ICSH guidelines for the standardization of bone marrow specimens and reports

Use of n-grams and K-means clustering to classify data from free text bone marrow reports

Natural language processing (NLP) has been used to extract information from and summarize medical reports. Currently, the most advanced NLP models require large training datasets of accurately labeled medical text. An approach to creating these large datasets is to use low resource intensive classical NLP algorithms. In this manuscript, we examined how an automated classical NLP algorithm was able to classify portions of bone marrow report text into their appropriate sections. A total of 1480 bone marrow reports were extracted from the laboratory information system of a tertiary healthcare network. The free text of these bone marrow reports were preprocessed by separating the reports into text blocks and then removing the section headers. A natural language processing algorithm involving n-grams and K-means clustering was used to classify the text blocks into their appropriate bone marrow sections. The impact of token replacement of numerical values, accession numbers, and clusters of differentiation, varying the number of centroids (1-19) and n-grams (1-5), and utilizing an ensemble algorithm were assessed. The optimal NLP model was found to employ an ensemble algorithm that incorporated token replacement, utilized 1-gram or bag of words, and 10 centroids for K-means clustering. This optimal model was able to classify text blocks with an accuracy of 89%, suggesting that classical NLP models can accurately classify portions of marrow report text.

Hematological cytomorphology: Where we are

The manuscript discusses the historical evolution of observing blood cell morphology under an optical microscope, from the earliest microscopes in the 17th century to the modern digital era, highlighting key advancements and contributions in the field. Blood has historically held symbolic importance in various cultures, with early medical observations dating back to Hippocrates and Galeno. The discovery of cells and subsequent advancements in microscopy by scientists like Hooke and van Leeuwenhoek paved the way for understanding blood cell morphology. Influential figures such as Hewson, Donné, and Ehrlich followed. Diagnostic cytology evolved from manual cell counting to the development of automated hematological systems. Automated complete blood counting came to support microscopic examination in diagnosing hematological disorders. Morphology is crucial in predicting disease outcomes and guiding treatment decisions, particularly hematological neoplasms. The introduction of flow cytometry and its integration with traditional morphological analysis and the new cytogenetic and molecular techniques revolutionized the classification and prognostication of hematologic disorders. Digital microscopy has emerged as a powerful tool in recent years, offering rapid acquisition and sharing of blood cell images. Integrating Artificial Intelligence with digital microscopy has further enhanced morphological analysis, improving diagnostic efficiency. We also discuss the prospects of AI in pre-classifying blood cells in bone marrow aspirate samples, potentially revolutionizing diagnostic pathways for hematologic diseases. Overall, the manuscript provides a comprehensive overview of the historical development, clinical significance and technological advancements in observing blood cell morphology, underscoring its continued relevance in modern hematology practice.

Performance Evaluation of a Novel Artificial Intelligence-Assisted Digital Microscopy System for the Routine Analysis of Bone Marrow Aspirates

Bone marrow aspiration (BMA) smear analysis is essential for diagnosis, treatment, and monitoring of a variety of benign and neoplastic hematological conditions. Currently, this analysis is performed by manual microscopy. We conducted a multicenter study to validate a computational microscopy approach with an artificial intelligence-driven decision support system. A total of 795 BMA specimens (615 Romanowsky-stained and 180 Prussian blue-stained) from patients with neoplastic and other clinical conditions were analyzed, comparing the performance of the Scopio Labs X100 Full Field BMA system (test method) with manual microscopy (reference method). The system provided an average of 1,385 ± 536 (range, 0-3,131) cells per specimen for analysis. An average of 39.98 ± 19.64 fields of view (range, 0-140) per specimen were selected by the system for analysis, of them 87% ± 21% (range, 0%-100%) were accepted by the qualified operators. These regions were included in an average of 17.62 ± 7.24 regions of interest (range, 1-50) per specimen. The efficiency, sensitivity, and specificity for primary and secondary marrow aspirate characteristics (maturation, morphology, and count assessment), as well as overall interuser agreement, were evaluated. The test method showed a high correlation with the reference method for comprehensive BMA evaluation, both on Romanowsky- (90.85% efficiency, 81.61% sensitivity, and 92.88% specificity) and Prussian blue-stained samples (90.0% efficiency, 81.94% sensitivity, and 93.38% specificity). The overall agreement between the test and reference methods for BMA assessment was 91.1%. For repeatability and reproducibility, all standard deviations and coefficients of variation values were below the predefined acceptance criteria both for discrete measurements (coefficient of variation below 20%) and differential measurements (SD below 5%). The high degree of correlation between the digital decision support system and manual microscopy demonstrates the potential of this system to provide a high-quality, accurate digital BMA analysis, expediting expert review and diagnosis of BMA specimens, with practical applications including remote BMA evaluation and possibly new opportunities for the research of normal and neoplastic hematopoiesis.

Digital morphology compared to the optical microscope: A validation study on reporting bone marrow aspirates

INTRODUCTION

This study aims to evaluate the effectiveness and reliability of the utilization for clinical reporting of the evaluation of digital images of bone marrow aspirates by morphologists and their comparability with the classic microscopic morphological evaluation.

METHODS

We scanned 180 consecutive bone marrow needle aspirates smears using the "Metafer4 VSlide" whole slide imaging (WSI) digital scanning system. We evaluated the statistical comparability and the risk of bias of the microscopic readings with those performed on the screen on the digitized medullary images.

RESULTS

The evaluation of cellularity on the screen was equivalent, with a higher frequency of "normal" than the analysis of digital preparations. The means and medians of the percentage values obtained on the different cell populations with the microscopic and digital reading were comparable as the main categories are concerned, with an average difference equal to 0 for the neutrophilic and eosinophilic granulocytic series, at -0.2% for the total myeloid cells, at 1.2% for the erythroid series, at -0.4% for the lymphocytes and at -0.4% for the blasts. Dysplastic features were consistently identified in 69/71 cell lineages.

CONCLUSION

Our study demonstrated that screen evaluation of digitized bone marrow needle aspirates provides quantitative and qualitative results comparable to traditional microscopic analysis of the corresponding slide smears. Digital images offer significant benefits in reducing the workload of experienced operators, reproducibility and sharing of observations, and image preservation. Even in routine diagnostic activities, their use does not alter the quality of the results obtained in evaluating bone marrow needle aspirates.

Validation of an automated iron stain process for use with bone marrow aspirate smear slides

The assessment of bone marrow iron stores is typically performed on an aspirate smear slide that has been manually stained by a technologist using a commercially available kit. This approach can contribute to inconsistent results and limit the broad use of iron staining in bone marrow specimens, particularly when laboratories have low staffing and/or high specimen volumes. Here, we describe the adaptation and validation of the Ventana Benchmark automated stainer and iron stain kit for routine clinical use of staining iron in bone marrow aspirate smear slides. We assessed accuracy and precision of the Ventana automated iron staining protocol compared to the Perls Prussian blue manual iron staining index method. Hematopathologists assigned Gale scores and enumerated the percentages of erythroid sideroblasts on paired patient bone marrow aspirate smear slides stained by the automated method and the manual iron staining method. We found a similar level of performance of the Ventana automated iron stain relative to the index manual method (as assessed by Pearson correlation and Bland-Altman analyses). In addition, there was low imprecision between replicates performed via the automated iron stain protocol. We also report superior qualitative findings of the automated method in ease of localization of iron storage, visualization of sideroblasts, and counterstain consistency. Automated iron staining of bone marrow aspirate smear slides performed similarly to the manual method and may allow for accurate routine evaluation of bone marrow iron stores as part of bone marrow analysis.

Prevalence of massively diluted bone marrow cell samples aspirated from patients with myelodysplastic syndromes (MDS) or suspected of MDS: A retrospective analysis of nationwide samples in Japan

Bone marrow (BM) examination is a key element in the diagnosis and prognostic grading of myelodysplastic syndromes (MDSs), and obtaining adequate BM cell samples is critical for accurate test results. Massive haemodilution of aspirated BM samples is a well-known problem; however, its incidence in patients with MDS has not been well studied. We report the first study to examine the incidence of massive haemodilution in nationwide BM samples aspirated from patients diagnosed with or suspected of MDS in Japan. Among 283 cases available for analysis, BM smears from 92 cases (32.5%) were hypospicular (massively haemodiluted) and, particularly, no BM particles were observed in 52 cases (18.4%). Regarding hypospicular cases, we examined how the doctors in charge interpreted the BM smears of their patients. In only 19 of 92 cases (20.7%), doctors realised that the BM smears were haemodiluted. Furthermore, the BM biopsy, which can help diagnose hypospicular cases, was oftentimes not performed when the haemodilution was overlooked by doctors (not performed in 50 of 73 such cases). These real-world data highlight that not only researchers who are working to improve diagnostic tests but also clinicians who perform and use diagnostic tests must realise this common and potentially critical problem.

Role of Interphase FISH Assay on Air-Dried Smears in Identifying Specific Structural Chromosomal Abnormalities among Pediatric Patients with Acute Leukemias

Leukemia-associated structural chromosomal abnormalities (SCA) can be identified either by karyotyping or interphase-fluorescence in-situ hybridization (i-FISH) assays. Both karyotyping and i-FISH on mononuclear cell suspension are time, resource, and manpower-consuming assays. In this study, we have compared the results of specific leukemia-associated SCAs identified by i-FISH on air-dried bone marrow (BM)/peripheral blood (PB) smears and BM karyotyping. The study was conducted among pediatric patients (age ≤ 18 years) diagnosed with acute leukemias between January 2018 to December 2022. The results of i-FISH on air-dried BM/PB smears and BM-karyotyping for our SCA of interest (BCR::ABL1, ETV6::RUNX1, TCF3::PBX1, KMT2A rearrangement, RUNX1::RUNX1T1, CBFB::MYH11, and PML::RARA) were entered in a contingency table and the agreement of results was calculated. The strength of agreement was assessed by Cramer's V test. Among 270 patients, SCA of interest was identified among 26% and 17% of patients by i-FISH on air-dried smears and karyotyping, respectively. Excluding 53 patients with metaphase failure, the remaining 217 patients had 92% agreement (Cramer's V of 0.931 with p < 0.000) between the results for specific SCAs identified by both techniques. On excluding samples with cryptic cytogenetic aberrancies, there was 99% agreement (Cramer's V of 0.953 with p < 0.000) for gross SCA identified by both techniques. In addition, i-FISH on air-dried smears identified SCA in 30% of patients with metaphase failure. I-FISH on air-dried PB/BMA smears is a less-labor and  resource-consuming assay. It can be considered an efficient alternative to conventional karyotyping for  identifying specific SCA of interest in under-resourced laboratories.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12288-023-01699-2.

Detection performance and prognostic value of initial bone marrow involvement in diffuse large B-cell lymphoma: a single centre 18F-FDG PET/CT and bone marrow biopsy evaluation study

BACKGROUND

Detection of bone marrow involvement (BMI) in diffuse large B-cell lymphoma (DLBCL) typically relies on invasive bone marrow biopsy (BMB) that faces procedure limitations, while 18F-FDG PET/CT imaging offers a noninvasive alternative. The present study assesses the performance of 18F-FDG PET/CT in DLBCL BMI detection, its agreement with BMB, and the impact of BMI on survival outcomes.

PATIENTS AND METHODS

This retrospective study analyzes baseline 18F-FDG PET/CT and BMB findings in145 stage II-IV DLBCL patients, evaluating both performance of the two diagnostic procedures and the impact of BMI on survival.

RESULTS

DLBCL BMI was detected in 38 patients (26.2%) using PET/CT and in 18 patients (12.4%) using BMB. Concordant results were seen in 79.3% of patients, with 20.7% showing discordant results. Combining PET/CT and BMB data, we identified 29.7% of patients with BMI. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of PET/CT for detecting DLBCL BMI were 88.4%, 100%, 100%, 95.3%, and 96.5%, respectively, while BMB showed lower sensitivity (41.9%) and NPV (46.8%). The median overall survival (OS) was not reached in any gender subgroup, with 5-year OS rates of 82% (total), 84% (female), and 80% (male) (p = 0.461), while different International Prognostic Index (IPI) groups exhibited varied 5-year OS rates: 94% for low risk (LR), 91% for low-intermediate risk (LIR), 84% for high-intermediate risk (HIR), and 65% for high risk (HR) (p = 0.0027). Bone marrow involvement did not impact OS significantly (p = 0.979).

CONCLUSIONS

18F-FDG PET/CT demonstrated superior diagnostic accuracy compared to BMB. While other studies reported poorer overall and BMI 5-year OS in DLBCL, our findings demonstrated favourable survival data.

Diagnostic performance of automated red cell parameters in predicting bone marrow iron stores

OBJECTIVES

The aim of the study was to determine the diagnostic performance of novel automated red cell parameters for estimating bone marrow iron stores.

METHODS

The study was a retrospective single-centre study based on data from an automated haematology analyser and results of bone marrow iron staining. Red cell parameters were measured on a Sysmex XN-series haematology analyser. Bone marrow iron stores were assessed semiquantitatively by cytochemical reaction according to Perls.

RESULTS

The analysis included 429 bone marrow aspirate smears from 393 patients. Median age of patients was 67 years, 52 % of them were female. The most common indication for bone marrow examination was a plasma cell dyscrasia (n=104; 24 %). Median values of percentage of hypochromic and hyperchromic red blood cells (%HYPO-He, %HYPER-He), reticulocyte haemoglobin equivalent (RET-He) and microcytic red blood cells (MicroR) were statistically significantly different between cases with iron deplete and iron replete bone marrow. In a logistic regression model, ferritin was the best predictor of bone marrow iron stores (AUC=0.891), outperforming RET-He and %HYPER-He (AUC=0.736 and AUC=0.722, respectively). In a combined model, ferritin/MicroR index achieved the highest diagnostic accuracy (AUC=0.915), outperforming sTfR/log ferritin index (AUC=0.855).

CONCLUSIONS

While single automated red cell parameters did not show improved diagnostic accuracy when compared to traditional iron biomarkers, a novel index ferritin/MicroR has the potential to outperform ferritin and sTfR/log ferritin index for predicting bone marrow iron stores. Further research is needed for interpretation and implementation of novel parameters and indices, especially in the context of unexplained anaemia and myelodysplastic syndromes.

Association between clinical outcomes, peripheral blood and cytomorphologic features of bone marrow in visceral leishmaniasis

INTRODUCTION

An intracellular parasite of mononuclear phagocytes, mainly distributed in the bone marrow and the spleen, causes visceral leishmaniasis. Complete blood count (CBC) reveals the poorly understood pathogenesis of anemia, leukopenia and thrombocytopenia. Our study aimed to compare the CBC with bone marrow cytomorphological features and their association with clinical outcomes to clarify this relevant issue.

METHODS

The CBC and bone marrow of 118 patients were described by two hematologists and compared to check their association with each other and mortality.

RESULTS

Peripheral cytopenias were common findings, particularly anemia, as seen in almost all patients. No relationship was found between values of hemoglobin, neutrophils and platelet count with fatal outcomes. The bone marrow was normocellular in 61.9% of the cases. Dysplasia figures were frequent and 49.1% of the samples had dysgranulopoiesis. Additionally, erythroid hyperplasia was found in 72% of the patients with severe anemia. Patients with reduced bone marrow cellularity, erythroid hypercellularity and dyserythropoiesis seem to have a riskier disease.

CONCLUSION

The study results suggest that the bone marrow of patients with visceral leishmaniasis manifests a reactional pattern to the inflammatory event, thereby modulating cytokines and other colony growth factors. This compensatory response may be dysplastic and ineffective and generate peripheral cytopenias of varying intensity. Further studies are needed to clarify the signaling pathways involved, which may be used as therapeutic tools in the future.

Clinical significance of total nucleated cell count in bone marrow of patients with acute lymphoblastic leukemia who underwent allogeneic hematopoietic stem cell transplantation

The clinical implications of recipient bone marrow nucleated cell count (NCC) prior to allogeneic hematopoietic stem cell transplantation (allo-HSCT) remain unknown. We conducted a multicenter retrospective study to evaluate the clinical significance of bone marrow NCC prior to allo-HSCT in patients with acute lymphoblastic leukemia. Patients who were in remission and underwent the initial allo-HSCT were included and stratified into high- and low-NCC groups using an NCC of 10 × 104/µL as the cut-off. The 3-year overall survival (OS), non-relapse mortality (NRM), and relapse rates for the high- and low-NCC groups were 51.2 vs. 84.5% (p < 0.001), 27.5 vs. 6.5% (p < 0.001), and 31.1 vs. 24.4% (p = 0.322), respectively. The high-NCC group had significantly poorer OS and higher NRM when compared with the low-NCC group. In summary, high recipient bone marrow NCC is associated with higher NRM and lower OS following allo-HSCT.

Evaluation of deep learning training strategies for the classification of bone marrow cell images

BACKGROUND AND OBJECTIVE

The classification of bone marrow (BM) cells by light microscopy is an important cornerstone of hematological diagnosis, performed thousands of times a day by highly trained specialists in laboratories worldwide. As the manual evaluation of blood or BM smears is very time-consuming and prone to inter-observer variation, new reliable automated systems are needed.

METHODS

We aim to improve the automatic classification performance of hematological cell types. Therefore, we evaluate four state-of-the-art Convolutional Neural Network (CNN) architectures on a dataset of 171,374 microscopic cytological single-cell images obtained from BM smears from 945 patients diagnosed with a variety of hematological diseases. We further evaluate the effect of an in-domain vs. out-of-domain pre-training, and assess whether class activation maps provide human-interpretable explanations for the models' predictions.

RESULTS

The best performing pre-trained model (Regnet_y_32gf) yields a mean precision, recall, and F1 scores of 0.787±0.060, 0.755±0.061, and 0.762±0.050, respectively. This is a 53.5% improvement in precision and 7.3% improvement in recall over previous results with CNNs (ResNeXt-50) that were trained from scratch. The out-of-domain pre-training apparently yields general feature extractors/filters that apply very well to the BM cell classification use case. The class activation maps on cell types with characteristic morphological features were found to be consistent with the explanations of a human domain expert. For example, the Auer rods in the cytoplasm were the predictive cellular feature for correctly classified images of faggot cells.

CONCLUSIONS

Our study provides data that can help hematology laboratories to choose the optimal training strategy for blood cell classification deep learning models to improve computer-assisted blood and bone marrow cell identification. It also highlights the need for more specific training data, i.e. images of difficult-to-classify classes, including cells labeled with disease information.

Immunohistochemical expression of perforin in adult systemic lupus erythematosus associated macrophage activation syndrome: Clinicohematological correlation and literature review

OBJECTIVE

To study the bone marrow (BM) immunohistomorphological characteristics in adult systemic lupus erythematosus (SLE) associated macrophage activation syndrome (SLE-MAS).

MATERIALS AND METHODS

Immunohistochemical (IHC) expression of CD3, CD8, perforin (PFN), and CD163 was studied on BM trephine biopsies from 30 cytopenic adult SLE cases (male: female = 1:5, age; 24 years, range; 19-32) and compared them with ten age matched controls. Clinicopathological parameters were compared among the cases likely (L) or unlikely (U) to have MAS using probability scoring criteria. The best cut off laboratory parameters to discriminate between the two were obtained through receiver operator curve (ROC) analysis.

RESULTS

MAS occurred in 12/30 (40%) cases and was more commonly associated with prior immunosuppressive therapy (p = .07), ≥ 3 system involvement (p = .09), lower fibrinogen (p < .01), increased triglyceride (p = .002), increased BM hemophagocytosis (p = .002), and higher MAS score [185 (176-203) vs. 105 (77-119), p < .01] than MAS-U subgroup. Although PFN+CD8+ T lymphocytes significantly decreased among cases than controls (p < .05), it was comparable between MAS-L and MAS-U subgroups. Fibrinogen (< 2.4 g/L, AUC; 0.93, p < .01), hemophagocytosis score (> 1.5, AUC; 0.71, p = .03), and an MAS probability score of ≥ 164 (AUC; 1, p < .01) discriminated MAS from those without MAS.

CONCLUSION

We noted a decrease in perforin mediated CD8 + T cell cytotoxicity in SLE. Immunohistochemical demonstration of the same along with histiocytic hemophagocytosis on BM biopsy may be useful adjunct in early diagnosis and management of MAS in SLE.

Bone marrow adipocytes fuel emergency hematopoiesis after myocardial infarction

After myocardial infarction (MI), emergency hematopoiesis produces inflammatory myeloid cells that accelerate atherosclerosis and promote heart failure. Since the balance between glycolysis and mitochondrial metabolism regulates hematopoietic stem cell homeostasis, metabolic cues may influence emergency myelopoiesis. Here, we show in humans and female mice that hematopoietic progenitor cells increase fatty acid metabolism after MI. Blockade of fatty acid oxidation by deleting carnitine palmitoyltransferase (Cpt1A) in hematopoietic cells of Vav1Cre/+Cpt1Afl/fl mice limited hematopoietic progenitor proliferation and myeloid cell expansion after MI. We also observed reduced bone marrow adiposity in humans, pigs and mice following MI. Inhibiting lipolysis in adipocytes using AdipoqCreERT2Atglfl/fl mice or local depletion of bone marrow adipocytes in AdipoqCreERT2iDTR mice also curbed emergency hematopoiesis. Furthermore, systemic and regional sympathectomy prevented bone marrow adipocyte shrinkage after MI. These data establish a critical role for fatty acid metabolism in post-MI emergency hematopoiesis.

The Effect of Video Streaming With Virtual Reality on Anxiety and Pain During Bone Marrow Aspiration and Biopsy Procedure

BACKGROUND

Pain and anxiety are among the most common symptoms in patients undergoing invasive procedures. Increased pain levels tend to worsen anxiety, and anxiety often leads to more frequent or severe pain.

AIMS

The study was conducted to determine the efficacy of virtual reality goggles (VRG) on pain and anxiety during bone marrow aspiration and biopsy (BMAB) procedure.

DESIGN

A randomized controlled experimental study.

SETTINGS

The outpatient unit of an adult hematology clinic of a tertiary care university hospital.

PARTICIPANTS/SUBJECTS

The study was conducted in patients aged 18 years and older who underwent a BMAB procedure. Thirty-five patients in the experimental (VRG) group and 40 patients in the control group.

METHODS

Patient identification form, visual analogue scale (VAS), state and trait anxiety inventory (STAI), and VRG were used to collect the data.

RESULTS

Postprocedural state anxiety mean scores were found to be statistically significantly higher in the control group than in the VRG group (p = .022). A statistically significant difference was found between groups in terms of procedure-related pain (p = .002). The postprocedural mean pain scores were found to be statistically significantly higher in the control group than in the VRG group (p < .001). A statistically significant but moderate positive correlation was found between the postprocedural pain and preprocedural state anxiety variable (r = 0.477). A statistically significant and strong positive correlation was found between the postprocedural pain and the postprocedural state anxiety variable (r = 0.657). A statistically significant but moderate positive relationship was found between preprocedural and postprocedural state anxiety variables (r = 0.519).

CONCLUSIONS

We determined that video streaming with VRG reduces pain and anxiety felt by adult patients during the BMAB procedure. VRG can be recommended to use in controlling pain and anxiety in patients undergoing a BMAB procedure.

Whole slide image representation in bone marrow cytology

One of the goals of AI-based computational pathology is to generate compact representations of whole slide images (WSIs) that capture the essential information needed for diagnosis. While such approaches have been applied to histopathology, few applications have been reported in cytology. Bone marrow aspirate cytology is the basis for key clinical decisions in hematology. However, visual inspection of aspirate specimens is a tedious and complex process subject to variation in interpretation, and hematopathology expertise is scarce. The ability to generate a compact representation of an aspirate specimen may form the basis for clinical decision-support tools in hematology. In this study, we leverage our previously published end-to-end AI-based system for counting and classifying cells from bone marrow aspirate WSIs, which enables the direct use of individual cells as inputs rather than WSI patches. We then construct bags of individual cell features from each WSI, and apply multiple instance learning to extract their vector representations. To evaluate the quality of our representations, we conducted WSI retrieval and classification tasks. Our results show that we achieved a mAP@10 of 0.58 ±0.02 in WSI-level image retrieval, surpassing the random-retrieval baseline of 0.39 ±0.1. Furthermore, we predicted five diagnostic labels for individual aspirate WSIs with a weighted-average F1 score of 0.57 ±0.03 using a k-nearest-neighbors (k-NN) model, outperforming guessing using empirical class prior probabilities (0.26 ±0.02). We present the first example of exploring trainable mechanisms to generate compact, slide-level representations in bone marrow cytology with deep learning. This method has the potential to summarize complex semantic information in WSIs toward improved diagnostics in hematology, and may eventually support AI-assisted computational pathology approaches.

Bone marrow haematopoiesis in patients with COVID-19

AIMS

Severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) infection broadly affects organ homeostasis, including the haematopoietic system. Autopsy studies are a crucial tool for investigation of organ-specific pathologies. Here we perform an in-depth analysis of the impact of severe coronavirus disease 2019 (COVID-19) on bone marrow haematopoiesis in correlation with clinical and laboratory parameters.

METHODS AND RESULTS

Twenty-eight autopsy cases and five controls from two academic centres were included in the study. We performed a comprehensive analysis of bone marrow pathology and microenvironment features with clinical and laboratory parameters and assessed SARS-CoV-2 infection of the bone marrow by quantitative polymerase chain reaction (qPCR) analysis. In COVID-19 patients, bone marrow specimens showed a left-shifted myelopoiesis (19 of 28, 64%), increased myeloid-erythroid ratio (eight of 28, 28%), increased megakaryopoiesis (six of 28, 21%) and lymphocytosis (four of 28, 14%). Strikingly, a high proportion of COVID-19 specimens showed erythrophagocytosis (15 of 28, 54%) and the presence of siderophages (11 of 15, 73%) compared to control cases (none of five, 0%). Clinically, erythrophagocytosis correlated with lower haemoglobin levels and was more frequently observed in patients from the second wave. Analysis of the immune environment showed a strong increase in CD68+ macrophages (16 of 28, 57%) and a borderline lymphocytosis (five of 28, 18%). The stromal microenvironment showed oedema (two of 28, 7%) and severe capillary congestion (one of 28, 4%) in isolated cases. No stromal fibrosis or microvascular thrombosis was found. While all cases had confirmed positive testing of SARS-CoV-2 in the respiratory system, SARS-CoV-2 was not detected in the bone marrow by high-sensitivity PCR, suggesting that SARS-CoV-2 does not commonly replicate in the haematopoietic microenvironment.

CONCLUSIONS

SARS-CoV-2 infection indirectly impacts the haematological compartment and the bone marrow immune environment. Erythrophagocytosis is frequent and associated with lower haemoglobin levels in patients with severe COVID-19.

Improved YOLOv7 Algorithm for Detecting Bone Marrow Cells

The detection and classification of bone marrow (BM) cells is a critical cornerstone for hematology diagnosis. However, the low accuracy caused by few BM-cell data samples, subtle difference between classes, and small target size, pathologists still need to perform thousands of manual identifications daily. To address the above issues, we propose an improved BM-cell-detection algorithm in this paper, called YOLOv7-CTA. Firstly, to enhance the model's sensitivity to fine-grained features, we design a new module called CoTLAN in the backbone network to enable the model to perform long-term modeling between target feature information. Then, in order to cooperate with the CoTLAN module to pay more attention to the features in the area to be detected, we integrate the coordinate attention (CoordAtt) module between the CoTLAN modules to improve the model's attention to small target features. Finally, we cluster the target boxes of the BM cell dataset based on K-means++ to generate more suitable anchor boxes, which accelerates the convergence of the improved model. In addition, in order to solve the imbalance between positive and negative samples in BM-cell pictures, we use the Focal loss function to replace the multi-class cross entropy. Experimental results demonstrate that the best mean average precision (mAP) of the proposed model reaches 88.6%, which is an improvement of 12.9%, 8.3%, and 6.7% compared with that of the Faster R-CNN model, YOLOv5l model, and YOLOv7 model, respectively. This verifies the effectiveness and superiority of the YOLOv7-CTA model in BM-cell-detection tasks.

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.

Detection of focal lesions in the clot section with negative bone marrow aspirate and trephine biopsy-A series of 5 cases

Bone marrow aspiration and trephine biopsies are commonly used procedures in clinical practice. The practice of making a clot section by using the leftover blood from the bone marrow aspirate material is not a commonly followed practice across centers. A clot section has the advantage of studying the added material with an increased possibility of detecting focal lesions such as myeloma, lymphoma, granuloma, and metastasis in the bone marrow. Bone marrow aspirate, trephine biopsy, and clot section were compared for the detection of focal lesions in a series of 5 patients, 3 of who presented with a history of fever and 2 were already diagnosed cases of Hodgkin lymphoma. Focal lesions were detected in the 5 cases in the clot section alone, whereas bone marrow aspirate and trephine biopsy did not show any focal lesion. Granulomatous infiltration was detected in 3 patients, and lymphomatous infiltration was detected in 2 patients in the clot section, whereas bone marrow aspirate and trephine biopsy were negative for any focal lesion in all 5 cases. A clot section is particularly useful in the detection of bone marrow lesions with a focal distribution. Hence, it must be studied alongside bone marrow aspirate smears, touch smears, and trephine biopsy to increase the diagnostic yield.

Bone Marrow Assessment in Liver Cirrhosis Patients with Otherwise Unexplained Peripheral Blood Cytopenia

We performed a retrospective single-center analysis to investigate the diagnostic yield of bone marrow puncture in patients with liver cirrhosis and cytopenia. Liver cirrhosis patients receiving bone marrow aspiration or biopsy for the diagnostic work-up of otherwise unexplained peripheral blood cytopenia at our institution between 2004 and 2020 were enrolled in this study. We evaluated findings from cytologic, histologic and immunologic assessment and final diagnostic outcomes. A total of 118 patients with a median age of 55 years and a median Child-Pugh score of B (8 points) were enrolled. The main etiologies of liver cirrhosis were viral hepatitis (B and C) or chronic alcohol consumption. The majority of patients (60%) exhibited concurrent anemia, leukocytopenia and thrombocytopenia. Bone marrow assessment revealed normal, unspecific or reactive alterations in 117 out of 118 patients (99%). One patient was diagnosed with myelodysplastic syndrome. Our findings suggest that peripheral blood cytopenia in patients with liver cirrhosis is rarely associated with a primary bone marrow pathology.

Digital assessment of peripheral blood and bone marrow aspirate smears

The diagnosis of benign and neoplastic hematologic disorders relies on analysis of peripheral blood and bone marrow aspirate smears. As demonstrated by the widespread laboratory adoption of hematology analyzers for automated assessment of peripheral blood, digital analysis of these samples provides many significant benefits compared to relying solely on manual review. Nonetheless, analogous instruments for digital bone marrow aspirate smear assessment have yet to be clinically implemented. In this review, we first provide a historical overview detailing the implementation of hematology analyzers for digital peripheral blood assessment in the clinical laboratory, including the improvements in accuracy, scope, and throughput of current instruments over prior generations. We also describe recent research in digital peripheral blood assessment, particularly in the development of advanced machine learning models that may soon be incorporated into commercial instruments. Next, we provide an overview of recent research in digital assessment of bone marrow aspirate smears and how these approaches could soon lead to development and clinical adoption of instrumentation for automated bone marrow aspirate smear analysis. Finally, we describe the relative advantages and provide our vision for the future of digital assessment of peripheral blood and bone marrow aspirate smears, including what improvements we can soon expect in the hematology laboratory.

Cell Count Differentials by Cytomorphology and Next-Generation Flow Cytometry in Bone Marrow Aspirate: An Evidence-Based Approach

Despite a lack of evidence, a bone marrow aspirate differential of 500 cells is commonly used in the clinical setting. We aimed to test the performance of 200-cell counts for daily hematological workup. In total, 660 consecutive samples were analyzed recording differentials at 200 and 500 cells. Additionally, immunophenotype results and preanalytical issues were also evaluated. Clinical and statistical differences between both cutoffs and both methods were checked. An independent control group of 122 patients was included. All comparisons between both cutoffs and both methods for all relevant types of cells did not show statistically significant differences. No significant diagnostic discrepancies were demonstrated in the contingency table analysis. This is a real-life study, and some limitations may be pointed out, such as a different sample sizes according to the type of cell in the immunophenotype analysis, the lack of standardization of some preanalytical events, and the relatively small sample size of the control group. The comparisons of differentials by morphology on 200 and 500 cells, as well as by morphology (both cutoffs) and by immunophenotype, are equivalent from the clinical and statistical point of view. The preanalytical issues play a critical role in the assessment of bone marrow aspirate samples.

An Automated Pipeline for Differential Cell Counts on Whole-Slide Bone Marrow Aspirate Smears

The pathologic diagnosis of bone marrow disorders relies in part on the microscopic analysis of bone marrow aspirate (BMA) smears and the manual counting of marrow nucleated cells to obtain a differential cell count (DCC). This manual process has significant limitations, including the analysis of only a small subset of optimal slide areas and nucleated cells, as well as interobserver variability due to differences in cell selection and classification. To address these shortcomings, we developed an automated machine learning-based pipeline for obtaining 11-component DCCs on whole-slide BMAs. This pipeline uses a sequential process of identifying optimal BMA regions with high proportions of marrow nucleated cells, detecting individual cells within these optimal areas, and classifying these cells into 1 of 11 DCC components. Convolutional neural network models were trained on 396,048 BMA region, 28,914 cell boundary, and 1,510,976 cell class images from manual annotations. The resulting automated pipeline produced 11-component DCCs that demonstrated a high statistical and diagnostic concordance with manual DCCs among a heterogeneous group of testing BMA slides with varying pathologies and cellularities. Additionally, we demonstrated that an automated analysis can reduce the intraslide variance in DCCs by analyzing the whole slide and marrow nucleated cells within all optimal regions. Finally, the pipeline outputs of region classification, cell detection, and cell classification can be visualized using whole-slide image analysis software. This study demonstrates the feasibility of a fully automated pipeline for generating DCCs on scanned whole-slide BMA images, with the potential for improving the current standard of practice for utilizing BMA smears in the laboratory analysis of hematologic disorders.

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.

Evaluation of two semi-supervised learning methods and their combination for automatic classification of bone marrow cells

Differential bone marrow (BM) cell counting is an important test for the diagnosis of various hematological diseases. However, it is difficult to accurately classify BM cells due to non-uniformity and the lack of reproducibility of differential counting. Therefore, automatic classification systems have been developed in which deep learning is used. These systems requires large and accurately labeled datasets for training. To overcome this, we used semi-supervised learning (SSL), in which learning proceeds while labeling. We used three methods: self-training (ST), active learning (AL), and a combination of these methods, and attempted to automatically classify 16 types of BM cell images. ST involves data verification, as in AL, before adding them to the training dataset (confirmed self-training: CST). After 25 rounds of CST, AL, and CST + AL, the initial number of training data increased from 425 to 40,518; 3682; and 47,843, respectively. Accuracies for the test data of 50 images for each cell type were 0.944, 0.941, and 0.976, respectively. Data added with CST or AL showed some imbalances between classes, while CST + AL exhibited fewer imbalances. We suggest that CST + AL, when combined with two SSL methods, is efficient in increasing training data for the development of automatic BM cells classification systems.

The necessity of bilateral staging bone marrow examinations for paediatric solid tumours

Background: Bone marrow aspirates and trephine biopsies (BMATs) form an important part of staging to detect bone marrow metastases of both haematological and nonhaematological neoplasms.Aim: The study’s primary aim was to determine whether it is necessary to perform bilateral BMATs on paediatric cancer patients as opposed to unilateral BMATs for the staging of solid tumours.Setting: The Paediatric Oncology Unit at Universitas Academic Hospital (UAH) in Bloemfontein, Free State, South Africa.Methods: A retrospective descriptive study was performed using laboratory reports from 01 January 2015 to 31 December 2019. Data were collected and reported on regarding the total number of staging BMATs performed, the average length of the trephine biopsies, the number of BMATs used for primary diagnosis, the number of bone marrow specimens where metastases were detected (left, right or both), the type of primary cancer and demographic information.Results: One hundred and eighteen patients were included for interpretation. Bone marrow metastases were detected in 28 patients, of which five patients had discrepant left and right results. These five cases included nephroblastoma (n = 2), Hodgkin lymphoma (n = 2) and a germ cell tumour (n = 1).Conclusion: Discrepant results were found in five cases (n = 28; 17.8%). Ultimately, the clinical implication of incorrectly staging solid tumours outweighs the small risks and discomfort of a bilateral bone marrow biopsy.

Digital morphology in hematology diagnosis and education: The experience of the European LeukemiaNet WP10

Hematological diagnostics is based on increasingly precise techniques of cellular and molecular analysis. The correct interpretation of the blood and bone marrow smears observed under an optical microscope still represents a cornerstone. Precise quantitative and qualitative cytomorphological criteria have recently been codified by up-to-date guidelines for diagnosing hematopoietic neoplasms. Morphological analysis has found formidable support in digital reproduction techniques, which have simplified the circulation of images for educational or consultation purposes. From 2007 to 2019, the Working Group WP10 of European LeukemiaNet (ELN) used, in annual exercises, digital images to support training in cytomorphology and verify harmonization and comparability in the interpretation of blood and bone marrow smears. We describe the design, development, and results of this program, which had 741 participants in-person or remotely, to which 2055 questions were submitted regarding the interpretation of cytomorphological images. We initially used circulation and presentation of digital microphotographs and then introduced a virtual microscopy (VM). Virtual slides were obtained using a whole slide imaging technique, similar to the one largely used in histopathology, to produce digitized scans of consecutive microscopic fields and reassembles them to obtain a complete virtual smear by stitching. Participants were required to identify cells in labeled fields of view of the virtual slides to obtain a morphological diagnosis. This work has demonstrated substantial improvements in diagnostic accuracy and harmonization with the VM technique. Between-observer concordance increased from 62.5% to 83.0%. The integrity of the digitalized film image, which provides a general context for cell abnormalities, was the main factor for this outcome.

Efficient and Highly Accurate Diagnosis of Malignant Hematological Diseases Based on Whole-Slide Images Using Deep Learning

Hematopoietic disorders are serious diseases that threaten human health, and the diagnosis of these diseases is essential for treatment. However, traditional diagnosis methods rely on manual operation, which is time consuming and laborious, and examining entire slide is challenging. In this study, we developed a weakly supervised deep learning method for diagnosing malignant hematological diseases requiring only slide-level labels. The method improves efficiency by converting whole-slide image (WSI) patches into low-dimensional feature representations. Then the patch-level features of each WSI are aggregated into slide-level representations by an attention-based network. The model provides final diagnostic predictions based on these slide-level representations. By applying the proposed model to our collection of bone marrow WSIs at different magnifications, we found that an area under the receiver operating characteristic curve of 0.966 on an independent test set can be obtained at 10× magnification. Moreover, the performance on microscopy images can achieve an average accuracy of 94.2% on two publicly available datasets. In conclusion, we have developed a novel method that can achieve fast and accurate diagnosis in different scenarios of hematological disorders.

Relapse surveillance of acute myeloid leukemia patients in first remission after consolidation chemotherapy: diagnostic value of regular bone marrow aspirations

The optimal follow-up care for relapse detection in acute myeloid leukemia (AML) patients in first remission after consolidation therapy with intensive chemotherapy is not established. In this retrospective study, we evaluate the diagnostic value of an intensive relapse surveillance strategy by regular bone marrow aspirations (BMA) in these patients. We identified 86 patients with newly diagnosed non-promyelocytic AML who had reached complete remission (CR) after intensive induction and consolidation chemotherapy between 2007 and 2019. Annual relapse rates were 40%, 17%, and 2% in years 1-3, respectively. Patients in CR were surveilled by BMA scheduled every 3 months for 2 years, followed by BMA every 6 months. This surveillance regimen detected 29 of 55 relapses (53%), 11 of which were molecular relapses (20%). The remaining 26 of 55 relapses (47%) were diagnosed by non-surveillance BMA prompted by specific suspicion of relapse. Most patients showed concurrent morphological abnormalities in peripheral blood (PB) at time of relapse. Seven percent of all morphological relapses occurred without simultaneous PB abnormalities and would have been delayed without surveillance BMA. Intensified monthly PB assessment paired with BMA every 3 months during the first 2 years may be a highly sensitive relapse surveillance strategy.

Automated bone marrow cytology using deep learning to generate a histogram of cell types

Background

Bone marrow cytology is required to make a hematological diagnosis, influencing critical clinical decision points in hematology. However, bone marrow cytology is tedious, limited to experienced reference centers and associated with inter-observer variability. This may lead to a delayed or incorrect diagnosis, leaving an unmet need for innovative supporting technologies.

Methods

We develop an end-to-end deep learning-based system for automated bone marrow cytology. Starting with a bone marrow aspirate digital whole slide image, our system rapidly and automatically detects suitable regions for cytology, and subsequently identifies and classifies all bone marrow cells in each region. This collective cytomorphological information is captured in a representation called Histogram of Cell Types (HCT) quantifying bone marrow cell class probability distribution and acting as a cytological patient fingerprint.

Results

Our system achieves high accuracy in region detection (0.97 accuracy and 0.99 ROC AUC), and cell detection and cell classification (0.75 mean average precision, 0.78 average F1-score, Log-average miss rate of 0.31).

Conclusions

HCT has potential to eventually support more efficient and accurate diagnosis in hematology, supporting AI-enabled computational pathology.

Identifying and counting cells in bone marrow samples, known as cytology, is critical for the diagnosis of blood disorders. This is a complex and labor-intensive process, with some variation in how hematopathologists interpret these samples. Here, we develop an artificial intelligence system for automated bone marrow cytology, which automatically detects and identifies all types of cells found in the bone marrow. This information is summarized in a chart that we call the Histogram of Cell Types (HCT), a new way to represent complex information generated in bone marrow cytology. Our system achieves high accuracy and precision in classifying the different types of bone marrow cells as a HCT. This tool may eventually help clinicians to make more efficient and accurate diagnoses.

Moosavi Tayebi et al. develop a deep learning-based computational pathology tool for automated bone marrow cytology from whole slide images. Their approach generates a histogram of cell types present within the bone marrow aspirate to aid in diagnostic haematopathology.

A method to classify bone marrow cells with rejected option

Bone marrow cell morphology has always been an important tool for the diagnosis of blood diseases. Still, it requires years of experience from a suitable person. Furthermore, the outcomes of their recognition are subjective and there is no objective quantitative standard. As a result, developing a deep learning automatic classification system for bone marrow cells is extremely important. However, typical classification machine learning systems only produce classification answers, and will not refuse to generate predictions when the prediction reliability is low. It will pose a big problem in some high-risk systems such as bone marrow cell recognition. This paper proposes a bone marrow cell classification method with rejected option (CMWRO) to classify 11 bone marrow cells. CMWRO is based on convolutional neural networks, ICP and SoftMax (CNN-ICP-SoftMax), containing a classifier with rejected option. When the rejected rate (RR) of tested samples is 0.3143, it can ensure that the precision, sensitivity, accuracy of the accepted samples reach 0.9921, 0.9917 and 0.9944 respectively. And the rejected samples will be handled by other ways, such as identified by doctors. Besides, the method has a good filtering effect on cell types that the classifier is not trained, such as abnormal cells and cells with less sample distribution. It can reach more than 82% in filtering efficiency. CMWRO improves the doctors' trust in the results of accepted samples to a certain extent. They only need to carefully identify the samples that CMWRO refuses to recognize, and finally combines the two results. It can greatly improve the efficiency and accuracy of bone marrow cell recognition.

Bone Marrow Collection: Comparison of Unassisted vs Assisted Bedside Collections by a Laboratory Technologist

OBJECTIVES

Bone marrow collections are often difficult, and creating quality smears and touch preparations at the bedside can prove challenging. The objective of this study is to compare the quality of bone marrow specimens between unassisted and assisted bone marrow collections by a bone marrow technologist.

METHODS

Data for this study were collected from 422 hematopathology reports over 14 months. We recorded the bone marrow quality of the different parts (aspirate smears, touch imprints, core biopsy, and clot/particle sections) as adequate, suboptimal, or inadequate. Student t test statistical analysis was performed between the corresponding parts in the two groups.

RESULTS

Our results demonstrate that the quality of assisted bone marrow specimens is significantly better compared with unassisted specimens, particularly for the aspirate smears (P < .0001) and touch imprints (P < .0001). Notably, the quality of aspirate smears was improved, which is important for cytologic evaluation.

CONCLUSIONS

We conclude that assistance by a bone marrow technologist resulted in a significant improvement in the quality of bone marrow collection.

Bone marrow aspiration and biopsy: techniques and practice implications

Bone marrow aspiration and biopsy (BMAB) is a valuable diagnostic procedure commonly performed for evaluation of a wide spectrum of diseases including hematologic abnormalities, nonhematologic malignancies, metabolic abnormalities, and tumor treatment response such as chemotherapy and bone marrow transplantation, hematologic tumor staging, and suspected infection in patients with fever of unknown origin. This minimally invasive intervention offers excellent safety profile and a high diagnostic yield. Radiologists should be familiar with clinical implications of BMAB for patient care and be able to implement various technical armamentarium available to achieve a safe intervention while maximizing procedure yield.

Sternal aspirate sampling of Bacillariophyceae (diatoms) and Cyanobacteria in suspected drowning cases

A diagnosis of drowning is not always possible based on the traditional autopsy findings. The most widely used ancillary methods are based on the detection of diatoms and other waterborne organisms in the organs of the systemic circulation by light microscope or polymerase chain reaction (PCR). One of the greatest concerns is sample contamination. Bone marrow is a favourable source because the compact bone protects the sample from water ingress in the case of advanced decay. In our pilot study, we aimed to adopt sternal bone marrow aspiration - which is a widely used technique in haematology - for postmortem sampling. Control experiments of non-drowning victims showed that cleaning the skin over the sternum can prevent external contamination. Sternal aspirate samples were taken from seven suspected drowning victims along with lung, spleen, and femoral bone marrow samples. All specimens were examined for the presence of diatoms by light microscope and Cyanobacteria-specific DNA by PCR. We were able to obtain bone marrow aspirates from all cases without complications. In four of the sternal samples both diatoms and cyanobacterial DNA were detected, while one additional sternum sample was tested positive with PCR, but no diatom shells were detectable. Sternal bone marrow aspiration is simple and quick, which can be performed at the beginning of an autopsy, minimizing the chance of contamination. We have shown that this sampling method can be adopted for postmortem diatom testing. This minimally invasive technique might be used in virtual autopsy (postmortem computed tomography, PMCT) settings without opening body cavities.

Image Guided Bone Marrow Biopsy

Bone marrow biopsy and aspiration are common diagnostic procedures used for the diagnosis and monitoring of multiple conditions including hematologic malignancies, non-hematologic malignancies, infection, and metabolic processes. While these procedures can be done on the inpatient floor or in clinic, imaging guidance has been utilized to improve patient safety. This article will review the patient work-up and considerations, as well as technique for performing both computed tomography and fluoroscopic guided bone marrow biopsies.

Bone Marrow Hypocellularity in Patients with End-Stage Kidney Disease

Background. Anemia and pancytopenia are not uncommon in patients with chronic kidney disease (CKD). Nevertheless, there is insufficient literature analyzing bone marrow pathology in patients with CKD or end-stage kidney disease (ESKD) receiving dialysis. Methods. This observational cohort study included 22 patients with ESKD and 23 patients with CKD that received bone marrow biopsy and aspiration at Chang Gung Memorial Hospital. Demographic, hematological, and biochemical data were collected at the time of bone marrow study for analysis. Results. Bone marrow aspiration demonstrated that patients with ESKD had a lower percentage of blasts than patients with CKD (0.52 ± 0.84 versus 1.06 ± 0.78 %, p = 0.033). Bone marrow biopsy revealed that the overall incidence of hypocellular bone marrow was 55.6%. Furthermore, patients with ESKD had higher proportion of hypocellular bone marrow than patients with CKD (72.7% versus 39.1%, p = 0.023). In a multivariate logistic regression model, it was revealed that ESKD status (odds ratio 9.43, 95% confidence interval 1.66–53.63, p = 0.011) and megakaryocyte count within bone marrow (odds ratio 0.48, 95% confidence interval 0.29–0.79, p = 0.004) were significant predictors for bone marrow hypocellularity. Conclusion. Bone marrow hypocellularity is common in patients with kidney dysfunction. Hypocellular marrow occurs more frequently in patients with ESKD than patients with CKD.

Deep learning for bone marrow cell detection and classification on whole-slide images

Bone marrow (BM) examination is an essential step in both diagnosing and managing numerous hematologic disorders. BM nucleated differential count (NDC) analysis, as part of BM examination, holds the most fundamental and crucial information. However, there are many challenges to perform automated BM NDC analysis on whole-slide images (WSIs), including large dimensions of data to process, complicated cell types with subtle differences. To the authors best knowledge, this is the first study on fully automatic BM NDC using WSIs with 40x objective magnification, which can replace traditional manual counting relying on light microscopy via oil-immersion 100x objective lens with a total 1000x magnification. In this study, we develop an efficient and fully automatic hierarchical deep learning framework for BM NDC WSI analysis in seconds. The proposed hierarchical framework consists of (1) a deep learning model for rapid localization of BM particles and cellular trails generating regions of interest (ROI) for further analysis, (2) a patch-based deep learning model for cell identification of 16 cell types, including megakaryocytes, mitotic cells, and four stages of erythroblasts which have not been demonstrated in previous studies before, and (3) a fast stitching model for integrating patch-based results and producing final outputs. In evaluation, the proposed method is firstly tested on a dataset with a total of 12,426 annotated cells using cross validation, achieving high recall and accuracy of 0.905 ± 0.078 and 0.989 ± 0.006, respectively, and taking only 44 seconds to perform BM NDC analysis for a WSI. To further examine the generalizability of our model, we conduct an evaluation on the second independent dataset with a total of 3005 cells, and the results show that the proposed method also obtains high recall and accuracy of 0.842 and 0.988, respectively. In comparison with the existing small-image-based benchmark methods, the proposed method demonstrates superior performance in recall, accuracy and computational time.

Neoteric Algorithm Using Cell Population Data (VCS Parameters) as a Rapid Screening Tool for Haematological Disorders

Hitherto, there has been no comprehensive study on the usefulness of cell population data (CPD) parameters as a screening tool in the discrimination of non-neoplastic and neoplastic haematological disorders. Hence, we aimed to develop an algorithm derived from CPD parameters to enable robust screening of neoplastic from non-neoplastic samples and subsequently to aid in differentiating various neoplastic haematological disorders. In this study, the CPD parameters from 245 subtypes of leukaemia and lymphoma were compared against 1103 non-neoplastic cases, and those CPD parameters that were vigorous discriminants were selected for algorithm development. We devised a novel algorithm: [(SD-V-NE*MN-UMALS-LY*SD-AL2-MO)/MN-C-NE] to distinguish neoplastic from non-neoplastic cases. Following that, the single parameter MN-AL2-NE was used as a discriminant to rule out reactive cases from neoplastic cases. We then assessed CPD parameters that were useful in delineating leukaemia subtypes as follows: AML (SD-MALS-NE and SD-UMALS-NE), APL (MN-V-NE and SD-V-MO), ALL (MN-MALS-NE and MN-LMALS-NE) and CLL (SD-C-MO). Prospective studies were carried out to validate the algorithm and single parameter, MN-AL2-NE. We propose these CPD parameter-based discriminant strategies to be adopted as an initial screening and flagging system in the preliminary evaluation of leukocyte morphology.

A Synoptic Reporting System to Monitor Bone Marrow Aspirate and Biopsy Quality

Objectives:

Bone marrow evaluation plays a critical role in the diagnosis, staging, and monitoring of many diseases. Although there are standardized guidelines for assessing bone marrow specimen quality, there is a lack of evidence-based tools to perform such assessments. The objective was to monitor bone marrow sample quality in real time by standardizing the basic components of a synoptic report and incorporating it into a bone marrow report template.

Materials and Methods:

A relational database of bone marrow quality parameters was developed and incorporated into our laboratory information system bone marrow report template, with data entry completed during specimen sign out. Data from multiple reports created within a date range were extracted by Structured Query Language query, and summarized in tabular form. Reports generated from these data were utilized in quality improvement efforts.

Results:

The synoptic reporting system was routinely used to record the quality of bone marrow specimens from adult patients. Data from 3189 bone marrow aspirates, 3302 biopsies, and 3183 biopsy touch imprints identified hemodilution as the principal issue affecting bone marrow aspirate quality, whereas aspiration artifact and fragmentation affected bone marrow biopsy quality.

Conclusions:

The bone marrow synoptic reporting process was easy to use, readily adaptable, and has proved a useful component of the overall quality assurance process to optimize bone marrow quality.

Pathological features in 'humanized' neonatal pig

Cytidine monophosphate-Nacetylneuraminic acid (Neu5Ac) hydroxylase (CMAH) and glycoprotein, alpha1, 3-galactosyltransferase (GGTA1) double knockout (DKO) pig models were produced to reduce immune reaction for xenotransplantation. However, the role of Neu5Gc and α-Gal in pigs has not been fully elucidated and it is necessary to consider the after-effect of inactivation of GGTA1 and CMAH in pigs. Hematological profiles of DKO pigs were analyzed through complete blood count (CBC). Histology of liver and spleen of DKO were investigated, and lectin blotting and mass spectrometry (MS) were performed to explore glycosylation changes in red blood cell (RBC) membranes of DKO pigs. DKO pigs showed common clinical signs such as weakness (100%), dyspnea (90%) and constipation (65%). DKO pigs revealed a significant decrease in RBC, hemoglobin (HGB) and hematocrit (HGB), and an increase in white blood cell (WBC), lymphocyte (LYM), monocyte (MON), and erythrocyte mean corpuscular volume (MCV). DKO piglets showed swollen liver and spleen, and exhibited raised deposition of hemosiderin and severe bleeding. Lectin assay and MS proved variations in glycosylation on RBC membranes. GGTA1/CMAH DKO pigs developed pathological features which are similar to anemic symptoms, and the variations in glycosylation on RBC membranes of DKO pigs may be attributed to the pathologies observed.