This session explores the evolving decision-making landscape in post-remission acute myeloid leukemia (AML), focusing on the critical question of whether to proceed with allogeneic hematopoietic cell transplantation. Dr. Pinkal Desai will examine contemporary risk stratification strategies integrating measurable residual disease (MRD), genomic profiling, and patient-specific factors to refine transplant candidacy. Recent data from major hematology meetings highlighting the prognostic impact of MRD status, the role of novel maintenance therapies (including FLT3 and IDH inhibitors), and outcomes with reduced-intensity conditioning will be discussed. The session will also address emerging approaches for older or unfit patients and the influence of targeted therapies on delaying or obviating transplant. Through case-based discussion, participants will gain practical insights into balancing relapse risk, treatment-related morbidity, and patient preferences in complex clinical scenarios.

This session focuses on optimizing treatment strategies in myelofibrosis, emphasizing practical decision-making on when to adjust therapy, switch agents, or continue observation. Dr. John Mascarenhas will explore emerging data shaping current practice, including the evolving role of JAK inhibitors beyond ruxolitinib, management of suboptimal response, and approaches to treatment-related cytopenias. Recent advances from major hematology meetings highlight novel agents such as BET inhibitors and combination strategies aimed at improving symptom control and modifying disease course. The discussion will also address molecular risk stratification, timing of therapeutic transitions, and integration of transplant considerations.

Artificial intelligence (AI) is rapidly transforming lymphoma pathology, offering new opportunities to enhance diagnostic accuracy, efficiency, and reproducibility. Recent advances presented at major hematology and oncology meetings highlight the integration of machine learning with digital pathology to improve classification of lymphoma subtypes, particularly in challenging or ambiguous cases. Deep learning algorithms can augment morphologic assessment, quantify tumor microenvironment features, and support biomarker identification, including immunophenotypic and molecular correlates. Emerging data also demonstrate AI’s role in predicting prognosis and therapeutic response through multi-omic data integration. Additionally, AI-enabled workflows may reduce interobserver variability and streamline pathology operations. Key discussions will address validation, regulatory considerations, and real-world implementation, as well as the evolving collaboration between pathologists and AI tools in precision lymphoma diagnosis.

Award Talk: Advancing Toward Cure in Follicular Lymphoma: Novel Therapies and Long-Term Outcomes