Nanaa, Ahmad

SummaryVenetoclax (VEN) is an FDA‐approved selective inhibitor of B‐cell leukaemia/lymphoma‐2 (BCL‐2), used for treating elderly or unfit acute myeloid leukaemia (AML) patients unable to undergo intensive chemotherapy. Combining VEN with hypomethylating agents (HMAs) has shown impressive response rates in high‐risk myelodysplastic syndromes (MDS) and relapsed/refractory AML. However, the efficacy of VEN and HMAs in treating DDX41‐mutated (mDDX41) MDS/AML patients remains uncertain. Despite the favourable prognostic nature of mDDX41 MDS/AML patients, there is a lack of clinical experience regarding their response to different treatment regimens, leading to an unknown optimal therapeutic approach.

Abstract DDX41 mutations (germline and somatic) are associated with late onset myelodysplastic syndromes/acute myeloid leukemia (MDS/AML). Myeloid neoplasms (MN) with germline predisposition was identified as a distinct category in the 2016 WHO classification revision, including MN with germline DDX41 mutation. We retrospectively analyzed the molecular findings and clinical characteristics of thirty-three DDX41-mutated (mDDX41) patients at our institution. We identified 14 distinct pathogenic DDX41 variants in 32 patients and 8 DDX41 variants of unknown significance (VUS) in 9 patients. Five (16%) patients had a second DDX41 somatic mutation p.R525H and 13 (40%) had at least one additional oncogenic co-mutation in other genes. The median age at the time of diagnosis was 66 years, with male predominance (72%) and the majority of patients had normal cytogenetics (91%). Two-year overall survival (OS) was 86% and 6 (21%) MDS/AML patients with relatively preserved hematopoietic function were observed without further intervention. In comparison to AML patients with prognostically more favorable subtypes [t(8;21), n=27 and inv(16), n=40], mDDX41 patients in our cohort showed similarly favorable OS. Our study highlights that mDDX41-MN patients often have an indolent course and mDDX41-AML has comparable OS to favorable-risk AML.

The accurate diagnosis of chronic myelomonocytic leukemia (CMML) and acute myeloid leukemia (AML) subtypes with monocytic differentiation relies on the proper identification and quantitation of blast cells and blast-equivalent cells, including promonocytes. This distinction can be quite challenging given the cytomorphologic and immunophenotypic similarities among the monocytic cell precursors. The aim of this study was to assess the performance of convolutional neural networks (CNN) in separating monocytes from their precursors (i.e., promonocytes and monoblasts). We collected digital images of 935 monocytic cells that were blindly reviewed by five experienced morphologists and assigned into three subtypes: monocyte, promonocyte, and blast. The consensus between reviewers was considered as a ground truth reference label for each cell. In order to assess the performance of CNN models, we divided our data into training (70%), validation (10%), and test (20%) datasets, as well as applied fivefold cross validation. The CNN models did not perform well for predicting three monocytic subtypes, but their performance was significantly improved for two subtypes (monocyte vs. promonocytes + blasts). Our findings (1) support the concept that morphologic distinction between monocytic cells of various differentiation level is difficult; (2) suggest that combining blasts and promonocytes into a single category is desirable for improved accuracy; and (3) show that CNN models can reach accuracy comparable to human reviewers (0.78 ± 0.10 vs. 0.86 ± 0.05). As far as we know, this is the first study to separate monocytes from their precursors using CNN.