shorter median progression-free survival compared with those without CPC detection (18 months vs. 34 months, p< .01).

CONCLUSIONS

Morphogo is a highly sensitive system for the automated detection of CPCs, with potential applications in initial screening, prognosis prediction, and posttreatment monitoring for MM patients.

PLAIN LANGUAGE SUMMARY

Diagnosing and monitoring multiple myeloma (MM), a type of blood cancer, requires identifying and quantifying specific cells called circulating plasma cells (CPCs) in the blood. The conventional method for detecting CPCs is manual microscopic examination, which is time-consuming and lacks sensitivity. This study introduces a highly sensitive CPC detection method using an artificial intelligence-based system, Morphogo. It demonstrated remarkable sensitivity and accuracy, surpassing conventional microscopy. This advanced approach suggests that early and accurate CPC detection is achievable by morphology examination, making efficient CPC screening more accessible for patients with MM. This innovative system has the potential to be used in the diagnosis and risk assessment of MM.

Changes in bone marrow fibrosis during momelotinib or ruxolitinib therapy do not correlate with efficacy outcomes in patients with myelofibrosis

Bone marrow fibrosis (BMF) is a pathological feature of myelofibrosis, with higher grades associated with poor prognosis. Limited data exist on the association between outcomes and BMF changes. We present BMF data from Janus kinase (JAK) inhibitor-naive patients from SIMPLIFY-1 (NCT01969838), a double-blind, randomized, phase 3 study of momelotinib vs ruxolitinib. Baseline and week 24 bone marrow biopsies were graded from 0 to 3 as per World Health Organization criteria. Other assessments included Total Symptom Score, spleen volume, transfusion independence status, and hemoglobin levels. Paired samples were available from 144 and 160 patients randomized to momelotinib and ruxolitinib. With momelotinib and ruxolitinib, transfusion independence was achieved by 87% and 44% of patients with BMF improvement of ≥1 grade and 76% and 56% of those with stable/worsening BMF; there was no association between BMF changes and transfusion independence for either arm (momelotinib, p = .350; ruxolitinib, p = .096). Regardless of BMF changes, hemoglobin levels also generally increased on momelotinib but decreased on ruxolitinib. In addition, no associations between BMF changes and spleen (momelotinib, p = .126; ruxolitinib, p = .407)/symptom (momelotinib, p = .617; ruxolitinib, p = .833) outcomes were noted, and no improvement in overall survival was observed with ≥1-grade BMF improvement (momelotinib, p = .395; ruxolitinib, p = .407). These data suggest that the anemia benefit of momelotinib is not linked to BMF changes, and question the use of BMF assessment as a surrogate marker for clinical benefit with JAK inhibitors.

Quantitative interpretation of bone marrow biopsies in MPN-What's the point in a molecular age?

The diagnosis of myeloproliferative neoplasms (MPN) requires the integration of clinical, morphological, genetic and immunophenotypic findings. Recently, there has been a transformation in our understanding of the cellular and molecular mechanisms underlying disease initiation and progression in MPN. This has been accompanied by the widespread application of high-resolution quantitative molecular techniques. By contrast, microscopic interpretation of bone marrow biopsies by haematologists/haematopathologists remains subjective and qualitative. However, advances in tissue image analysis and artificial intelligence (AI) promise to transform haematopathology. Pioneering studies in bone marrow image analysis offer to refine our understanding of the boundaries between reactive samples and MPN subtypes and better capture the morphological correlates of high-risk disease. They also demonstrate potential to improve the evaluation of current and novel therapeutics for MPN and other blood cancers. With increased therapeutic targeting of diverse molecular, cellular and extra-cellular components of the marrow, these approaches can address the unmet need for improved objective and quantitative measures of disease modification in the context of clinical trials. This review focuses on the state-of-the-art in image analysis/AI of bone marrow tissue, with an emphasis on its potential to complement and inform future clinical studies and research in MPN.

Histopathology imagery dataset of Ph-negative myeloproliferative neoplasm

Tumorous cancer has been a widely known and well-studied medical phenomenon; however, rare diseases like Myeloproliferative Neoplasm (MPN) have received less attention, leading to delayed diagnosis. Despite the availability of advanced technology in diagnostic tools that can boost the procedure, the morphological assessment of bone marrow trephine (BMT) images remains critical to confirm and differentiate MPN subtypes. This paper reports a histopathological imagery dataset that was created to focus on the most common MPN from the Philadelphia Chromosome (Ph)-negative type, namely Essential Thrombocythemia (ET), Polycythemia Vera (PV), and Primary Myelofibrosis (MF). The dataset consisted of 300 BMT images that can be used to enable computer vision applications, such as image segmentation, disease classification, and object recognition, in assisting the classification of the MPN disease. Ethical approval was obtained from the Ministry of Health, Malaysia and the bone marrow trephine images were captured using a digital microscope from the Olympus model (BX41 Dual head microscope) with x10, x20, and x40 lens types. The development of comprehensive tools deployed from this dataset can assist medical practitioners in diagnosing diseases, thus overcoming the current challenges.

Bio-inspired microfluidics: A review

Biomicrofluidics, a subdomain of microfluidics, has been inspired by several ideas from nature. However, while the basic inspiration for the same may be drawn from the living world, the translation of all relevant essential functionalities to an artificially engineered framework does not remain trivial. Here, we review the recent progress in bio-inspired microfluidic systems via harnessing the integration of experimental and simulation tools delving into the interface of engineering and biology. Development of "on-chip" technologies as well as their multifarious applications is subsequently discussed, accompanying the relevant advancements in materials and fabrication technology. Pointers toward new directions in research, including an amalgamated fusion of data-driven modeling (such as artificial intelligence and machine learning) and physics-based paradigm, to come up with a human physiological replica on a synthetic bio-chip with due accounting of personalized features, are suggested. These are likely to facilitate physiologically replicating disease modeling on an artificially engineered biochip as well as advance drug development and screening in an expedited route with the minimization of animal and human trials.

Cell projection plots: A novel visualization of bone marrow aspirate cytology

Deep models for cell detection have demonstrated utility in bone marrow cytology, showing impressive results in terms of accuracy and computational efficiency. However, these models have yet to be implemented in the clinical diagnostic workflow. Additionally, the metrics used to evaluate cell detection models are not necessarily aligned with clinical goals and targets. In order to address these issues, we introduce novel, automatically generated visual summaries of bone marrow aspirate specimens called cell projection plots (CPPs). Encompassing relevant biological patterns such as neutrophil maturation, CPPs provide a compact summary of bone marrow aspirate cytology. To gauge clinical relevance, CPPs were inspected by 3 hematopathologists, who decided whether corresponding diagnostic synopses matched with generated CPPs. Pathologists were able to match CPPs to the correct synopsis with a matching degree of 85%. Our finding suggests CPPs can represent clinically relevant information from bone marrow aspirate specimens and may be used to efficiently summarize bone marrow cytology to pathologists. CPPs could be a step toward human-centered implementation of artificial intelligence (AI) in hematopathology, and a basis for a diagnostic-support tool for digital pathology workflows.

Revisiting Circulating Extracellular Matrix Fragments as Disease Markers in Myelofibrosis and Related Neoplasms

Philadelphia chromosome-negative chronic myeloproliferative neoplasms (MPNs) arise due to acquired somatic driver mutations in stem cells and develop over 10-30 years from the earliest cancer stages (essential thrombocythemia, polycythemia vera) towards the advanced myelofibrosis stage with bone marrow failure. The JAK2V617F mutation is the most prevalent driver mutation. Chronic inflammation is considered to be a major pathogenetic player, both as a trigger of MPN development and as a driver of disease progression. Chronic inflammation in MPNs is characterized by persistent connective tissue remodeling, which leads to organ dysfunction and ultimately, organ failure, due to excessive accumulation of extracellular matrix (ECM). Considering that MPNs are acquired clonal stem cell diseases developing in an inflammatory microenvironment in which the hematopoietic cell populations are progressively replaced by stromal proliferation-"a wound that never heals"-we herein aim to provide a comprehensive review of previous promising research in the field of circulating ECM fragments in the diagnosis, treatment and monitoring of MPNs. We address the rationales and highlight new perspectives for the use of circulating ECM protein fragments as biologically plausible, noninvasive disease markers in the management of MPNs.

Molecular Studies for the Early Detection of Philadelphia-Negative Myeloproliferative Neoplasms

JAK2 V617F is the predominant driver mutation in patients with Philadelphia-negative myeloproliferative neoplasms (MPN). JAK2 mutations are also frequent in clonal hematopoiesis of indeterminate potential (CHIP) in otherwise "healthy" individuals. However, the period between mutation acquisition and MPN diagnosis (known as latency) varies widely between individuals, with JAK2 mutations detectable several decades before diagnosis and even from birth in some individuals. Here, we will review the current evidence on the biological factors, such as additional mutations and chronic inflammation, which influence clonal expansion and may determine why some JAK2-mutated individuals will progress to an overt neoplasm during their lifetime while others will not. We will also introduce several germline variants that predispose individuals to CHIP (as well as MPN) identified from genome-wide association studies. Finally, we will explore possible mutation screening or interventions that could help to minimize MPN-associated cardiovascular complications or even delay malignant progression.

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

Applied machine learning in hematopathology

An increasing number of machine learning applications are being developed and applied to digital pathology, including hematopathology. The goal of these modern computerized tools is often to support diagnostic workflows by extracting and summarizing information from multiple data sources, including digital images of human tissue. Hematopathology is inherently multimodal and can serve as an ideal case study for machine learning applications. However, hematopathology also poses unique challenges compared to other pathology subspecialities when applying machine learning approaches. By modeling the pathologist workflow and thinking process, machine learning algorithms may be designed to address practical and tangible problems in hematopathology. In this article, we discuss the current trends in machine learning in hematopathology. We review currently available machine learning enabled medical devices supporting hematopathology workflows. We then explore current machine learning research trends of the field with a focus on bone marrow cytology and histopathology, and how adoption of new machine learning tools may be enabled through the transition to digital pathology.

Myelofibrosis

The clinical phenotype of primary and post-polycythemia vera and postessential thrombocythemia myelofibrosis (MF) is dominated by splenomegaly, symptomatology, a variety of blood cell alterations, and a tendency to develop vascular complications and blast phase. Diagnosis requires assessing complete cell blood counts, bone marrow morphology, deep genetic evaluations, and disease history. Driver molecular events consist of JAK2V617F, CALR, and MPL mutations, whereas about 8% to 10% of MF are "triple-negative." Additional myeloid-gene variants are described in roughly 80% of patients. Currently available clinical-based and integrated clinical/molecular-based scoring systems predict the survival of patients with MF and are applied for conventional treatment decision-making, indication to stem cell transplant (SCT) and allocation in clinical trials. Standard treatment consists of anemia-oriented therapies, hydroxyurea, and JAK inhibitors such as ruxolitinib, fedratinib, and pacritinib. Overall, spleen volume reduction of 35% or greater at week 24 can be achieved by 42% of ruxolitinib-, 47% of fedratinib-, 19% of pacritinib-, and 27% of momelotinib-treated patients. Now, it is time to move towards new paradigms for evaluating efficacy like disease modification, that we intend as a robust and unequivocal effect on disease biology and/or on patient survival. The growing number of clinical trials potentially pave the way for new strategies in patients with MF. Translational studies of some molecules showed an early effect on bone marrow fibrosis and on variant allele frequencies of myeloid genes. SCT is still the only curative option, however, it is associated with relevant challenges. This review focuses on the diagnosis, prognostication, and treatment of MF.

Cytological Diagnosis of Classic Myeloproliferative Neoplasms at the Age of Molecular Biology

Myeloproliferative neoplasms (MPN) are clonal hematopoietic stem cell-derived disorders characterized by uncontrolled proliferation of differentiated myeloid cells. Two main groups of MPN, BCR::ABL1-positive (Chronic Myeloid Leukemia) and BCR::ABL1-negative (Polycythemia Vera, Essential Thrombocytosis, Primary Myelofibrosis) are distinguished. For many years, cytomorphologic and histologic features were the only proof of MPN and attempted to distinguish the different entities of the subgroup BCR::ABL1-negative MPN. World Health Organization (WHO) classification of myeloid neoplasms evolves over the years and increasingly considers molecular abnormalities to prove the clonal hematopoiesis. In addition to morphological clues, the detection of JAK2, MPL and CALR mutations are considered driver events belonging to the major diagnostic criteria of BCR::ABL1-negative MPN. This highlights the preponderant place of molecular features in the MPN diagnosis. Moreover, the advent of next-generation sequencing (NGS) allowed the identification of additional somatic mutations involved in clonal hematopoiesis and playing a role in the prognosis of MPN. Nowadays, careful cytomorphology and molecular biology are inseparable and complementary to provide a specific diagnosis and to permit the best follow-up of these diseases.

Applications of Artificial Intelligence in Philadelphia-Negative Myeloproliferative Neoplasms

Philadelphia-negative (Ph-) myeloproliferative neoplasms (MPNs) are a group of hematopoietic malignancies identified by clonal proliferation of blood cell lineages and encompasses polycythemia vera (PV), essential thrombocythemia (ET), and primary myelofibrosis (PMF). The clinical and laboratory features of Philadelphia-negative MPNs are similar, making them difficult to diagnose, especially in the preliminary stages. Because treatment goals and progression risk differ amongst MPNs, accurate classification and prognostication are critical for optimal management. Artificial intelligence (AI) and machine learning (ML) algorithms provide a plethora of possible tools to clinicians in general, and particularly in the field of malignant hematology, to better improve diagnosis, prognosis, therapy planning, and fundamental knowledge. In this review, we summarize the literature discussing the application of AI and ML algorithms in patients with diagnosed or suspected Philadelphia-negative MPNs. A literature search was conducted on PubMed/MEDLINE, Embase, Scopus, and Web of Science databases and yielded 125 studies, out of which 17 studies were included after screening. The included studies demonstrated the potential for the practical use of ML and AI in the diagnosis, prognosis, and genomic landscaping of patients with Philadelphia-negative MPNs.

Myelofibrosis-type megakaryocyte dysplasia (MTMD) as a distinct category of BCR::ABL-negative myeloproliferative neoplasms. Challenges and perspectives

In this Perspective, we discuss criteria for defining a new disease entity or variant of a recognized disease or disorder. We do so in the context of the current topography of the BCR::ABL-negative myeloproliferative neoplasms (MPNs) where two new variants are reported: clonal megakaryocyte dysplasia with normal blood values (CMD-NBV) and clonal megakaryocyte dysplasia with isolated thrombocytosis (CMD-IT). The cardinal feature of these variants is bone marrow megakaryocyte hyperplasia and atypia corresponding the WHO histological criteria for primary myelofibrosis (myelofibrosis-type megakaryocyte dysplasia-MTMD). Persons with these new variants have a different disease course and features from others in the MPN domain. In a broader context we suggest myelofibrosis-type megakaryocyte dysplasia defines a spectrum of related MPN variants including CMD-NBV, CMD-IT, pre-fibrotic myelofibrosis and overt myelofibrosis, which differ from polycythemia vera and essential thrombocythemia. Our proposal needs external validation and we stress the need for a consensus definition of the megakaryocyte dysplasia which is the hallmark of these disorders.

Artificial Intelligence in Bone Marrow Histological Diagnostics: Potential Applications and Challenges

The expanding digitalization of routine diagnostic histological slides holds a potential to apply artificial intelligence (AI) to pathology, including bone marrow (BM) histology. In this perspective, we describe potential tasks in diagnostics that can be supported, investigations that can be guided, and questions that can be answered by the future application of AI on whole-slide images of BM biopsies. These range from characterization of cell lineages and quantification of cells and stromal structures to disease prediction. First glimpses show an exciting potential to detect subtle phenotypic changes with AI that are due to specific genotypes. The discussion is illustrated by examples of current AI research using BM biopsy slides. In addition, we briefly discuss current challenges for implementation of AI-supported diagnostics.

Continuous Indexing of Fibrosis (CIF): improving the assessment and classification of MPN patients

The grading of fibrosis in myeloproliferative neoplasms (MPN) is an important component of disease classification, prognostication and monitoring. However, current fibrosis grading systems are only semi-quantitative and fail to fully capture sample heterogeneity. To improve the quantitation of reticulin fibrosis, we developed a machine learning approach using bone marrow trephine (BMT) samples (n = 107) from patients diagnosed with MPN or a reactive marrow. The resulting Continuous Indexing of Fibrosis (CIF) enhances the detection and monitoring of fibrosis within BMTs, and aids MPN subtyping. When combined with megakaryocyte feature analysis, CIF discriminates between the frequently challenging differential diagnosis of essential thrombocythemia (ET) and pre-fibrotic myelofibrosis with high predictive accuracy [area under the curve = 0.94]. CIF also shows promise in the identification of MPN patients at risk of disease progression; analysis of samples from 35 patients diagnosed with ET and enrolled in the Primary Thrombocythemia-1 trial identified features predictive of post-ET myelofibrosis (area under the curve = 0.77). In addition to these clinical applications, automated analysis of fibrosis has clear potential to further refine disease classification boundaries and inform future studies of the micro-environmental factors driving disease initiation and progression in MPN and other stem cell disorders.

Single-cell methods in myeloproliferative neoplasms: old questions, new technologies

Myeloproliferative neoplasms (MPN) are a group of clonal stem cell-derived hematopoietic malignancies driven by aberrant Janus kinase-signal transducer and activator of transcription proteins (JAK/STAT) signaling. Although these are genetically simple diseases, MPNs are phenotypically heterogeneous, reflecting underlying intratumoral heterogeneity driven by the interplay of genetic and nongenetic factors. Their evolution is determined by factors that enable certain cellular subsets to outcompete others. Therefore, techniques that resolve cellular heterogeneity at the single-cell level are ideally placed to provide new insights into MPN biology. With these insights comes the potential to uncover new approaches to predict the clinical course and treat these cancers, ultimately improving outcomes for patients. MPNs present a particularly tractable model of cancer evolution, because most patients present in an early disease phase and only a small proportion progress to aggressive disease. Therefore, it is not surprising that many groundbreaking technological advances in single-cell omics have been pioneered by their application in MPNs. In this review article, we explore how single-cell approaches have provided transformative insights into MPN disease biology, which are broadly applicable across human cancers, and discuss how these studies might be swiftly translated into clinical pathways and may eventually underpin precision medicine.

The Application of Morphogo in the Detection of Megakaryocytes from Bone Marrow Digital Images with Convolutional Neural Networks

The evaluation of megakaryocytes is an important part of the work up on bone marrow smear examination. It has significance in the differential diagnosis, therapeutic efficacy assessment, and predication of prognosis of many hematologic diseases. The process of manual identification of megakaryocytes are tedious and lack of reproducibility; therefore, a reliable method of automated megakaryocytic identification is urgently needed. Three hundred and thirty-three bone marrow aspirate smears were digitized by Morphogo system. Pathologists annotated megakaryocytes on the digital images of marrow smears are applied to construct a large dataset for testing the system's predictive performance. Subsequently, we obtained megakaryocyte count and classification for each sample by different methods (system-automated analysis, system-assisted analysis, and microscopic examination) to study the correlation between different counting and classification methods. Morphogo system localized cells likely to be megakaryocytes on digital smears, which were later annotated by pathologists and the system, respectively. The system showed outstanding performance in identifying megakaryocytes in bone marrow smears with high sensitivity (96.57%) and specificity (89.71%). The overall correlation between the different methods was confirmed the high consistency (r ≥ 0.7218, R² ≥ 0.5211) with microscopic examination in classifying megakaryocytes. Morphogo system was proved as a reliable screen tool for analyzing megakaryocytes. The application of Morphogo system shows promises to advance the automation and standardization of bone marrow smear examination.

MarrowQuant 2.0: A Digital Pathology Workflow Assisting Bone Marrow Evaluation in Experimental and Clinical Hematology

Bone marrow (BM) cellularity assessment is a crucial step in the evaluation of BM trephine biopsies for hematologic and nonhematologic disorders. Clinical assessment is based on a semiquantitative visual estimation of the hematopoietic and adipocytic components by hematopathologists, which does not provide quantitative information on other stromal compartments. In this study, we developed and validated MarrowQuant 2.0, an efficient, user-friendly digital hematopathology workflow integrated within QuPath software, which serves as BM quantifier for 5 mutually exclusive compartments (bone, hematopoietic, adipocytic, and interstitial/microvasculature areas and other) and derives the cellularity of human BM trephine biopsies. Instance segmentation of individual adipocytes is realized through the adaptation of the machine-learning-based algorithm StarDist. We calculated BM compartments and adipocyte size distributions of hematoxylin and eosin images obtained from 250 bone specimens, from control subjects and patients with acute myeloid leukemia or myelodysplastic syndrome, at diagnosis and follow-up, and measured the agreement of cellularity estimates by MarrowQuant 2.0 against visual scores from 4 hematopathologists. The algorithm was capable of robust BM compartment segmentation with an average mask accuracy of 86%, maximal for bone (99%), hematopoietic (92%), and adipocyte (98%) areas. MarrowQuant 2.0 cellularity score and hematopathologist estimations were highly correlated (R² = 0.92-0.98, intraclass correlation coefficient [ICC] = 0.98; interobserver ICC = 0.96). BM compartment segmentation quantitatively confirmed the reciprocity of the hematopoietic and adipocytic compartments. MarrowQuant 2.0 performance was additionally tested for cellularity assessment of specimens prospectively collected from clinical routine diagnosis. After special consideration for the choice of the cellularity equation in specimens with expanded stroma, performance was similar in this setting (R² = 0.86, n = 42). Thus, we conclude that these validation experiments establish MarrowQuant 2.0 as a reliable tool for BM cellularity assessment. We expect this workflow will serve as a clinical research tool to explore novel biomarkers related to BM stromal components and may contribute to further validation of future digitalized diagnostic hematopathology workstreams.

Deep learning application of the discrimination of bone marrow aspiration cells in patients with myelodysplastic syndromes

Myelodysplastic syndromes (MDS) are a group of hematologic neoplasms accompanied by dysplasia of the bone marrow hematopoietic cells with cytopenia. Detecting dysplasia is important in the diagnosis of MDS, but it takes considerable time and effort. Also, since the assessment of dysplasia is subjective and difficult to quantify, a more efficient tool is needed for quality control and standardization of bone marrow aspiration smear interpretation. In this study, we developed and evaluated an algorithm to automatically discriminate hematopoietic cell lineages and detect dysplastic cells in bone marrow aspiration smears using deep learning technology. Bone marrow aspiration images were acquired from 34 patients diagnosed with MDS and from 24 normal bone marrow slides. In total, 8065 cells were classified into eight categories: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, blasts, and others. The algorithm demonstrated acceptable performance in classifying dysplastic cells, with an AUC of 0.945-0.996 and accuracy of 0.912-0.993. The algorithm developed in this study could be used as an auxiliary tool for diagnosing patients with MDS and is expected to contribute to shortening the time required for MDS bone marrow aspiration diagnosis and standardizing visual reading.

A Review of Artificial Intelligence Applications in Hematology Management: Current Practices and Future Prospects

Background

Machine learning (ML) and deep learning (DL) methods have recently garnered a great deal of attention in the field of cancer research by making a noticeable contribution to the growth of predictive medicine and modern oncological practices. Considerable focus has been particularly directed toward hematologic malignancies because of the complexity in detecting early symptoms. Many patients with blood cancer do not get properly diagnosed until their cancer has reached an advanced stage with limited treatment prospects. Hence, the state-of-the-art revolves around the latest artificial intelligence (AI) applications in hematology management.

Objective

This comprehensive review provides an in-depth analysis of the current AI practices in the field of hematology. Our objective is to explore the ML and DL applications in blood cancer research, with a special focus on the type of hematologic malignancies and the patient’s cancer stage to determine future research directions in blood cancer.

Methods

We searched a set of recognized databases (Scopus, Springer, and Web of Science) using a selected number of keywords. We included studies written in English and published between 2015 and 2021. For each study, we identified the ML and DL techniques used and highlighted the performance of each model.

Results

Using the aforementioned inclusion criteria, the search resulted in 567 papers, of which 144 were selected for review.

Conclusions

The current literature suggests that the application of AI in the field of hematology has generated impressive results in the screening, diagnosis, and treatment stages. Nevertheless, optimizing the patient’s pathway to treatment requires a prior prediction of the malignancy based on the patient’s symptoms or blood records, which is an area that has still not been properly investigated.

Integrating artificial intelligence into haematology training and practice: Opportunities, threats and proposed solutions

There remains a limited emphasis on the use beyond the research domain of artificial intelligence (AI) in haematology and it does not feature significantly in postgraduate medical education and training. This perspective article considers recent developments in the field of AI research in haematology and anticipates the potential benefits and risks associated with its deeper integration into the specialty. Anxiety towards the greater use of AI in healthcare stems from legitimate concerns surrounding data protection, lack of transparency in clinical decision-making, and erosion of the doctor-patient relationship. The specialty of haematology has successfully embraced multiple disruptive innovations. We are at the cusp of a new era of closer integration of AI into routine haematology practice that will ultimately benefit patient care but to harness its benefits the next generation of haematologists will need access to bespoke learning opportunities with input from data scientists.

Multi-Scale Graphical Representation of Cell Environment

We present a multi-scale graphical network that can capture the relevant representations of individual cell morphology, topological structure of cell communities in a tissue image, as well as whole slide level attributes. This helps to effectively merge the disease relevant cell morphology to the overall topological context within the sample, within one unified deep framework. From the explainability point of view, instead of empirical design, the graphs are designed with biomedical considerations in mind in order to have translational validity. We also provide a clinically interpretable visualisation of the cells and their micro- and macro-environment by leveraging label noise reduction. We demonstrate the efficacy of our methodology on myeloproliferative neoplasms (MPN), a haematopoietic stem cell disorder as an exemplar test case. The proposed method achieves an encouraging performance in the robust separation of different MPN subtypes in this exciting new dataset as part of this work.

Challenges of diagnosing and managing pre-fibrotic myelofibrosis: A case-based and practical approach

Pre-Fibrotic Myelofibrosis is a frequently under-recognised entity that has distinct features separate to those of both Essential Thrombocythaemia and overt Primary Myelofibrosis. Misdiagnosis is relatively common due to subtle differences in bone marrow trephine morphology and multidisciplinary approaches are required. The clinical phenotype and disease course is heterogeneous and hence management approaches tend to vary widely. Although patients may initially be asymptomatic, disease-related complications can include troublesome symptom burdens, increased incidence of both arterial and venous thromboses, haemorrhage, anaemia and an inherent risk of disease evolution to either overt myelofibrosis or blastic phase disease. Specific prognostic tools with high discriminatory power are lacking. Within this review we use case-based approaches to review the current literature, highlight challenges in both diagnostics and disease management and suggest contemporary approaches to improve patient outcomes.

Chronic Lymphocytic Leukemia Progression Diagnosis with Intrinsic Cellular Patterns via Unsupervised Clustering

Simple Summary

Distinguishing between chronic lymphocytic leukemia (CLL), accelerated CLL (aCLL), and full-blown transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications. Identifying cellular phenotypes via unsupervised clustering provides the most robust analytic performance in analyzing digitized pathology slides. This study serves as a proof of concept that using an unsupervised machine learning scheme can enhance diagnostic accuracy.

Abstract

Identifying the progression of chronic lymphocytic leukemia (CLL) to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications as it prompts a major change in patient management. However, the differentiation between these disease phases may be challenging in routine practice. Unsupervised learning has gained increased attention because of its substantial potential in data intrinsic pattern discovery. Here, we demonstrate that cellular feature engineering, identifying cellular phenotypes via unsupervised clustering, provides the most robust analytic performance in analyzing digitized pathology slides (accuracy = 0.925, AUC = 0.978) when compared to alternative approaches, such as mixed features, supervised features, unsupervised/mixed/supervised feature fusion and selection, as well as patch-based convolutional neural network (CNN) feature extraction. We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients with histologic evidence of disease progression. The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not easily see.

Deep learning-based histopathological segmentation for whole slide images of colorectal cancer in a compressed domain

Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score, the pixel accuracy, and the Jaccard score were 0.804 ± 0.125, 0.957 ± 0.025, and 0.690 ± 0.174, respectively. We can train the networks for the high-resolution image with the large region of interest compared to the result in the low-resolution and the small region of interest in the spatial domain. The average Dice score, pixel accuracy, and Jaccard score are significantly increased by 2.7%, 0.9%, and 2.7%, respectively. We believe that our approach has great potential for accurate diagnosis.

Using deep learning for quantification of cellularity and cell lineages in bone marrow biopsies and comparison to normal age-related variation

Cellularity estimation forms an important aspect of the visual examination of bone marrow biopsies. In clinical practice, cellularity is estimated by eye under a microscope, which is rapid, but subjective and subject to inter- and intraobserver variability. In addition, there is little consensus in the literature on the normal variation of cellularity with age. Digital image analysis may be used for more objective quantification of cellularity. As such, we developed a deep neural network for the segmentation of six major cell and tissue types in digitized bone marrow trephine biopsies. Using this segmentation, we calculated the overall bone marrow cellularity in a series of biopsies from 130 patients across a wide age range. Using intraclass correlation coefficients (ICC), we measured the agreement between the quantification by the neural network and visual estimation by two pathologists and compared it to baseline human performance. We also examined the age-related changes of cellularity and cell lineages in bone marrow and compared our results to those found in the literature. The network was capable of accurate segmentation (average accuracy and dice score of 0.95 and 0.76, respectively). There was good neural network-pathologist agreement on cellularity measurements (ICC=0.78, 95% CI 0.58-0.85). We found a statistically significant downward trend for cellularity, myelopoiesis and megakaryocytes with age in our cohort. The mean cellularity began at approximately 50% in the third decade of life and then decreased ±2% per decade to 40% in the seventh and eighth decade, but the normal range was very wide (30-70%).

Learning Cellular Phenotypes through Supervision

Image-based cell phenotyping is an important and open problem in computational pathology. The two principal challenges are: 1) making the cell cluster properties insensitive to experimental settings (like seed point and feature selection) and 2) ensuring that the phenotypes emerging are biologically relevant and support clinical reporting. To gauge robustness, we first compare the consistency of the phenotypes using self-supervised and supervised features. Through case classification, we analyse the relevance of the self-supervised and supervised feature sets with respect to the clinical diagnosis. In addition, we demonstrate how we can add model explainability through Shapley values to identify more disease relevant cellular phenotypes and measure their importance in context of the disease. Here, myeloproliferative neoplasms, a haematopoietic stem cell disorder, where one particular cell type is of diagnostic relevance is used as an exemplar. The experiments conducted on a set of bone marrow trephines demonstrate an improvement of 7.4 % in accuracy for case classification using cellular phenotypes derived from the supervised scenario.

Self-Organizing Maps for Cellular In Silico Staining and Cell Substate Classification

Cellular composition and structural organization of cells in the tissue determine effective antitumor response and can predict patient outcome and therapy response. Here we present Seg-SOM, a method for dimensionality reduction of cell morphology in H&E-stained tissue images. Seg-SOM resolves cellular tissue heterogeneity and reveals complex tissue architecture. We leverage a self-organizing map (SOM) artificial neural network to group cells based on morphological features like shape and size. Seg-SOM allows for cell segmentation, systematic classification, and in silico cell labeling. We apply the Seg-SOM to a dataset of breast cancer progression images and find that clustering of SOM classes reveals groups of cells corresponding to fibroblasts, epithelial cells, and lymphocytes. We show that labeling the Lymphocyte SOM class on the breast tissue images accurately estimates lymphocytic infiltration. We further demonstrate how to use Seq-SOM in combination with non-negative matrix factorization to statistically describe the interaction of cell subtypes and use the interaction information as highly interpretable features for a histological classifier. Our work provides a framework for use of SOM in human pathology to resolve cellular composition of complex human tissues. We provide a python implementation and an easy-to-use docker deployment, enabling researchers to effortlessly featurize digitalized H&E-stained tissue.

Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies

The use of immunohistochemistry in the reporting of prostate biopsies is an important adjunct when the diagnosis is not definite on haematoxylin and eosin (H&E) morphology alone. The process is however inherently inefficient with delays while waiting for pathologist review to make the request and duplicated effort reviewing a case more than once. In this study, we aimed to capture the workflow implications of immunohistochemistry requests and demonstrate a novel artificial intelligence tool to identify cases in which immunohistochemistry (IHC) is required and generate an automated request. We conducted audits of the workflow for prostate biopsies in order to understand the potential implications of automated immunohistochemistry requesting and collected prospective cases to train a deep neural network algorithm to detect tissue regions that presented ambiguous morphology on whole slide images. These ambiguous foci were selected on the basis of the pathologist requesting immunohistochemistry to aid diagnosis. A gradient boosted trees classifier was then used to make a slide-level prediction based on the outputs of the neural network prediction. The algorithm was trained on annotations of 219 immunohistochemistry-requested and 80 control images, and tested by threefold cross-validation. Validation was conducted on a separate validation dataset of 222 images. Non IHC-requested cases were diagnosed in 17.9 min on average, while IHC-requested cases took 33.4 min over multiple reporting sessions. We estimated 11 min could be saved on average per case by automated IHC requesting, by removing duplication of effort. The tool attained 99% accuracy and 0.99 Area Under the Curve (AUC) on the test data. In the validation, the average agreement with pathologists was 0.81, with a mean AUC of 0.80. We demonstrate the proof-of-principle that an AI tool making automated immunohistochemistry requests could create a significantly leaner workflow and result in pathologist time savings.

Synoptic Diagnostics of Myeloproliferative Neoplasms: Morphology and Molecular Genetics

Simple Summary

The diagnosis of myeloproliferative neoplasms requires assessment of a combination of clinical, morphological, immunophenotypic and genetic features, and this integrated, multimodal approach forms the basis for precise classification. Evaluation includes cell counts and morphology in the peripheral blood, bone marrow aspiration and trephine biopsy, and may encompass flow cytometry for specific questions. Diagnosis nowadays is completed by targeted molecular analysis for the detection of recurrent driver and, optionally, disease-modifying mutations. According to the current World Health Organization classification, all myeloproliferative disorders require assessment of molecular features to support the diagnosis or confirm a molecularly defined entity. This requires a structured molecular analysis workflow tailored for a rapid and cost-effective diagnosis. The review focuses on the morphological and molecular features of Ph-negative myeloproliferative neoplasms and their differential diagnoses, addresses open questions of classification, and emphasizes the enduring role of histopathological assessment in the molecular era.

Abstract

The diagnosis of a myeloid neoplasm relies on a combination of clinical, morphological, immunophenotypic and genetic features, and an integrated, multimodality approach is needed for precise classification. The basic diagnostics of myeloid neoplasms still rely on cell counts and morphology of peripheral blood and bone marrow aspirate, flow cytometry, cytogenetics and bone marrow trephine biopsy, but particularly in the setting of Ph− myeloproliferative neoplasms (MPN), the trephine biopsy has a crucial role. Nowadays, molecular studies are of great importance in confirming or refining a diagnosis and providing prognostic information. All myeloid neoplasms of chronic evolution included in this review, nowadays feature the presence or absence of specific genetic markers in their diagnostic criteria according to the current WHO classification, underlining the importance of molecular studies. Crucial differential diagnoses of Ph− MPN are the category of myeloid/lymphoid neoplasms with eosinophilia and gene rearrangement of PDGFRA, PDGFRB or FGFR1, or with PCM1-JAK2, and myelodysplastic/myeloproliferative neoplasms (MDS/MPN). This review focuses on morphological, immunophenotypical and molecular features of BCR-ABL1-negative MPN and their differential diagnoses. Furthermore, areas of difficulties and open questions in their classification are addressed, and the persistent role of morphology in the area of molecular medicine is discussed.

How artificial intelligence might disrupt diagnostics in hematology in the near future

Artificial intelligence (AI) is about to make itself indispensable in the health care sector. Examples of successful applications or promising approaches range from the application of pattern recognition software to pre-process and analyze digital medical images, to deep learning algorithms for subtype or disease classification, and digital twin technology and in silico clinical trials. Moreover, machine-learning techniques are used to identify patterns and anomalies in electronic health records and to perform ad-hoc evaluations of gathered data from wearable health tracking devices for deep longitudinal phenotyping. In the last years, substantial progress has been made in automated image classification, reaching even superhuman level in some instances. Despite the increasing awareness of the importance of the genetic context, the diagnosis in hematology is still mainly based on the evaluation of the phenotype. Either by the analysis of microscopic images of cells in cytomorphology or by the analysis of cell populations in bidimensional plots obtained by flow cytometry. Here, AI algorithms not only spot details that might escape the human eye, but might also identify entirely new ways of interpreting these images. With the introduction of high-throughput next-generation sequencing in molecular genetics, the amount of available information is increasing exponentially, priming the field for the application of machine learning approaches. The goal of all the approaches is to allow personalized and informed interventions, to enhance treatment success, to improve the timeliness and accuracy of diagnoses, and to minimize technically induced misclassifications. The potential of AI-based applications is virtually endless but where do we stand in hematology and how far can we go?

The potential of proliferative and apoptotic parameters in clinical flow cytometry of myeloid malignancies

Standardization of the detection and quantification of leukocyte differentiation markers by the EuroFlow Consortium has led to a major step forward in the integration of flow cytometry into classification of leukemia and lymphoma. In our opinion, this now enables introduction of markers for more dynamic parameters, such as proliferative and (anti)apoptotic markers, which have proven their value in the field of histopathology in the diagnostic process of solid tumors and lymphoma. Although use of proliferative and (anti)apoptotic markers as objective parameters in the diagnostic process of myeloid malignancies was studied in the past decades, this did not result in the incorporation of these biomarkers into clinical diagnosis. This review addresses the potential of these markers for implementation in the current, state-of-the-art multiparameter analysis of myeloid malignancies. The reviewed studies clearly recognize the importance of proliferation and apoptotic mechanisms in the pathogenesis of bone marrow (BM) malignancies. The literature is, however, contradictory on the role of these processes in myelodysplastic syndrome (MDS), MDS/myeloproliferative neoplasms, and acute myeloid leukemia. Furthermore, several studies underline the need for the analysis of the proliferative and apoptotic rates in subsets of hematopoietic BM cell lineages and argue that these results can have diagnostic and prognostic value in patients with myeloid malignancies. Recent developments in multiparameter flow cytometry now allow quantification of proliferative and (anti)apoptotic indicators in myeloid cells during their different maturation stages of separate hematopoietic cell lineages. This will lead to a better understanding of the biology and pathogenesis of these malignancies.

Application of Single-Cell Approaches to Study Myeloproliferative Neoplasm Biology

Philadelphia-negative myeloproliferative neoplasms (MPNs) are an excellent tractable disease model of a number of aspects of human cancer biology, including genetic evolution, tissue-associated fibrosis, and cancer stem cells. In this review, we discuss recent insights into MPN biology gained from the application of a number of new single-cell technologies to study human disease, with a specific focus on single-cell genomics, single-cell transcriptomics, and digital pathology.

The Contemporary Approach to CALR-Positive Myeloproliferative Neoplasms

CALR mutations are a revolutionary discovery and represent an important hallmark of myeloproliferative neoplasms (MPN), especially essential thrombocythemia and primary myelofibrosis. To date, several CALR mutations were identified, with only frameshift mutations linked to the diseased phenotype. It is of diagnostic and prognostic importance to properly define the type of CALR mutation and subclassify it according to its structural similarities to the classical mutations, a 52-bp deletion (type 1 mutation) and a 5-bp insertion (type 2 mutation), using a statistical approximation algorithm (AGADIR). Today, the knowledge on the pathogenesis of CALR-positive MPN is expanding and several cellular mechanisms have been recognized that finally cause a clonal hematopoietic expansion. In this review, we discuss the current basis of the cellular effects of CALR mutants and the understanding of its implementation in the current diagnostic laboratorial and medical practice. Different methods of CALR detection are explained and a diagnostic algorithm is shown that aids in the approach to CALR-positive MPN. Finally, contemporary methods joining artificial intelligence in accordance with molecular-genetic biomarkers in the approach to MPN are presented.

The Potential of Artificial Intelligence to Detect Lymphovascular Invasion in Testicular Cancer

Testicular cancer is the most common cancer in men aged from 15 to 34 years. Lymphovascular invasion refers to the presence of tumours within endothelial-lined lymphatic or vascular channels, and has been shown to have prognostic significance in testicular germ cell tumours. In non-seminomatous tumours, lymphovascular invasion is the most powerful prognostic factor for stage 1 disease. For the pathologist, searching multiple slides for lymphovascular invasion can be highly time-consuming. The aim of this retrospective study was to develop and assess an artificial intelligence algorithm that can identify areas suspicious for lymphovascular invasion in histological digital whole slide images. Areas of possible lymphovascular invasion were annotated in a total of 184 whole slide images of haematoxylin and eosin (H&E) stained tissue from 19 patients with testicular germ cell tumours, including a mixture of seminoma and non-seminomatous cases. Following consensus review by specialist uropathologists, we trained a deep learning classifier for automatic segmentation of areas suspicious for lymphovascular invasion. The classifier identified 34 areas within a validation set of 118 whole slide images from 10 patients, each of which was reviewed by three expert pathologists to form a majority consensus. The precision was 0.68 for areas which were considered to be appropriate to flag, and 0.56 for areas considered to be definite lymphovascular invasion. An artificial intelligence tool which highlights areas of possible lymphovascular invasion to reporting pathologists, who then make a final judgement on its presence or absence, has been demonstrated as feasible in this proof-of-concept study. Further development is required before clinical deployment.

Machine learning and augmented human intelligence use in histomorphology for haematolymphoid disorders

Advances in digital pathology have allowed a number of opportunities such as decision support using artificial intelligence (AI). The application of AI to digital pathology data shows promise as an aid for pathologists in the diagnosis of haematological disorders. AI-based applications have embraced benign haematology, diagnosing leukaemia and lymphoma, as well as ancillary testing modalities including flow cytometry. In this review, we highlight the progress made to date in machine learning applications in haematopathology, summarise important studies in this field, and highlight key limitations. We further present our outlook on the future direction and trends for AI to support diagnostic decisions in haematopathology.