Computer vision quantitation of erythrocyte shape abnormalities provides diagnostic, prognostic, and mechanistic insight.

Examination of red blood cell (RBC) morphology in peripheral blood smears can help diagnose hematologic diseases, even in resource-limited settings, but this analysis remains subjective and semiquantitative with low throughput. Prior attempts to develop automated tools have been hampered by their poor reproducibility and limited clinical validation. Here, we present a novel, open-source machine-learning approach (denoted as RBC-diff) to quantify abnormal RBCs in peripheral smear images and generate an RBC morphology differential. RBC-diff cell counts showed high accuracy for single-cell classification (mean AUC, 0.93) and quantitation across smears (mean R2, 0.76 compared with experts, interexperts R2, 0.75). RBC-diff counts were concordant with the clinical morphology grading for 300 000+ images and recovered the expected pathophysiologic signals in diverse clinical cohorts. Criteria using RBC-diff counts distinguished thrombotic thrombocytopenic purpura and hemolytic uremic syndrome from other thrombotic microangiopathies, providing greater specificity than clinical morphology grading (72% vs 41%; P < .001) while maintaining high sensitivity (94% to 100%). Elevated RBC-diff schistocyte counts were associated with increased 6-month all-cause mortality in a cohort of 58 950 inpatients (9.5% mortality for schist. >1%, vs 4.7% for schist; <0.5%; P < .001) after controlling for comorbidities, demographics, clinical morphology grading, and blood count indices. RBC-diff also enabled the estimation of single-cell volume-morphology distributions, providing insight into the influence of morphology on routine blood count measures. Our codebase and expert-annotated images are included here to spur further advancement. These results illustrate that computer vision can enable rapid and accurate quantitation of RBC morphology, which may provide value in both clinical and research contexts.

Vasculopathy and Increased Vascular Congestion in Fatal COVID-19 and Acute Respiratory Distress Syndrome.

Rationale: The leading cause of death in coronavirus disease 2019 (COVID-19) is severe pneumonia, with many patients developing acute respiratory distress syndrome (ARDS) and diffuse alveolar damage (DAD). Whether DAD in fatal COVID-19 is distinct from other causes of DAD remains unknown. Objective: To compare lung parenchymal and vascular alterations between patients with fatal COVID-19 pneumonia and other DAD-causing etiologies using a multidimensional approach. Methods: This autopsy cohort consisted of consecutive patients with COVID-19 pneumonia (n = 20) and with respiratory failure and histologic DAD (n = 21; non-COVID-19 viral and nonviral etiologies). Premortem chest computed tomography (CT) scans were evaluated for vascular changes. Postmortem lung tissues were compared using histopathological and computational analyses. Machine-learning-derived morphometric analysis of the microvasculature was performed, with a random forest classifier quantifying vascular congestion (CVasc) in different microscopic compartments. Respiratory mechanics and gas-exchange parameters were evaluated longitudinally in patients with ARDS. Measurements and Main Results: In premortem CT, patients with COVID-19 showed more dilated vasculature when all lung segments were evaluated (P = 0.001) compared with controls with DAD. Histopathology revealed vasculopathic changes, including hemangiomatosis-like changes (P = 0.043), thromboemboli (P = 0.0038), pulmonary infarcts (P = 0.047), and perivascular inflammation (P < 0.001). Generalized estimating equations revealed significant regional differences in the lung microarchitecture among all DAD-causing entities. COVID-19 showed a larger overall CVasc range (P = 0.002). Alveolar-septal congestion was associated with a significantly shorter time to death from symptom onset (P = 0.03), length of hospital stay (P = 0.02), and increased ventilatory ratio [an estimate for pulmonary dead space fraction (Vd); p = 0.043] in all cases of ARDS. Conclusions: Severe COVID-19 pneumonia is characterized by significant vasculopathy and aberrant alveolar-septal congestion. Our findings also highlight the role that vascular alterations may play in Vd and clinical outcomes in ARDS in general.

Factors associated with myocardial SARS-CoV-2 infection, myocarditis, and cardiac inflammation in patients with COVID-19.

COVID-19 has been associated with cardiac injury and dysfunction. While both myocardial inflammatory cell infiltration and myocarditis with myocyte injury have been reported in patients with fatal COVID-19, clinical-pathologic correlations remain limited. The objective was to determine the relationships between cardiac pathological changes in patients dying from COVID-19 and cardiac infection by SARS-CoV-2, laboratory measurements, clinical features, and treatments. In a retrospective study, 41 consecutive autopsies of patients with fatal COVID-19 were analyzed for the associations between cardiac inflammation, myocarditis, cardiac infection by SARS-CoV-2, clinical features, laboratory measurements, and treatments. Cardiac infection was assessed by in situ hybridization and NanoString transcriptomic profiling. Cardiac infection by SARS-CoV-2 was present in 30/41 cases: virus+ with myocarditis (n = 4), virus+ without myocarditis (n = 26), and virus- without myocarditis (n = 11). In the cases with cardiac infection, SARS-CoV-2+ cells in the myocardium were rare, with a median density of 1 cell/cm2. Virus+ cases showed higher densities of myocardial CD68+ macrophages and CD3+ lymphocytes, as well as more electrocardiographic changes (23/27 vs 4/10; P = 0.01). Myocarditis was more prevalent with IL-6 blockade than with nonbiologic immunosuppression, primarily glucocorticoids (2/3 vs 0/14; P = 0.02). Overall, SARS-CoV-2 cardiac infection was less prevalent in patients treated with nonbiologic immunosuppression (7/14 vs 21/24; P = 0.02). Myocardial macrophage and lymphocyte densities overall were positively correlated with the duration of symptoms but not with underlying comorbidities. In summary, cardiac infection with SARS-CoV-2 is common among patients dying from COVID-19 but often with only rare infected cells. Cardiac infection by SARS-CoV-2 is associated with more cardiac inflammation and electrocardiographic changes. Nonbiologic immunosuppression is associated with lower incidences of myocarditis and cardiac infection by SARS-CoV-2.

Retrospective analysis of outcomes in patients with acute hypertriglyceridemic pancreatitis treated without therapeutic plasma exchange.

BACKGROUND: Therapeutic plasma exchange (TPE) is often used to decrease serum triglyceride levels in hypertriglyceridemic pancreatitis (HTGP), although there is a lack of high-quality data directly attributing improved clinical outcomes to TPE. There are currently no large studies evaluating the treatment of HTGP without TPE. STUDY DESIGN AND METHODS: This study retrospectively analyzes clinical and laboratory outcomes of 115 encounters at Massachusetts General Hospital (MGH) wherein a HTGP patient was treated without TPE and compares these outcomes to those of HTGP patients in the literature treated with TPE. RESULTS: After management without TPE, the median reduction in serum triglycerides was 48% (IQR 29%-63%) on day one and 74% (IQR 60%-84%) on day two in 115 episodes of acute HTGP. The reductions were comparable to those reported in several large published case series after a course of TPE (65.8% to 81% reduction). In 25 episodes among 24 patients, treatment included admission to an intensive care unit. There was no significant difference in mortality or rates of local complication, mechanical ventilation, or use of vasoactive medication or renal replacement therapy between this ICU subset and published cohorts (all P > .05). CONCLUSIONS: HTGP patients who do not receive TPE do not experience inferior outcomes compared to patients in the literature treated with TPE. The added value of TPE in HTGP, if any exists, needs to be demonstrated in controlled trials.

Tonsillar p16-Positive Follicular Dendritic Cell Sarcoma Mimicking HPV-Related Oropharyngeal Squamous Cell Carcinoma: A Case Report and Review of Reported Cases.

Follicular dendritic cell sarcoma (FDCS) is a rare entity which can share morphologic features with non-keratinizing squamous cell carcinoma. Recent reports suggest that up to half of FDCSs show immunohistochemical positivity for p16 (Zhang et al., in Hum Pathol 66:40-47, 2017), a stain that is conventionally used in the risk stratification of oropharyngeal squamous cell carcinoma (OPSCC). Herein, we report a case of p16-positive FDCS with clinical and histomorphologic overlap with human papilloma virus (HPV)-related OPSCC.