RESUMO
Accurate identification and classification of bone marrow (BM) nucleated cell morphology are crucial for the diagnosis of hematological diseases. However, the subjective and time-consuming nature of manual identification by pathologists hinders prompt diagnosis and patient treatment. To address this issue, we developed Morphogo, a convolutional neural network-based system for morphological examination. Morphogo was trained using a vast dataset of over 2.8 million BM nucleated cell images. Its performance was evaluated using 508 BM cases that were categorized into five groups based on the degree of morphological abnormalities, comprising a total of 385,207 BM nucleated cells. The results demonstrated Morphogo's ability to identify over 25 different types of BM nucleated cells, achieving a sensitivity of 80.95%, specificity of 99.48%, positive predictive value of 76.49%, negative predictive value of 99.44%, and an overall accuracy of 99.01%. In most groups, Morphogo cell analysis and Pathologists' proofreading showed high intragroup correlation coefficients for granulocytes, erythrocytes, lymphocytes, monocytes, and plasma cells. These findings further validate the practical applicability of the Morphogo system in clinical practice and emphasize its value in assisting pathologists in diagnosing blood disorders.
Assuntos
Aprendizado Profundo , Humanos , Granulócitos , Monócitos , Eritrócitos , Redes Neurais de ComputaçãoRESUMO
BACKGROUND: In HBV-infected patients, different genotypes of the hepatitis B virus influence liver disease progression and response to antiviral therapy. Moreover, long-term antiviral therapy will eventually select for drug-resistant mutants. Detection of mutations associated to antiviral therapy and HBV genotyping are essential for monitoring treatment of chronic hepatitis B patients. RESULTS: In this study, a simple method of partial-S gene sequencing using a common PCR amplification was established for genotyping clinical HBV isolates sensitively, which could detect the drug-resistant mutations successfully at the same time. CONCLUSIONS: The partial S gene sequencing assay developed in this study has potential for application in HBV genotyping and drug resistant mutation detection. It is simpler and more convenient than traditional S gene sequencing, but has nearly the same sensitivity and specificity when compared to S gene sequencing.