T cell phenotype and lack of eosinophilia are not uncommon in extramedullary myeloid/lymphoid neoplasms with ETV6::FLT3 fusion: a case report and review of the literature.

In the 2022, WHO and ICC classifications, myeloid/lymphoid neoplasms with eosinophilia (M/LN-eo) and tyrosine kinase gene fusions represent rare hematologic malignancies driven by rearrangements of PDGFRA, PDGFRB, FGFR1, JAK2, FLT3, and ETV6::ABL1 fusion. Eosinophilia is the most constant finding, whereas the clinicopathological features are quite heterogeneous, presenting as Chronic eosinophilic leukemia (CEL) NOS, myelodysplastic/myeloproliferative neoplasm (MDS/MPN), MDS, MPN, systemic mastocytosis (SM), T or B cell acute lymphoblastic leukemia/lymphoblastic lymphoma (ALL/LBL), acute myeloid leukemia (AML), blastic phase of MPN, or mixed phenotype acute leukemia (MPAL). Extramedullary involvement at diagnosis or during progression is common. Here, we report a very unusual case of myeloid/lymphoid neoplasm with ETV6::FLT3 fusion with a nodal presentation without associated eosinophilia. Our case draws attention to diagnostic pitfalls in these rare entities.

Federated learning for predicting histological response to neoadjuvant chemotherapy in triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is a rare cancer, characterized by high metastatic potential and poor prognosis, and has limited treatment options. The current standard of care in nonmetastatic settings is neoadjuvant chemotherapy (NACT), but treatment efficacy varies substantially across patients. This heterogeneity is still poorly understood, partly due to the paucity of curated TNBC data. Here we investigate the use of machine learning (ML) leveraging whole-slide images and clinical information to predict, at diagnosis, the histological response to NACT for early TNBC women patients. To overcome the biases of small-scale studies while respecting data privacy, we conducted a multicentric TNBC study using federated learning, in which patient data remain secured behind hospitals' firewalls. We show that local ML models relying on whole-slide images can predict response to NACT but that collaborative training of ML models further improves performance, on par with the best current approaches in which ML models are trained using time-consuming expert annotations. Our ML model is interpretable and is sensitive to specific histological patterns. This proof of concept study, in which federated learning is applied to real-world datasets, paves the way for future biomarker discovery using unprecedentedly large datasets.

Wholistic approach: Transcriptomic analysis and beyond using archival material for molecular diagnosis.

Many neoplasms remain unclassified after histopathological examination, which requires further molecular analysis. To this regard, mesenchymal neoplasms are particularly challenging due to the combination of their rarity and the large number of subtypes, and many entities still lack robust diagnostic hallmarks. RNA transcriptomic profiles have proven to be a reliable basis for the classification of previously unclassified tumors and notably for mesenchymal neoplasms. Using exome-based RNA capture sequencing on more than 5000 samples of archival material (formalin-fixed, paraffin-embedded), the combination of expression profiles analyzes (including several clustering methods), fusion genes, and small nucleotide variations has been developed at the Centre Léon Bérard (CLB) in Lyon for the molecular diagnosis of challenging neoplasms and the discovery of new entities. The molecular basis of the technique, the protocol, and the bioinformatics algorithms used are described herein, as well as its advantages and limitations.

Late revelation of a subphrenic extralobar pulmonary sequestration as a suprarenal mass.

Pulmonary sequestrations are some rare congenital anomalies. The incidence was estimated of 0.15% to 1.7%. They are characterized by a mass of non functioning pulmonary tissue that has no communication to the normal bronchial tree. The vascularisation is supplied by systemic arteries. They are classified further as intralobar and extralobar types. Extralobar sequestration, so-called accessory lung, is separated from the normal lung. We present a rare case of subphrenic extralobar pulmonary sequestration in a 57 years old patient. The lesion was initially presented as a non-typical suprarenal mass discovered on CT scan. The approach by laparatomy permitted the resection and the definitive diagnosis.