ABSTRACT
Objective@#To describe the MICM (morphology, immunology, cytogenetics and molecular biology) characteristics of a case of acute myelomonocytic leukemia M 4C . @*Methods@#The medical history data of the case of M 4C admitted to our hospital was reviewed. The results of bone marrow cell morphology, cytochemical stains, bone marrow biopsy, immunophenotype, cytogenetics, molecular test and NGS (next-generation sequencing) of the case were analyzed. @*Results@#The bone marrow smear showed markedly active proliferation of bone marrow cells in which the myelomonocytic cells accounted for 85.6%. Cytochemical stains showed peroxidase (POX) stain partially and weakly positive; specific esterase AS-DCE partially positive; non-specific esterase α-NBE partially positive and smothered by sodium fluoride; non-specific esterase AS-DAE partially positive and smothered by sodium fluoride. Bone marrow biopsy showed hyperproliferative cells and diffused hyperplasia of blasts. Immunophenotype analysis showed that the abnormal cell population was positive for CD11B, CD64, CD56, cMPO, CD33, CD41, CD61, CD38 and CD58, but negative for CD13, CD34, CD117, CD7, CD123, HLA-DR, CD10, CD19, CD20, CD2, CD14, CD235, CD15, CD303, CD304, CD25, cCD79a, cCD3, cCD22, CD1a and TDT. Cytogenetic analysis showed 47, XY, t(9;11) (p22;q23),+mar. The molecular test for leukemia showed MLLT3/KMT2A gene rearrangement. NGS showed NRAS and TET2 mutation. The case was finally diagnosed as AML (acute myelomonocytic leukemia) M 4C with t(9;11)(p22;q23), MLLT3-KMT2A. @*Conclusion@#Leukemia M 4C may show the characteristics of both granulocytes and monocytes with complex morphological features. The combined examination of MICM should be necessary for the diagnosis of M 4C with great significance.
ABSTRACT
The support vector machine (SVM) is a new learning technique based on the statistical learning theory. It was originally developed for two-class classification. In this paper, the SVM approach is extended to multi-class classification problems, a hierarchical SVM is applied to classify blood cells in different maturation stages from bone marrow. Based on stepwise decomposition, a hierarchical clustering method is presented to construct the architecture of the hierarchical (tree-like) SVM, then the optimal control parameters of SVM are determined by some criterion for each discriminant step. To verify the performances of classifiers, the SVM method is compared with three classical classifiers using 3-fold cross validation. The preliminary results indicate that the proposed method avoids the curse of dimensionality and has greater generalization. Thus, the method can improve the classification correctness for blood cells from bone marrow.