Performance evaluation of a novel artificial intelligence (AI)-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 multi-center study to validate a computational microscopy approach with an artificial intelligence (AI)-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 1385±536 (range 0-3131) 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 inter-user agreement, were evaluated. The test method showed high correlation with the reference method for comprehensive BMA evaluation, both on Romanowsky (90.85% efficiency, 81.61% sensitivity; specificity 92.88%) and Prussian blue (90.0% efficiency, 81.94% sensitivity; 93.38% specificity) stained samples. The overall agreement between the test and reference method for BMA assessment was 91.1%. For repeatability and reproducibility, all standard deviations and coefficients of variation values were below the pre-defined acceptance criteria both for discrete measurements (CV below 20%) and for 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.

Fulminant intravascular lymphoma presenting as fever of unknown origin.

Intravascular large cell lymphoma (IVLL) is a rare neoplasm characterized by the proliferation of malignant lymphoid cells within the lumens of small to medium-sized blood vessels. The central nervous system, skin, and endocrine systems are most commonly involved. IVLL may disseminate to the heart, pancreas, liver, spleen, kidneys, and adrenal glands. We report a 52-year-old patient who was admitted for fever of unknown origin for 3 weeks, jaundice and abnormal liver function tests. Fever, high levels of bilirubin, severe anemia, thrombocytopenia, and a very fulminant course characterized the clinical picture. Although bone marrow involvement is quite rare, the diagnosis of IVLL in this patient was done by bone marrow biopsy. The patient was treated with CHOP protocol and received the first course but the aggressive disease led to the patient's death.