1 April 2015 in Cytotherapy
8 September 2021 in Leukemia
The evaluation of bone marrow morphology by experienced hematopathologists is essential in the diagnosis of acute myeloid leukemia (AML); however, it suffers from a lack of standardization and inter-observer variability. Deep learning (DL) can process medical image data and provides data-driven class predictions. Here, we apply a multi-step DL approach to automatically segment cells from bone marrow images, distinguish between AML samples and healthy controls with an area under the receiver operating characteristic (AUROC) of 0.9699, and predict the mutation status of Nucleophosmin 1 (NPM1)—one of the most common mutations in AML—with an AUROC of 0.92 using only image data from bone marrow smears. Utilizing occlusion sensitivity maps, we observed so far unreported morphologic cell features such as a pattern of condensed chromatin and perinuclear lightening zones in myeloblasts of NPM1-mutated AML and prominent nucleoli in wild-type NPM1 AML enabling the DL model to provide accurate class predictions.
13 January 2016 in British Journal of Haematology
T(the Study Alliance Leukaemia (SAL)
the Study Alliance Leukaemia (SAL)
+20
15 January 2016 in Blood Cancer Journal
A complex aberrant karyotype consisting of multiple unrelated cytogenetic abnormalities is associated with poor prognosis in patients with acute myeloid leukemia (AML). The European Leukemia Net classification and the UK Medical Research Council recommendation provide prognostic categories that differ in the definition of unbalanced aberrations as well as the number of single aberrations. The aim of this study on 3526 AML patients was to redefine and validate a cutoff for karyotype complexity in AML with regard to adverse prognosis. Our study demonstrated that (1) patients with a pure hyperdiploid karyotype have an adverse risk irrespective of the number of chromosomal gains, (2) patients with translocation t(9;11)(p21∼22;q23) have an intermediate risk independent of the number of additional aberrations, (3) patients with ⩾4 abnormalities have an adverse risk per se and (4) patients with three aberrations in the absence of abnormalities of strong influence (hyperdiploid karyotype, t(9;11)(p21∼22;q23), CBF-AML, unique adverse-risk aberrations) have borderline intermediate/adverse risk with a reduced overall survival compared with patients with a normal karyotype.
1 June 2018 in Journal of Autoimmunity