Acute Leukemia is the most common hematologic malignancy in children and adolescents. A key methodology in the diagnostic evaluation of this malignancy is immunophenotyping based on Multiparameter Flow Cytometry (FCM). However, this approach is manual, and thus time-consuming and subjective. To alleviate this situation, we propose in this paper the FCM-Former, a machine learning, self-attention based FCM-diagnostic tool, automating the immunophenotyping assessment in Childhood Acute Leukemia. The FCM-Former is trained in a supervised manner, by directly using flow cytometric data. Our FCM-Former achieves an accuracy of 96.5% assigning lineage to each sample among 960 cases of either acute B-cell, T-cell lymphoblastic, and acute myeloid leukemia (B-ALL, T-ALL, AML). To the best of our knowledge, the FCM-Former is the first work that automates the immunophenotyping assessment with FCM data in diagnosing pediatric Acute Leukemia.

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC53108.2024.10781595DOI Listing

Publication Analysis

Top Keywords

acute leukemia
16
immunophenotyping assessment
12
childhood acute
8
acute
6
leukemia
5
automated immunophenotyping
4
assessment diagnosing
4
diagnosing childhood
4
leukemia set-transformers
4
set-transformers acute
4

Similar Publications

The landscape of adult acute lymphoblastic leukemia (ALL) is dramatically changing. With very promising results seen with novel immunotherapeutics in the setting of relapsed and refractory disease, the prospect of using these agents in first-line therapy has prompted the development of multiple clinical trials addressing this question. This review seeks to outline and expand the current standard of care, as well as new advances, in the treatment of adult patients with ALL and address future areas of research.

View Article and Find Full Text PDF

ObjectivesAcute leukemia often leads to severe complications such as febrile neutropenia. Mortality rates remain high, underscoring the need for novel prognostic markers. Regulatory T cells (Tregs) have not been extensively studied in this context.

View Article and Find Full Text PDF

Objectives: Recent studies show that blocking CD47-SIRPα interactions is a promising target in checkpoint inhibition for cancer immunotherapy. However, to date, the expression of CD47 is not well characterized in various hematolymphoid neoplasms.

Methods: This study evaluates CD47 expression in a wide range of hematolymphoid neoplasms using immunohistochemistry on 834 cases.

View Article and Find Full Text PDF

Cytomegalovirus (CMV) infection post-hematopoietic cell transplantation (HCT) remains a significant cause of morbidity and mortality. While letermovir prophylaxis is available for CMV-seropositive recipients, optimal donor selection for CMV-seronegative recipients remains unclear, with donor age often prioritized over CMV serostatus. We investigated the relative impact of donor age and CMV serostatus in CMV-seronegative recipients (n = 1013) with either CMV-seropositive (n = 318) or CMV-seronegative donors (n = 695), who underwent HCT with HLA-matched sibling donors with calcineurin inhibitor-based or post-transplant cyclophosphamide (PTCy)-based graft-versus-host disease prophylaxis, or haploidentical donors with PTCy.

View Article and Find Full Text PDF

Tumour cells, which are often found in the peripheral blood of patients with acute leukaemia, may harbour multiple somatic alterations throughout the genome, including changes in the HLA region and short tandem repeat (STR) regions. We investigated whether such somatic alterations interfere with HLA and chimerism diagnostics conducted in preparation for an allogeneic haematopoietic stem cell transplantation (allo-HSCT). This study describes 10 patient-based cases for which laboratory diagnostics were performed prior to a possible stem cell transplant in the Maastricht University Medical Center.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!