RESUMO
Philadelphia chromosome-positive chronic myeloid leukemia (CML) is cytogenetically characterized by the classic translocation t(9;22)(q34;q11), whereas additional non-Philadelphia aberrations (nPhAs) have been studied extensively in adult patients with CML, knowledge on nPhAs in pediatric patients with CML is still sparse. Here, we have determined nPhAs in a cohort of 161 patients younger than 18 years diagnosed with chronic phase CML and consecutively enrolled in the German national CML-PAED-II registry. In 150 cases (93%), an informative cytogenetic analysis had been performed at diagnosis. In total, 21 individuals (13%) showed nPhAs. Of these, 12 (8%) had a variant translocation, 4 (3%) additional chromosomal aberrations (ACAs) and 5 (3%) harbored a complex karyotype. Chromosome 15 was recurrently involved in variant translocations. No significant impact of the cytogenetic subgroup on the time point of cytogenetic response was observed. Patients with a complex karyotype showed an inferior molecular response compared to patients carrying the classic translocation t(9;22)(q34;q11), variant translocations or ACAs. No significant differences in the probability of progression-free survival and overall survival was found between patients with nPhAs and patients with the classic Philadelphia translocation only. Our results highlight the distinct biology of pediatric CML and underline the need for joint international efforts to acquire more data on the disease pathogenesis in this age group.
RESUMO
Karyotype analysis has a great impact on the diagnosis, treatment and prognosis in hematologic neoplasms. The identification and characterization of chromosomes is a challenging process and needs experienced personal. Artificial intelligence provides novel support tools. However, their safe and reliable application in diagnostics needs to be evaluated. Here, we present a novel laboratory approach to identify chromosomes in cancer cells using a convolutional neural network (CNN). The CNN identified the correct chromosome class for 98.8% of chromosomes, which led to a time saving of 42% for the karyotyping workflow. These results demonstrate that the CNN has potential application value in chromosome classification of hematologic neoplasms. This study contributes to the development of an automatic karyotyping platform.
Assuntos
Bandeamento Cromossômico/métodos , Neoplasias Hematológicas/genética , Cariotipagem Espectral/métodos , Algoritmos , Feminino , Humanos , Masculino , Metáfase , Redes Neurais de Computação , Reprodutibilidade dos Testes , Fatores de TempoRESUMO
Additional data on blast phase (BP) chronic myeloid leukaemia (CML) in children and adolescents is essential for improving diagnostic and therapeutic approaches of this rare but serious condition. Here, we describe distinct clinical and genetic characteristics of 18 paediatric patients with de novo (n = 10) and secondary (n = 8) BP CML enrolled in the CML-PAED-II trial and registry. Our findings suggest that paediatric patients exhibit a diverse cytogenetic profile compared to adults with BP CML. In addition, patients with de novo BP CML in this cohort presented at a younger age, whereas patients with secondary BP CML more often harboured complex karyotypes.