Acute basophilic leukemia (ABL) transformed from myelodysplastic syndrome is exceedingly rare. We report the case of a 73-year-old man with ABL which transformed from IPSS-M High risk MDS. The patient had a history of metastatic castration-sensitive prostate cancer. Further investigations demonstrated circulating blasts on peripheral blood smear. Upon bone marrow examination, a diagnosis of ABL arising from underlying MDS was established, characterized by cytogenetic analysis demonstrating trisomy 8 (+ 8), with the additional copy of chromosome 8 present in the form of a ring chromosome, and a WT1 frameshift mutation. The patient was treated with azacitidine and venetoclax, followed by best supportive care after disease progression. This case highlights the rare occurrence of ABL secondary to MDS and provides insight into the diagnostic challenges, clonal evolution, and therapeutic limitations associated with this aggressive entity.

Emperipolesis, a cell-in-cell phenomenon, involves a viable cell being transiently internalized within another cell’s cytoplasm from which it can exit without damaging either cell. In this report, we discuss the rarity of the emperipolesis of erythrocytes and erythroblasts, instead of the more commonly observed neutrophils. We report the case of a 52-year-old Chinese male who presented with pancytopenia and 33% blasts. Multiple mutations were revealed, including DNMT3A K826R, RUNX1 F396fs159, BCOR Q1208fs8, BCORL1 S575*, and PHF6 H302R. The patient was diagnosed with acute myeloid leukemia, myelodysplasia-related changes (AML-MR), and was treated with azacitidine and venetoclax, followed by daunorubicin and cytarabine (DA 3+7). This case highlights the rare occurrence of emperipolesis involving erythroid cells in AML-MR. We conducted a literature review exploring emperipolesis using PubMed, with search terms consisting of “emperipolesis”, “megakaryocytes”, “erythrocyte”, “erythroblast”, “neutrophil” and “lymphocyte”. A total of 24 articles that observed erythroid emperipolesis were referenced in this review, including 7 relevant case reports/series.

Thrombotic microangiopathies (TMA) can be attributed to a wide variety of causes and the diagnostic process is often challenging, especially when the clinical scenario is full of other confounding factors. Hemolysis can be due to complement-mediated thrombotic microangiopathies and drug-induced hemolytic anemia in the appropriate clinical context. In this case presentation, two patients with TMA including a patient diagnosed with complement-mediated TMA after a through screen of other differential diagnoses, and a multiple myeloma patient on chemotherapy with primaquine-induced hemolytic anemia in the background of treatment for possible pneumocystis jirovecii pneumonia. A thorough review of the drug history of patients presenting with TMA should be conducted, along with a heightened index of suspicion for complement-mediated disorders such as complement-mediated TMA, which should be entertained after ruling out a wide variety of differential diagnoses.

It is not common to observe a variety of paraproteins produced in the body which are capable of leading to inaccurate values in laboratory testing. The current case report focused on an 82-year-old Malay male, initially presenting with symptoms of hyperviscosity syndrome (HVS), including unilateral weakness and reduced level of effort tolerance, who had a paraprotein in the body that interfered with the values of the complete blood count (CBC) in the laboratory. A routine sample of CBC was dispatched to the laboratory and was reported as clotted in the automated analysis. The laboratory was unable to proceed to analyze bone marrow aspirate, serum electrophoresis (ELP), and flow cytometry due to the presence of the paraprotein. To properly identify the paraprotein and to enable correct analysis of the necessary laboratory testing, a water bath of 37°C was employed with the blood tube, and glacial acetic acid, along with Owren-Koller buffer, was utilized to make the paraprotein soluble. Subsequently, the CBC and serum ELP were manually performed, demonstrating a paraprotein of immunoglobulin M (IgM) lambda. Symptoms were HVS gradually resolved with rituximab and bendamustine, with a reduction in the level of the IgM paraprotein. The current case highlights the importance of an effective, alternative method of solubilization for a paraprotein that interfered with usual laboratory practices.

BACKGROUND:The peripheral blood film (PBF) analysis traditionally relies on manual microscopy (MM), a labour-intensive method with inter-observer variability. This study evaluates Blade (a semi-supervised AI model) and CellaVision DM9600 (commercial benchmark) against MM in automated leukocyte classification. METHODS:PBFs from 168 patients were prepared using automated staining and scanned digitally. Blade, trained on 185 412 cells (75 435 labelled, 109 977 unlabelled) via ResNet34 and RetinaNet architectures, underwent pseudo-labelling and AdamW optimisation. Performance was evaluated on 1675 cells against MM using the concordance correlation coefficient (CCC), Bland-Altman analysis, Deming/Passing-Bablok regression and diagnostic accuracy measures across nine leukocyte subtypes. RESULTS:When evaluated individually against MM, both systems showed high agreement. Blade achieved excellent correlation for common cells (neutrophils: ccc = 0.988; lymphocytes: ccc = 0.985; eosinophil: ccc = 0.953) and comparable results to CellaVision for monocytes (ccc = 0.852 vs. 0.847) and basophils (ccc = 0.762 vs. 0.794). Blade performed better for metamyelocytes (ccc = 0.905 vs. 0.756) and showed higher sensitivity for monocytes (75% vs. 63%) and myelocytes (87% vs. 74%). Regression analysis showed slopes close to 1.0 for most cell types, with Blade displaying narrower Limits of Agreement in Bland-Altman analysis. Both systems achieved 100% sensitivity for blasts and reactive lymphocytes. Overall macro-averaged performance was comparable between Blade (sensitivity 89.2%, specificity 96.3%) and CellaVision (86.3% and 96.7%). CONCLUSION:Blade and CellaVision demonstrated strong concordance with MM, validating their clinical utility. Blade's semi-supervised learning confers marginal advantages in rare cell detection and stability, highlighting AI's potential to enhance diagnostic accuracy. While both systems reduce labour and variability, Blade's performance has potential for integration into haematology workflows. Future validation in diverse cohorts is recommended.

Department of Haematology, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Khoo Teck Puat Hospital, Singapore Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore Yong Loo Lin School of Medicine, National University of Singapore, Singapore ASUS Intelligent Cloud Services (AICS), Singapore Department of Laboratory Medicine, Tan Tock Seng Hospital, Singapore School of Computing, National University of Singapore, Singapore

Artificial intelligence (AI) is a disruptive technology that holds great promise in medicine, due to its ability to effortlessly assimilate, integrate, and generate vast amounts of clinical data. In the hematology laboratory, the quality of digital blood cell images captured from peripheral blood films used in AI algorithms for blood cell classification1 far surpasses the early twentieth-century hand-drawn medical artwork of blood cells as seen under the light microscope (Image 1A). Advances in laboratory automation, coupled with high-throughput digital slide scanners allow the acquisition of high-resolution, whole-slide images of Romanowsky-stained peripheral blood films. This has enabled the creation of large image databanks of blood cells, allowing the exponential growth of artificial intelligence (AI) studies in blood cell classification and identification of blood-borne parasites such as malaria.2 Departing from existing commercial laboratory solutions3 and conventional AI approaches in hematology focused on pattern recognition and task automation,4, 5 we describe the novel use of an AI generation algorithm to synthesize artificial, yet morphologically realistic images of leukemic blasts. We utilized an open-source AI StyleSwin algorithm6 which is based on a generative adversarial network (GAN), for the image synthesis of realistic leukemic blasts. A total of 21 739 pre-annotated digital images (for examples, see Image 1B, C) derived from peripheral blood films of our patients with acute myeloid leukemia (Wright stain, 80× objective, Motic EasyScan Infinity 60) were used in the training and evaluation process. A total of 17 431 images of leukemic blasts were used for training, with 4308 images randomly chosen for model evaluation. The annotation of each cell was performed by 2 laboratory-certified medical technologists and validated by a hematologist. The StyleSwin GAN model was trained with default parameters and a batch size of 3 on a Tesla V100 GPU with a graphics RAM size of 16 GB. Sample images were generated at every 50 000 steps for evaluation, and the model was trained with a total of 500 000 steps. The AI-generated blasts had classic morphological features, which included a high nuclear-cytoplasmic ratio, the appearance of less condensed nuclei with an immature chromatin pattern, as well as the presence of prominent nucleoli7 (Image 1D–F). The AI-generated images of red blood cells in the image background were representative of the classic red cell appearance, with anuclear red blood cells with characteristic central pallor seen. The main limitation of the AI-generated leukemic blasts was that there was coarse pixelation of nuclei and nucleoli, whereas in digitized images of peripheral blood film-captured blasts (Image 1B, C), the fine chromatin pattern of the nuclei is seen without obvious pixelation. An explanation for the coarse pixelation may be due to either the image resolution limitations of StyleSwim's image generation method or the limited amount of GAN training performed; or both factors. Furthermore, other features that are characteristic of myeloid blasts such as Auer rods were not generated, even though the training dataset did have a small proportion of blasts with Auer rods (approximately 2% of all images). The AI model also generated a series of blasts that were less realistic (Image 2). These had irregular nuclei with a checkered pixelated pattern which were morphologically not consistent with myeloid blasts. However, the less realistic artificially created blasts still demonstrated some classic features, which include a high nuclear-cytoplasmic ratio, and in some cells, the presence of a crude, irregularly, pixelated nucleolus. This suggests that the GAN was able to assimilate and capture the key morphological features of blasts from the training dataset, but not able to generate highly accurate versions consistently. AI-generated medical images using GAN8 can help overcome medical data scarcity and mitigate privacy concerns regarding the use of patient data. These images may potentially be enhanced with advanced computer algorithms or recreated with higher resolution with less noise and used to augment research datasets. Such images could also contribute to testing in computer-simulated benchtop trials for regulatory evaluation of AI software as a medical device (SaMD). Finally, AI-powered image generation offers a unique tool to facilitate the education of healthcare staff.9 In digital morphology, learners can be presented with images of one or more relevant cell types depicting existing morphological features to reinforce the structure appearance and key characteristics of different cells. Further frameworks are needed to evaluate the validity of AI-generated images for use in clinically meaningful endpoints and should be subjected to quality control by domain experts to reduce the risk of harm-by-data that result in algorithmic biases,10 before clinical application in patient care. All authors contributed to the image curation, annotation, and analysis. Ngai Tung Eric Kwok performed the AI training and generation of digital images, with Stefan Winkler providing supervision and technical guidance. Bingwen Eugene Fan is supported by the National Medical Research Council (NMRC) Clinician Innovator Development Award (NMRC/CIDA19May-0004). This work was funded in part by the Centre for Medical Technologies and Innovations—National Health Innovation Centre grant (CMTi-NHIC3-21-01-07). The authors declare no conflicts of interest. The data that support the findings of this study are available from the corresponding author upon reasonable request.

We declare no conflicts of interest. The data that support the findings of this study are available from the corresponding author upon reasonable request.

Artificial intelligence (AI) and its application in classification of blood cells in the peripheral blood film is an evolving field in haematology. We performed a rapid review of the literature on AI and peripheral blood films, evaluating the condition studied, image datasets, machine learning models, training set size, testing set size and accuracy. A total of 283 studies were identified, encompassing 6 broad domains: malaria (n = 95), leukemia (n = 81), leukocytes (n = 72), mixed (n = 25), erythrocytes (n = 15) or Myelodysplastic syndrome (MDS) (n = 1). These publications have demonstrated high self-reported mean accuracy rates across various studies (95.5% for malaria, 96.0% for leukemia, 94.4% for leukocytes, 95.2% for mixed studies and 91.2% for erythrocytes), with an overall mean accuracy of 95.1%. Despite the high accuracy, the challenges toward real world translational usage of these AI trained models include the need for well-validated multicentre data, data standardisation, and studies on less common cell types and non-malarial blood-borne parasites.

aDepartment of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA bClinical Microbiology Laboratory, Hospital of the University of Pennsylvania, Philadelphia, PA, USA cInfectious Disease Diagnostics Laboratory, Children’s Hospital of Philadelphia, Philadelphia, PA, USA dDivision of Infectious Diseases, Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

American Journal of HematologyVolume 96, Issue 12 p. 1715-1716 IMAGES IN HEMATOLOGYFree Access Chronic dapsone use causing methemoglobinemia with oxidative hemolysis and dyserythropoiesis Christian Aledia Gallardo, Corresponding Author Christian Aledia Gallardo [email protected] orcid.org/0000-0001-5048-4259 Department of Haematology, Tan Tock Seng Hospital, Singapore Correspondence Christian Aledia Gallardo, Department of Haematology, Tan Tock Seng Hospital, Singapore. Email: [email protected]Search for more papers by this authorBingwen Eugene Fan, Bingwen Eugene Fan orcid.org/0000-0003-4367-5182 Department of Haematology, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Khoo Teck Puat Hospital, Singapore Lee Kong Chian School of Medicine, Singapore Yong Loo Lin School of Medicine, SingaporeSearch for more papers by this authorKian Guan Eric Lim, Kian Guan Eric Lim Department of Laboratory Medicine, Tan Tock Seng Hospital, SingaporeSearch for more papers by this authorPonnudurai Kuperan, Ponnudurai Kuperan Department of Haematology, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Khoo Teck Puat Hospital, Singapore Lee Kong Chian School of Medicine, Singapore Yong Loo Lin School of Medicine, SingaporeSearch for more papers by this author Christian Aledia Gallardo, Corresponding Author Christian Aledia Gallardo [email protected] orcid.org/0000-0001-5048-4259 Department of Haematology, Tan Tock Seng Hospital, Singapore Correspondence Christian Aledia Gallardo, Department of Haematology, Tan Tock Seng Hospital, Singapore. Email: [email protected]Search for more papers by this authorBingwen Eugene Fan, Bingwen Eugene Fan orcid.org/0000-0003-4367-5182 Department of Haematology, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Khoo Teck Puat Hospital, Singapore Lee Kong Chian School of Medicine, Singapore Yong Loo Lin School of Medicine, SingaporeSearch for more papers by this authorKian Guan Eric Lim, Kian Guan Eric Lim Department of Laboratory Medicine, Tan Tock Seng Hospital, SingaporeSearch for more papers by this authorPonnudurai Kuperan, Ponnudurai Kuperan Department of Haematology, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Tan Tock Seng Hospital, Singapore Department of Laboratory Medicine, Khoo Teck Puat Hospital, Singapore Lee Kong Chian School of Medicine, Singapore Yong Loo Lin School of Medicine, SingaporeSearch for more papers by this author First published: 01 February 2021 https://doi.org/10.1002/ajh.26116Citations: 2AboutSectionsPDF ToolsRequest permissionExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL An 82-year-old Chinese female known to have erythrodermic pemphigus with background of psoriasis was started on dapsone for 4 months prior to admission. She was then admitted due to delirium and desaturation. On admission, oxygen saturation was 89% on room air, which subsequently improved with high flow oxygen therapy. The full blood count showed hemoglobin 11.2 g/dL (reference range: 13.6–16.6 g/dL), white blood cells 23.9 × 109/L (reference range: 4.0–9.6 × 109/L), platelets 362 × 109/L (reference range: 150–360 × 109/L) and reticulocyte counts 220.8 × 109/L (reference range: 25–85 × 109/L). Markers of hemolytic anemia were present, including an elevated LDH at 730 U/L (reference range: 270–550 U/L), elevated total bilirubin 54 mmol/L (reference range: 5–30 mmol/L) and low haptoglobulin at <30 mg/dL (reference range: 36–200 mg/dL) but direct Coombs test was negative. Peripheral blood film showed significant numbers of irregularly contracted red cells, bite cells and fragmented cells, suggestive of oxidative hemolysis. There were also Howell-Jolly bodies and Papenheimer bodies seen suggestive of possible dyserythropoiesis. Blood methemoglobin level was elevated at 8.2%. Her G6PD assay was normal. In view of clinical findings of oxidative hemolysis and methemoglobinemia, dapsone was stopped. She was then started on folic acid and vitamin C at 1 gram twice a day. Two days after, her oxygen saturation improved, and a repeat blood methemoglobin level improved to 1.8%. IMAGE 1Open in figure viewerPowerPoint Image 1A: Features of red cell oxidative hemolysis including bite cells (yellow arrow), blister cells (green arrow) and irregularly contracted cells (orange arrow) on a background of polychromasia. There are also Howell-Jolly bodies seen (blue arrow). Image 1B: Dyserythropoietic changes in the red cell series showing Pappenheimer bodies (yellow arrow) on the background of oxidative hemolysis showing bite cells (green arrow). Image 1C: Dyserythropoietic changes in the red cell series showing Howell-Jolly Bodies (blue arrow) on the background of oxidative hemolysis showing bite cells (green arrow) Dapsone is known as a cause of drug induced hemolytic anemia and methemoglobinemia due to N-hydroxylation to a hydroxylamine derivative that is directly toxic to RBCs.1, 2 The amine metabolites of dapsone are capable of oxidation of heme iron, resulting in acquired methemoglobinemia and hemoglobin denaturation forming Heinz bodies which are removed by splenic macrophages, forming bite cells and irregularly contracted cells.3 In addition, given the chronic consumption of dapsone for 4 months, compounded with the long standing oxidative hemolysis, the features observed in the patient's blood film such as the presence of Howell-Jolly and Pappenheimer bodies probably represent dyserythropoiesis secondary to erythroid stress. FINANCIAL DISCLOSURES None. FUNDING INFORMATION None. Open Research DATA AVAILABILITY STATEMENT Data is available on request from the corresponding author. REFERENCES 1Pendse A, Ferdoriw Y, Willis M, et al. Unexpected cause of anemia in 45-year-old patient with acute lymphoblastic leukemia. Laboratory Medicine. 2010; 41(11): 645- 648. https://doi.org/10.1309/LMK7OA1GYP3SRDBD 2Weil A, Whinney C. Hemolytic anemia in Dapsone overdose: a late complication. Journal of Hospital Medicine, 2009; 4(S1): 135. May 14-17, Chicago, Ill. Abstract 210. 3McLeaod-Kennedy L, Leach M, et al. Dapsone Poisoining. Blood. 2019; 133(23): 2551. https://doi.org/10.1182/blood.2019000201 Citing Literature Volume96, Issue12December 2021Pages 1715-1716 This article also appears in:Celebrating Hematology Research from Asia FiguresReferencesRelatedInformation

A 36-year-old Chinese man with a recent diagnosis of COVID-19 infection was treated in the National Centre for Infectious Diseases, Singapore. He was found to have severe lymphopenia and moderate thrombocytopenia on admission to ICU and required ventilatory support. Peripheral blood smear performed in view of a rising MCV from 86 fL to 92 fL demonstrated cold agglutination and rouleaux formation, lymphopenia with few reactive lymphocytes and rare lymphoplasmacytoid cells (Image 1A,B, Wright stain, 100x objective). There was no significant anemia or biochemical haemolysis and direct agglutination test was negative. Antibody screen revealed anti-I antibody, a cold agglutinin titer of 1:8 with a mycoplasma pneumoniae antibody titer of 1:160. Serum electrophoresis did not show a monoclonal antibody. Respiratory multiplex PCR for other common respiratory viruses was negative. Reactive lymphocytes are frequently seen in COVID-19 infection (unlike in SARS), while in mycoplasma pneumoniae infection cold agglutination is common. COVID-19 coinfection with other common respiratory pathogens such as mycoplasma pneumoniae may exacerbate clinical symptoms, increase morbidity and may cause prolonged ICU stay if left undetected or untreated. Clinicians managing patients with COVID-19 infection should be mindful of coinfections with common respiratory pathogens during this COVID-19 outbreak and screen for these with appropriate microbiologic tests.