Timm, Michael M

Abstract Measurable residual disease (MRD) assessment by flow cytometry (FC) plays an essential role in prognosis and therapy escalation of B-cell acute lymphoblastic leukemia (B-ALL). However, the high degree of expertise and manual analysis time required limits the availability of this assay. To overcome this limitation, we developed a data-enhancing artificial intelligence (AI) pipeline that accelerates and simplifies MRD analysis. Unaltered FC files from 171 B-ALL MRD-positive and 89 MRD-negative cases were processed through an AI pipeline trained with 31 expert-gated negative controls. Cluster-informed downsampling reduced FC files from 1.2 million to 155 884 cells per case, on average, (87% cellularity reduction), whereas preserving small MRD populations (median, 100% retention for MRD of <1%) and allowing for true percentage MRD estimates using a correction factor. A deep neural network cell classifier automatically identified normal hematopoietic subsets (macro-averaged F1 score of 0.86); and an AI measure of anomaly discriminated B-ALL from benign mononuclear (area under the curve [AUC] of 0.98) or B-lymphoid cells (AUC of 0.94). Manual analysis of AI-enhanced files was completed in only 1.01 minutes per case, on average (standard deviation of ±0.57); with 100% positive agreement with conventional analysis (for MRD of ≥0.01%), 100% negative agreement, and excellent quantitative correlation (R2 = 0.92). Our cloud-based AI-enhancement solution accelerates B-ALL MRD identification without compromising test performance and has the potential of facilitating B-ALL MRD analysis by more clinical laboratories.

Background: Flow cytometric detection of minimal residual disease (MRD) in chronic lymphocytic leukemia (CLL) is complex, time-consuming, and subject to inter-operator variability. Deep neural networks (DNNs) offer potential for standardization and efficiency improvement, but require rigorous validation and monitoring for safe clinical implementation. Methods: We evaluated a DNN-assisted human-in-the-loop approach for CLL MRD detection. Initial validation included method comparison against manual analysis (n = 240), precision studies, and analytical sensitivity verification. Post-implementation monitoring comprised four components: daily electronic quality control, input data drift detection, error analysis, and attribute acceptance sampling. Laboratory efficiency was assessed through a timing study of 161 cases analyzed by five technologists. Results: Method comparison demonstrated 97.5% concordance with manual analysis for qualitative classification (sensitivity 100%, specificity 95%) and excellent correlation for quantitative assessment (r = 0.99, Deming slope = 0.99). Precision studies confirmed high repeatability and within-laboratory precision across multiple operators. Analytical sensitivity was verified at 0.002% MRD. Post-implementation monitoring identified 2.97% of cases (26/874) with input data drift, primarily high-burden CLL and non-CLL neoplasms. Error analysis showed the DNN alone achieved 97% sensitivity compared to human-in-the-loop-reviewed results, with 13 missed cases (1.5%) showing atypical immunophenotypes. Attribute acceptance sampling confirmed 98.8% of reported negative cases were true negatives. The DNN-assisted workflow reduced average analysis time by 60.3% compared to manual analysis (4.2 ± 2.3 vs. 10.5 ± 5.8 min). Conclusions: The implementation of a DNN-assisted approach for CLL MRD detection in a clinical laboratory provides diagnostic performance equivalent to expert manual analysis while substantially reducing analysis time. Comprehensive performance monitoring ensures ongoing safety and effectiveness in routine clinical practice. This approach provides a model for responsible AI integration in clinical laboratories, balancing automation benefits with expert oversight.

Background/Objectives: Acute myeloid leukemia (AML) is a biologically heterogeneous malignancy with a variable prognosis. Despite many patients achieving complete remission, relapse remains common, underscoring the need for effective prognostic markers. Measurable residual disease (MRD) has emerged as a critical prognostic indicator, associated with higher relapse risk and shorter survival. This study reports on our initial experience of MRD detection by flow cytometry in 385 bone marrow samples from 126 AML patients. Methods: The flow cytometry MRD assay, validated according to stringent consensus recommendations, consists of a 3-tube, 10-color panel incorporating a broad spectrum of lineage differentiation markers. Analytical specificity, sensitivity, precision, and reproducibility were evaluated, demonstrating the assay’s robustness. Results: The results reveal distinct immunophenotypic aberrancies in all AML cases, with consistent identification of aberrant immunophenotypes in follow-up specimens. AML MRD was detected in 32 out of 126 patients (25%) and in 77 out of 385 analyses (20%), with a median aberrant blast percentage of 1.87% (range, 0.01–12). A change in immunophenotype was documented in 21% of the MRD-positive cases. MRD positivity detected in the first sample studied was associated with reduced overall survival (HR: 5.153; p < 0.0001). Conclusions: Our findings support the integration of flow cytometric MRD analysis into routine clinical practice to enhance risk stratification and treatment planning for AML patients, as currently recommended by professional guidelines.

Abstract Objectives Fluorescence in situ hybridization (FISH) for plasma cell neoplasms (PCNs) requires plasma cell (PC) identification or purification strategies to optimize results. We compared the efficacy of cytoplasmic immunoglobulin FISH (cIg-FISH) and fluorescence-activated cell sorting FISH (FACS-FISH) in a clinical laboratory setting. Methods The FISH analysis results of 14,855 samples from individuals with a suspected PCN subjected to cytogenetic evaluation between 2019 and 2022 with cIg-FISH (n = 6917) or FACS-FISH (n = 7938) testing were analyzed. Results Fluorescence-activated cell sorting–FISH increased the detection rate of abnormalities in comparison with cIg-FISH, with abnormal results documented in 54% vs 50% of cases, respectively (P &lt; .001). It improved the detection of IGH::CCND1 (P &lt; .001), IGH::MAF (P &lt; .001), IGH::MAFB (P &lt; .001), other IGH rearrangements (P &lt; .001), and gains/amplifications of 1q (P &lt; .001), whereas the detection rates of IGH::FGFR3 fusions (P = .3), loss of 17p (P = .3), and other abnormalities, including hyperdiploidy (P = .5), were similar. Insufficient PC yield for FISH analysis was decreased between cIg-FISH and FACS-FISH (22% and 3% respectively, P &lt; .001). Flow cytometry allowed establishment of ploidy status in 91% of cases. In addition, FACS-FISH decreased analysis times, workload efforts, and operating costs. Conclusions Fluorescence-activated cell sorting–FISH is an efficient PC purification strategy that affords significant improvement in diagnostic yield and decreases workflow requirements in comparison with cIg-FISH.

AbstractBackgroundDespite the unprecedented success of ibrutinib in lymphoma therapy, the development of ibrutinib resistance due to acquired BTK or PLCγ2 mutations has become a new clinical problem. However, not all resistance is mediated by these mutations and these mechanisms are poorly understood due to a lack of study tools that truly recapitulate this clinical scenario.MethodsWe established a novel patient‐derived ibrutinib‐resistant mantle cell lymphoma (MCL) line named MCIR1. Using immunological, molecular, and cytogenetic approaches, we comprehensively characterized MCIR1 and further demonstrated its utility in the study of resistance mechanisms and treatments to overcome this resistance.ResultsWe show that MCIR1 is a bona fide ibrutinib‐resistant MCL cell line with normal BTK‐/PLCγ2 but ibrutinib‐resistant ERK1/2 and AKT1 signaling. RNA‐Seq analysis revealed a robust non‐canonical NF‐kB signaling that drives the ibrutinib resistance. We also demonstrate the potential utility of a MCIR1‐based cell and mouse model for the discovery of new treatments to overcome BTK inhibitor resistance.ConclusionsWe have established the first patient‐derived ibrutinib‐resistant MCL cell line MCIR1 that lacks BTK or PLCγ2 mutations but exhibits a hyperactive non‐canonical NF‐kB pathway. We further demonstrate its utility in the discovery and validation of new drugs to overcome this resistance.

Key Points Systemic immune microenvironment signatures in CMML indicate an altered T- and natural killer cell balance. CMML bone marrow dendritic cell aggregates associate with disease progression and systemic regulatory T-cell phenotypic switch.

Abstract Objectives Distinguishing between T-cell and natural killer (NK)–cell neoplasms could be difficult given their overlapping immunophenotype. In this study, we investigated whether a flow cytometry assay with cytoplasmic staining for CD3 could be used for this purpose. Methods Flow cytometry immunophenotyping was performed on 19 surface CD3 (sCD3)–negative mature T-cell neoplasms, 10 sCD3-positive mature T-cell neoplasms, 13 mature NK-cell neoplasms, and 19 normal controls. In addition to routine antibody panels (CD2, sCD3, CD4, CD5, CD7, CD8, CD16, CD45, CD56, CD57, CD94, CD158a, CD158b, CD158e, NKG2A TCRγ/δ), cytoplasmic staining for a monoclonal CD3 antibody (clone SK7/Leu-4) was assessed in all cases. A molecular study for T-cell receptor (TCR) gene rearrangement and an immunohistochemical study for TCRβ were performed. Results Our data showed all T-cell neoplasms were uniformly positive for cytoplasmic CD3 (cCD3) regardless of sCD3 expression, whereas 85% of NK-cell neoplasms completely lacked cCD3 expression. The 2 cases with classic NK-cell immunophenotype but partial cCD3 expression showed no molecular genetic features of T-cell lineage by TCR gene rearrangement studies. Conclusions Uniform cCD3 positivity and homogeneous cCD3 negativity highly suggest T-cell and NK lineage, respectively. When partial cCD3 expression is encountered, additional confirmatory studies should be pursued for the most accurate lineage assignment.