Horna, Pedro

Abstract Objectives Diagnosing adult T-cell leukemia/lymphoma (ATLL) remains challenging due to its clinical and histopathologic heterogeneity. While HTLV-1 serology is a key diagnostic criterion, it is often unavailable at the time of diagnosis and does not confirm viral integration in tumor cells. The HTLV-1–encoded HBZ RNA is a reliable diagnostic biomarker for ATLL. We evaluated the diagnostic performance of RNAscope in situ hybridization (ISH) for HBZ RNA in formalin-fixed, paraffin-embedded (FFPE) tissues to distinguish ATLL from other T-cell lymphomas. Methods HBZ ISH was evaluated in 72 cases, including 52 ATLLs and 20 non-ATLL T-cell lymphomas, to determine diagnostic sensitivity and specificity, interobserver agreement, interlaboratory reproducibility, and comparison with digital gene expression. Results This assay demonstrated 86.5% sensitivity and 100% specificity, with sensitivity improving to 97% when excluding bone marrow clot sections and FFPE blocks older than 5 years. Interobserver agreement among 3 pathologists was excellent (κ = 0.92, percent agreement: 94%). Interlaboratory reproducibility of HBZ ISH was high, with 93% to 95% concordance across these Clinical Laboratory Improvement Amendments–certified laboratories. HBZ RNA ISH–positive cases demonstrated significantly higher HBZ gene expression levels by digital gene expression profiling. Conclusions We established HBZ ISH as a reliable tissue-based surrogate for HTLV-1 infection in ATLL. This assay will enhance diagnostic accuracy, expedite definitive diagnosis, and improve patient selection for targeted therapies and clinical trials, particularly in regions with a high prevalence of HTLV-1.

Abstract Background: Flow cytometry (FC) is widely utilized for the identification of measurable residual disease (MRD) in multiple myeloma (MM), providing an essential laboratory indicator for prognostic assessment and therapeutic management. Unfortunately, the high level of expertise required, long manual analysis time, and complexity of FC data files currently limit the offering of this testing to selected reference laboratories. Methods: We developed an artificial intelligence (AI) pipeline to automatically enhance unaltered FC files, minimizing the expertise and manual analysis time needed to detect MM MRD using the 2-tube Euroflow Consortium Panel (Cytognos). Raw FC files corresponding to 150 MRD-positive bone marrow samples (MRD < 5%, median = 0.0022%), and 39 MRD-negative samples were processed through our CCADDAS (Clustering and Classification of All events, Dimensionality reduction, Downsampling and Aberrancy Scaling) pipeline, deployed on a custom clinical-grade cloud environment (Biolegend). Automated processing steps included elimination of acquisition errors (FlowCut), state-of-the-art clustering (PARC), cluster-informed and density-based downsampling with preservation of low-event subsets, dimensionality reduction (UMAP), and cluster-based anomaly detection compared to negative controls (29 bone marrow aspirates). In addition, a deep neural network (DNN) trained on expert-defined subpopulations from negative controls was included for automatic gating of normal subsets (Tensorflow v2). AI-enhanced data files were analyzed using a general-purpose flow cytometry analysis software (Kaluza v 2.3, Beckman Coulter), and %MRD estimates were compared to reported results based on traditional expert analysis of original FC files. Results: Cluster-informed downsampling reduced the number of cells to be manually analyzed from 4.1 million to 196,761 cells per tube, on average (95% cellularity reduction); resulting in a smaller FC data file (from 203.2 MB to 20.5 MB; 90% data reduction). Importantly, low-level MRD events were adequately preserved after downsampling (median 88% and 77% retention, for 0.01-0.001% MRD and < 0.001% MRD, respectively). True number of events were accurately estimated on gated subsets using an “upsampling factor” parameter [observed # events x mean (upsampling factor)]. Gating of normal subsets was completely automated using a DNN classifier parameter. In 96% of positive cases, MRD was rapidly identified as immunoglobulin light chain-restricted plasma cells on a single pre-calculated UMAP plot (tube 2), after dual coloring for kappa and lambda. On the remainder 4% of positive cases, MRD was easily segregated from benign plasma cells using the AI-generated “aberrancy scale” parameter or other strategies. The use of AI-enhanced files reduced manual analysis time from 15.05 minutes (SD = 6.84) to 1.29 minutes (SD = 0.90) per case, on average (p < 0.0001) (91% reduction of manual analysis time). MM MRD was detected in all positive cases above limit of detection for our assay (≥0.0002%), with excellent quantitative correlation with conventional analysis on original FC files (linear regression slope = 0.9841, P < 0.0001). Conclusion: We introduce a largely unsupervised AI pipeline that transforms raw MM MRD FC data from the Euroflow Consortium panel into a markedly smaller, AI-annotated and software-agnostic FC file, including comparison to normal controls. This CCADDAS pipeline simplifies and accelerates detection of MM MRD in clinical diagnostics, reducing the number of cells analyzed by 95% and manual analysis time by 91%, without impacting test performance. Moreover, CCADDAS can be utilized for any laboratory-developed MM MRD assay, and its small-sized export is compatible with any clinical FC software, computing platform, and analysis strategy. Adoption of CCADDAS is likely to facilitate the implementation of MM MRD FC analysis by more clinical laboratories.

Abstract Background: Recent advances in computer vision have given rise to image foundation models (FMs), large-scale neural networks pre-trained on millions of unlabeled histopathology patches, which can learn generalizable representations of tissue morphology. In many cancers, these FMs have predicted genetic mutations and prognoses directly from histology, suggesting that morphology encodes “hidden” molecular information. In lymphoma, this field is nascent but growing.General-purpose histopathology FMs have limited representation of lymphoid morphology. We developed and evaluated LymphoVision, a lymphoma-specialized image foundation model pretrained with self-supervised learning, to extract clinically meaningful features from routine hematoxylin and eosin (H&E) histology. Methods: LymphoVision was pre-trained using knowledge distillation and consistency (DINOv2) on over 37 million multi-resolution patches (5x, 10x, 20x, 40x) sampled using a density-aware strategy from 31,211 H&E whole slide images (WSIs) from 9,155 archival lymphoma and reactive lymphoproliferative cases. To ensure diverse, representative samples, our patch sampling method uses an efficient graph-based clustering algorithm and prioritizes morphologically informative regions by clustering patch embeddings and performing density sampling within each cluster. The pretrained encoder was evaluated using a clustering-constrained attention multiple instance learning (MIL) framework on three diagnostic tasks: (1) cell-of-origin (COO) classification in diffuse large B-cell lymphoma (DLBCL), distinguishing germinal center B-cell (GCB) from non-GCB subtypes based on the Hans immunohistochemistry algorithm; (2) follicular lymphoma (FL) grading, differentiating low-grade (grades 1–2) from high-grade (grade 3); and (3) multiclass lymphoma subtype classification across six categories: DLBCL, FL, marginal zone lymphoma (MZL), mantle cell lymphoma (MCL), classical Hodgkin lymphoma (CHL), and benign/reactive lymphoid conditions. WSI-level labels were derived from pathology reports, and none of the evaluation cases were included in pretraining. Models used a ViT-Giant LymphoVision backbone to generate 20x patch embeddings, followed by MIL using 50% training data and 2-fold cross-validation (25% validation, 25% test). Performance was assessed using area under the receiver operating characteristic curve (AUC), accuracy, recall (sensitivity) and F1 score. Results: For DLBCL COO classification (total n=358 cases), LymphoVision achieved a mean test AUC of 0.93 (range 0.92–0.94), accuracy of 84.5% and F1 of 0.85 across two independent test folds (n=91 per fold, 50% GCB). These results outperformed general-purpose FMs on the same task and cases, including Virchow-v2 (AUC 0.85) and UNI-v2 (AUC 0.88), despite those models being pretrained on 10–100 times more images. For FL grading (total n=660 cases), the test set in each fold included 166 cases (18% grade 3), yielding a mean test AUC of 0.88 (range 0.87–0.90), accuracy of 89.2% and F1 of 0.80. In multiclass lymphoma subtype classification (total n=1,176 cases), the test set included 296 cases per fold. LymphoVision achieved a mean test AUC of 0.98 (range 0.97-0.99), mean test accuracy of 87.1% and mean F1 of 0.84. Class-wise recall was 92.0% for DLBCL (n=112), 88.2% for FL (n=72), 77.2% for MZL (n=29), 70.8% for MCL (n=35), 87.5% for CHL (n=24), and 95.8% for benign/reactive lymphoid conditions (n=24). Conclusion: LymphoVision is a lymphoma-specialized FM trained using self-supervision that achieves high diagnostic accuracy across multiple clinically meaningful tasks using weak supervision and standard H&E images, suggesting the encoder has learned fine-grained lymphoma morphology. Based on historical benchmarks from the 1997 International Lymphoma Study Group classification project, expert hematopathologists achieved diagnostic agreement rates of 55% to 84% using H&E morphology alone for the non-Hodgkin lymphoma (NHL) entities included in our multiclass task. LymphoVision approached or exceeded these benchmarks. These findings underscore the value of our approach using disease-specialized pretraining and intelligent patch sampling for data-efficient histopathology learning. LymphoVision has the potential to augment diagnostics, enable scalable AI-powered classification in real-world workflows, and serve as a foundation for prognostic and theragnostic applications. External validation and multimodal integration are ongoing.

Abstract The diagnosis of T‐cell neoplasms remains one of the most challenging areas in hematopathology due to the immunophenotypic heterogeneity and subtle aberrancies often present in these entities. This “Best Practice” manuscript provides a practical framework for laboratories to design, validate, and interpret immunophenotyping studies of immature and mature T‐cell neoplasms. We outline the utility of key antigens in the screening and classification of T‐cell lymphomas/leukemia including TRBC1 and TRBC2. Analytical strategies using the “difference from normal” method and template‐based gating are discussed, along with validation considerations aligned with CLSI H62 guidelines. By integrating these principles into laboratory workflows, this manuscript aims to standardize and improve the assessment of T‐cell neoplasms across diverse clinical settings.

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.

Introduction: Myeloma response to treatment can be biochemical, pathological, or radiological, with pathological assessments being invasive. Next-generation blood flow (PBF) for assessment of circulating tumor plasma cells (CTCs) has shown promising results as a prognostic in Multiple Myeloma (MM) patients. CTC detection via PBF has a potential to serve as non-invasive method for assessing pathological burden of disease and response to treatment. Comparing CTC responses to the International Myeloma Working Group (IMWG) criteria will further help to understand PBF's utility in predicting response to therapy. Patients and Methods: The study conducted is a retrospective observational study. We included patients with MM treated at Mayo Clinic from 01/01/2011 to 12/31/2019 with CTC records available at the time of best response (BR) to frontline therapy. The CTC values were expressed as the number of plasma cell events per 150,000 Peripheral Blood Mononuclear Cells (CD38, CD138, CD19, CD45, Kappa, Lambda). The CTC levels were compared across all response(IMWG Criteria) groups at BR, and at baseline. The CTC response was expressed as % CTC decrease at BR from baseline. Time-to-event analyses utilized the Kaplan Meier method and Cox-proportional hazards models, with comparisons made using the log-rank test. Results: We identified 621 patients with CTC data at the time of BR to frontline therapy. Of these, 148 (24%) had baseline CTC data from diagnosis. The median age at diagnosis was 62.3 (27.2-83.7). The median follow-up was 66.15 months; the distribution of patients by treatment class is as follows- Alkylator: 0.8%, PI(Proteasome Inhibitor)+Cyclophosphamide: 27.4%, IMid: 12.7%, PI+IMid(Immunomodulator): 55.9%, PI+IMid+antiCD38: 3.2%; 378 patients (78.8%) underwent an autologous transplant. BR to initial therapy was sCR/stringent Complete Response (10, 1.6%), CR (230, 36.9%), VGPR/Very Good Partial Response (224, 36.1%), PR (123, 19.8%), MR/Minimal Response (12, 1.9%), SD/Stable Disease (14, 2.3%), PD/Progressive Disease (8, 1.3%). In the study, 64 patients (10.31%) had detectable CTCs at their BR. The distribution of CTCs across the different response categories was as follows: none (0%) in sCR, 3 patients (1.3%) in CR, 18 patients (8%) in VGPR, 24 patients (19.5%) in PR, 8 patients (66.7%) in MR, 6 patients (42.9%) in SD, and 5 patients (62.5%) in PD. The median CTC counts and their interquartile ranges for these categories showed significant variability: CR had a median of 46 (IQR: 28.5, 923), VGPR had 39.5 (IQR: 15.5, 111.25), PR had 47 (IQR: 22.75, 82.5), MR had 55 (IQR: 28.5, 85), SD had 96.5 (IQR: 22.25, 218.75), and PD had 317 (IQR: 57, 415). This Analysis of Variance (ANOVA) for response-wise distribution of CTC was &lt;0.01. Response was dichotomized as PR and above for sCR, CR, VGPR, PR and less than PR for MR, SD and PD. Median Overall Survival(OS) for PR and above was 127.8 months (vs less than PR 56.7 months, p=0.01). Median OS for CTC+ at BR was 56.7 months (vs 134.8 for CTC negative, p=0.01). On multivariate analysis, presence of CTC at best response (Hazards Ratio = 2.9, n=1.1-2.9), RISS staging at diagnosis (Hazards Ratio = 2.35, n=1.5-3.05), less than PR (Hazards Ratio =1.8, 1.1-2.9) were independent predictors of inferior OS. In patients with data for CTC available at both baseline and at BR to frontline therapy (n=148), 110 had CTC detectable at diagnosis. Among patients in various response categories, a complete disappearance of CTCs was observed in sCR (n=3, 75.0%), CR (n=36, 69.2%), VGPR (n=38, 64.4%), and PR (n=14, 60.9%). CTC responses greater than 90% were noted in VGPR (n=3, 5.1%), PR (n=2, 8.7%), and SD (n=2, 40.0%). No CTC response was reported in sCR (1, 25.0%), CR (16, 30.8%), VGPR (2, 3.4% and 13, 22.0%), PR (3, 13.0% and both 2, 8.7%), SD (1, 20.0% and both 2, 40.0%), MR (1, 50.0%), and PD (1, 33.3% and 1, 50.0%, respectively). The median OS for those with a CTC response was 112.4 months vs 28.2 months for no response. (p=0.01). Conclusion: The presence of CTC at best response is an independent prognostic marker for inferior OS. Depth of response to frontline therapy correspond to a high rate of clearance of CTCs. Presence of CTC at best response provides independent prognostic value beyond the depth of response. A complete clearance of CTC at best response is associated with improved OS. CTC levels have not been corrected for WBC counts and may not be applicable in all settings.

Background: Flow cytometry (FC) is widely utilized for the identification of minimal residual disease (MRD) in B acute lymphoblastic leukemia (BALL), providing an essential laboratory indicator for prognostic assessment and therapeutic management. Unfortunately, the high level of expertise required, long manual analysis time, and complexity of FC data files limit the offering of this testing to selected reference laboratories. Methods: We developed an artificial intelligence (AI) pipeline to automatically enhance unaltered FC files, minimizing the expertise and manual analysis time needed to detect BALL-MRD on a single-tube 10-color panel (CD10, CD19, CD20, CD22, CD24, CD34, CD38, CD45, CD58, CD66c). Raw FC files corresponding to peripheral blood or bone marrow specimens from 171 BALL MRD positive cases (MRD &lt; 5%, median = 0.11%, 107 patients), and 89 MRD-negative cases (63 patients) were processed through our CCADDAS (Clustering and Classification of All events, Dimensionality reduction, Downsampling and Aberrancy Scaling) pipeline on a cloud environment (Google Vertex AI). Automated processing steps included elimination of acquisition errors (FlowCut), state-of-the-art clustering (PARC), dimensionality reduction (UMAP), cluster-based anomaly detection compared to negative controls (24 bone marrow aspirates and 7 peripheral bloods), and cluster-informed downsampling with preservation of low-event subsets. In addition, a deep neural network (DNN) trained on expert-defined subpopulations from negative controls was included for automatic gating of normal subsets (Tensorflow v2). AI-enhanced data files were analyzed using a general purpose flow cytometry analysis software (Kaluza v 3.5, Beckman Coulter), and %MRD estimates compared to reported results based on expert analysis of original FC files. Results: Cluster-informed downsampling reduced the number of cells per case to be manually analyzed from 1.2 million to 155,884 cells on average (87% cellularity reduction); resulting in a smaller FC data file (from 64.5 MB to 13.7 MB; 79% data reduction). Importantly, low-level MRD events were adequately preserved after downsampling (median 100% retention for both MRD&lt;0.01% and MRD 0.01-1%). True number of events were accurately estimated on gated subsets using an “upsampling factor” parameter [observed # events x mean (upsampling factor)]. Gating of normal subsets was completely automated using a DNN classifier parameter. Identification of MRD was aided by an AI-generated “aberrancy scale” parameter that discriminated BALL (median: 991) from both benign mononuclear cells (median: 486, p &lt; 0.0001) and background B-lymphoid cells (median: 379, p &lt; 0.0001), with a performance (AUC: 0.98 and 0.94 for mononuclear and B-lymphoid cells, respectively) superior to CD20 (0.54 and 0.69), CD38 (0.60 and 0.81), CD45 (0.75 and 0.74), CD58 (0.52 and 0.89), CD66c (0.56 and 0.72) and all other antigens studied. The use of AI-enhanced files reduced manual analysis time from 14.16 minutes (SD = 3.7) to 1.05 minutes (SD = 0.6) per case, on average (p &lt; 0.0001) (93% reduction). BALL MRD was detected in all positive cases above clinically relevant threshold (≥0.01%, as recommended by NCCN guidelines), and in 28 of 32 (88%) cases below this threshold, with excellent quantitative correlation with conventional analysis on original FC files (linear regression slope = 1.18, intercept = 0.04%, R squared = 0.92, P &lt; 0.0001). Conclusion: We introduce a largely unsupervised AI pipeline that transforms raw BALL-MRD FC data into a markedly smaller, AI-annotated and software-agnostic FC file, including comparison to normal controls. This CCADDAS pipeline simplifies and accelerates detection of BALL-MRD in clinical diagnostics, reducing number of cells analyzed by 87% and manual analysis time by 93%, without impacting test performance. Moreover, CCADDAS can be utilized for any labroatory-developed BALL-MRD assay, and its small-sized export is compatible with any clinical FC software, computing platform and analysis strategy. Adoption of CCADDAS is likely to facilitate the implementation of BALL-MRD FC analysis by more clinical laboratories.