Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery.

: Pancreatic ductal adenocarcinoma (PDAC) is a cancer with very poor prognosis despite early surgical management. To date, only clinical variables are used to predict outcome for decision-making about adjuvant therapy. We sought to generate a deep learning approach based on hematoxylin and eosin (H&E) or hematoxylin, eosin and saffron (HES) whole slides to predict patients' outcome, compare these new entities with known molecular subtypes and question their biological significance; : We used as a training set a retrospective private cohort of 206 patients treated by surgery for PDAC cancer and a validation cohort of 166 non-metastatic patients from The Cancer Genome Atlas (TCGA) PDAC project.

Reappraisal of Oncocytic Adenocarcinoma: Unveiling Its Connection to Oncocytic Variants of Salivary Duct Carcinoma and Mucoepidermoid Carcinoma Through ImmunoHisto-Molecular Perspectives.

Oncocytic adenocarcinoma (OC) of the salivary glands is a rare and controversial entity. It was recently reclassified as "salivary carcinoma NOS and emerging entities" in the 2022 WHO classification of head and neck tumors. The lack of specific molecular alterations and its potential affiliation with other salivary gland carcinomas, such as the oncocytic mucoepidermoid carcinomas (OMEC) or the oncocytic subtype of salivary duct carcinomas (OSDC) justified this reclassification.

The level of expression of HPV16 early transcripts is not associated with the natural history of cervical lesions.

The natural history of cervical cancer is closely linked to that of high-risk human papillomaviruses (HPV) infection. It is recognized that upon HPV DNA integration, partial or complete loss of the E2 open reading frame precludes expression of the corresponding protein, resulting in upregulation of the E6 and E7 viral oncoproteins. To better characterize HPV16 infection at the cervical level, viral load, viral DNA integration, and viral early transcript expression (E2, E5, and E6) were analyzed in a series of 158 cervical specimens representative of the full spectrum of cervical disease.

Prognostic Factors for Long-Term Eribulin Response in a Cohort of Patients With HER2-Negative Metastatic Breast Cancer.

Context And Aims: Eribulin is used in taxane and anthracycline refractory HER2-negative metastatic breast cancers (MBC). Patients treated in pivotal clinical trials achieved low survival rates, therefore, the identification of prognostic criteria for long progression-free survival (PFS) is still an unmet medical need. In this study, we sought to determine potential prognostic criteria for long-term eribulin response in HER2-negative MBC.