Alan Aberdeen
Alan Aberdeen has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Royston
Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
6 shared publications - Jens Rittscher
University of Oxford
6 shared publications - Adam J. Mead
Medical Research Council Molecular Haematology Unit, Weatherall Institute of Molecular Medicine, Radcliffe Department of Medicine and National Institute of Health Research, Oxford Biomedical Research Centre, University of Oxford, Oxford, United Kingdom
4 shared publications - Bethan Psaila
MRC Weatherall Institute of Molecular Medicine University of Oxford Oxford UK
4 shared publications Gabrielle Rees
Department of Pathology, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
4 shared publications- Hosuk Ryou
Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
4 shared publications
Latest Publications
- Open Access
- 16 September 2026
- Published by Springer Nature in Leukemia
- p. 1-9
Clinical evaluation of AI-assisted quantitative marrow fibrosis assessment using Continuous Indexing of Fibrosis (CIF)
Assessment of fibrosis is central to the evaluation of diagnostic bone marrow trephine (BMT) biopsies. However, manual fibrosis grading is subjective and only semi-quantitative. We evaluated the clinical utility of a previously developed AI-based quantitative fibrosis assessment tool, Continuous Indexing of Fibrosis (CIF), using ~1000 consecutive BMT biopsies without pre-selection. An international panel of 14 haematopathologists performed manual reads using whole-slide images (WSI) of reticulin-stained slides and two types of CIF-assisted reads ( Sequential-assisted and Concurrent-assisted ) across three study rounds. The AI-derived CIF scores correlated strongly with the manual consensus MF grade (Spearman ρ = 0.770) and demonstrated good discriminative performance across adjacent MF grade boundaries. The CIF-assisted protocols significantly improved intra-observer and inter-observer agreement compared to manual assessment, without increasing read times. Sequential-assisted reads yielded the largest gain in inter-observer agreement (12.6 percentage points; 95% CI 10.5–14.8) and improved agreement with the consensus reference (3.0 percentage points; 95% CI 0.4–5.7). Both assisted protocols reduced discordance across the clinically significant MF-1 / MF-2 boundary. These findings demonstrate that AI-assisted quantitative bone marrow fibrosis assessment using CIF is reproducible, efficient and well suited for future clinical deployment testing. This supports a future role in standardising routine diagnostic haematopathology and enhancing the sensitivity of fibrosis-based clinical trial endpoints.
- 16 September 2026
- Published by Springer Nature in Leukemia
- p. 1-9
Open AccessClinical evaluation of AI-assisted quantitative marrow fibrosis assessment using Continuous Indexing of Fibrosis (CIF)
Assessment of fibrosis is central to the evaluation of diagnostic bone marrow trephine (BMT) biopsies. However, manual fibrosis grading is subjective and only semi-quantitative. We evaluated the clinical utility of a previously developed AI-based quantitative fibrosis assessment tool, Continuous Indexing of Fibrosis (CIF), using ~1000 consecutive BMT biopsies without pre-selection. An international panel of 14 haematopathologists performed manual reads using whole-slide images (WSI) of reticulin-stained slides and two types of CIF-assisted reads ( Sequential-assisted and Concurrent-assisted ) across three study rounds. The AI-derived CIF scores correlated strongly with the manual consensus MF grade (Spearman ρ = 0.770) and demonstrated good discriminative performance across adjacent MF grade boundaries. The CIF-assisted protocols significantly improved intra-observer and inter-observer agreement compared to manual assessment, without increasing read times. Sequential-assisted reads yielded the largest gain in inter-observer agreement (12.6 percentage points; 95% CI 10.5–14.8) and improved agreement with the consensus reference (3.0 percentage points; 95% CI 0.4–5.7). Both assisted protocols reduced discordance across the clinically significant MF-1 / MF-2 boundary. These findings demonstrate that AI-assisted quantitative bone marrow fibrosis assessment using CIF is reproducible, efficient and well suited for future clinical deployment testing. This supports a future role in standardising routine diagnostic haematopathology and enhancing the sensitivity of fibrosis-based clinical trial endpoints.
- Open Access
- 13 June 2024
- Published by Wiley in HemaSphere
- Vol. 8 (6) , e105
Quantitative analysis of bone marrow fibrosis highlights heterogeneity in myelofibrosis and augments histological assessment: An Insight from a phase II clinical study of zinpentraxin alfa
- 13 June 2024
- Published by Wiley in HemaSphere
- Vol. 8 (6) , e105
Open AccessQuantitative analysis of bone marrow fibrosis highlights heterogeneity in myelofibrosis and augments histological assessment: An Insight from a phase II clinical study of zinpentraxin alfa
- Open Access
- 12 January 2023
- Published by Springer Nature in Leukemia
- Vol. 37 (2) , 503
Correction: Continuous Indexing of Fibrosis (CIF): improving the assessment and classification of MPN patients
- 12 January 2023
- Published by Springer Nature in Leukemia
- Vol. 37 (2) , 503
Open AccessCorrection: Continuous Indexing of Fibrosis (CIF): improving the assessment and classification of MPN patients
- Open Access
- 5 December 2022
- Published by Springer Nature in Leukemia
- Vol. 37 (2) , 348-358
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.
- 5 December 2022
- Published by Springer Nature in Leukemia
- Vol. 37 (2) , 348-358
Open AccessContinuous 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.
- Open Access
Continuous Indexing of Fibrosis (CIF): Improving the Assessment and Classification of MPN Patients
The detection and grading of fibrosis in myeloproliferative neoplasms (MPN) is an important component of disease classification, prognostication and disease monitoring. However, current fibrosis grading systems are only semi-quantitative and fail to capture sample heterogeneity. To improve the detection, quantitation and representation of reticulin fibrosis, we developed a machine learning (ML) approach using bone marrow trephine (BMT) samples (n = 107) from patients diagnosed with MPN or a reactive / nonneoplastic marrow. The resulting Continuous Indexing of Fibrosis (CIF) enhances the detection and monitoring of fibrosis within BMTs, and aids the discrimination of MPN subtypes. When combined with megakaryocyte feature analysis, CIF discriminates between the frequently challenging differential diagnosis of essential thrombocythemia (ET) and pre-fibrotic myelofibrosis (pre-PMF) with high predictive accuracy [area under the curve = 0.94]. CIF also shows significant 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 (PT-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. The image analysis methods used to generate CIF can be readily integrated with those of other key morphological features in MPNs, including megakaryocyte morphology, that lie beyond the scope of conventional histological assessment. Key Points: Machine learning enables an objective and quantitative description of reticulin fibrosis within the bone marrow of patients with myeloproliferative neoplasms (MPN), Automated analysis and Continuous Indexing of Fibrosis (CIF) captures heterogeneity within MPN samples and has utility in refined classification and disease monitoring Quantitative fibrosis assessment combined with topological data analysis may help to predict patients at increased risk of progression to post-ET myelofibrosis, and assist in the discrimination of ET and pre-fibrotic PMF (pre-PMF)
Open AccessContinuous Indexing of Fibrosis (CIF): Improving the Assessment and Classification of MPN Patients
The detection and grading of fibrosis in myeloproliferative neoplasms (MPN) is an important component of disease classification, prognostication and disease monitoring. However, current fibrosis grading systems are only semi-quantitative and fail to capture sample heterogeneity. To improve the detection, quantitation and representation of reticulin fibrosis, we developed a machine learning (ML) approach using bone marrow trephine (BMT) samples (n = 107) from patients diagnosed with MPN or a reactive / nonneoplastic marrow. The resulting Continuous Indexing of Fibrosis (CIF) enhances the detection and monitoring of fibrosis within BMTs, and aids the discrimination of MPN subtypes. When combined with megakaryocyte feature analysis, CIF discriminates between the frequently challenging differential diagnosis of essential thrombocythemia (ET) and pre-fibrotic myelofibrosis (pre-PMF) with high predictive accuracy [area under the curve = 0.94]. CIF also shows significant 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 (PT-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. The image analysis methods used to generate CIF can be readily integrated with those of other key morphological features in MPNs, including megakaryocyte morphology, that lie beyond the scope of conventional histological assessment. Key Points: Machine learning enables an objective and quantitative description of reticulin fibrosis within the bone marrow of patients with myeloproliferative neoplasms (MPN), Automated analysis and Continuous Indexing of Fibrosis (CIF) captures heterogeneity within MPN samples and has utility in refined classification and disease monitoring Quantitative fibrosis assessment combined with topological data analysis may help to predict patients at increased risk of progression to post-ET myelofibrosis, and assist in the discrimination of ET and pre-fibrotic PMF (pre-PMF)
- Open Access
Phenotyping of Klf14 mouse white adipose tissue enabled by whole slide segmentation with deep neural networks
White adipose tissue (WAT) plays a central role in metabolism, with multiple diseases and genetic mutations causing its remodeling. Quantitative analysis of white adipocyte size is of great interest to understand physiology and disease, but previous studies of H&E histology have been limited to a subsample of whole depot cross-sections. In this paper, we present the deep learning pipeline DeepCytometer, that can segment mouse and human whole slides (≃40,000 cells per mouse slide on average) using an adaptive tiling method, correct for cell overlap and reject non-white adipocytes from the segmentation. Using quantile colour maps we show intra- and inter-depot cell size heterogeneity with local correlation; quantile estimates also suggest significant differences in population estimates from 75 whole slides compared to smaller data sets. We propose three linked levels (body weight BW, depot weight DW and cell area quartiles) for exploratory analysis of mouse Klf14 phenotypes in gonadal and subcutaneous depots. We find a rich set of phenotypes when stratifying by sex, depot and three genotype strata: (1) WTs/Hets with a Het father (Controls), (2) WTs with a Het mother, and (3) Hets with a Het mother (functional KOs or FKOs). Namely, at BW level, mean difference testing suggests that female FKOs are similar to Controls, but WTs with a Het mother are significantly larger. At DW and cell levels, linear models with interaction terms and BW or DW covariates, respectively, reveal phenotypes not shown by difference of means tests. For example, at DW level, gonadal and subcutaneous models are similar, and female FKOs have lower fat percentage than Controls due to both an offset and the DW/BW slope in the linear model. Meanwhile, female WTs with a Het mother have on average similar fat percentage to Controls, but as their slopes are close to zero, their DWs are uncorrelated to BW, suggesting that larger female WTs with a Het mother have lower fat percentage than smaller ones. In contrast to depot level, at cell level female gonadal phenotypes diverge from subcutaneous ones. Furthermore, male Controls and FKOs have similar average area values in subcutaneous depots, but area~DW slope flattening in FKOs suggests that larger DWs could be caused by cell size increase in Controls and by cell count increase in FKOs. Thus, DeepCytometer and associated exploratory analysis reveal new insights into adipocyte heterogeneity and phenotyping.
Open AccessPhenotyping of Klf14 mouse white adipose tissue enabled by whole slide segmentation with deep neural networks
White adipose tissue (WAT) plays a central role in metabolism, with multiple diseases and genetic mutations causing its remodeling. Quantitative analysis of white adipocyte size is of great interest to understand physiology and disease, but previous studies of H&E histology have been limited to a subsample of whole depot cross-sections. In this paper, we present the deep learning pipeline DeepCytometer, that can segment mouse and human whole slides (≃40,000 cells per mouse slide on average) using an adaptive tiling method, correct for cell overlap and reject non-white adipocytes from the segmentation. Using quantile colour maps we show intra- and inter-depot cell size heterogeneity with local correlation; quantile estimates also suggest significant differences in population estimates from 75 whole slides compared to smaller data sets. We propose three linked levels (body weight BW, depot weight DW and cell area quartiles) for exploratory analysis of mouse Klf14 phenotypes in gonadal and subcutaneous depots. We find a rich set of phenotypes when stratifying by sex, depot and three genotype strata: (1) WTs/Hets with a Het father (Controls), (2) WTs with a Het mother, and (3) Hets with a Het mother (functional KOs or FKOs). Namely, at BW level, mean difference testing suggests that female FKOs are similar to Controls, but WTs with a Het mother are significantly larger. At DW and cell levels, linear models with interaction terms and BW or DW covariates, respectively, reveal phenotypes not shown by difference of means tests. For example, at DW level, gonadal and subcutaneous models are similar, and female FKOs have lower fat percentage than Controls due to both an offset and the DW/BW slope in the linear model. Meanwhile, female WTs with a Het mother have on average similar fat percentage to Controls, but as their slopes are close to zero, their DWs are uncorrelated to BW, suggesting that larger female WTs with a Het mother have lower fat percentage than smaller ones. In contrast to depot level, at cell level female gonadal phenotypes diverge from subcutaneous ones. Furthermore, male Controls and FKOs have similar average area values in subcutaneous depots, but area~DW slope flattening in FKOs suggests that larger DWs could be caused by cell size increase in Controls and by cell count increase in FKOs. Thus, DeepCytometer and associated exploratory analysis reveal new insights into adipocyte heterogeneity and phenotyping.
- Open Access
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.
Open AccessThe 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.
- Open Access
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 3-fold cross-validation. Validation was conducted on a separate validation dataset of 212 images. Non IHC-requested cases were diagnosed in 17.9 minutes on average, while IHC-requested cases took 33.4 minutes over multiple reporting sessions. We estimated 11 minutes 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.
Open AccessArtificial 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 3-fold cross-validation. Validation was conducted on a separate validation dataset of 212 images. Non IHC-requested cases were diagnosed in 17.9 minutes on average, while IHC-requested cases took 33.4 minutes over multiple reporting sessions. We estimated 11 minutes 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.
- Open Access
- 24 July 2020
- Published by American Society of Hematology in Blood Advances
- Vol. 4 (14) , 3284-3294
Artificial intelligence–based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients
Accurate diagnosis and classification of myeloproliferative neoplasms (MPNs) requires integration of clinical, morphological, and genetic findings. Despite major advances in our understanding of the molecular and genetic basis of MPNs, the morphological assessment of bone marrow trephines (BMT) is critical in differentiating MPN subtypes and their reactive mimics. However, morphological assessment is heavily constrained by a reliance on subjective, qualitative, and poorly reproducible criteria. To improve the morphological assessment of MPNs, we have developed a machine learning approach for the automated identification, quantitative analysis, and abstract representation of megakaryocyte features using reactive/nonneoplastic BMT samples (n = 43) and those from patients with established diagnoses of essential thrombocythemia (n = 45), polycythemia vera (n = 18), or myelofibrosis (n = 25). We describe the application of an automated workflow for the identification and delineation of relevant histological features from routinely prepared BMTs. Subsequent analysis enabled the tissue diagnosis of MPN with a high predictive accuracy (area under the curve = 0.95) and revealed clear evidence of the potential to discriminate between important MPN subtypes. Our method of visually representing abstracted megakaryocyte features in the context of analyzed patient cohorts facilitates the interpretation and monitoring of samples in a manner that is beyond conventional approaches. The automated BMT phenotyping approach described here has significant potential as an adjunct to standard genetic and molecular testing in established or suspected MPN patients, either as part of the routine diagnostic pathway or in the assessment of disease progression/response to treatment.
- 24 July 2020
- Published by American Society of Hematology in Blood Advances
- Vol. 4 (14) , 3284-3294
Open AccessArtificial intelligence–based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients
Accurate diagnosis and classification of myeloproliferative neoplasms (MPNs) requires integration of clinical, morphological, and genetic findings. Despite major advances in our understanding of the molecular and genetic basis of MPNs, the morphological assessment of bone marrow trephines (BMT) is critical in differentiating MPN subtypes and their reactive mimics. However, morphological assessment is heavily constrained by a reliance on subjective, qualitative, and poorly reproducible criteria. To improve the morphological assessment of MPNs, we have developed a machine learning approach for the automated identification, quantitative analysis, and abstract representation of megakaryocyte features using reactive/nonneoplastic BMT samples (n = 43) and those from patients with established diagnoses of essential thrombocythemia (n = 45), polycythemia vera (n = 18), or myelofibrosis (n = 25). We describe the application of an automated workflow for the identification and delineation of relevant histological features from routinely prepared BMTs. Subsequent analysis enabled the tissue diagnosis of MPN with a high predictive accuracy (area under the curve = 0.95) and revealed clear evidence of the potential to discriminate between important MPN subtypes. Our method of visually representing abstracted megakaryocyte features in the context of analyzed patient cohorts facilitates the interpretation and monitoring of samples in a manner that is beyond conventional approaches. The automated BMT phenotyping approach described here has significant potential as an adjunct to standard genetic and molecular testing in established or suspected MPN patients, either as part of the routine diagnostic pathway or in the assessment of disease progression/response to treatment.